-
Notifications
You must be signed in to change notification settings - Fork 17
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
ELF note types for LLPC cache hash #2
base: amd-gfx-gpuopen-dev
Are you sure you want to change the base?
ELF note types for LLPC cache hash #2
Commits on Oct 10, 2019
-
Buffer memory op merging pass for s_buffer_load
This pass attempts to merge s_buffer_load_dword instructions into larger sizes. Constraints are that the resource descriptor, glc flag and size are all the same for contiguous load instructions. TODO: it should be possible to add different instructions to this as well such as s_buffer_store and the vector variants buffer_load/buffer_store V2: Fixes to sbuff-merge test V3: Fixed smrd test for smem merging V4: Fixed for gfx10 changes Change-Id: Ie98107ad3b27b3c8c2da7afc3d129336f924895a
Configuration menu - View commit details
-
Copy full SHA for e5c01b9 - Browse repository at this point
Copy the full SHA e5c01b9View commit details -
[AMDGPU] intrintrics for byte/short load/store
Summary: Added intrinsics for the instructions: - buffer_load_ubyte - buffer_load_ushort - buffer_store_byte - buffer_store_short Added test cases to existing buffer load/store tests. Now that upstream supports byte/short overloads of the normal load/store intrinsics, this change is only needed until LLPC stops using the intrinsics added here. Change-Id: I1b8a0910c508c9520a84b74a14d0aea8293cef38
Tim Corringham authored and Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for ef9b539 - Browse repository at this point
Copy the full SHA ef9b539View commit details -
[AMDGPU] Fix issue for zext of f16 to i32
Vulkan exposed an issue with this for a case with v_mad_mixlo_f16 where the upper 16 bits were not cleared. Modifying this to clear the bits instead of just copying fixed the problem. V2: Fixed up "Fix issue for zext of f16 to i32" V3: Fixed fcanonicalize-elimination test Change-Id: I6128deaf8ebc3489fdd3e0caead837410bb47160
Configuration menu - View commit details
-
Copy full SHA for fa5c650 - Browse repository at this point
Copy the full SHA fa5c650View commit details -
[AMDGPU] Use waterfall for readlane with non-uniform index
Readlane should have a uniform index - but in some cases it can be non-uniform. The original implementation of readlane defaulted to using a readfirstlane of the vgpr index on the assumption that the index would be uniform across all lanes. However, there are some cases where we might want a readlane like operation that is lowered to a waterfall that performs a readlane for each distinct index value across lanes. Essentially we form a loop that uses readfirstlane to get the first enabled lane's index - enable all lanes with the same index, perform a readlane and put the result into the vgpr result register, then disable those lanes and repeat. The pathological case will form a loop of 64 - but in most cases it will be fewer. In the case where the index IS uniform across all lanes, it will loop once, which is slightly more expensive than the original code, but not a lot more. V2: Initialize accumulator register in waterfall code V3: Fixed for gfx10 changes Change-Id: Ic52dfb14b053db7713b61c85e8ac766991aecdb8
Configuration menu - View commit details
-
Copy full SHA for 72ee292 - Browse repository at this point
Copy the full SHA 72ee292View commit details -
[AMDGPU] Fix-up cases where writelane has 2 SGPR operands
Even though writelane doesn't have the same constraints as other valu instructions it still can't violate the >1 SGPR operand constraint Due to later register propagation (e.g. fixing up vgpr operands via readfirstlane) changing writelane to only have a single SGPR is tricky. This implementation puts a new check after SIFixSGPRCopies that prevents multiple SGPRs being used in any writelane instructions. The algorithm used is to check for trivial copy prop of constants into one of the SGPR operands and perform that if possible. If this isn't possible put an explicit copy of Src1 SGPR into M0 and use that instead (this is allowable for writelane as the constraint is for SGPR read-port and not constant-bus access). V2: Fix-up cases where writelane has 2 SGPR operands - bug fixes Update to previous commit to fix an issue where immediates are tested for copy propagation but aren't suitable as inline constants. The old method caused issues that resulted in seg faults in later cse phases. Even though writelane doesn't have the same constraints as other valu instructions it still can't violate the >1 SGPR operand constraint Due to later register propagation (e.g. fixing up vgpr operands via readfirstlane) changing writelane to only have a single SGPR is tricky. This implementation puts a new check after SIFixSGPRCopies that prevents multiple SGPRs being used in any writelane instructions. The algorithm used is to check for trivial copy prop of constants into one of the SGPR operands and perform that if possible. If this isn't possible put an explicit copy of Src1 SGPR into M0 and use that instead (this is allowable for writelane as the constraint is for SGPR read-port and not constant-bus access). Change-Id: Ic3045df22db738ca6572af00138520fd28563990
Configuration menu - View commit details
-
Copy full SHA for 7438b5d - Browse repository at this point
Copy the full SHA 7438b5dView commit details -
[AMDGPU] Implement set of waterfall intrinsics
Implements 3 new intrinsics for implementing waterfall code for regions of code. Waterfall is implemented as a loop that iterates over an index of values for active lanes. For each iteration an index is picked (the first active lane) and all lanes with the same index are left active (the rest are disabled). The body of the code is then executed and the result accumulated into a result vector register. The active lane is then disabled and the next index chosen for the next iteration. The worst case for waterfall is one iteration per lane - but it is usually far less than this. The implementation uses 3 intrinsics to mark a region: - llvm.amdgcn.waterfall.begin - llvm.amdgcn.waterfall.readfirstlane - llvm.amdgcn.waterfall.end The group must contain one begin and at least one readfirstlane and end intrinsic - if the readfirstlane uses the begin index, then there will only be a single readfirstlane and not 2. The readfirstlane and end intrinsics are not limited to single dword values. The waterfall loop will enclose all instructions from the begin to the final end intrinsic. See the test case for specific examples of use. V2: [AMDGPU] Updates to waterfall intrinsic support Some fixes for waterfall support. 1. Intrinsics are better defined so enforce type correctness 2. Creation of the waterfall loop requires removing kill flag for operands moved into the loop, this can otherwise cause an assert during verification 3. Fixed issue causing a tablegen failure due to float return type being used for a scalar return value (incorrectly). The matching for intrinsic to pseudo instruction now uses 2 template parameter types to disambiguate when using float src types. 4. Ensure that any analyses are invalidated due to insertion of new basic blocks. This should have been the default anyway. 5. Updated test in light of these changes. These are good exemplars for implementors to check against. V3: [AMDGCN] Fixed waterfall intrinsic groups for multiple groups per BB For cases with more than one waterfall group per basic block, the implementation would go wrong after creating the first waterfall loop (incorrectly tracking current BB). Also added a test case. V4: [AMDGCN] Waterfall enhancements Extra waterfall test for multiple readfirstlane intrinsics. Make sure that the waterfall intrinsic clauses support multiple readfirstlane intrinsics. Extended support for begin to allow multi-dword indices for the waterfall loop. This allows the use of multiple indexes (and multiple non-uniform values) in the same waterfall loop by combining the individual indices into a single multi-dword index. This has the same worst-case of 64 iterations (wave size) as before. Added a new test case to demonstrate using multi-dword indices. Added support for i16/f16 Changed the implementation to prevent CSE from merging clauses (by tagging the intrinsics as having side effects and enhancing uniform detection to work in this case as well). Left in some support added to partially support EarlyCSE merging as it is still valid, but probably won't be triggered much now merging is disabled. Added support for a last.use intrinsic. See the test for an example of this. This works in the same way as the end intrinsic, but you tag a last_use instead (so it includes the next use in the waterfall loop). More than one use is acceptable as long as it is in the same BB. All instructions up to the last last.use will be included in the waterfall loop. An important rule for waterfall clauses (that isn't detected if violated) is that you can't have something inside the loop that is dependent on an end intrinsic in the loop - this restriction is logically consistent - you have to use two loops instead. V5: [AMDGPU] Handle unexpected uniform inputs in waterfall intrinsics Waterfall intrinsic input operands can sometimes be uniform. The waterfall handling pass should deal with this gracefully, even though this could be sub-optimal. This is an initial fix for a problem observed in a game. Subsequent better fix being worked on which should produce optimal code (by removing redundant waterfall loops entirely if all the elements turn out to be uniform anyway). V6: [AMDGPU] Improved handling of uniform waterfalls This builds on a previous fix for uniform values being specified in waterfall loop intrinsic groups. Previous fix would just remove any waterfall.readfirstlane intrinsics if the input was uniform. This fix improves on this by spotting when ALL waterfall.readfirstlanes are uniform and removing the waterfall loop entirely. The tests have been extended to test this mode. The update also handles the case where not all waterfall.readfirstlanes are removed. This is also covered in the associated tests. V7: [AMDGCN] Re-order waterfall and wholequadmode passes Running WholeQuadMode pass after waterfall can have bad consequences. Changing the order improves the outcome - but there may still be problems in some unusual cases. For the known uses of the waterfall intrinsics this change will work for now. V8: waterfall test fixup Change-Id: I95b4391b8c0570bd399d70ed64af355d13ef4c84
Configuration menu - View commit details
-
Copy full SHA for feaf835 - Browse repository at this point
Copy the full SHA feaf835View commit details -
[RegisterCoalescer] Extend subranges to uses after join
Summary: The test shows a case where a full use is not in a subrange because the subreg is undefined at the use point, but, after a coalesce, the subrange incorrectly still does not include the use even though the subreg is now defined at that point. The incorrect live range causes a "subrange join unreachable" assert on a later coalesce. This commit ensures that a subrange is extended to all uses that can be reached from a definition. V2: Completely different fix, instead of working round the problem in the later coalesce that actually asserted. V5: Fixed to not extend liveness to an undef use. Spun second test out into its own D51257 as it is a completely different problem with the same "subrange join unreachable" symptom. V6: Ignore debug uses. V7: Set up undefs correctly, to avoid generating invalid subranges. Differential Revision: https://reviews.llvm.org/D49097 Change-Id: I172cfe16d360690e921ebe606d3e90dd1cdd1b71
Configuration menu - View commit details
-
Copy full SHA for 565436a - Browse repository at this point
Copy the full SHA 565436aView commit details -
[RegisterCoalescer] Do not eliminateUndefCopy for a partial copy
eliminateUndefCopy was incorrectly eliminating a copy that was only a partial write of the target. In the test case, the resulting incorrect live range caused a subrange join unreachable later. The test case does not fail for me until I have D49097. Differential Revision: https://reviews.llvm.org/D51257 Change-Id: Ibb767d8a016934431660764b0194634e2113fea2
Configuration menu - View commit details
-
Copy full SHA for 3fa50ba - Browse repository at this point
Copy the full SHA 3fa50baView commit details -
[LiveRangeCalc] Fixed findReachingDefs bug
Summary: findReachingDefs was incorrectly using its fast path of just blitting in the live range extension when it did not see an undef itself but encountered an undef live out of a predecessor block. Now RegisterCoalescing calls extendToIndices (D49097), the bug was causing an incorrect subrange which led to a "Couldn't join subrange!" assert in a later coalesce. Subscribers: MatzeB, jvesely, nhaehnle, llvm-commits Differential Revision: https://reviews.llvm.org/D51574 Change-Id: I01c942b41ab5a145348289c8b221c45a2ec7200f
Configuration menu - View commit details
-
Copy full SHA for c7bf31b - Browse repository at this point
Copy the full SHA c7bf31bView commit details -
[RegisterCoalescer] Avoid "Use not jointly dominated by defs" in remo…
…vePartialRedundancy Summary: removePartialRedundancy was using extendToIndices on each subrange without passing in an Undefs vector containing main reg defs that are undef in the subrange, causing the above assert. Unfortunately I can only reproduce this in an ll test. Turning it into a mir test makes the problem go away. Subscribers: MatzeB, qcolombet, jvesely, nhaehnle, llvm-commits Differential Revision: https://reviews.llvm.org/D51849 Change-Id: I4f3ba2afb20d79f9467afb3d882f0328d38531be
Configuration menu - View commit details
-
Copy full SHA for 8b6ea62 - Browse repository at this point
Copy the full SHA 8b6ea62View commit details -
[RegisterCoalescer] Only look at main ranges in valuesIdentical/follo…
…wCopyChain valuesIdentical is called to determine whether a def can be considered an "identical erase" because following copy chains proves that the value being copied is the same value as the value of the other register. The tests show up problems where the main range decides that a def is an "identical erase" but a subrange disagrees, because following the copy chain leads to a def that does not define all subregs in the subrange (in the case of one test) or a different def to that found in the main range (in the case of the other test). The fix here is to only detect an "identical erase" in the main range. If it is found, it is automatically inherited by the corresponding def in any subrange, without further analysis of that subrange value. This fix supersedes D49535/rL338070 and D51848. Change-Id: I059b5b2273ed6f186d134b98c118fef0494e02f8
Configuration menu - View commit details
-
Copy full SHA for 68e4f33 - Browse repository at this point
Copy the full SHA 68e4f33View commit details -
Do not force skip over export instruction in PS
This is a temporary fix to avoid a breakage where the export(s) for a pixel shader are in control flow (due to a kill). A pixel shader must execute an export done, even with exec=0. A better fix would be to have a pixel-shader-only pass that inserts a null export done in the final basic block if there is not one already there. Change-Id: I22f201f95d52ff699aa8cac26bb019717b20432e
Configuration menu - View commit details
-
Copy full SHA for 30fbc81 - Browse repository at this point
Copy the full SHA 30fbc81View commit details -
[AMDGPU] Temporarily disabled immarg check in verifier
LLPC has .ll file library functions that break this verifier check. We need to fix those before re-enabling the check. Change-Id: I4c000793a805a50f1d91d1ae55c567a356e72519
Configuration menu - View commit details
-
Copy full SHA for 2635ffd - Browse repository at this point
Copy the full SHA 2635ffdView commit details -
[InstCombine] Fix a vector-of-pointers instcombine undef bug.
This commit fixes a really fun bug with inst combine where you have a vector-of-pointers and only one element of this vector is used. InstCombine correctly notes that an element is not used, and then will go back through a gep into that vector-of-pointers and set all vector elements to undef. This is fine in all cases except that the langref (and a ton of places in the optimizer) requires that indexing into a struct has the same index for each element of the vector-of-pointers. To fix the bug I've just made the gep/undef propagation check that the current type being indexed into is not a struct when doing the undef propagation. Differential Revision: https://reviews.llvm.org/D60600 Change-Id: I6eba34b1cde9c14751c39f04627e39425639ab3b
Configuration menu - View commit details
-
Copy full SHA for 6587f10 - Browse repository at this point
Copy the full SHA 6587f10View commit details -
[StackProtector][AMDGPU] Uniform values being used outside loop marke…
…d non-divergent Summary: This fixes an issue where values are uniform inside of a loop but the uses of that value outside the loop can be divergent. This is a temporary fix until the library linker issues can be resolved in llvm. Change-Id: I94d3d2e30cc2a6ae8d59e92cadf6f1b6cb7e708b
rtayl authored and Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for 219314a - Browse repository at this point
Copy the full SHA 219314aView commit details -
[AMDGPU] Revised optional bounds checking for scratch accesses
Implement a pass, enabled by -amdgpu-scratch-bounds-checking, or the subtarget feature "enable-scratch-bounds-checks", which adds bounds checks to scratch accesses. When this pass is enabled, out-of-bounds writes have no effect and out-of-bounds reads return zero. This is useful for GFX9 where hardware no longer performs bounds checking on scratch accesses and hence page faults result for out-of-bounds accesses by generated by shaders. Change-Id: Id2ee4b1f32e70b6bde2541db755727b6a407721b
Configuration menu - View commit details
-
Copy full SHA for 9bfc4a1 - Browse repository at this point
Copy the full SHA 9bfc4a1View commit details -
[LiveInterval] Removed bogus empty subrange assert
stripValuesNotDefiningMask was asserting that it did not leave an empty subrange. However that was bogus because the subrange could have been empty to start with, in the case that LiveRangeCalc::calculate saw a subreg use that caused a subrange to be created empty. Differential Revision: https://reviews.llvm.org/D63510 Change-Id: Ibf862415ea422198975cc7a2ca2d98531beec08d
Configuration menu - View commit details
-
Copy full SHA for 946e612 - Browse repository at this point
Copy the full SHA 946e612View commit details -
Revert "AMDGPU: Be explicit about whether the high-word in SI_PC_ADD_…
…REL_OFFSET is 0" This reverts commit 58b3837. That commit was causing an unnecessary reloc when accessing a global in the same section. On PAL, that breaks our use of a read-only global variable as an optimization of a local variable with constant initialization, because the PAL loader ignores the reloc. Change-Id: I2792404227d08d98baee69504509828de7e9b36c
Configuration menu - View commit details
-
Copy full SHA for 27dc5a8 - Browse repository at this point
Copy the full SHA 27dc5a8View commit details -
[AMDGPU] Add Wave32 Support to Scratch Bounds Checking Pass
Implement appropriate register allocation and exec mask usage for wave32 scenarios. Change-Id: I844018f6c07fdda46366af51654017fb4b654d8a
Configuration menu - View commit details
-
Copy full SHA for cd87f1a - Browse repository at this point
Copy the full SHA cd87f1aView commit details -
[AMDGCN] Support wave32/64 in waterfall intrinsics
Extended test to check wave32 and gfx10 Change-Id: I620c6d9e737ddccdfd3494abf72632d7ecc4a53f
Configuration menu - View commit details
-
Copy full SHA for 6efb5e0 - Browse repository at this point
Copy the full SHA 6efb5e0View commit details -
[AMDGPU] Fix getDwordOffset in buffer mem merging pass
Change-Id: I3557477344135f7dbece33a2945bcb9f4063c10f
Configuration menu - View commit details
-
Copy full SHA for dcf74f4 - Browse repository at this point
Copy the full SHA dcf74f4View commit details -
Extend LoadStoreOptimizer to handle IMAGE_LOAD and IMAGE_SAMPLE. Change-Id: Id49c992b9781254e39e1352125f5ffb212fe4f24
Configuration menu - View commit details
-
Copy full SHA for dc3170a - Browse repository at this point
Copy the full SHA dc3170aView commit details -
[AMDGPU] Prevent backend override of WGP when using PAL
Summary: Backend defaults to setting WGP mode to 0 or 1 depending on the cumode feature. For PAL clients we want PAL to set this mode. Adding check to prevent the backend overriding whatever the front end has set. Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, tpr, t-tye, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63639 Change-Id: Ia3bac3e562fb47089f05c11cae47d1c92f7195ee
Configuration menu - View commit details
-
Copy full SHA for b8c9a08 - Browse repository at this point
Copy the full SHA b8c9a08View commit details -
Fixed "Merge MIMG instructions"
Fix a breakage in areMemAccessesTriviallyDisjoint, caused by trying to merge a non-load MIMG instruction IMAGE_GET_RESINFO. Only MIMG that loads from memory should be considered. Change-Id: I012435534b3e6161ee7feb686d4711097d2ab980
Configuration menu - View commit details
-
Copy full SHA for ce17a44 - Browse repository at this point
Copy the full SHA ce17a44View commit details -
[AMDGPU] Temporarily Disable Atomic Optimizer for GFX10
Currently the atomic optimizer does not support wave32, and may generate DPP which is incompatible with GFX10. This change allows the atomic optimizer to be enabled unconditionally by the LLPC for all ASICs. Change-Id: Ia26b527675b6e07319f4299b3f82ad405916bad6
Configuration menu - View commit details
-
Copy full SHA for 1acef8b - Browse repository at this point
Copy the full SHA 1acef8bView commit details -
[SDA] Don't stop divergence propagation at the IPD.
Summary: This fixes B42473 and B42706. This patch makes the SDA propagate branch divergence until the end of the RPO traversal. Before, the SyncDependenceAnalysis propagated divergence only until the IPD in rpo order. RPO is incompatible with post dominance in the presence of loops. This made the SDA crash because blocks were missed in the propagation. Reviewers: foad, nhaehnle Subscribers: jvesely, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D65274 Change-Id: Ic3fcc51e5850fde3a4649ec3dd84a040a07aaca9
Configuration menu - View commit details
-
Copy full SHA for 2edcce6 - Browse repository at this point
Copy the full SHA 2edcce6View commit details -
[AMDGPU] gfx10 atomic optimizer changes.
Summary: Add support for gfx10, where all DPP operations are confined to work within a single row of 16 lanes, and wave32. Reviewers: arsenm, sheredom, critson, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, t-tye, hiraditya, jfb, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D65644 Change-Id: I1f8991e9cf732e79a139e79e70a2bf62650693d4
Configuration menu - View commit details
-
Copy full SHA for d050e52 - Browse repository at this point
Copy the full SHA d050e52View commit details -
Reinstate "AMDGPU: Be explicit about whether the high-word in SI_PC_A…
…DD_REL_OFFSET is 0" This reverts commit ad3ea6fe0eedc9fe48b96453cfed51f8c1dd79de.
Configuration menu - View commit details
-
Copy full SHA for d702c00 - Browse repository at this point
Copy the full SHA d702c00View commit details -
Partially revert D61491 "AMDGPU: Be explicit about whether the high-w…
…ord in SI_PC_ADD_REL_OFFSET is 0" (From Jay) D61491 caused us to use relocs when they're not strictly necessary, to refer to symbols in the text section. This is a pessimization and it's a problem for some loaders that don't support relocs yet. Differential Revision: https://reviews.llvm.org/D65813 Change-Id: Ia84de963ad099b7d2fcfb9cd2b908fa2e5a4788b
Configuration menu - View commit details
-
Copy full SHA for 5af7874 - Browse repository at this point
Copy the full SHA 5af7874View commit details -
Change-Id: I3dddc18d5dea0fd1050633e35d0ac463a9ed26ca
Configuration menu - View commit details
-
Copy full SHA for c62b84d - Browse repository at this point
Copy the full SHA c62b84dView commit details -
[AMDGPU] Fix to 'Fold readlane from copy of SGPR or imm'
That change (r363670) could leave a copy from vgpr to sgpr. Fixed. Differential Revision: https://reviews.llvm.org/D66133 Change-Id: I00c3fe6fda2e8e1e36f53195b881b1449c777ea4
Configuration menu - View commit details
-
Copy full SHA for 4c5cbb2 - Browse repository at this point
Copy the full SHA 4c5cbb2View commit details -
Revert "[AMDGPU] Enable merging m0 initializations."
This reverts D64766. That change caused me a problem where an LDS instruction was missing its m0 initialization on gfx7 on a Vulkan CTS test on the GPUOpen driver. Compiling the same code with llc on the upstream LLVM that our Vulkan branch is based on did not show the problem. This needs further investigation. Change-Id: I94b380f60b074a117075ae12d15ae4babbc8c7af
Configuration menu - View commit details
-
Copy full SHA for c84ccc6 - Browse repository at this point
Copy the full SHA c84ccc6View commit details -
[InstCombine][AMDGPU] Simplify tbuffer loads
Summary: Add missing tbuffer loads intrinsics in SimplifyDemandedVectorElts. Reviewers: arsenm, nhaehnle Reviewed By: arsenm Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D66926 Change-Id: I63f53e8cd45f2e3683d109fb7624ba04eac365e7 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370475 91177308-0d34-0410-b5e6-96231b3b80d8
Configuration menu - View commit details
-
Copy full SHA for f4f9552 - Browse repository at this point
Copy the full SHA f4f9552View commit details -
[TLI][AMDGPU] AMDPAL does not have library functions
Configure TLI to say that r600/amdgpu does not have any library functions, such that InstCombine does not do anything like turn sin/cos into the library function @tan with sufficient fast math flags. Differential Revision: https://reviews.llvm.org/D67406 Change-Id: I02f907d3e64832117ea9800e9f9285282856e5df
Configuration menu - View commit details
-
Copy full SHA for 37ba27f - Browse repository at this point
Copy the full SHA 37ba27fView commit details -
[AMDGPU] Remove unnecessary movs for v_fmac operands
Summary: This propagates a sgpr->vgpr copy into an operand of a v_fma/v_mad that is generated from v_fmac, given it doesn't break constant bus restriction Change-Id: I39cacf43205e15982f7405c805d67b7a8b11d2a9
rtayl authored and Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for fc7af57 - Browse repository at this point
Copy the full SHA fc7af57View commit details -
Revert "Reapply "AMDGPU: Split block for si_end_cf""
This reverts commit eb43d3e. Change-Id: I3d2e12c87aa3dd6ecae9115832635381c67177b7
Configuration menu - View commit details
-
Copy full SHA for d0e9bdb - Browse repository at this point
Copy the full SHA d0e9bdbView commit details -
Revert "[AMDGPU] Remove unnecessary movs for v_fmac operands"
We had test problems with this. It will be reinstated as soon as a fix is identified. This reverts commit d14be0a652cb943bea16919e8542f00348c36586. Change-Id: Icb4d534e5bfec37e740707cbd6d860bbd1ec53f3
Configuration menu - View commit details
-
Copy full SHA for 0539a12 - Browse repository at this point
Copy the full SHA 0539a12View commit details -
Revert "[InstCombine][AMDGPU] Simplify tbuffer loads"
Temporarily reverting this as it has missed most of the testing cycle. This reverts commit 560afd3c65a73d0b06badbb19d6e5b0a4414bee5. Change-Id: Idafd4baaf6f4440c64f39182942973affe881cce
Configuration menu - View commit details
-
Copy full SHA for 77ceb89 - Browse repository at this point
Copy the full SHA 77ceb89View commit details -
Overwritten with: 77ceb89 Revert "[InstCombine][AMDGPU] Simplify tbuf…
…fer loads" Based on upstream llvm 368122: 989679c Reverts commit r368117, r368115 and r368112 Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for ccf09e1 - Browse repository at this point
Copy the full SHA ccf09e1View commit details -
Buffer memory op merging pass for s_buffer_load
This pass attempts to merge s_buffer_load_dword instructions into larger sizes. Constraints are that the resource descriptor, glc flag and size are all the same for contiguous load instructions. TODO: it should be possible to add different instructions to this as well such as s_buffer_store and the vector variants buffer_load/buffer_store V2: Fixes to sbuff-merge test V3: Fixed smrd test for smem merging V4: Fixed for gfx10 changes Change-Id: Ie98107ad3b27b3c8c2da7afc3d129336f924895a
Configuration menu - View commit details
-
Copy full SHA for 26f5a10 - Browse repository at this point
Copy the full SHA 26f5a10View commit details -
[AMDGPU] intrinsics for byte/short load/store
Summary: Added intrinsics for the instructions: - buffer_load_ubyte - buffer_load_ushort - buffer_store_byte - buffer_store_short Added test cases to existing buffer load/store tests. Now that upstream supports byte/short overloads of the normal load/store intrinsics, this change is only needed until LLPC stops using the intrinsics added here. Differential Revision: https://reviews.llvm.org/D42885 Change-Id: I1b8a0910c508c9520a84b74a14d0aea8293cef38
Tim Corringham authored and Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for 76e0a66 - Browse repository at this point
Copy the full SHA 76e0a66View commit details -
[AMDGPU] Fix issue for zext of f16 to i32
Vulkan exposed an issue with this for a case with v_mad_mixlo_f16 where the upper 16 bits were not cleared. Modifying this to clear the bits instead of just copying fixed the problem. V2: Fixed up "Fix issue for zext of f16 to i32" V3: Fixed fcanonicalize-elimination test Differential Revision: https://reviews.llvm.org/D51925 Change-Id: I6128deaf8ebc3489fdd3e0caead837410bb47160
Configuration menu - View commit details
-
Copy full SHA for dfe14ed - Browse repository at this point
Copy the full SHA dfe14edView commit details -
[AMDGPU] Fix-up cases where writelane has 2 SGPR operands
Even though writelane doesn't have the same constraints as other valu instructions it still can't violate the >1 SGPR operand constraint Due to later register propagation (e.g. fixing up vgpr operands via readfirstlane) changing writelane to only have a single SGPR is tricky. This implementation puts a new check after SIFixSGPRCopies that prevents multiple SGPRs being used in any writelane instructions. The algorithm used is to check for trivial copy prop of constants into one of the SGPR operands and perform that if possible. If this isn't possible put an explicit copy of Src1 SGPR into M0 and use that instead (this is allowable for writelane as the constraint is for SGPR read-port and not constant-bus access). V2: Fix-up cases where writelane has 2 SGPR operands - bug fixes Update to previous commit to fix an issue where immediates are tested for copy propagation but aren't suitable as inline constants. The old method caused issues that resulted in seg faults in later cse phases. Even though writelane doesn't have the same constraints as other valu instructions it still can't violate the >1 SGPR operand constraint Due to later register propagation (e.g. fixing up vgpr operands via readfirstlane) changing writelane to only have a single SGPR is tricky. This implementation puts a new check after SIFixSGPRCopies that prevents multiple SGPRs being used in any writelane instructions. The algorithm used is to check for trivial copy prop of constants into one of the SGPR operands and perform that if possible. If this isn't possible put an explicit copy of Src1 SGPR into M0 and use that instead (this is allowable for writelane as the constraint is for SGPR read-port and not constant-bus access). Differential Revision: https://reviews.llvm.org/D51932 Change-Id: Ic3045df22db738ca6572af00138520fd28563990
Configuration menu - View commit details
-
Copy full SHA for 34c9330 - Browse repository at this point
Copy the full SHA 34c9330View commit details -
[AMDGPU] Implement set of waterfall intrinsics
Implements 3 new intrinsics for implementing waterfall code for regions of code. Waterfall is implemented as a loop that iterates over an index of values for active lanes. For each iteration an index is picked (the first active lane) and all lanes with the same index are left active (the rest are disabled). The body of the code is then executed and the result accumulated into a result vector register. The active lane is then disabled and the next index chosen for the next iteration. The worst case for waterfall is one iteration per lane - but it is usually far less than this. The implementation uses 3 intrinsics to mark a region: - llvm.amdgcn.waterfall.begin - llvm.amdgcn.waterfall.readfirstlane - llvm.amdgcn.waterfall.end The group must contain one begin and at least one readfirstlane and end intrinsic - if the readfirstlane uses the begin index, then there will only be a single readfirstlane and not 2. The readfirstlane and end intrinsics are not limited to single dword values. The waterfall loop will enclose all instructions from the begin to the final end intrinsic. See the test case for specific examples of use. V2: [AMDGPU] Updates to waterfall intrinsic support Some fixes for waterfall support. 1. Intrinsics are better defined so enforce type correctness 2. Creation of the waterfall loop requires removing kill flag for operands moved into the loop, this can otherwise cause an assert during verification 3. Fixed issue causing a tablegen failure due to float return type being used for a scalar return value (incorrectly). The matching for intrinsic to pseudo instruction now uses 2 template parameter types to disambiguate when using float src types. 4. Ensure that any analyses are invalidated due to insertion of new basic blocks. This should have been the default anyway. 5. Updated test in light of these changes. These are good exemplars for implementors to check against. V3: [AMDGCN] Fixed waterfall intrinsic groups for multiple groups per BB For cases with more than one waterfall group per basic block, the implementation would go wrong after creating the first waterfall loop (incorrectly tracking current BB). Also added a test case. V4: [AMDGCN] Waterfall enhancements Extra waterfall test for multiple readfirstlane intrinsics. Make sure that the waterfall intrinsic clauses support multiple readfirstlane intrinsics. Extended support for begin to allow multi-dword indices for the waterfall loop. This allows the use of multiple indexes (and multiple non-uniform values) in the same waterfall loop by combining the individual indices into a single multi-dword index. This has the same worst-case of 64 iterations (wave size) as before. Added a new test case to demonstrate using multi-dword indices. Added support for i16/f16 Changed the implementation to prevent CSE from merging clauses (by tagging the intrinsics as having side effects and enhancing uniform detection to work in this case as well). Left in some support added to partially support EarlyCSE merging as it is still valid, but probably won't be triggered much now merging is disabled. Added support for a last.use intrinsic. See the test for an example of this. This works in the same way as the end intrinsic, but you tag a last_use instead (so it includes the next use in the waterfall loop). More than one use is acceptable as long as it is in the same BB. All instructions up to the last last.use will be included in the waterfall loop. An important rule for waterfall clauses (that isn't detected if violated) is that you can't have something inside the loop that is dependent on an end intrinsic in the loop - this restriction is logically consistent - you have to use two loops instead. V5: [AMDGPU] Handle unexpected uniform inputs in waterfall intrinsics Waterfall intrinsic input operands can sometimes be uniform. The waterfall handling pass should deal with this gracefully, even though this could be sub-optimal. This is an initial fix for a problem observed in a game. Subsequent better fix being worked on which should produce optimal code (by removing redundant waterfall loops entirely if all the elements turn out to be uniform anyway). V6: [AMDGPU] Improved handling of uniform waterfalls This builds on a previous fix for uniform values being specified in waterfall loop intrinsic groups. Previous fix would just remove any waterfall.readfirstlane intrinsics if the input was uniform. This fix improves on this by spotting when ALL waterfall.readfirstlanes are uniform and removing the waterfall loop entirely. The tests have been extended to test this mode. The update also handles the case where not all waterfall.readfirstlanes are removed. This is also covered in the associated tests. V7: [AMDGCN] Re-order waterfall and wholequadmode passes Running WholeQuadMode pass after waterfall can have bad consequences. Changing the order improves the outcome - but there may still be problems in some unusual cases. For the known uses of the waterfall intrinsics this change will work for now. V8: waterfall test fixup Change-Id: I95b4391b8c0570bd399d70ed64af355d13ef4c84
Configuration menu - View commit details
-
Copy full SHA for a8dcacf - Browse repository at this point
Copy the full SHA a8dcacfView commit details -
[RegisterCoalescer] Extend subranges to uses after join
Summary: The test shows a case where a full use is not in a subrange because the subreg is undefined at the use point, but, after a coalesce, the subrange incorrectly still does not include the use even though the subreg is now defined at that point. The incorrect live range causes a "subrange join unreachable" assert on a later coalesce. This commit ensures that a subrange is extended to all uses that can be reached from a definition. V2: Completely different fix, instead of working round the problem in the later coalesce that actually asserted. V5: Fixed to not extend liveness to an undef use. Spun second test out into its own D51257 as it is a completely different problem with the same "subrange join unreachable" symptom. V6: Ignore debug uses. V7: Set up undefs correctly, to avoid generating invalid subranges. Differential Revision: https://reviews.llvm.org/D49097 Change-Id: I172cfe16d360690e921ebe606d3e90dd1cdd1b71
Configuration menu - View commit details
-
Copy full SHA for 5cd6143 - Browse repository at this point
Copy the full SHA 5cd6143View commit details -
[RegisterCoalescer] Do not eliminateUndefCopy for a partial copy
eliminateUndefCopy was incorrectly eliminating a copy that was only a partial write of the target. In the test case, the resulting incorrect live range caused a subrange join unreachable later. The test case does not fail for me until I have D49097. Differential Revision: https://reviews.llvm.org/D51257 Change-Id: Ibb767d8a016934431660764b0194634e2113fea2
Configuration menu - View commit details
-
Copy full SHA for ba17323 - Browse repository at this point
Copy the full SHA ba17323View commit details -
[LiveRangeCalc] Fixed findReachingDefs bug
Summary: findReachingDefs was incorrectly using its fast path of just blitting in the live range extension when it did not see an undef itself but encountered an undef live out of a predecessor block. Now RegisterCoalescing calls extendToIndices (D49097), the bug was causing an incorrect subrange which led to a "Couldn't join subrange!" assert in a later coalesce. Subscribers: MatzeB, jvesely, nhaehnle, llvm-commits Differential Revision: https://reviews.llvm.org/D51574 Change-Id: I01c942b41ab5a145348289c8b221c45a2ec7200f
Configuration menu - View commit details
-
Copy full SHA for d067cbd - Browse repository at this point
Copy the full SHA d067cbdView commit details -
[RegisterCoalescer] Avoid "Use not jointly dominated by defs" in remo…
…vePartialRedundancy Summary: removePartialRedundancy was using extendToIndices on each subrange without passing in an Undefs vector containing main reg defs that are undef in the subrange, causing the above assert. Unfortunately I can only reproduce this in an ll test. Turning it into a mir test makes the problem go away. Subscribers: MatzeB, qcolombet, jvesely, nhaehnle, llvm-commits Differential Revision: https://reviews.llvm.org/D51849 Change-Id: I4f3ba2afb20d79f9467afb3d882f0328d38531be
Configuration menu - View commit details
-
Copy full SHA for 2bb2965 - Browse repository at this point
Copy the full SHA 2bb2965View commit details -
[RegisterCoalescer] Only look at main ranges in valuesIdentical/follo…
…wCopyChain valuesIdentical is called to determine whether a def can be considered an "identical erase" because following copy chains proves that the value being copied is the same value as the value of the other register. The tests show up problems where the main range decides that a def is an "identical erase" but a subrange disagrees, because following the copy chain leads to a def that does not define all subregs in the subrange (in the case of one test) or a different def to that found in the main range (in the case of the other test). The fix here is to only detect an "identical erase" in the main range. If it is found, it is automatically inherited by the corresponding def in any subrange, without further analysis of that subrange value. This fix supersedes D49535/rL338070 and D51848. Differential Revision: https://reviews.llvm.org/D52061 Change-Id: I059b5b2273ed6f186d134b98c118fef0494e02f8
Configuration menu - View commit details
-
Copy full SHA for 06e3144 - Browse repository at this point
Copy the full SHA 06e3144View commit details -
Do not force skip over export instruction in PS
This is a temporary fix to avoid a breakage where the export(s) for a pixel shader are in control flow (due to a kill). A pixel shader must execute an export done, even with exec=0. A better fix would be to have a pixel-shader-only pass that inserts a null export done in the final basic block if there is not one already there. Change-Id: I22f201f95d52ff699aa8cac26bb019717b20432e
Configuration menu - View commit details
-
Copy full SHA for c883396 - Browse repository at this point
Copy the full SHA c883396View commit details -
[AMDGPU] Temporarily disabled immarg check in verifier
LLPC has .ll file library functions that break this verifier check. We need to fix those before re-enabling the check. Change-Id: I4c000793a805a50f1d91d1ae55c567a356e72519
Configuration menu - View commit details
-
Copy full SHA for 18cb9b2 - Browse repository at this point
Copy the full SHA 18cb9b2View commit details -
[StackProtector][AMDGPU] Uniform values being used outside loop marke…
…d non-divergent Summary: This fixes an issue where values are uniform inside of a loop but the uses of that value outside the loop can be divergent. This is a temporary fix until the library linker issues can be resolved in llvm. Differential Revision: https://reviews.llvm.org/D60834 Change-Id: I94d3d2e30cc2a6ae8d59e92cadf6f1b6cb7e708b
rtayl authored and Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for f20ae31 - Browse repository at this point
Copy the full SHA f20ae31View commit details -
[AMDGPU] Revised optional bounds checking for scratch accesses
Implement a pass, enabled by -amdgpu-scratch-bounds-checking, or the subtarget feature "enable-scratch-bounds-checks", which adds bounds checks to scratch accesses. When this pass is enabled, out-of-bounds writes have no effect and out-of-bounds reads return zero. This is useful for GFX9 where hardware no longer performs bounds checking on scratch accesses and hence page faults result for out-of-bounds accesses by generated by shaders. Differential Revision: https://reviews.llvm.org/D60772 Change-Id: Id2ee4b1f32e70b6bde2541db755727b6a407721b
Configuration menu - View commit details
-
Copy full SHA for 011e0e0 - Browse repository at this point
Copy the full SHA 011e0e0View commit details -
Extend LoadStoreOptimizer to handle IMAGE_LOAD and IMAGE_SAMPLE. Change-Id: Id49c992b9781254e39e1352125f5ffb212fe4f24
Configuration menu - View commit details
-
Copy full SHA for cef330f - Browse repository at this point
Copy the full SHA cef330fView commit details -
[SDA] Don't stop divergence propagation at the IPD.
Summary: This fixes B42473 and B42706. This patch makes the SDA propagate branch divergence until the end of the RPO traversal. Before, the SyncDependenceAnalysis propagated divergence only until the IPD in rpo order. RPO is incompatible with post dominance in the presence of loops. This made the SDA crash because blocks were missed in the propagation. Reviewers: foad, nhaehnle Subscribers: jvesely, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D65274 Change-Id: Ic3fcc51e5850fde3a4649ec3dd84a040a07aaca9
Configuration menu - View commit details
-
Copy full SHA for cc72be2 - Browse repository at this point
Copy the full SHA cc72be2View commit details -
[AMDGPU] Add llvm.amdgcn.wqm.demote intrinsic
Add intrinsic which demotes all active lanes to helper lanes. This is used to implement demote to helper vulkan extension. In practice demoting a lane to helper simply means removing it from the mask of live lanes used for WQM/WWM/Exact mode. Where the shader does not use WQM demotes become kills. To support this live lanes must now be tracked through entire shader. This involves adding PHI nodes during WQM pass, which can expose exec mask change issues. This is overcome by split blocks on changes from WQM/WWM to Exact mode. As a result the WQM pass no longer preserves CFG, slot indexes or live intervals as these is no way of maintaining when blocks are split. Change-Id: I086fa95a1ba0880aa2799c0430242ecd02eb0a11
Configuration menu - View commit details
-
Copy full SHA for 8e41591 - Browse repository at this point
Copy the full SHA 8e41591View commit details -
Overwritten with: 8e41591 [AMDGPU] Add llvm.amdgcn.wqm.demote intrinsic
Based on upstream llvm 371856: b4160cb [ADT] Remove a workaround for old versions of clang Local (non-upstream) changes since ccf09e1: 8e41591 [AMDGPU] Add llvm.amdgcn.wqm.demote intrinsic Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for ce9a97b - Browse repository at this point
Copy the full SHA ce9a97bView commit details -
[AMDGPU] Add llvm.amdgcn.wqm.helper intrinsic to complement demote
Originally llvm.amdgcn.wqm.demote worked with llvm.amdgcn.ps.live; however, this required changing the type signature of ps.live. While the type signature of ps.live can be updated in LLPC, other users such as Mesa should not be expected to change. Change-Id: I7a18e7931bd7f2b4e0bfd4dc5718ff3718bb9d27
Configuration menu - View commit details
-
Copy full SHA for 4055769 - Browse repository at this point
Copy the full SHA 4055769View commit details -
Overwritten with: 4055769 [AMDGPU] Add llvm.amdgcn.wqm.helper intrins…
…ic to complement demote Based on upstream llvm 371856: b4160cb [ADT] Remove a workaround for old versions of clang Local (non-upstream) changes since ce9a97b: 4055769 [AMDGPU] Add llvm.amdgcn.wqm.helper intrinsic to complement demote Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for 0866736 - Browse repository at this point
Copy the full SHA 0866736View commit details -
Overwritten with: 92b4e09 [AMDGPU] Use waterfall for readlane with no…
…n-uniform index Based on upstream llvm 371856: b4160cb [ADT] Remove a workaround for old versions of clang Local (non-upstream) changes since 0866736: 92b4e09 [AMDGPU] Use waterfall for readlane with non-uniform index b9cf832 [AMDGPU] Allow FP inline constant in v_madak_f16 and v_fmaak_f16 Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for 9d4e892 - Browse repository at this point
Copy the full SHA 9d4e892View commit details -
Overwritten with: 56002f2 [SLC] Allow llvm.pow(x,2.0) -> x*x etc even…
… if no pow() lib func Based on upstream llvm 371856: b4160cb [ADT] Remove a workaround for old versions of clang Local (non-upstream) changes since 9d4e892: 56002f2 [SLC] Allow llvm.pow(x,2.0) -> x*x etc even if no pow() lib func Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for 6256c6e - Browse repository at this point
Copy the full SHA 6256c6eView commit details -
Overwritten with: fbb18a0 Merged from upstream llvm 373192: ac0f4f5b2…
…f2 [NFC][ARM][MVE] More tests Based on upstream llvm 373192: e3b4f0e [NFC][ARM][MVE] More tests No local (non-upstream) changes since 6256c6e. Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for 2b5181f - Browse repository at this point
Copy the full SHA 2b5181fView commit details -
Overwritten with: b8e9180 Merged from upstream llvm 373423: [X86] Add…
… broadcast load folding patterns to the NoVLX compare patterns. Based on upstream llvm 373423: 8d6a863 [X86] Add broadcast load folding patterns to the NoVLX compare patterns. Local (non-upstream) changes since 2b5181f: e1d5296 Merge MIMG instructions e0dc265 Revert "Merge MIMG instructions" Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 10, 2019 Configuration menu - View commit details
-
Copy full SHA for 40fbaf4 - Browse repository at this point
Copy the full SHA 40fbaf4View commit details
Commits on Oct 11, 2019
-
Overwritten with: b19c164 Remove dubious logic in bidirectional list …
…scheduler Based on upstream llvm 373958: 46d317f [Bitcode] Update naming of UNOP_NEG to UNOP_FNEG Local (non-upstream) changes since 40fbaf4: b19c164 Remove dubious logic in bidirectional list scheduler 8c7f063 Revert "[SimplifyCFG] FoldTwoEntryPHINode(): consider *total* speculation cost, not per-BB cost" b24f8ac Revert "[AMDGPU] Run `unreachable-mbb-elimination` after isel to clean up PHIs." 2544d5d [LiveRangeCalc] Fixed findReachingDefs bug - test fixup 25e8457 Merge MIMG instructions a1e75ec Revert "Merge MIMG instructions" 8c1a51e Revert "[AMDGPU] Use waterfall for readlane with non-uniform index" 35a70ca [AMDGPU] Remove waterfalls with dead readfirstlane intrinsics Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 11, 2019 Configuration menu - View commit details
-
Copy full SHA for 33e6f13 - Browse repository at this point
Copy the full SHA 33e6f13View commit details
Commits on Oct 21, 2019
-
Overwritten with: acb3c7c Fixes after merge due to change to always i…
…ssue export Based on upstream llvm 374864: bbb8ead [Format] Add machine-readable SPDX license ID to clang-format.el Local changes since 33e6f13: acb3c7c Fixes after merge due to change to always issue export aa25f98 Fix up tests based on changes to upstream and locally bd63510 Merged upstream 374864: bbb8ead [Format] Add machine-readable SPDX license ID to clang-format.el 548c005 XFAIL after reversion [SimplifyCFG] FoldTwoEntryPHINode() 7938afb Merge "Update MIR tests" into amd-gfx ba0a3d8 Fix local MIR tests after upstream merge changed sreg_128 -> sgpr_128 519f3c6 Update autogenerated test checks after recent merge from upstream. 93ff911 Merged from upstream llvm 374566: ee0a0a3 [AArch64][SVE] Implement sdot and udot (lane) intrinsics Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 21, 2019 Configuration menu - View commit details
-
Copy full SHA for 068af91 - Browse repository at this point
Copy the full SHA 068af91View commit details
Commits on Oct 25, 2019
-
Overwritten with: b4d32d7 XFAIL dpp_combine.mir after reverting faili…
…ng change for merge Based on upstream llvm 375398: 3cc4835 Use Align for TFL::TransientStackAlignment Local changes since 068af91: b4d32d7 XFAIL dpp_combine.mir after reverting failing change for merge 33d8cd6 Revert "[AMDGPU] Allow DPP combiner to work with REG_SEQUENCE" c5aefa7 Fixes for problems after upstream merge fd005be Manual merge llvm.org master 375398: 3cc4835 ec94370 Revert "[AMDGPU] Fix-up cases where writelane has 2 SGPR operands" 556e5e3 Revert "Merge MIMG instructions" Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedOct 25, 2019 Configuration menu - View commit details
-
Copy full SHA for 56636f1 - Browse repository at this point
Copy the full SHA 56636f1View commit details
Commits on Nov 1, 2019
-
Revert "[AMDGPU] Come back patch for the 'Assign register class for c…
…ross block values according to the divergence.'" This reverts commit c4d256a. Also xfailed three tests. Change-Id: I6d301a01be105d1a93ef3b148cd8c1b852da7f25
Tim Renouf committedNov 1, 2019 Configuration menu - View commit details
-
Copy full SHA for 717c9c6 - Browse repository at this point
Copy the full SHA 717c9c6View commit details -
Revert "AMDGPU: Use SGPR_128 instead of SReg_128 for vregs"
This reverts commit eea1a46f3f4a2333380097682079ba2e28f88f4f. Change-Id: I9ff5b491fe3764ca1498a9c1740771766a1dbed1
Tim Renouf committedNov 1, 2019 Configuration menu - View commit details
-
Copy full SHA for 6b257bf - Browse repository at this point
Copy the full SHA 6b257bfView commit details -
Overwritten with: 6b257bf Revert "AMDGPU: Use SGPR_128 instead of SRe…
…g_128 for vregs" Based on upstream llvm 374864: bbb8ead [Format] Add machine-readable SPDX license ID to clang-format.el Local changes since 068af91: 6b257bf Revert "AMDGPU: Use SGPR_128 instead of SReg_128 for vregs" 717c9c6 Revert "[AMDGPU] Come back patch for the 'Assign register class for cross block values according to the divergence.'" Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: Ic5f917c4913614a2bd11c948025bac802edf2c7a
Tim Renouf committedNov 1, 2019 Configuration menu - View commit details
-
Copy full SHA for 2c15e55 - Browse repository at this point
Copy the full SHA 2c15e55View commit details
Commits on Nov 4, 2019
-
Revert "AMDGPU: Use SGPR_128 instead of SReg_128 for vregs"
This reverts commit eea1a46f3f4a2333380097682079ba2e28f88f4f. Change-Id: I9ff5b491fe3764ca1498a9c1740771766a1dbed1
Tim Renouf committedNov 4, 2019 Configuration menu - View commit details
-
Copy full SHA for 2c07340 - Browse repository at this point
Copy the full SHA 2c07340View commit details -
Overwritten with: 2c07340 Revert "AMDGPU: Use SGPR_128 instead of SRe…
…g_128 for vregs" This is a branch off amd-gfx b4d32d7 XFAIL dpp_combine.mir after reverting failing change for merge containing the reversion below. Based on upstream llvm 375398: 3cc4835 Use Align for TFL::TransientStackAlignment Local changes since 56636f1: 2c07340 Revert "AMDGPU: Use SGPR_128 instead of SReg_128 for vregs" Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: I73de8e6164feee31d59d1894a9e56e228ae41c73
Tim Renouf committedNov 4, 2019 Configuration menu - View commit details
-
Copy full SHA for 0071048 - Browse repository at this point
Copy the full SHA 0071048View commit details
Commits on Nov 5, 2019
-
This is to avoid a history break when moving from the branch with the "Revert use SGPR_128" change back to mainline. Change-Id: I87153683f22f6c0471d6820317e6ab8847dd07a9
Tim Renouf committedNov 5, 2019 Configuration menu - View commit details
-
Copy full SHA for 65129cf - Browse repository at this point
Copy the full SHA 65129cfView commit details -
Overwritten with: 3bbd3f1 Revert "AMDGPU: Use SGPR_128 instead of SRe…
…g_128 for vregs" Based on upstream llvm : 08c7ff9 [libunwind] [Windows] Add a log message if EnumProcessModules fails Local (non-upstream) changes since 65129cf: 3bbd3f1 Revert "AMDGPU: Use SGPR_128 instead of SReg_128 for vregs" f91ccb0 Revert "Revert "[SimplifyCFG] FoldTwoEntryPHINode(): consider *total* speculation cost, not per-BB cost"" eb5facd [AMDGPU] Fix vccz after v_readlane/v_readfirstlane to vcc_lo/hi 654dede Revert "Revert "[AMDGPU] Allow DPP combiner to work with REG_SEQUENCE"" 2817d90 Revert "XFAIL dpp_combine.mir after reverting failing change for merge" 42a79ae Revert "Revert "AMDGPU: Erase redundant redefs of m0 in SIFoldOperands"" 4017707 Revert "Test fixups for reversion of Erase redundant redefs of m0 in SIFoldOperands" 736e7e8 Test fixups for reversion of Erase redundant redefs of m0 in SIFoldOperands 7c3184c Revert "AMDGPU: Erase redundant redefs of m0 in SIFoldOperands" Added AMD modification notices and removed non-LLVM directories and some GPL files.
Tim Renouf committedNov 5, 2019 Configuration menu - View commit details
-
Copy full SHA for 220194b - Browse repository at this point
Copy the full SHA 220194bView commit details
Commits on Nov 11, 2019
-
Overwritten with: d401164 Merged master:0703db39892 into amd-gfx:37ae…
…0f5cabd Based on upstream llvm : 0703db3 [CostModel] Fixed isExtractSubvectorMask for undef index off end Local changes since 220194b: d401164 Merged master:0703db39892 into amd-gfx:37ae0f5cabd 37ae0f5 Merged master:6bf9e88ae4a into amd-gfx:1b269b1013d 1b269b1 Merged master:41449c58c58 into amd-gfx:94d9f17da94 94d9f17 Merged master:0f88caeef8f into amd-gfx:fea644ea3cc fea644e Merged master:bcf754a3212 into amd-gfx:2e774eed464 2e774ee Merged master:de61aa3118b into amd-gfx:1747a4ec9e6 1747a4e Merged master:9577ee84e63 into amd-gfx:76cd82d528c 76cd82d Merged master:6c3fee47a64 into amd-gfx:d1f949b785b d1f949b Merged master:092452d402d into amd-gfx:9972ad51bc8 9972ad5 Merged master:bc496677d0e into amd-gfx:1f32295b917 1f32295 Merged master:39525a67238 into amd-gfx:3bbd3f1235f Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: If58e4a508b4de6780de67b72ab237180104c1b88
Configuration menu - View commit details
-
Copy full SHA for b3cb789 - Browse repository at this point
Copy the full SHA b3cb789View commit details
Commits on Nov 19, 2019
-
Overwritten with: a62196f Manual merge master:b0c1900820c into amd-gf…
…x:aa6473684ac Based on upstream llvm : b0c1900 [ARM,MVE] Add reversed isel patterns for MVE `vcmp qN,rN` Local changes since b3cb789: a62196f Manual merge master:b0c1900820c into amd-gfx:aa6473684ac aa64736 Merged master:1587c7e86f1 into amd-gfx:c4fabe0ca62 c4fabe0 Manually merged master:32dfbd131da into amd-gfx:668f0b909c2 668f0b9 Merged master:1583158042a into amd-gfx:742c4b581f8 742c4b5 Merged master:e9bf7a60a03 into amd-gfx:06bb84fb51f 06bb84f Merged master:3d6b53980ce into amd-gfx:cf4b9356a59 cf4b935 Merged master:86f07e826f4 into amd-gfx:1b898c6c158 1b898c6 Merged master:f7499011ca2 into amd-gfx:5980e79c13d 5980e79 Merged master:a12f588ebb1 into amd-gfx:d3cebd9c93a d3cebd9 Merged master:fd9fa9995cd into amd-gfx:35089c4c3b6 35089c4 Merged master:fed17867cd4 into amd-gfx:065f7d6ebe6 065f7d6 Merged master:9a1c243aa5d into amd-gfx:3cc5daff06c 3cc5daf Merged master:d384ad6b636 into amd-gfx:b1a4e621b5a b1a4e62 Merged master:ef150e2ea51 into amd-gfx:dbed94f8efc dbed94f Merged master:592dd459242 into amd-gfx:cbf5809133d cbf5809 Merged master:7d0b1d77b3d into amd-gfx:a850655dec9 a850655 Merged master:eb8710cb93a into amd-gfx:c8e1ec406d7 c8e1ec4 Merged master:49fb4a96e0b into amd-gfx:1613c2ba305 1613c2b Merged master:fdf3d1766bb into amd-gfx:82c58d0dd35 82c58d0 Merged master:59d3fbc227c into amd-gfx:b1e28d1cf0a b1e28d1 Merged master:51adeae1c90 into amd-gfx:f5179b4e8c1 f5179b4 Merged master:15bc4dc9a89 into amd-gfx:d401164f02a Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: I2488ebcc3395e6214a722845c8d2c575170cf80c
Configuration menu - View commit details
-
Copy full SHA for 9894965 - Browse repository at this point
Copy the full SHA 9894965View commit details
Commits on Nov 21, 2019
-
Overwritten with: a3f66b0 Merged master:a9bb669e59f into amd-gfx:7404…
…bcaed72 Based on upstream llvm : a9bb669 [FileCollector] Ignore empty paths. Local changes since 9894965: a3f66b0 Merged master:a9bb669e59f into amd-gfx:7404bcaed72 7404bca Merged master:a21940eac14 into amd-gfx:776f23f3a1f 776f23f Merged master:82dc32e2d45 into amd-gfx:f8723175451 f872317 Merged master:c502bae5241 into amd-gfx:e40ee12b6f1 e40ee12 Merge "[AMDGPU] Make WQM aware of Waterfall intrinsics" into amd-gfx 4dfd372 [AMDGPU] Extra fixes for "Use SGPR_128 instead of SReg_128" c086c04 Reinstate "AMDGPU: Use SGPR_128 instead of SReg_128 for vregs" Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: Ic9aa663cafa27a70255b545fadb1142d478c6d4f
Configuration menu - View commit details
-
Copy full SHA for cc9adb3 - Browse repository at this point
Copy the full SHA cc9adb3View commit details
Commits on Nov 26, 2019
-
Overwritten with: 5e3bf90 AMDGPU: Partially revert Make WQM aware of …
…Waterfall intrinsics Based on upstream llvm : 339502c [clangd] Reland b5135a8: Fix a crash in expected types Local changes since cc9adb3: 5e3bf90 AMDGPU: Partially revert Make WQM aware of Waterfall intrinsics 3e8531d AMDGPU: Fix lit test checks with dag option 0da4840 Manual merge master:339502cc8ab into amd-gfx:a3f66b052d7 Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: I1a02d9a144841e2bfe849c1ed97bea1dff663bd1
Configuration menu - View commit details
-
Copy full SHA for 728902d - Browse repository at this point
Copy the full SHA 728902dView commit details
Commits on Dec 2, 2019
-
Overwritten with: cad4275 Revert "AMDGPU: Change boolean content type…
… to 0 or 1" Based on upstream llvm : e9e1daf [ARM] Remove VHADD patterns Local changes since 728902d: cad4275 Revert "AMDGPU: Change boolean content type to 0 or 1" e9043c4 Merged master:e9e1daf2b9e into amd-gfx:e99a753251e e99a753 Merged master:3b0b7536a31 into amd-gfx:64b7877eaf8 64b7877 Merged master:19daa21f841 into amd-gfx:f034d7824a1 f034d78 Merged master:bc7f1df6b61 into amd-gfx:3295d541ef7 3295d54 Merged master:acd7fe8636a into amd-gfx:41e478fb64a 41e478f Merged master:f39277c1d37 into amd-gfx:448e14f2c88 448e14f Merged master:2e3c040ee06 into amd-gfx:6a77ef46e2d 6a77ef4 Merged master:943d8326dd3 into amd-gfx:0b6cee493f3 0b6cee4 Merged master:bb7d75ef1df into amd-gfx:23891d0bd4b 23891d0 Merged master:5e6b728763e into amd-gfx:f4c4257d522 f4c4257 Merged master:0f4383faa75 into amd-gfx:b06bbd87396 b06bbd8 Merged master:a29aa471062 into amd-gfx:52900510643 5290051 Merged master:3b35603a56b into amd-gfx:aca1eb387fa aca1eb3 Merged master:d11dc9e77b6 into amd-gfx:d4d1cb7cfcf d4d1cb7 Merged master:49a2b2a3d2c into amd-gfx:48b7fbb31f9 48b7fbb Merged master:d7be3eab5c0 into amd-gfx:1bdf52add2d 1bdf52a Merged master:8805316172a into amd-gfx:36c2fd72e78 36c2fd7 Merged master:5f8b8d28204 into amd-gfx:68f7718e978 68f7718 [AMDGPU] Extend the pre-gfx8 vccz bug workaround d34946f Merge "AMDGPU: Update llvm.amdgcn.mfma.ll fix to match upstream version" into amd-gfx e0f4c8d Merged master:7fbaa8097ec into amd-gfx:63502dc8564 63502dc Merged master:d1782133d96 into amd-gfx:17856c3f0bd 17856c3 Merged master:29b4d8f19e3 into amd-gfx:5b66d8d1fb7 5b66d8d Merged master:e841029aef7 into amd-gfx:fd06200fd90 fd06200 Merged master:bae5aac1ff4 into amd-gfx:bb5eee37b2f bb5eee3 Merged master:01e8dd2e7a8 into amd-gfx:148e72f8974 148e72f Merged master:80cd6b6e043 into amd-gfx:28ca29a47cf 28ca29a Merged master:6b2431e0c2a into amd-gfx:fb843514f54 fb84351 Merged master:cb15ba84fe7 into amd-gfx:2c47006251b 2c47006 Merged master:96cf5c8d478 into amd-gfx:36a59782837 36a5978 Merged master:0b0dca9f6fe into amd-gfx:572453d9582 572453d Merged master:b9a26a80c81 into amd-gfx:64a41bc33bd 64a41bc Merged master:3b901ce3675 into amd-gfx:6d0babc8a6d 6d0babc Merged master:4dc2fb123dc into amd-gfx:f3580a1dc82 f3580a1 Merged master:1b9ef3bbb59 into amd-gfx:a8ee5c870a9 a8ee5c8 Merged master:d3fec7fb456 into amd-gfx:5e3bf90389a Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: Id8c12084797e2733736f4fb38e7f8283fdc5bef6
Configuration menu - View commit details
-
Copy full SHA for 7858771 - Browse repository at this point
Copy the full SHA 7858771View commit details -
Revert "AMDGPU: Change boolean content type to 0 or 1"
This reverts commit 31479d8. Change-Id: I04bc9c209e06704bdc23e42e08af1634d91ae002
Configuration menu - View commit details
-
Copy full SHA for 1532478 - Browse repository at this point
Copy the full SHA 1532478View commit details -
Overwritten with: 1532478 Revert "AMDGPU: Change boolean content type…
… to 0 or 1" Based on upstream llvm : a9bb669 [FileCollector] Ignore empty paths. Local changes since cc9adb3: 1532478 Revert "AMDGPU: Change boolean content type to 0 or 1" Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: Ie6a2f1013fea74b803d84bc8f8c367be74a74b8c
Configuration menu - View commit details
-
Copy full SHA for a62a00e - Browse repository at this point
Copy the full SHA a62a00eView commit details
Commits on Dec 3, 2019
-
Merged amd-gfx-legal-branch2 into amd-gfx-legal-branch
amd-gfx-legal-branch2 was created just to cherry-pick the fix 1532478 Revert "AMDGPU: Change boolean content type to 0 or 1" for an already underway testing cycle. That fix is already in amd-gfx-legal. Merging amd-gfx-legal-branch2 ensures we have an unbroken history when pushing out to GPUOpen drivers on Github. Change-Id: I75474b46b9c3679fa6024e0ff2b53ab568b3cbbf
Configuration menu - View commit details
-
Copy full SHA for 9dad443 - Browse repository at this point
Copy the full SHA 9dad443View commit details
Commits on Dec 6, 2019
-
Revert "[InstCombine] remove identity shuffle simplification for mask…
… with undefs" This reverts commit f575f12. Change-Id: I7ff1354de1a7894c3f2c1f10b86b7c4ca3a0ca96
Configuration menu - View commit details
-
Copy full SHA for 198b0c7 - Browse repository at this point
Copy the full SHA 198b0c7View commit details -
Overwritten with: 198b0c7 Revert "[InstCombine] remove identity shuff…
…le simplification for mask with undefs" Based on upstream llvm : e9e1daf [ARM] Remove VHADD patterns Local (non-upstream) changes since 9dad443: 198b0c7 Revert "[InstCombine] remove identity shuffle simplification for mask with undefs" Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: I9283b44ac9c307eebf010d41754dbdb28acc7520
Configuration menu - View commit details
-
Copy full SHA for cc0df5a - Browse repository at this point
Copy the full SHA cc0df5aView commit details
Commits on Dec 11, 2019
-
Overwritten with: 9333d68 Merged master:170ee645f4d into amd-gfx:8177…
…33143d1 Based on upstream llvm : 170ee64 [clang-tidy] Link shared library clangTidyOpenMPModule to library LLVMFrontendOpenMP Local changes since cc0df5a: 9333d68 Merged master:170ee645f4d into amd-gfx:817733143d1 8177331 Merged master:6dad5e441db into amd-gfx:e29b386cb9a e29b386 Merged master:d32484f40cb into amd-gfx:8980a783ffd 8980a78 Merged master:9ed681f9261 into amd-gfx:999cf270203 999cf27 Merged master:a38396939c5 into amd-gfx:763ce7cebd8 763ce7c Merged master:03a242bd41e into amd-gfx:b48a1ce2a82 b48a1ce Revert "[InstCombine] remove identity shuffle simplification for mask with undefs" 6ad9050 Merged master:2c63e8e36df into amd-gfx:f4c51959c4b f4c5195 Merged master:39ccc099c90 into amd-gfx:9da89266d74 9da8926 Merged master:4dac97eb1e6 into amd-gfx:12c2f1bbf74 12c2f1b Merged master:a9f10ebffaa into amd-gfx:4765caf2752 4765caf Merged master:01e5290b49b into amd-gfx:d6d21f5cf6c d6d21f5 Merged master:09311459e37 into amd-gfx:0f31e70c1aa 0f31e70 Merged master:41eeded8043 into amd-gfx:936fb7dd0a6 936fb7d Merged master:82f6ae5433c into amd-gfx:f07e6001b81 f07e600 Merged master:cd04e8349bd into amd-gfx:12ed18ff8c4 12ed18f Merged master:46db6068342 into amd-gfx:e5ca2af09e0 e5ca2af Merged master:c4c464f8a50 into amd-gfx:de0adae431b de0adae Merged master:5595249e48e into amd-gfx:9ddf7c26de0 9ddf7c2 Merged master:8bf31e28d7b into amd-gfx:6a1ebdb306e 6a1ebdb Merged master:409350deeaf into amd-gfx:9b5c6e5fe65 9b5c6e5 Merged master:057626b4393 into amd-gfx:b253b7e85b8 b253b7e Merged master:33f93ea23a0 into amd-gfx:1758334b25d 1758334 Merged master:3ebfab70958 into amd-gfx:0be2e48798b 0be2e48 Merged master:dcf11c5e86c into amd-gfx:fab49ccd7ae fab49cc Merged master:4f728bfc13c into amd-gfx:cad42751dee Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: I88a97fb3e54619c28d204de4eda0c8f9afff835b
Configuration menu - View commit details
-
Copy full SHA for 0549a86 - Browse repository at this point
Copy the full SHA 0549a86View commit details
Commits on Dec 16, 2019
-
Overwritten with: 131b828 Merge master:fce1a6f5848 into amd-gfx:9e2b7…
…a4f3b3 Based on upstream llvm : fce1a6f Revert "AMDGPU: Try to commute sub of boolean ext" Local changes since 0549a86: 131b828 Merge master:fce1a6f5848 into amd-gfx:9e2b7a4f3b3 9e2b7a4 Revert "Revert "AMDGPU: Change boolean content type to 0 or 1"" 296f1a2 Merged master:7b774b7cd48 into amd-gfx:9333d68d986 Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: I6fc27f14d2679f78e0e85a2b66e41f370f3d7651
Configuration menu - View commit details
-
Copy full SHA for c22b899 - Browse repository at this point
Copy the full SHA c22b899View commit details
Commits on Jan 4, 2020
-
Overwritten with: 724d215 Merged master:0f0330a7870 into amd-gfx:4d56…
…2be294b Based on upstream llvm : 0f0330a [PowerPC] Legalize rounding nodes Local changes since c22b899: 724d215 Merged master:0f0330a7870 into amd-gfx:4d562be294b 4d562be Merged master:948e745270d into amd-gfx:6760a4d8875 6760a4d Merged master:4a188fdfa79 into amd-gfx:e10a557109a e10a557 Merged master:36ae255663c into amd-gfx:2b14c805739 2b14c80 Merged master:134ef0fb4b9 into amd-gfx:4d73740ec7e 4d73740 Merged master:3356e268f6c into amd-gfx:3d542200e83 3d54220 Merged master:e25e3d75850 into amd-gfx:8545c1fc925 8545c1f Merged master:cda94d3e8ae into amd-gfx:a78cf91cc1a a78cf91 Merged master:e2d9f4e6a28 into amd-gfx:1291a95764f 1291a95 Merged master:e308a0ca15a into amd-gfx:8b31d4bb755 8b31d4b Merged master:54c52242034 into amd-gfx:669a5b9da2e 669a5b9 Merged master:d2a8e14177f into amd-gfx:25c967a1eec 25c967a Merged master:80c45e49c33 into amd-gfx:7522b40c1cb 7522b40 Merged master:1a2d2b492a3 into amd-gfx:8f52c0ef660 8f52c0e Merged master:8304781cae9 into amd-gfx:c64ea0409b2 c64ea04 Merged master:c7c05b0c8a0 into amd-gfx:f946f65516c f946f65 Merged master:e40ac74dacd into amd-gfx:45c4cfde3cf 45c4cfd Merged master:982a9e3d46b into amd-gfx:f2ac07a81ed f2ac07a Merged master:76d294cb874 into amd-gfx:0185fe179ea 0185fe1 Merged master:6d5e35e89d7 into amd-gfx:f9336878686 f933687 Merged master:ff92c56ef97 into amd-gfx:fca8d3e2414 fca8d3e Merged master:a9c845395f8 into amd-gfx:96f3f925d93 96f3f92 Merged master:e498be57387 into amd-gfx:b8f35abb804 b8f35ab Merged master:88a973cf688 into amd-gfx:a1a4da7d53a a1a4da7 Merged master:40425183352 into amd-gfx:c99629390cb c996293 Merged master:830e08b98bc into amd-gfx:4b00afd8032 4b00afd Manually Merged master:308b8b76cee into amd-gfx:4c172c4c298 4c172c4 Merged master:345f59667d8 into amd-gfx:c7c3b88d580 c7c3b88 Merged master:f8495017f02 into amd-gfx:a6cdb6608ab a6cdb66 Revert "Revert "[InstCombine] remove identity shuffle simplification for mask with undefs"" 8d1fae4 Merged master:959ed0e2944 into amd-gfx:131b8289ffd Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: I991443a941e8316f431a6074231217ba637d41b2
Configuration menu - View commit details
-
Copy full SHA for 08268e9 - Browse repository at this point
Copy the full SHA 08268e9View commit details
Commits on Jan 16, 2020
-
Overwritten with: 293ea45 Manually merged master:6d6a4590c5d into amd…
…-gfx:7c951d6eaf5 Based on upstream llvm : 6d6a459 [DWARF5][clang]: Added support for DebugInfo generation for auto return type for C++ member functions. Local (non-upstream) changes since 08268e9: 821d322 Fix up tests to work with merge of master:a000f2e53f5 d366c9a Fix up tests to work with merge of master:1247865fe02 Added AMD modification notices and removed non-LLVM directories and some GPL files. Change-Id: I12d8889fc67c73d71d62d8ffe836a084fe1d8de2
Tim Renouf committedJan 16, 2020 Configuration menu - View commit details
-
Copy full SHA for 1ecf0a1 - Browse repository at this point
Copy the full SHA 1ecf0a1View commit details
Commits on Jan 24, 2020
-
Overwritten with: 293ea45 Manually merged master:6d6a4590c5d into amd…
…-gfx:7c951d6eaf5 This is the first amd-gfx-legal that includes all llvm-project files, not just llvm itself. Based on upstream llvm : 6d6a459 [DWARF5][clang]: Added support for DebugInfo generation for auto return type for C++ member functions. No local changes since 1ecf0a1. Added AMD modification notices and removed some GPL files. Change-Id: I43433157887114e29540eefb57daf2d4ea5de1d7
Configuration menu - View commit details
-
Copy full SHA for b8057d9 - Browse repository at this point
Copy the full SHA b8057d9View commit details
Commits on Jan 27, 2020
-
Overwritten with: 7ebe085 Manually merged master:b54aa053d3a into amd…
…-gfx:e9c2e262572 Based on upstream llvm : b54aa05 Update clang-interpreter example to incorporate changes in ce2207a. Local changes since b8057d9: 7ebe085 Manually merged master:b54aa053d3a into amd-gfx:e9c2e262572 e9c2e26 Manually merged master:25afe91fd1b into amd-gfx:66dfcd6fd7a 66dfcd6 Manual merge master:cfd366ba74c into amd-gfx:293ea4504e7 Added AMD modification notices and removed some GPL files. Change-Id: Id032693f00003a779b46bc6c6c49aafbcd845beb
Configuration menu - View commit details
-
Copy full SHA for 861404a - Browse repository at this point
Copy the full SHA 861404aView commit details
Commits on Feb 6, 2020
-
Overwritten with: 0cd3f3e [AMDGPU] Don't remove short branches over k…
…ills Based on upstream llvm : b54aa05 Update clang-interpreter example to incorporate changes in ce2207a. Local changes since 861404a: 0cd3f3e [AMDGPU] Don't remove short branches over kills Added AMD modification notices and removed some GPL files. Change-Id: I500f5772f5b844856a726845d2fbd4e84493fe80
Configuration menu - View commit details
-
Copy full SHA for 71e5ca0 - Browse repository at this point
Copy the full SHA 71e5ca0View commit details -
Overwritten with: f54c614 AMDGPU: During img instruction ret value co…
…nstruction cater for non int values Based on upstream llvm : 69558c8 [AArch64][SVE] Add remaining SVE2 intrinsics for uniform DSP operations Local changes since 71e5ca0: f54c614 AMDGPU: During img instruction ret value construction cater for non int values 366c47a Revert "AMDGPU/SILoadStoreOptimizer: Improve merging of out of order offsets" f455871 Revert "[AMDGPU] Temporarily disabled immarg check in verifier" fc8ae3c Test fixups for merge of master:69558c84871 d3e076a Manually merge master:69558c84871 into amd-gfx:0cd3f3ea2fb Added AMD modification notices and removed some GPL files. Change-Id: I226cb3f71a4bd48b8427b0206c65aa11fa6824b7
Configuration menu - View commit details
-
Copy full SHA for bf355f2 - Browse repository at this point
Copy the full SHA bf355f2View commit details
Commits on Feb 10, 2020
-
Overwritten with: 0d6eb9a Revert "[codegen,amdgpu] Enhance MIR DIE an…
…d re-arrange it for AMDGPU." Based on upstream llvm : 69558c8 [AArch64][SVE] Add remaining SVE2 intrinsics for uniform DSP operations Local changes since bf355f2: 0d6eb9a Revert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU." b6c8ff9 Revert "AMDGPU: Fix handling of infinite loops in fragment shaders" 3d04cee Revert "AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns" Added AMD modification notices and removed some GPL files. Change-Id: I329cb27ff14d7d43762a64efc02ac649eca73b72
Tim Renouf committedFeb 10, 2020 Configuration menu - View commit details
-
Copy full SHA for a163b38 - Browse repository at this point
Copy the full SHA a163b38View commit details
Commits on Feb 25, 2020
-
AMDGPU: Correct const_index_stride for wave 32
Since there is a single scratch resource descriptor for all shaders, if there is a wave32 and a wave64 shader (for instance the default for gfx10 VsFs pairs) then the const_index_stride will be incorrect for wave32 shaders. This change is a temporary fix to alter the const_index_stride appropriately. A longer term solution will be determined shortly. Change-Id: I0a3d4a56beacd8fa25fbd1a0a6c27d880e499f2c
Configuration menu - View commit details
-
Copy full SHA for 4048811 - Browse repository at this point
Copy the full SHA 4048811View commit details -
Overwritten with: 4048811 AMDGPU: Correct const_index_stride for wave 32
Based on upstream llvm : 69558c8 [AArch64][SVE] Add remaining SVE2 intrinsics for uniform DSP operations Local changes since a163b38: 4048811 AMDGPU: Correct const_index_stride for wave 32 Added AMD modification notices and removed some GPL files. Change-Id: Icbcea1af23dc402921bc53f14eee889165643e25
Configuration menu - View commit details
-
Copy full SHA for 434a284 - Browse repository at this point
Copy the full SHA 434a284View commit details
Commits on Feb 26, 2020
-
Dummy change to td files to fix build problem
We're getting a Windows build failure that we suspect might be due to a dependency problem with td files. Once this has filtered through the build machines, we can revert it. Change-Id: I705859ff6a0679878a8d67a373132e066d107ab0
Configuration menu - View commit details
-
Copy full SHA for 3bc4902 - Browse repository at this point
Copy the full SHA 3bc4902View commit details -
Overwritten with: 3bc4902 Dummy change to td files to fix build problem
Based on upstream llvm : c66db21 AMDGPU/GlobalISel: Un-XFAIL a test Local changes since 434a284: 3bc4902 Dummy change to td files to fix build problem d4554b3 Manually merged master:c66db211650 into amd-gfx:28d97c2b5b0 28d97c2 Fix up tests after manual merge. 931c4f8 Manually merged master:bd5b22070b6 into amd-gfx:722590f2d47 722590f AMDGPU: Correct const_index_stride for wave 32 22b4f0e Fix up tests after resolving manual merge c728071 Manually merged master:5125803d344 into amd-gfx:3246ef2f59c 3246ef2 Manually merged master:025ff5a4eaf7 into amd-gfx:46ae95423c7a3 46ae954 Revert "Revert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU."" 66a2582 [AMDGPU] Extend the vccz after write to vcc_lo/hi workaround Added AMD modification notices and removed some GPL files. Change-Id: Ia6cc9c8cc9f79e7bf39e4a6709b2c4a563ef4279
Configuration menu - View commit details
-
Copy full SHA for 878d4bd - Browse repository at this point
Copy the full SHA 878d4bdView commit details
Commits on Mar 11, 2020
-
Cherry-picked: Revert "Revert "Revert "[codegen,amdgpu] Enhance MIR D…
…IE and re-arrange it for AMDGPU.""" This reverts commit 46ae954. Change-Id: Ibf349d02332713b2e9f070c103b93bdbc665d2c8
Configuration menu - View commit details
-
Copy full SHA for 0d25720 - Browse repository at this point
Copy the full SHA 0d25720View commit details -
Overwritten with: 0d25720 Cherry-picked: Revert "Revert "Revert "[cod…
…egen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU.""" Based on upstream llvm : c66db21 AMDGPU/GlobalISel: Un-XFAIL a test Local changes since 878d4bd: 0d25720 Cherry-picked: Revert "Revert "Revert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU.""" Added AMD modification notices and removed some GPL files. Change-Id: Ied2f7d06ce21cc49c4e82bcf71320828e4b9df4c
Configuration menu - View commit details
-
Copy full SHA for e404e4b - Browse repository at this point
Copy the full SHA e404e4bView commit details -
Overwritten with: 2ad1b3f Revert "Revert "Revert "[codegen,amdgpu] En…
…hance MIR DIE and re-arrange it for AMDGPU.""" Based on upstream llvm : f0de8d0 [Arm] Do not lower vmax/vmin to Neon instructions Local changes since e404e4b: 2ad1b3f Revert "Revert "Revert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU.""" 0a6ed48 [AMDGPU] Add llvm.amdgcn.raw.atomic.buffer.load intrinsic to support OpAtomicLoad lowering ab553d6 Merged master:f0de8d09409 into amd-gfx:200eabe9376 200eabe Merged master:5aa5c943f7d into amd-gfx:81fd7fd17ec 81fd7fd Manual merge master:6518b72f93f into amd-gfx:35b401f69b2 35b401f Merged master:7391885d5c5 into amd-gfx:798e169e5a9 798e169 Merged master:c7b6fa8f4b8 into amd-gfx:66294fedccd 66294fe Merged master:11ab687c660 into amd-gfx:e2971dba8d6 e2971db Merged master:92a295eb399 into amd-gfx:7056b492b07 7056b49 Merged master:cada5b881b6 into amd-gfx:1c25ee221c3 1c25ee2 Merged master:7a11cc06a4f into amd-gfx:3b5ca44ba62 3b5ca44 Merged master:a2fe17cdc65 into amd-gfx:432f3e0b84b 432f3e0 Merged master:ffcb4923275 into amd-gfx:3c58ed3a731 3c58ed3 Merged master:3245dd59b12 into amd-gfx:2ef014e09ed 2ef014e Merged master:ec3060c72de into amd-gfx:d6568380fb6 d656838 Merged master:068b2f313c7 into amd-gfx:53ca5638111 53ca563 Merged master:8ba8ab8c95f into amd-gfx:5e49f586b6a 5e49f58 Fix up tests after manual merge 5662ccf Manually merged master:237625757a1 into amd-gfx:dc1257ed3f4 dc1257e Manually merged master:1d104f75498 into amd-gfx:c625fb9f60f c625fb9 Fix unintended line end changes introduced in manual merge. b5b13d1 Merged master:740ed617f7d into amd-gfx:d696f961d2a d696f96 Merged master:197bda587b4 into amd-gfx:e96bde62482 e96bde6 Manually merged master:016d91ccbd4 into amd-gfx:d4554b34e07 Added AMD modification notices and removed some GPL files. Change-Id: Idc5018f529b066f1da0ced4c75f3c448c8718171
Configuration menu - View commit details
-
Copy full SHA for 0aab7f3 - Browse repository at this point
Copy the full SHA 0aab7f3View commit details
Commits on Mar 12, 2020
-
Overwritten with: 80e004f [AMDGPU] Add transformation of kills to dem…
…otes in simple scenarios Based on upstream llvm : f0de8d0 [Arm] Do not lower vmax/vmin to Neon instructions Local changes since 0aab7f3: 80e004f [AMDGPU] Add transformation of kills to demotes in simple scenarios ca9afc9 [AMDGPU] Optimize conditional discard 3df0df0 [AMDGPU] Implement unused helper cleanup and early term for demote 4b66c31 AMDGPU: Remove SI_DEMOTE_I1_TERMINATOR Added AMD modification notices and removed some GPL files. Change-Id: I5cc8fdac57b827d1bf308b2af0903c3d1fa7ca4b
Configuration menu - View commit details
-
Copy full SHA for 9ad2301 - Browse repository at this point
Copy the full SHA 9ad2301View commit details
Commits on Mar 13, 2020
-
Overwritten with: 46601da Reinstate getSplat(unsigned NumElts, Consta…
…nt *V) Based on upstream llvm : 09c8f38 [X86] Add isel patterns for X86VBroadcast with i16 truncates from i16->i64 zextload/extload. Local changes since 9ad2301: 46601da Reinstate getSplat(unsigned NumElts, Constant *V) d8c450e Manually merged master:09c8f38924d into amd-gfx:3207753660b 3207753 Merged master:c8f0d27ef37 into amd-gfx:80e004f6b88 Added AMD modification notices and removed some GPL files. Change-Id: Iab2481af10c7bb30fca78cd5dafd17d4c4dc6d11
Configuration menu - View commit details
-
Copy full SHA for 815afb5 - Browse repository at this point
Copy the full SHA 815afb5View commit details
Commits on Mar 14, 2020
-
Overwritten with: 0aab7f3 Overwritten with: 2ad1b3f Revert "Revert "R…
…evert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU.""" Based on upstream llvm : f0de8d0 [Arm] Do not lower vmax/vmin to Neon instructions This _reverts_ the following local changes since 815afb5: 46601da Reinstate getSplat(unsigned NumElts, Constant *V) d8c450e Manually merged master:09c8f38924d into amd-gfx:3207753660b 3207753 Merged master:c8f0d27ef37 into amd-gfx:80e004f6b88 80e004f [AMDGPU] Add transformation of kills to demotes in simple scenarios ca9afc9 [AMDGPU] Optimize conditional discard 3df0df0 [AMDGPU] Implement unused helper cleanup and early term for demote 4b66c31 AMDGPU: Remove SI_DEMOTE_I1_TERMINATOR The reversion was because one of the demote/kill/discard changes was causing a small number of CTS failures. Added AMD modification notices and removed some GPL files. Change-Id: Ic38828e54c0fd1e1f5b0019b413fe511ace9bf36
Configuration menu - View commit details
-
Copy full SHA for 5c958c7 - Browse repository at this point
Copy the full SHA 5c958c7View commit details
Commits on Mar 17, 2020
-
Overwritten with: da5f3ad Merged master:536ba6373f0 into amd-gfx:4833…
…3f64843 Based on upstream llvm : 536ba63 [Object] Change ELFObjectFile<ELFT>::getFileFormatName() to use BFD names Local changes since 5c958c7: da5f3ad Merged master:536ba6373f0 into amd-gfx:48333f64843 48333f6 Merged master:332edcc6bd1 into amd-gfx:0e6fea325fb 0e6fea3 Revert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU." c9ea143 Fix up test after manual merge 5c92a0d Merged master:b1a7a245ec2 into amd-gfx:08dd4e64e34 4f0a0d6 Revert "Revert "Revert "Revert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU."""" 08dd4e6 Merged master:7b74b0d4e54 into amd-gfx:46601da50bc Also unreverted the changes that were reverted last time: 46601da Reinstate getSplat(unsigned NumElts, Constant *V) d8c450e Manually merged master:09c8f38924d into amd-gfx:3207753660b 3207753 Merged master:c8f0d27ef37 into amd-gfx:80e004f6b88 80e004f [AMDGPU] Add transformation of kills to demotes in simple scenarios ca9afc9 [AMDGPU] Optimize conditional discard 3df0df0 [AMDGPU] Implement unused helper cleanup and early term for demote 4b66c31 AMDGPU: Remove SI_DEMOTE_I1_TERMINATOR Added AMD modification notices and removed some GPL files. Change-Id: If426bf03fe119c8cfbccb8985ce87e29daf1b26b
Configuration menu - View commit details
-
Copy full SHA for b2b163f - Browse repository at this point
Copy the full SHA b2b163fView commit details
Commits on Mar 20, 2020
-
Overwritten with: c263608 Merged master:ac1d23ed7de into amd-gfx:5c70…
…4214880 Local branch amd-gfx 5c70421 Revert "Revert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU."" Remote branch master ac1d23e Replace MCTargetOptionsCommandFlags.inc and CommandFlags.inc by runtime registration Based on upstream llvm : ac1d23e Replace MCTargetOptionsCommandFlags.inc and CommandFlags.inc by runtime registration Local changes since b2b163f: c263608 Merged master:ac1d23ed7de into amd-gfx:5c704214880 Local branch amd-gfx 5c70421 Revert "Revert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU."" Remote branch master ac1d23e Replace MCTargetOptionsCommandFlags.inc and CommandFlags.inc by runtime registration 5c70421 Revert "Revert "[codegen,amdgpu] Enhance MIR DIE and re-arrange it for AMDGPU."" 7f46ac1 [AMDGPU] Fix AMDGPUUnifyDivergentExitNodes 7102251 Revert "Revert "AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns"" c36d5fd Revert "Revert "AMDGPU: Fix handling of infinite loops in fragment shaders"" 1d901ab Manually merged master:4ece6f051bd into amd-gfx:26c8789ad97 26c8789 Merge "[AMDGPU] Reorder target-specific passes" into amd-gfx Added AMD modification notices and removed some GPL files. Change-Id: I05317f922e8315f5cd9417850c682555bc0d8156
Configuration menu - View commit details
-
Copy full SHA for 1ebc431 - Browse repository at this point
Copy the full SHA 1ebc431View commit details
Commits on Apr 6, 2020
-
Overwritten with: 82bcf11 Revert "Reinstate getSplat(unsigned NumElts…
…, Constant *V)" Based on upstream llvm : d0d076f [Driver] Flip the CC1 default of -fdiagnostics-show-option Local changes since 1ebc431: 82bcf11 Revert "Reinstate getSplat(unsigned NumElts, Constant *V)" 443a747 Manually merged master:d0d076fed96 into amd-gfx:c9b42a6a87f c9b42a6 Merged master:b632fe5a363 into amd-gfx:0a785d33aa1 0a785d3 Merged master:3807079d705 into amd-gfx:ab17141fca4 ab17141 Manually merged master:c9d5c195976 into amd-gfx:69f9009f076 69f9009 Merged master:667781592a4 into amd-gfx:a4c6533f135 a4c6533 Merged master:36ed0ceec7d into amd-gfx:7dc0b13fd24 7dc0b13 Merged master:30a8b77080b into amd-gfx:752bb16716c 752bb16 Merged master:30c1f9a5584 into amd-gfx:2e66db910c4 2e66db9 Merged master:40076c14fef into amd-gfx:dd5f1cd5a80 dd5f1cd Merged master:8f1651ccead into amd-gfx:7fbfb2b069f 7fbfb2b Merged master:e951a489962 into amd-gfx:e67cd8b6bf1 e67cd8b Merged master:472d282046d into amd-gfx:56d934d52a0 56d934d Merged master:83346a4077b into amd-gfx:649834bc5a7 649834b Merged master:c3417592c84 into amd-gfx:19c857072d7 19c8570 Merged master:714402147da into amd-gfx:833246485c5 8332464 Merged master:b6732056a44 into amd-gfx:81c26571b86 81c2657 Merged master:ca21e60fdf3 into amd-gfx:295b0e5ef13 295b0e5 Temporarily allow ExpensiveCombines 6b29d00 Merged master:62fdb1f534b into amd-gfx:a2f019651d4 a2f0196 Manually merged master:a2459433551 into amd-gfx:d2d1dce7705 Local branch amd-gfx d2d1dce Manually merged master:60b1967c393 into amd-gfx:c818b137788 Remote branch master a245943 [LiveDebugValues] Speed up collectIDsForRegs, NFC d2d1dce Manually merged master:60b1967c393 into amd-gfx:c818b137788 Local branch amd-gfx c818b13 Manually merged master:30bb113beb3 into amd-gfx:6aa2f8eadfd Remote branch master 60b1967 [AMDGPU] Add Scratch Wave Offset to Scratch Buffer Descriptor in entry functions c818b13 Manually merged master:30bb113beb3 into amd-gfx:6aa2f8eadfd Local branch amd-gfx 6aa2f8e Manually merged master:d1a7bfca743 into amd-gfx:8b1c0b36a16 Remote branch master 30bb113 [AMDGPU][NFC] Refactor emitEntryFunctionPrologue 6aa2f8e Manually merged master:d1a7bfca743 into amd-gfx:8b1c0b36a16 Local branch amd-gfx 8b1c0b3 Manually merged master:6e29846b29d into amd-gfx:c2636080d53 Remote branch master d1a7bfc [AMDGPU] Fix AMDGPUUnifyDivergentExitNodes 8b1c0b3 Manually merged master:6e29846b29d into amd-gfx:c2636080d53 Local branch amd-gfx c263608 Merged master:ac1d23ed7de into amd-gfx:5c704214880 Remote branch master 6e29846 [AMDGPU] Fix whole wavefront mode Added AMD modification notices and removed some GPL files. Change-Id: Ib9dbd031e2f945e1646f517086371674610b1261
Configuration menu - View commit details
-
Copy full SHA for 0e27e33 - Browse repository at this point
Copy the full SHA 0e27e33View commit details
Commits on Apr 7, 2020
-
Overwritten with: 5583605 [AMDGPU] Disable endcf collapse again
Configuration menu - View commit details
-
Copy full SHA for f675b27 - Browse repository at this point
Copy the full SHA f675b27View commit details
Commits on Apr 8, 2020
-
Overwritten with: c60a9bf [AMDGPU] Revert scratch wave offset changes
Configuration menu - View commit details
-
Copy full SHA for 84d753b - Browse repository at this point
Copy the full SHA 84d753bView commit details
Commits on Apr 9, 2020
-
[AMDGPU] Disable endcf collapse again
This was reenabled and supposedly fixed by D76154 but it is still causing problems. Change-Id: Iefe2abd2da7db126915743eec435053c0d076266
Configuration menu - View commit details
-
Copy full SHA for c7c3927 - Browse repository at this point
Copy the full SHA c7c3927View commit details -
Overwritten with: c7c3927 [AMDGPU] Disable endcf collapse again
Based on upstream llvm : ac1d23e Replace MCTargetOptionsCommandFlags.inc and CommandFlags.inc by runtime registration Local changes since 1ebc431: c7c3927 [AMDGPU] Disable endcf collapse again Added AMD modification notices and removed some GPL files. Change-Id: I78d18e03d4fdbcb479c8cd6f7fa651f74e03a1ec
Configuration menu - View commit details
-
Copy full SHA for 50077fc - Browse repository at this point
Copy the full SHA 50077fcView commit details
Commits on Apr 10, 2020
-
Merged amd-gfx-legal-branch3 info amd-gfx-legal
Just to avoid a history break in future amd-gfx-gpuopen-master pushes. Change-Id: I6cec1cb61b9e646c1046f9fa657e62952a0e7165
Tim Renouf committedApr 10, 2020 Configuration menu - View commit details
-
Copy full SHA for 7b14353 - Browse repository at this point
Copy the full SHA 7b14353View commit details
Commits on Apr 17, 2020
-
Overwritten with: d486507 Merged master:8812b0cc5cc into amd-gfx:f1a6…
…783f747 Based on upstream llvm : 8812b0c [NFC] Rename Sema.FPFeatures to CurFPFeatures and accessor to getCurFPFeatures Local changes since 7b14353: d486507 Merged master:8812b0cc5cc into amd-gfx:f1a6783f747 f1a6783 Merged master:69040d5b0bf into amd-gfx:708698a0004 708698a XFAIL a test while we have locally reverted "AMDGPU: Remove denormal subtarget features" 8f4f6a4 Manually merged master:7a7f2230428 into amd-gfx:5c3c4327a87 5c3c432 Manually merged master:72e8754916f into amd-gfx:bd574e0b662 bd574e0 [AMDGPU] Implement copyPhysReg for 16 bit subregs 73acb78 Revert "AMDGPU: Remove denormal subtarget features" 6d45e8b Revert "AMDGPU: Add some tests for exotic denormal mode combinations" 73eab2d Merge "[AMDGPU] Add function attributes for conditional discard transform" into amd-gfx 2fc9b5d Merge branch 'merge-candidate' into amd-gfx Added AMD modification notices and removed some GPL files. Change-Id: I025be72c8b9967c3d3eb36e98c637865f46e4919
Configuration menu - View commit details
-
Copy full SHA for 5ae05ed - Browse repository at this point
Copy the full SHA 5ae05edView commit details
Commits on Apr 21, 2020
-
Overwritten with: 240ccfe Revert "[AMDGPU] Set the CostPerUse value f…
…or vgpr registers." Based on upstream llvm : fce1156 [Support][X86] Include sched.h after D78324 Local changes since 5ae05ed: 240ccfe Revert "[AMDGPU] Set the CostPerUse value for vgpr registers." 70c1043 Merged master:fce115681b7 into amd-gfx:59298bad9f4 59298ba Merged master:96b61571d03 into amd-gfx:66f7f0f88e5 66f7f0f Make the test more lenient ae9286b Revert "Revert "AMDGPU: Add some tests for exotic denormal mode combinations"" e2da9a8 Revert "Revert "AMDGPU: Remove denormal subtarget features"" 59cba1b Revert "XFAIL a test while we have locally reverted "AMDGPU: Remove denormal subtarget features"" Added AMD modification notices and removed some GPL files. Change-Id: I2d58f5b8a5673cbb277fa08de3823ade9b9d12ac
Configuration menu - View commit details
-
Copy full SHA for a1299ba - Browse repository at this point
Copy the full SHA a1299baView commit details -
Revert "[AMDGPU] Set the CostPerUse value for vgpr registers."
This reverts commit 728b878. Change-Id: I2ab4231e4d0a6b3a5574ed2993cc38059cf2f5a0
Configuration menu - View commit details
-
Copy full SHA for 3b3df72 - Browse repository at this point
Copy the full SHA 3b3df72View commit details -
Overwritten with: 3b3df72 Revert "[AMDGPU] Set the CostPerUse value f…
…or vgpr registers." Based on upstream llvm : d0d076f [Driver] Flip the CC1 default of -fdiagnostics-show-option Local changes since 84d753b: 3b3df72 Revert "[AMDGPU] Set the CostPerUse value for vgpr registers." Added AMD modification notices and removed some GPL files. Change-Id: Ic4c6d830a575432417997316a1d93802e2e07cbd
Configuration menu - View commit details
-
Copy full SHA for 15d123d - Browse repository at this point
Copy the full SHA 15d123dView commit details -
Merge amd-gfx-legal-branch4 into amd-gfx-legal
This is just to avoid losing history. There is no change. Change-Id: I2220b80292c85b4b77c5524ce6376d4796a258bc
Configuration menu - View commit details
-
Copy full SHA for f02738a - Browse repository at this point
Copy the full SHA f02738aView commit details
Commits on Apr 24, 2020
-
Overwritten with: ae0e477 Merge "[AMDGPU] Avoid more hard-coded line …
…numbers in error message checks" into amd-gfx Based on upstream llvm : 7aaff8f [ADT] Move allocate_buffer to MemAlloc.h and out of line Local changes since f02738a: ae0e477 Merge "[AMDGPU] Avoid more hard-coded line numbers in error message checks" into amd-gfx b801492 Merged master:7aaff8fd2da into amd-gfx:bae146db16f bae146d Fixups for problems with merge 0343ef9 Merged master:1dfc4731773 into amd-gfx:40efb63f41a 40efb63 Revert "Revert "AMDGPU/SILoadStoreOptimizer: Improve merging of out of order offsets"" 1339c87 Merged master:9174e0229fc into amd-gfx:a9b0ae69420 a9b0ae6 [AMDGPU] Initialize a couple more backend passes 929923b Fixes for upstream commit 0337017 [AMDGPU] Use SGPR instead of SReg classes 022c217 Manually merged master:3a5380618e8 into amd-gfx:eb2e6253f6f eb2e625 Merged master:002164461b5 into amd-gfx:dfd93953c6b dfd9395 Merged master:21caba599e6 into amd-gfx:f8a0520db91 f8a0520 Merged master:4330d783e7d into amd-gfx:7d45429f286 7d45429 Merged master:7b5497f2585 into amd-gfx:ba79f461a9e ba79f46 Merged master:3db893b3712 into amd-gfx:488a696f368 488a696 Merged master:478619cf9a2 into amd-gfx:4b9228caf0f 4b9228c Merged master:2464d8135e2 into amd-gfx:8058cc0c5cc 8058cc0 Merged master:1109dcba20d into amd-gfx:ea5d6b7a9cc ea5d6b7 Merged master:54b3f91d205 into amd-gfx:3a3ac626562 3a3ac62 Revert "Temporarily allow ExpensiveCombines" 84f6726 Merged master:b2f06bd20bd into amd-gfx:f9146da7cc2 f9146da Manual merge master:2fa17cdd7ad into amd-gfx:240ccfe95f7 Added AMD modification notices and removed some GPL files. Change-Id: I109b47f867175599bc51fa088506b0dd924cc54a
Configuration menu - View commit details
-
Copy full SHA for 53692d9 - Browse repository at this point
Copy the full SHA 53692d9View commit details
Commits on May 13, 2020
-
[MsgPack] MsgPackDocument::readFromBlob now merges
The readFromBlob method can now be used to read MsgPack into a Document that already contains something, merging the two. There is a new Merger argument to readFromBlob, a callback function to resolve conflicts. Differential Revision: https://reviews.llvm.org/D79671 Change-Id: Icf3e959217fe33cd907a41516c0386aef2847c0c
Configuration menu - View commit details
-
Copy full SHA for 4ae16c2 - Browse repository at this point
Copy the full SHA 4ae16c2View commit details -
Overwritten with: 4ae16c2 [MsgPack] MsgPackDocument::readFromBlob now…
Configuration menu - View commit details
-
Copy full SHA for c57487b - Browse repository at this point
Copy the full SHA c57487bView commit details
Commits on May 22, 2020
-
Overwritten with: 536937b [AMDGPU] Fixed incorrect PAL metadata regis…
…ter naming Based on upstream llvm : 1108f5c Revert "[Analyzer][WebKit] RefCntblBaseVirtualDtorChecker" Local changes since c57487b: 536937b [AMDGPU] Fixed incorrect PAL metadata register naming fea33b8 [MsgPack] Added convenience assignment to MsgPackDocument a8a9afa [MsgPack] MsgPackDocument::readFromBlob now merges a6ecbe0 Revert "[MsgPack] MsgPackDocument::readFromBlob now merges" f8d60b6 Merged master:1108f5c737d into amd-gfx:532c99a8595 532c99a Merged master:60dff35fd43 into amd-gfx:90f8570b7b5 90f8570 Merged master:cb2a8be8842 into amd-gfx:ca31f9b6b2a ca31f9b Merged master:1c8f999e0b5 into amd-gfx:2a5ce91cde1 2a5ce91 Merged master:259eb619ff6 into amd-gfx:623a3b74462 623a3b7 Manually merged master:b0614509a0f into amd-gfx:23191ac2b63 23191ac Merged master:f7c9f77ef37 into amd-gfx:dc7e60f7ee9 dc7e60f Merged master:58684fbb6f2 into amd-gfx:df7835fce04 df7835f Merged master:9f2ce5b915a into amd-gfx:da500a271aa da500a2 Merged master:a45fb1942fc into amd-gfx:313eb908304 313eb90 Merged master:fe1a3a7e8c8 into amd-gfx:1c924b1df42 1c924b1 Merged master:d5b1643c74e into amd-gfx:18277e45d3c 18277e4 Merged master:3181273be73 into amd-gfx:ecacc9b6665 ecacc9b Merged master:81a73fde5ce into amd-gfx:6cfa4a5eaa9 6cfa4a5 Merged master:575c59cf6a3 into amd-gfx:a289501ada2 a289501 Merged master:500479dba33 into amd-gfx:ed93d6f8c68 ed93d6f Merged master:31ecef76275 into amd-gfx:d0b408567a7 d0b4085 Merged master:22d40cc3a72 into amd-gfx:e7412f8ea89 e7412f8 Merged master:a675c1dee48 into amd-gfx:173ac078342 173ac07 [IR] Temporarily reintroduce StoreInst::setAlignment(MaybeAlign) 3e876bb Merge commit master:11aa3707e30 into amd-gfx:552b1c4508d 552b1c4 Merged master:62efd1eca20 into amd-gfx:2c69c504bf3 2c69c50 Merged master:1a68b5f048c into amd-gfx:3bc2ff3aa0a 3bc2ff3 Manually merged master:0ef62fc25d3 into amd-gfx:f36c7f6a8e9 f36c7f6 Revert "[StructurizeCFG] Fix region nodes ordering" cfefc88 Merged master:2668775f666 into amd-gfx:73aeaa42863 73aeaa4 Merged master:e072b20bdea into amd-gfx:54b554c0358 54b554c Merged master:e25a2601aaa into amd-gfx:3ee97c0b0f6 3ee97c0 Merged master:e59744fd9b4 into amd-gfx:1218e1e125b 1218e1e [MsgPack] MsgPackDocument::readFromBlob now merges fb57c7c Merged master:085234bedc3 into amd-gfx:120607dc739 120607d Merged master:67087a7b765 into amd-gfx:420522c57c1 420522c Merged master:96282b1a0c4 into amd-gfx:c8c3ec5d216 c8c3ec5 Merged master:cb22ab74035 into amd-gfx:6dda7cf89cb 6dda7cf Merged master:59ba19c56e1 into amd-gfx:7c9eaf391f7 7c9eaf3 Merged master:11c8c2a551c into amd-gfx:401de8383fd 401de83 Merged master:b56b1e67e38 into amd-gfx:50a6dc63b7f 50a6dc6 Merged master:494c7ecef92 into amd-gfx:0818bf78a8c 0818bf7 Revert "Revert "[AMDGPU] Vectorize alloca thru bitcast"" 9f5a7cd Revert "[AMDGPU] Vectorize alloca thru bitcast" 7eee638 Merged master:0dd42e5fd32 into amd-gfx:4f8013da1d1 4f8013d Merged master:e9b41139028 into amd-gfx:fb0f2ab6ceb fb0f2ab Merged master:e20a215992d into amd-gfx:791da285c8e 791da28 Merged master:710fa2c4ee3 into amd-gfx:ca022c58f8c ca022c5 Merged master:9c198b550eb into amd-gfx:319f48f5c47 319f48f Merged master:5e74cf29991 into amd-gfx:704963904e8 7049639 Merged master:4356aa20bce into amd-gfx:8e279c1a019 8e279c1 Merged master:b6c6bab9a5b into amd-gfx:3d88383fde3 3d88383 Merged master:16027bbc3ba into amd-gfx:697069a621d 697069a Merge master:6999ffcc399 into amd-gfx 0aaf507 Merge master:0d4d86cbd19 into amd-gfx e9ce1da Remove some unnecessary diffs from upstream a15e7c1 Merge master:f7060f4f88f into amd-gfx 04eeded Revert "[AMDGPU] Revert scratch wave offset changes" 92671f2 Revert "Make the test more lenient" 40c0da7 Merge master:2f1fe1864d2 into amd-gfx bef5b30 Merged master:5010b5b7e6c into amd-gfx:7b0a59c9089 7b0a59c Merged master:7d507ff55f6 into amd-gfx:8f20270d5ce 8f20270 Merge remote-tracking branch 'llvm/master' into HEAD d00989c Merge remote-tracking branch 'llvm/master' into HEAD 6fd51e5 Manual merge master:cd3a54c55a3 into amd-gfx:89342745e9c 8934274 Merge "[AMDGPU] Fix waterfall intrinsic divergence with image sample" into amd-gfx ed17950 Merged master:19f5da9c1d6 into amd-gfx:f5f1c06d6e8 f5f1c06 Remove unnecessary diffs from upstream. 52d60fe Merge remote-tracking branch 'llvm/master' into HEAD 0646bde Merged master:1e89f36c984 into amd-gfx:cff93414885 cff9341 Merged master:762fb1c40ee into amd-gfx:bb38fed2f6b bb38fed Merged master:14cb0bdf2b6 into amd-gfx:9976fa23769 9976fa2 Merged master:6fe20a44fd3 into amd-gfx:a047b378c8b a047b37 Merged master:81e48ae2b4a into amd-gfx:b7de78e8ad2 b7de78e Merged master:911e06f5eba into amd-gfx:9cf4847617a 9cf4847 Manually merged master:1e5793345bc into amd-gfx:e9e04d625cc 1b19d46 Merged master:b7e2358220f into amd-gfx:e9e04d625cc e9e04d6 Merged master:ff6a0b6a8ee into amd-gfx:9f5a06205c0 9f5a062 Merged master:8fa4d4a43cc into amd-gfx:dc7628e1c0d dc7628e Merged master:57818885be5 into amd-gfx:e45e6a1e841 e45e6a1 Merged master:999f04ce347 into amd-gfx:fed3063da30 fed3063 Merged master:0d5caa89401 into amd-gfx:979e34575c1 979e345 Merged master:334931f54b9 into amd-gfx:8aefd0b6608 8aefd0b Merge remote-tracking branch 'llvm/master' into HEAD cc088b2 Merged master:1428f86cf98 into amd-gfx:51fdcfa6daa 51fdcfa Merge remote-tracking branch 'llvm/master' into HEAD 1dc9121 Manually merged master:53ff95254df into amd-gfx:65be4e017a5 52fafd3 Revert "[AMDGPU] Remove WaitcntBrackets::MixedPendingEvents[]. NFC." 65be4e0 Merged master:bc029fa6c5c into amd-gfx:46e9f135e19 46e9f13 Merged master:c7878ad231e into amd-gfx:7c4ecec51ae 7c4ecec Merged master:d3dc4c32afb into amd-gfx:5af3e48076b 5af3e48 Merged master:209ab6d8835 into amd-gfx:4076e02b546 4076e02 Manually merged master:e018b8bbb0b into amd-gfx:64a620f53d2 64a620f [AMDGPU] Preserve dominators trees in WQM pass 6475878 Merged master:096b25a8d8e into amd-gfx:859d3327686 859d332 Merged master:3e14b95d99d into amd-gfx:4ddd982cddd 4ddd982 Merged master:a0919ac0809 into amd-gfx:bbe8bdb416f bbe8bdb Merged master:65f58878e72 into amd-gfx:e196777af18 e196777 Merged master:10bc12588da into amd-gfx:309ca4e723f 309ca4e Merged master:a9104f89b11 into amd-gfx:cb67ab9457b cb67ab9 Merged master:7720d6578cc into amd-gfx:4c72a307524 4c72a30 Merged master:25e22613dfd into amd-gfx:ae0e4779765 Added AMD modification notices and removed some GPL files. Change-Id: Id5538f3917501d364df3e54c24618e5f75ea1079
Tim Renouf committedMay 22, 2020 Configuration menu - View commit details
-
Copy full SHA for 3a1103f - Browse repository at this point
Copy the full SHA 3a1103fView commit details
Commits on May 28, 2020
-
Overwritten with: 05ca407 Merged master:c295a65da49 into amd-gfx:6748…
…894db1e Based on upstream llvm : c295a65 [mlir] [VectorOps] Add 'vector.flat_transpose' operation Local changes since 3a1103f: 05ca407 Merged master:c295a65da49 into amd-gfx:6748894db1e 6748894 Merged master:31f40f603d0 into amd-gfx:80e19880323 80e1988 Revert "[AMDGPU] Disable endcf collapse again" f6f8dba Merged master:6bbaa62d26b into amd-gfx:c2f8b73ef35 c2f8b73 Merged master:8e3307f5519 into amd-gfx:ffdc239d29e ffdc239 Merged master:9a0b0855a96 into amd-gfx:652b20556cf 652b205 Merged master:9eacda51fa2 into amd-gfx:06c312c8862 06c312c Merged master:d1f0a76b219 into amd-gfx:b609c6bc6d4 b609c6b Merged master:8bc03d21682 into amd-gfx:960c5e1190d 960c5e1 Merged master:792575ff323 into amd-gfx:e5da9f90ea0 e5da9f9 Merged master:c5bbc8dd6d6 into amd-gfx:5187bdabc9e 5187bda Revert local changes to LiveRangeCalc and RegisterCoalescer 099d9b5 Merged master:80cc43b420a into amd-gfx:1bf369d0317 1bf369d Merged master:34e39eb2adc into amd-gfx:44cde4286be 44cde42 Merged master:9d55e4ee136 into amd-gfx:e145900d8f8 e145900 Merged master:9a8d7bd7704 into amd-gfx:d30d5903bc7 d30d590 Merged master:3a2df3bad07 into amd-gfx:418304c43ae 418304c Merged master:179c80117c9 into amd-gfx:ea6f2908759 ea6f290 Merged master:51a276c759c into amd-gfx:a442e1e9af7 a442e1e Merged master:5bf2409a4e4 into amd-gfx:f02e6eca3c9 f02e6ec Merged master:7c298c104bf into amd-gfx:e379e37ab69 e379e37 Merged master:5d6c5b463ca into amd-gfx:d32f34d54b9 d32f34d Merged master:9ff361b099f into amd-gfx:ab819ab2285 ab819ab Merged master:83bd2c4a068 into amd-gfx:71137c55831 71137c5 Merged master:5b7ff6f07ff into amd-gfx:1d7df14175b 1d7df14 Merged master:1b79509f97b into amd-gfx:70a6b363e2e 70a6b36 Merged master:52b03aaa22f into amd-gfx:6e018a3ff5a 6e018a3 Merged master:d0da5d2bbe8 into amd-gfx:ecb862b706c ecb862b Merged master:2be92b7f7e4 into amd-gfx:d4d66176d0b d4d6617 Merged master:8a5aea7b504 into amd-gfx:71e7cbc5398 71e7cbc Merged master:d43fac052e1 into amd-gfx:ce3589e69ce ce3589e Merged master:4c5818dd8cd into amd-gfx:6e1d643447e 6e1d643 Merged master:3ed8ebc2f6b into amd-gfx:8da38b55bb2 8da38b5 Merged master:f794808bb9e into amd-gfx:05320d7a26f 05320d7 Merged master:2bb822bc902 into amd-gfx:283cdda3e48 283cdda Merged master:088fb973484 into amd-gfx:c4aada5f72c c4aada5 Merged master:9292ece9956 into amd-gfx:60c505a7221 60c505a Merged master:b631f86ac5b into amd-gfx:f8f92f28e4b f8f92f2 Merged master:2e43bab1c16 into amd-gfx:6b278f1396b 6b278f1 Merged master:27fe841aa65 into amd-gfx:5b87fc6d838 5b87fc6 Merged master:304b0ed4039 into amd-gfx:d6da82a01ea d6da82a Merged master:174322c2737 into amd-gfx:1fc9c9226d7 1fc9c92 Merged master:0c6bba71e39 into amd-gfx:b977c4043a3 b977c40 Merged master:0f6bd9cda6c into amd-gfx:9471c21a32e 9471c21 Merged master:64356b6d94e into amd-gfx:da21a0b39de da21a0b Merged master:a8a048ac725 into amd-gfx:1f4f0bca85c 1f4f0bc Merged master:0231227e5d8 into amd-gfx:5c3fdab71ab 5c3fdab Merged master:a28e9f12086 into amd-gfx:792ac253c69 792ac25 Merged master:e4bb3e25e44 into amd-gfx:3974042f37e 3974042 Merged master:5451289abaf into amd-gfx:f0cd56a3ab6 f0cd56a Merged master:8a6333ef380 into amd-gfx:308fc24ba51 308fc24 Merged master:c7e5454acec into amd-gfx:dbabb2bf465 dbabb2b Merged master:329abed10b8 into amd-gfx:92039d2cd59 92039d2 Merged master:49a4f3f7d88 into amd-gfx:9c1698c4caf 9c1698c Merged master:bb7fb6d7b2f into amd-gfx:9d914d750a0 9d914d7 Merged master:628f008b201 into amd-gfx:536937b3dc3 Added AMD modification notices and removed some GPL files. Change-Id: I2c76a37a09c4a866ff0bb1b346af9fed9426d707
Tim Renouf committedMay 28, 2020 Configuration menu - View commit details
-
Copy full SHA for 7b9d0cf - Browse repository at this point
Copy the full SHA 7b9d0cfView commit details -
Overwritten with: c307fd8 Manual merge master:1ddac9563d7f into amd-g…
…fx:05ca407e6cd1 Based on upstream llvm : 1ddac95 [X86][SSE] Peek though MOVMSK source sign bits using SimplifyMultipleUseDemandedBits Local changes since 7b9d0cf: c307fd8 Manual merge master:1ddac9563d7f into amd-gfx:05ca407e6cd1 Added AMD modification notices and removed some GPL files. Change-Id: I99343c7fe70126748de0749095423327afbe91e6
Tim Renouf committedMay 28, 2020 Configuration menu - View commit details
-
Copy full SHA for e90e9d4 - Browse repository at this point
Copy the full SHA e90e9d4View commit details
Commits on Jun 2, 2020
-
Overwritten with: 357ead6 Suppress switch with only default warning f…
…or Windows builds Based on upstream llvm : 81bf1e2 [flang] Fix release build flags. Local changes since e90e9d4: 357ead6 Suppress switch with only default warning for Windows builds 572cea8 Merged master:81bf1e29aae into amd-gfx:078f4efc643 078f4ef Merged master:6c733f5a132 into amd-gfx:869e2a4225c 869e2a4 [AMDGPU] Fixup use of StackPtrOffsetReg when not initialized 7ebf895 [AMDGPU] Fix discard transformation 446d3a5 Merged master:a6a42df506c into amd-gfx:652d2b7e64f 652d2b7 Merged master:07239c736a5 into amd-gfx:5df6a2a9b9a 5df6a2a Merged master:801d823bdec into amd-gfx:0194603d562 0194603 Merged master:a0b674fd7f0 into amd-gfx:3738c6e1244 3738c6e Merged master:b429a0fef04 into amd-gfx:3b6c0c63d99 3b6c0c6 Merged master:06aaf0b3431 into amd-gfx:531f94605a3 531f946 Merged master:1ab092b7585 into amd-gfx:d0649bf61e4 d0649bf Merged master:f97a609b176 into amd-gfx:896ff1d947a 896ff1d Merged master:d9943e7f0ce into amd-gfx:81ca3beb775 81ca3be Merged master:8d9070e040d into amd-gfx:8d98476cb3e 8d98476 Merged master:e8bcf4ef07c into amd-gfx:6c9d03142c4 6c9d031 Merged master:e75efcc3c1a into amd-gfx:5370b73ab7f 5370b73 Merged master:40a3fcb05c8 into amd-gfx:903e724f00a 903e724 Merged master:af38074874c into amd-gfx:b31d525baee b31d525 Merged master:3101601b54f into amd-gfx:b6fc631da0a b6fc631 Merged master:a8ca0ec2670 into amd-gfx:28c0fb04db7 28c0fb0 Merged master:77e1181df44 into amd-gfx:216ed1d226d 216ed1d Merged master:8f2f613a6ec into amd-gfx:af3866b06c5 af3866b Merged master:59521256915 into amd-gfx:5ccf858b005 5ccf858 Merged master:f4b0ebb89b3 into amd-gfx:563eb59b3c9 563eb59 Merged master:4a2673d79fd into amd-gfx:e87ce7d5df8 e87ce7d Merged master:45ebe38ffc4 into amd-gfx:86103e348b6 86103e3 Merged master:bfdf9ef009a into amd-gfx:1cc12f0b22d 1cc12f0 Merged master:2768edfff19 into amd-gfx:add882592ba add8825 Merged master:234eba90f4f into amd-gfx:6794d4ca2e2 6794d4c Merged master:d04eb253c71 into amd-gfx:c147dad29f0 c147dad Merged master:07e8a780d81 into amd-gfx:243518ce51b 243518c Merged master:16976cb9253 into amd-gfx:47c5bb7b612 47c5bb7 Merged master:44119626ded into amd-gfx:5aa340ab320 5aa340a Merged master:065bf124fde into amd-gfx:5f23258411c 5f23258 Merged master:d99a1848c4f into amd-gfx:bf87f406f7f bf87f40 Merged master:2b881f7911d into amd-gfx:8ea8c467816 8ea8c46 Merged master:5a918b7e134 into amd-gfx:51dd7925e2f 51dd792 Merged master:81b50a78237 into amd-gfx:ddcbd714800 ddcbd71 Merged master:92063228f85 into amd-gfx:8793c74c592 8793c74 Merged master:20c9bb44ec1 into amd-gfx:54bd13cd900 54bd13c Merged master:21fee0921d5 into amd-gfx:1a36c0ece28 1a36c0e Merged master:0892a96a05a into amd-gfx:6e4b349b90b 6e4b349 Merged master:7318e240000 into amd-gfx:6b995c35b22 6b995c3 Merged master:e75325cfc39 into amd-gfx:2f325bf0203 2f325bf Merged master:1a5c97f3a4b into amd-gfx:49b9992a301 49b9992 Merged master:61412b762df into amd-gfx:6a76c7a3f9c 6a76c7a Merged master:9e0b52e2e68 into amd-gfx:5a80597b2fc 5a80597 Merged master:9819976032c into amd-gfx:16263922300 1626392 Merged master:aa93659c9ff into amd-gfx:b71fb3cd5d4 b71fb3c Merged master:a3418631e8a into amd-gfx:c307fd81e7c Added AMD modification notices and removed some GPL files. Change-Id: Ide1a8cfef680de8c276a4cb7339b42ce47480fe7
Configuration menu - View commit details
-
Copy full SHA for daedcee - Browse repository at this point
Copy the full SHA daedceeView commit details -
Overwritten with: 357ead6 Suppress switch with only default warning f…
Configuration menu - View commit details
-
Copy full SHA for a7cfa00 - Browse repository at this point
Copy the full SHA a7cfa00View commit details
Commits on Jun 6, 2020
-
Overwritten with: 242b037 AMDGPU more fix-ups to the StackPtrOffsetReg
Based on upstream llvm : 1813451 [Test] Add test showing missing opportunity of folding ICmp(Phi(Consts...)) Local changes since a7cfa00: 242b037 AMDGPU more fix-ups to the StackPtrOffsetReg 3659c6a Merged master:18134511d93 into amd-gfx:311a20af0d4 311a20a Merged master:af6e054730a into amd-gfx:ba2cbb0d475 ba2cbb0 Merged master:b28167928d2 into amd-gfx:b09e69cbef7 b09e69c Merged master:ab6779bbd8f into amd-gfx:3e53220dbf6 3e53220 Merged master:116e38fd8b8 into amd-gfx:ac9866a082e ac9866a Merged master:f4d42732653 into amd-gfx:46422bde7eb 46422bd Merged master:6de794e2074 into amd-gfx:636dfa22996 636dfa2 Merged master:ba4afe6f7a8 into amd-gfx:e01377778c6 e013777 Merged master:37d93b528c1 into amd-gfx:76914bf4c8c 76914bf Merged master:007098d7e6b into amd-gfx:0e75eff74dd 0e75eff Revert "Suppress switch with only default warning for Windows builds" 4dd181d Merged master:a26cd73d337 into amd-gfx:6931a9e8b3a 6931a9e Merged master:99b8f3570a3 into amd-gfx:7deeffc604f 7deeffc Manual merge master:e128f01be996 into amd-gfx:a223fab2879d a223fab Merged master:a09bb6d77b3 into amd-gfx:85c90d8e4e4 85c90d8 Merged master:4c53d4801cb into amd-gfx:6b06a1a334f 6b06a1a Merged master:16437992cac into amd-gfx:3eed7b7802f 3eed7b7 Merged master:b836ae24a9f into amd-gfx:357ead6e3d1 Added AMD modification notices and removed some GPL files. Change-Id: I748aac229c995f54026ce82f676b3cd4d8192ad3
Configuration menu - View commit details
-
Copy full SHA for 0c3b9cd - Browse repository at this point
Copy the full SHA 0c3b9cdView commit details
Commits on Jun 10, 2020
-
Revert "[AMDGPU] Make SGPR spills exec mask agnostic"
This reverts commit d9eac0de01acdfb500a1133b6542a253084517c0. Change-Id: I7ec399ccd4757758b71cc4e461b62e8916ce2700
Configuration menu - View commit details
-
Copy full SHA for f3e0a98 - Browse repository at this point
Copy the full SHA f3e0a98View commit details -
Overwritten with: f3e0a98 Revert "[AMDGPU] Make SGPR spills exec mask…
… agnostic" Based on upstream llvm : 1813451 [Test] Add test showing missing opportunity of folding ICmp(Phi(Consts...)) Local changes since 0c3b9cd: f3e0a98 Revert "[AMDGPU] Make SGPR spills exec mask agnostic" Added AMD modification notices and removed some GPL files. Change-Id: I6a0fa2b92ab6ddd7e10ef1e03f3e7f46b8b2cd1f
Configuration menu - View commit details
-
Copy full SHA for 3274df1 - Browse repository at this point
Copy the full SHA 3274df1View commit details
Commits on Jun 15, 2020
-
[AMDGPU] Temporary fix to get previous intrinsic cost
Changes to the way cost is calculated mean that the compiler has started making different decisions for loop unroll which affects some shaders adversely. See llvm@871556a Changing the behaviour back to the original temporarily until the correct approach is determined. Change-Id: I550fb8dddd7189008c046027d7cd1d575e11e480
Configuration menu - View commit details
-
Copy full SHA for 7d6e549 - Browse repository at this point
Copy the full SHA 7d6e549View commit details -
Overwritten with: 7d6e549 [AMDGPU] Temporary fix to get previous intr…
…insic cost Based on upstream llvm : 1813451 [Test] Add test showing missing opportunity of folding ICmp(Phi(Consts...)) Local changes since 3274df1: 7d6e549 [AMDGPU] Temporary fix to get previous intrinsic cost Added AMD modification notices and removed some GPL files. Change-Id: I41bd0df98ee126682864831063243b0e4eed1f71
Configuration menu - View commit details
-
Copy full SHA for da64bde - Browse repository at this point
Copy the full SHA da64bdeView commit details
Commits on Jun 21, 2020
-
Overwritten with: ad0cb95 Manual merge master:88f722c269a into amd-gfx:
Based on upstream llvm : 88f722c [DSE,MSSA] Enable XFAIL'd merge-stores.ll test (NFC). Local changes since da64bde: ad0cb95 Manual merge master:88f722c269a into amd-gfx: 30d3325 Merged master:7df80e3f23b into amd-gfx:dad54ad1ea9 dad54ad Merged master:120c0592929 into amd-gfx:6618d614ef1 6618d61 Merged master:e1741e34e00 into amd-gfx:da89f3bc942 da89f3b [AMDGPU] Temporary fix to get previous intrinsic cost 3cebb4d Merged master:ff4c5103376 into amd-gfx:e590dba81bd e590dba Merged master:1e87261ba17 into amd-gfx:b313f433300 b313f43 Merged master:3dcfd482cb1 into amd-gfx:b927e58a6c3 b927e58 Merged master:2e92b397ae4 into amd-gfx:f982686ca1e f982686 Merged master:6f0ce46873b into amd-gfx:5615b1ef183 5615b1e Merged master:c966ed8dc7c into amd-gfx:7e2b6a2d3b9 7e2b6a2 Merged master:519b019a0a6 into amd-gfx:f8e6c611a2d f8e6c61 Merged master:8472ae1773a into amd-gfx:036904c0a38 036904c Merged master:1c03389c29f into amd-gfx:78c4105e266 78c4105 Merged master:6239d670018 into amd-gfx:c08830d801d c08830d Merged master:59491b208f3 into amd-gfx:66793841c4c 6679384 Merged master:e82eff7a03b into amd-gfx:7708b7d09b3 7708b7d Merged master:2843e7495b7 into amd-gfx:40d760c210d 40d760c Merged master:904f91db5fc into amd-gfx:f5013394bd5 f501339 Merged master:e4184c84ca0 into amd-gfx:054e834e686 054e834 Merged master:0ee47cc92f5 into amd-gfx:7d86b8a1c00 7d86b8a Revert "[AMDGPU] Make SGPR spills exec mask agnostic" 1b3041b Merged master:ceaee253f4f into amd-gfx:0304f564ba2 0304f56 Merged master:938cc573ee1 into amd-gfx:c852aeff68b c852aef Merged master:01e64c97126 into amd-gfx:8a50ada4530 8a50ada Merged master:d5c28c40943 into amd-gfx:a1b414ebfc7 a1b414e Merged master:de019b88dd5 into amd-gfx:0b6b177d481 0b6b177 Merged master:55c365d247b into amd-gfx:2110e94aa1e 2110e94 Merged master:f22b0727fe7 into amd-gfx:aaef88a2ebd aaef88a Manually merged master:d8f651d3e8e into amd-gfx:b1b348f5444 b1b348f Merged master:bc2b70982be into amd-gfx:36d6d1e9ba5 36d6d1e Merged master:e3546c78cab into amd-gfx:98a96240c8f 98a9624 Merged master:c9790d54f83 into amd-gfx:e7e884ea599 e7e884e Merged master:7e58d0ded09 into amd-gfx:c20d9f185ac c20d9f1 Merged master:ba10bedf563 into amd-gfx:ec24565c877 ec24565 Merged master:a92ce3b706d into amd-gfx:67cb9805444 67cb980 Merged master:22c2dc5931a into amd-gfx:4af5d330416 4af5d33 Merged master:936ec89e91e into amd-gfx:120f4a20ffa 120f4a2 Merged master:28ccd09d700 into amd-gfx:4af26405971 4af2640 Merged master:4c50cf91973 into amd-gfx:bd3b822e680 bd3b822 Merged master:9c3909556b3 into amd-gfx:c8494c6314f c8494c6 Merged master:1778564f911 into amd-gfx:242b037f79c Added AMD modification notices and removed some GPL files. Change-Id: I10506cde6c266a959a80608d4d6ecbad6367eb3a
Configuration menu - View commit details
-
Copy full SHA for 7ce7cdb - Browse repository at this point
Copy the full SHA 7ce7cdbView commit details
Commits on Jun 23, 2020
-
Overwritten with: 9a8a1b7 Revert "[InstCombine] canonicalize bitcast …
…after insertelement into undef" Based on upstream llvm : 88f722c [DSE,MSSA] Enable XFAIL'd merge-stores.ll test (NFC). Local changes since 7ce7cdb: 9a8a1b7 Revert "[InstCombine] canonicalize bitcast after insertelement into undef" Added AMD modification notices and removed some GPL files. Change-Id: I5fcf07f51eef9a143e515a0dbe4fe3a56ed73677
Configuration menu - View commit details
-
Copy full SHA for cca1a02 - Browse repository at this point
Copy the full SHA cca1a02View commit details
Commits on Jun 26, 2020
-
Overwritten with: c8f92d0 Merged master:1b10c618e928 into amd-gfx:850…
…4aad041f6 Based on upstream llvm : 1b10c61 LoopVectorize.h - reduce AliasAnalysis.h include to forward declaration. NFC. Local changes since cca1a02: c8f92d0 Merged master:1b10c618e928 into amd-gfx:8504aad041f6 8504aad Merged master:ae47d158a096 into amd-gfx:7b117dcd2448 7b117dc Merged master:d4adac48320e into amd-gfx:a7ec3c4bc816 a7ec3c4 Merged master:ed398c3ca404 into amd-gfx:6f1c05b7154e 6f1c05b Merged master:161ae1f39816 into amd-gfx:da5e1e7f68df da5e1e7 Merged master:ca8b7ef76379 into amd-gfx:f7c46830e129 f7c4683 Merged master:6e11ed52057f into amd-gfx:76d5787c8265 76d5787 Merged master:6673d69226d8 into amd-gfx:cfbac71a8b87 cfbac71 [AMDGPU] Suppress integral constant overflow warning for VS 559186b Merged master:16501782c8d into amd-gfx:54284162c5c 5428416 Merged master:17326ebbd6c into amd-gfx:4d9eea57b9f 4d9eea5 Merged master:4837daf8836 into amd-gfx:b603a109cd4 b603a10 Merge master:03b902752e3 into amd-gfx. 532704d Merge master:778351df777 into amd-gfx. 15b32a1 [AMDGPU] Update more live intervals in SIWholeQuadMode dd854f0 Merge master:b769eb02b52 into amd-gfx. 926524d [AMDGPU] Preserve LiveIntervals through WQM pass aa01743 Merge master:db777eaea3a into amd-gfx. ddf2dae Mark master:9761d3cf9c1 as merged into amd-gfx. e002e6f Merge master:f38f068b14d into amd-gfx. 3f39561 Merge master:4a7de36afc7 into amd-gfx. 7d34fb0 Revert "Revert "[AMDGPU] Make SGPR spills exec mask agnostic"" 86eceea Merge master:b885b1b92d3 into amd-gfx. Added AMD modification notices and removed some GPL files. Change-Id: I06a9c82c7107dc315c1d6bc9143b1f8f37429ad1
Configuration menu - View commit details
-
Copy full SHA for 71b4c58 - Browse repository at this point
Copy the full SHA 71b4c58View commit details
Commits on Jun 29, 2020
-
Revert "[InstCombine] canonicalize bitcast after insertelement into u…
…ndef" This reverts commit 856cc60. The change is causing inappropriate reordering of floating point operations in edge cases. Change-Id: Ic474948b53d563e73d2a7af89c601476b704d967
Configuration menu - View commit details
-
Copy full SHA for d361f76 - Browse repository at this point
Copy the full SHA d361f76View commit details -
Overwritten with: d361f76 Revert "[InstCombine] canonicalize bitcast …
…after insertelement into undef" Based on upstream llvm : 1813451 [Test] Add test showing missing opportunity of folding ICmp(Phi(Consts...)) Local changes since da64bde: d361f76 Revert "[InstCombine] canonicalize bitcast after insertelement into undef" Added AMD modification notices and removed some GPL files. Change-Id: Ie47acaf14b1b45591d01ac09a45de776100484b1
Configuration menu - View commit details
-
Copy full SHA for a458b29 - Browse repository at this point
Copy the full SHA a458b29View commit details -
Merged -sours proposed next amd-gfx-gpuopen-master
This is to avoid breaking history. Change-Id: Ic2d2ae5509e3c0d3bd52e38291f658430477b04f
Configuration menu - View commit details
-
Copy full SHA for b3a0782 - Browse repository at this point
Copy the full SHA b3a0782View commit details
Commits on Jul 21, 2020
-
Overwritten with: 28c226b Merged master:0ebdc3be417 into amd-gfx:bb2d…
…75d74a4 Based on upstream llvm : 0ebdc3b [ARM] Predicated MVE reduction tests. NFC Local changes since b3a0782: 28c226b Merged master:0ebdc3be417 into amd-gfx:bb2d75d74a4 bb2d75d Merged master:865ee64bf80 into amd-gfx:d3f3f70aa9e d3f3f70 Merged master:1ef3ed0eb49 into amd-gfx:4f9dd3bbbd3 4f9dd3b Merged master:fc24d1eaddd into amd-gfx:dd0e70e874d dd0e70e Merged master:b1a6d373d5e into amd-gfx:e98202e73c5 e98202e Merged master:f07ddbc9c4b into amd-gfx:de1098e3466 de1098e Merged master:e88b6ed7486 into amd-gfx:d8cd891b87e d8cd891 Merged master:ab7abd8bf41 into amd-gfx:a5f829983d1 a5f8299 Merge master:63f0b10b8ce into amd-gfx fdff124 Merge master:62fd7f767c4 into amd-gfx 19b7ca8 Merge master:f3fab392f57 into amd-gfx 9cf4dbc Merge master:79f67cae91e into amd-gfx cab3dd4 Merge master:971dd3f1509 into amd-gfx 6d9da41 Revert "[IR] Temporarily reintroduce StoreInst::setAlignment(MaybeAlign)" 2957462 Merged master:30f6c08ba3b into amd-gfx:a01fd68ad68 a01fd68 Reinstate createCFGSimplificationPass 1fa313e Merged master:fc553086287 into amd-gfx:afd574f5030 afd574f Merged master:ed6b578040a into amd-gfx:d6efc5307af d6efc53 Merged master:f3731d34faa into amd-gfx:d4155ad0bd6 d4155ad Merged master:f233b92f92a into amd-gfx:0319e206077 0319e20 Merged master:d3849dddd26 into amd-gfx:e4688907c11 e468890 Merged master:f819d257982 into amd-gfx:802fca2c6ba 802fca2 Merged master:3a6c2a61c64 into amd-gfx:774eac45315 774eac4 Merged master:3382c243baf into amd-gfx:48fe0476935 48fe047 Merged master:14bc5e149d1 into amd-gfx:fab53ef46c3 fab53ef Merged master:92f7bd3a399 into amd-gfx:fff79ad56c7 fff79ad Merged master:d87c92e5a2e into amd-gfx:346dcd2264f 346dcd2 Merged master:81cfb90f858 into amd-gfx:e6e1842d4bb e6e1842 Merged master:984e12ab48c into amd-gfx:55d2aa0527b 55d2aa0 Merged master:2b42080b51c into amd-gfx:7a7b4d7f0a1 7a7b4d7 Merged master:438e95e95bf into amd-gfx:e4504519d97 e450451 Merged master:e1ca7a65222 into amd-gfx:77fff925279 77fff92 Merged master:8978032a17c into amd-gfx:0c4d09e9afe 0c4d09e Merged master:7ef17638d53 into amd-gfx:aa464168645 aa46416 Merged master:3ae9f5d179c into amd-gfx:05966e8f969 05966e8 Merged master:fefe6a6642e into amd-gfx:0d68222dd6f 0d68222 Merged master:b8460fb2cd0 into amd-gfx:afdde63778a afdde63 Merged master:e51c7fb842e into amd-gfx:3a1737abf1c 3a1737a Merged master:340c376b87c into amd-gfx:e4f18c6a7d7 e4f18c6 Merged master:2d3b8cc83fe into amd-gfx:73e365b16db 73e365b Merged master:a2552f76ac6 into amd-gfx:c4d8558937a c4d8558 Merged master:725412f1f54 into amd-gfx:343e81448cc 343e814 AMDGPU: Finesse the merging performed by SIBufMemMerge when SGPR pressure high 1e2df53 Merged master:e73d0b57199 into amd-gfx:713afb9f262 713afb9 Merged master:6ac9e589f86 into amd-gfx:74ec450f607 74ec450 Merged master:07c4c7e7959 into amd-gfx:15dc82ddef4 15dc82d Merged master:e808cab8244 into amd-gfx:b045f60c3ee b045f60 Merged master:c94332919bd into amd-gfx:1c1d40820bb 1c1d408 Merged master:b4dbb37f32e into amd-gfx:f0e131d5410 f0e131d Merged master:111167895d4 into amd-gfx:ae7f0e2effa ae7f0e2 Merged master:02cfa7530d9 into amd-gfx:f0324e8b619 f0324e8 Merged master:4ff7ed33108 into amd-gfx:d6b5a94f882 d6b5a94 Merged master:65dc97b79eb into amd-gfx:0150a9d44b0 0150a9d Merged master:d589372704f into amd-gfx:10d31d8f1b1 10d31d8 Merged master:66f1dcd872d into amd-gfx:87433172145 8743317 Merged master:77272d177a2 into amd-gfx:034689d84bb 034689d Merged master:d1bcddb5c1f into amd-gfx:48d7fbb7f94 48d7fbb Merged master:6792069a3fd into amd-gfx:cf461db7835 cf461db Merged master:d8c35031a39 into amd-gfx:d2cfd549230 d2cfd54 Merged master:8f183d9f3d1 into amd-gfx:4e734857620 4e73485 Merged master:81db614411b into amd-gfx:c4eb54cdc07 c4eb54c Merged master:850b150cff3 into amd-gfx:de6e30aaac2 de6e30a Merged master:d7a05698efc into amd-gfx:2adece2880f 2adece2 Merged master:8fb91dfeed1 into amd-gfx:175d7f8ffb5 175d7f8 Merged master:dce6bc18c4e into amd-gfx:813be34c52a 813be34 Merged master:b5667d00e04 into amd-gfx:72b94bfee53 72b94bf Merged master:849d4405f53 into amd-gfx:91481b34002 91481b3 Merged master:28acaf84230 into amd-gfx:dc281463803 dc28146 Merged master:881af6eb003 into amd-gfx:2ff9840a68a 2ff9840 Merged master:c0bc995429c into amd-gfx:68adaf5abf4 68adaf5 Merged master:169c83208f3 into amd-gfx:b84e3982f0d b84e398 Merged master:1cf6f210a2e into amd-gfx:042be23e3d9 042be23 AMDGPU: A simple register pressure analysis 3c36faf Merged master:864586d0fd7 into amd-gfx:b36eaecb0ee b36eaec Merged master:22c8a08fd8a into amd-gfx:7c59985cdf1 7c59985 Merged master:4c5a93bd58b into amd-gfx:daefff488b4 daefff4 Merged master:a25487fd8cb into amd-gfx:955d3cbbb18 955d3cb Merged master:5f41ca48d1c into amd-gfx:d5bbbc9d494 d5bbbc9 Merged master:7bf168390fd into amd-gfx:a06e03ac400 a06e03a Merged master:760bbda2d82 into amd-gfx:3377900a4e6 3377900 Merged master:c20c1960c15 into amd-gfx:fc4a32150a5 fc4a321 Merged master:fbef6c55bc2 into amd-gfx:c981d60f027 c981d60 Merged master:78fe6a3ee24 into amd-gfx:0094d1eb38a 0094d1e Merged master:77f8f813a9a into amd-gfx:50ff9a5e4b4 50ff9a5 Merged master:ff5b9a7b3b2 into amd-gfx:5077035f507 5077035 Merged master:918e6531863 into amd-gfx:1bebf3cd354 1bebf3c Merged master:3cca818efab into amd-gfx:2165191f92e 2165191 Merged master:6f5d9136b27 into amd-gfx:f9471172f74 f947117 Merged master:b44470547e2 into amd-gfx:624dd346d16 624dd34 Merged master:9e7fddbd36f into amd-gfx:80e74e06131 80e74e0 Merged master:305b500eaf8 into amd-gfx:0db75208590 0db7520 Merged master:371c94fca03 into amd-gfx:8dba914c803 8dba914 Merged master:24aa4efffd8 into amd-gfx:b5c06262a08 b5c0626 Merged master:5a98581d196 into amd-gfx:3ae5401bda5 3ae5401 Merged master:339f1b49037 into amd-gfx:4880966cddc 4880966 Merged master:0b39d2d7527 into amd-gfx:3e3397820f3 3e33978 Merged master:6ab3208d779 into amd-gfx:337c0210e3d 337c021 Merged master:a0749842509 into amd-gfx:6fd999d7d0b 6fd999d Merged master:64363a9d930 into amd-gfx:f6f83e6c43a f6f83e6 Merged master:695b33a5691 into amd-gfx:9ba3de3c886 9ba3de3 Merged master:e9f943429c8 into amd-gfx:f8416c3e42a f8416c3 Merged master:edc7da24057 into amd-gfx:5925a948df2 5925a94 Merged master:f54d0e36be6 into amd-gfx:5596bea4e4c 5596bea Merged master:e885f336fd7 into amd-gfx:233f5f4f6e0 233f5f4 Merged master:cb82de29601 into amd-gfx:63385c36b23 63385c3 Merged master:0d7401cf9d5 into amd-gfx:cba70fee0b1 cba70fe Merged master:0d7286a6523 into amd-gfx:7a72f3ba645 7a72f3b Merged master:e10e034f4bb into amd-gfx:af9b354efe9 af9b354 Merged master:a256193afa4 into amd-gfx:f19d086ae89 f19d086 Merged master:2cdf108d329 into amd-gfx:c51048ebf06 c51048e [AMDGPU] Fix discard to demote conversion 65124bb Merge master:cd7f8051ac7 into amd-gfx 95c2894 Merged master:2247f7218a3 into amd-gfx:c0f939d6618 c0f939d Merged master:779432690fb into amd-gfx:8b56293a0f3 8b56293 Merged master:3fc97f9636b into amd-gfx:5f0d3f91d62 5f0d3f9 Merged master:68e07da3e5d into amd-gfx:066923d731c 066923d Merged master:afd81a637df into amd-gfx:acfb9c62b73 acfb9c6 Merged master:65330f394b2 into amd-gfx:355d691d0d0 355d691 Merged master:05c5ff5ab0b into amd-gfx:06955ecf185 06955ec Merged master:76123d338dc into amd-gfx:503960afe2f 503960a Merged master:120c5f1057d into amd-gfx:87a4ac44584 87a4ac4 Merged master:45b5c79a31d into amd-gfx:3636901db3f 3636901 Merged master:c352e0885a6 into amd-gfx:26add629de1 26add62 Merged master:e75f2d5a8cd into amd-gfx:a83795bc938 a83795b Merged master:fba8523fb55 into amd-gfx:e8a39ad292e e8a39ad Merged master:17a15c32aff into amd-gfx:29527e09863 29527e0 Merged master:c7cabf9d608 into amd-gfx:2d249ff0d3d 2d249ff Merged master:40fcc42498d into amd-gfx:5a143718a20 5a14371 Merged master:3b4a0adec27 into amd-gfx:d08bdca3b40 d08bdca Merged master:0f03b2bfda9 into amd-gfx:145e568c385 145e568 [AMD-GFX] Define LLVM_HAVE_BRANCH_AMD_GFX in llvm-config.h 3982afa Merged master:8bf4c40af81 into amd-gfx:013ee6a8ccb 013ee6a Merged master:3faec833760 into amd-gfx:df856ee50d9 df856ee Manually merged master:eb305631bec into amd-gfx:1733b4ba0b9 1733b4b Merged master:103d62e1313 into amd-gfx:b8129ef3667 b8129ef Merged master:e0968ad4594 into amd-gfx:58eb9aa127f 58eb9aa Merged master:8dbafd24d6d into amd-gfx:bee70b7d831 bee70b7 Merged master:559685d0bbd into amd-gfx:66e2e9d7a70 66e2e9d Merged master:11b1eeeaec6 into amd-gfx:6cf36500793 6cf3650 Merged master:c59aec0ca1e into amd-gfx:05eb2feedd2 05eb2fe Merged master:c9f251aa6f6 into amd-gfx:82a1cbd5a0f 82a1cbd Merged master:88874f07464 into amd-gfx:a7090a916d1 a7090a9 Merged master:48c196f5c8b into amd-gfx:f751009c1b7 f751009 Merged master:003a086ffc0 into amd-gfx:85511cf7fec 85511cf Merged master:e1581540876 into amd-gfx:f02aacb0020 f02aacb Merged master:f11305780f0 into amd-gfx:88baa0832e9 88baa08 Merged master:c83ec0a6335 into amd-gfx:b2bf65867bf b2bf658 Merged master:a03dc8c9fa8 into amd-gfx:5fc05c258fe 5fc05c2 Merged master:2c7af6dffc0 into amd-gfx:13b4e3c2331 13b4e3c Merged master:4b9ae1b7e5e into amd-gfx:3cde5bf94da 3cde5bf Merged master:a8e582c8307 into amd-gfx:44c4478e58c 44c4478 Merged master:f5e0ae240f2 into amd-gfx:ed82099fba5 ed82099 Merged master:9a5e3a43923 into amd-gfx:ab48c4072da ab48c40 Merged master:144e57fc953 into amd-gfx:0a66eff7455 0a66eff Merged master:c8f1d442d085 into amd-gfx:f962ee3d4a2c f962ee3 Merged master:ce6153a5282c into amd-gfx:1f4ea6f8b241 1f4ea6f Merged master:8ba4867c2700 into amd-gfx:a1a3a9d22ab9 a1a3a9d Merged master:8032727a43ca into amd-gfx:9c600f889dbd 9c600f8 Merged master:c37d25f0d1e0 into amd-gfx:8f0252f78f37 8f0252f Merged master:2c5ff48e61b5 into amd-gfx:9fa26cfbb268 9fa26cf Manually merged master:226cda58d505 into amd-gfx:24d6f7604e35 24d6f76 Merged master:876df18aecb into amd-gfx:03117f64026 03117f6 Merged master:368a5e3a666f into amd-gfx:38f0481316bc 38f0481 Merged master:e503851d80e7 into amd-gfx:ce5a4a27008d ce5a4a2 Merged master:e34523c87c3 into amd-gfx:a5cf30ee811 a5cf30e Merged master:8f73c4432b5f into amd-gfx:42ca388d8048 42ca388 Merged master:1becd298b82e into amd-gfx:3ee91d2f67ad 3ee91d2 Merged master:a28d38a6bca1 into amd-gfx:97deb2a587ec 97deb2a Merged master:25521150d7b5 into amd-gfx:3c512be3c491 3c512be Merged master:8758e14c6f12 into amd-gfx:f786c5b0592a f786c5b Merged master:614b995cace9 into amd-gfx:c667b862dd03 c667b86 Merged master:c73966c2f792 into amd-gfx:98acc6627628 98acc66 Merged master:b9306fd042ce into amd-gfx:242c36a54a72 242c36a Merged master:ab4627364aef into amd-gfx:8356ebb3ca23 8356ebb Merged master:66b7ba52b7b4 into amd-gfx:f7d7424ea5ed f7d7424 Merged master:8cd117c24f48 into amd-gfx:da580bbf98e6 da580bb Merged master:85b53598a984 into amd-gfx:3eaf04d2d198 3eaf04d Merged master:393b4bd1362f into amd-gfx:9908032f9d6a 9908032 Merged master:d698ff92a59c into amd-gfx:ee6a1ec25edf ee6a1ec Merged master:f0634100cdc into amd-gfx:bee18ab3cb8 bee18ab Merged master:a43b99a1e38e into amd-gfx:10cafb2786c6 10cafb2 Merged master:878a24d369ea into amd-gfx:ef75ad354d25 ef75ad3 Merged master:89812eeee97c into amd-gfx:e2151b81834f e2151b8 Merged master:c19e82c6b38b into amd-gfx:43821d8113e1 43821d8 Merged master:f31811f2dcbe into amd-gfx:9ed09349f0b6 9ed0934 Merged master:b925ca37a8f2 into amd-gfx:507c08757414 507c087 Merged master:d298acde828f into amd-gfx:31bae1013413 31bae10 Merged master:990f8702c911 into amd-gfx:b75afd4f6b03 b75afd4 Merged master:7cc5307c73ca into amd-gfx:962dcb104a19 962dcb1 Merged master:ae74252341a0 into amd-gfx:a7ff35a78a7d a7ff35a Merged master:befd8f82fe20 into amd-gfx:97f9808176a7 97f9808 Merged master:44f06db43941 into amd-gfx:d2353566e772 d235356 Merged master:bb26838ceffb into amd-gfx:c8f92d00575c Added AMD modification notices and removed some GPL files. Change-Id: I4de7e8582961ecd23bf69b8b5b4e6516b19c22d0
Configuration menu - View commit details
-
Copy full SHA for dc1f5d9 - Browse repository at this point
Copy the full SHA dc1f5d9View commit details -
Overwritten with: 28c226b Merged master:0ebdc3be417 into amd-gfx:bb2d…
Configuration menu - View commit details
-
Copy full SHA for 8abd948 - Browse repository at this point
Copy the full SHA 8abd948View commit details
Commits on Jul 31, 2020
-
Overwritten with: 572b572 Merged master:e40315d2b4e into amd-gfx:3a69…
…43f7847 Based on upstream llvm : e40315d [GVN] Rewrite IsValueFullyAvailableInBlock(): no recursion, less false-negatives Local changes since 8abd948: 572b572 Merged master:e40315d2b4e into amd-gfx:3a6943f7847 3a6943f Merged master:8c9241a051f into amd-gfx:0ad5094d066 0ad5094 Merged master:a23f62343cb into amd-gfx:bddc52bbfda bddc52b Merged master:930fc0b300b into amd-gfx:c0aa0f028de c0aa0f0 Merged master:f250eb37cd4 into amd-gfx:5fc5dbff8db 5fc5dbf Merged master:c37bb5e2a54 into amd-gfx:0d6feb723e1 0d6feb7 Merged master:4589dd924dfc into amd-gfx:9a4c659a6ab9 9a4c659 Merged master:891759db73f into amd-gfx:64f77d560c5 64f77d5 Merged master:1d09ecf3617 into amd-gfx:80a12155686 80a1215 Merged master:183342c0a98 into amd-gfx:bd825eb42a4 bd825eb Merged master:def48b0e888 into amd-gfx:1fd38bfef96 1fd38bf Merged master:84980b1395d into amd-gfx:06bdec4bd97 06bdec4 Merged master:d720ba1e4b6 into amd-gfx:cd615274e49 cd61527 Merged master:697c6d8907e into amd-gfx:cf59832d40e cf59832 Merged master:65fd651980a into amd-gfx:05ccdba0083 05ccdba Merged master:e4dd964df01 into amd-gfx:a657d6ac63c a657d6a Merged master:99ad956fdae into amd-gfx:32b6f0e3cd4 32b6f0e Merged master:23cc19d1cfe into amd-gfx:a7fc070727d a7fc070 Merged master:3fff5acd8f5 into amd-gfx:c1fd4c1fe54 c1fd4c1 Merged master:b198de67e0b into amd-gfx:6357d679802 6357d67 Merged master:1c7037a2a55 into amd-gfx:f3c1125efa9 f3c1125 Merged master:4e171c9f19d into amd-gfx:8a632c331e7 8a632c3 Merged master:82dbb1b2b4f into amd-gfx:cc7ab8f29fb cc7ab8f Merged master:a1b12a934d9 into amd-gfx:75acce66862 75acce6 Merged master:e4ef948a434 into amd-gfx:6a6cb0e5da2 6a6cb0e Merged master:320389e849f into amd-gfx:a4a145f548f a4a145f Merged master:a361aa52498 into amd-gfx:81d68cace0c 81d68ca Merged master:ce04d4e39c9 into amd-gfx:001abb1aefc 001abb1 Merged master:923cf890d15 into amd-gfx:80d4df0f0e3 80d4df0 Merged master:0d3a5d09e3e into amd-gfx:8b421fc8176 8b421fc Merged master:86ab98b0014 into amd-gfx:5d93707997f 5d93707 Merged master:5c15426d7c6 into amd-gfx:9313e0714d7 9313e07 [AMDGPU][GlobalISel] Select waterfall intrinsics 44408c8 [AMDGPU] Fix regclass for operand subregs in SIInsertWaterfall 3dbeb7a Merged master:566b49884d6 into amd-gfx:28c226b4dca Added AMD modification notices and removed some GPL files. Change-Id: I1f60dc2c5ce8a4b28ec558f20733bf330ecedd3f
Configuration menu - View commit details
-
Copy full SHA for cc5e107 - Browse repository at this point
Copy the full SHA cc5e107View commit details
Commits on Aug 10, 2020
-
Overwritten with: 862f3da Merged master:8119d6c14695 into amd-gfx:ca7…
…382823610 Based on upstream llvm : 8119d6c [lldb][NFC] Remove dead code in BreakpointResolverAddress Local changes since cc5e107: 862f3da Merged master:8119d6c14695 into amd-gfx:ca7382823610 ca73828 Manually merged master:4b211b94d713 into amd-gfx:df3188633313 df31886 Merged master:23817cbd0b65 into amd-gfx:130f95796777 130f957 Merged master:53ac14484869 into amd-gfx:1e5c9755f03e 1e5c975 Merged master:43bdac290663 into amd-gfx:c65081476587 c650814 Merged master:c8b629a3a585 into amd-gfx:3797c7ce933e 3797c7c Merged master:c990455db91e into amd-gfx:fa8e5d83f08a fa8e5d8 Merged master:bc8be3054067 into amd-gfx:2c90f80163df 2c90f80 Merged master:fdfdee98ac81 into amd-gfx:849afe5716dc 849afe5 Merged master:5fd49911db54 into amd-gfx:7dc36faa6e99 7dc36fa Merged master:b317321545aa into amd-gfx:12d47203ed53 12d4720 Merged master:ccbc1485b55f into amd-gfx:41523d1a5dec 41523d1 Merged master:654e8aadfdda into amd-gfx:aab61286598f aab6128 Merged master:c814eca3e4c6 into amd-gfx:3d52bae5ee3a 3d52bae Merged master:cd5ab56bc406 into amd-gfx:12107ad063b9 12107ad Merged master:f22ac1d15b1b into amd-gfx:e715bf7d18b5 e715bf7 Merged master:38537307e502 into amd-gfx:59587658cebf 5958765 Merged master:0b90a08f7722 into amd-gfx:0ac624b43068 0ac624b Merged master:872bdc0be7dd into amd-gfx:9826d1030105 9826d10 Merged master:fb943696cbc6 into amd-gfx:33edaf1406e2 33edaf1 Merged master:ca4bcfbf2ccd into amd-gfx:8a01d813bd9f 8a01d81 Merged master:d3dfd8cec440 into amd-gfx:2b82436a5493 2b82436 Merged master:bb4b70f79215 into amd-gfx:10744143d422 1074414 Merged master:ac3e720dc1af into amd-gfx:58d3a7df8949 58d3a7d Disable selection of S_ADD_CO_PSEUDO and S_SUB_CO_PSEUDO 7cee446 Merged master:6c64f05b905e into amd-gfx:4327003c06f2 4327003 Merged master:fcefb5322251 into amd-gfx:ca2271391291 ca22713 Merged master:be8b3f0c2204 into amd-gfx:63ec046a4625 63ec046 Merged master:f3cc4df51da4 into amd-gfx:4429fec2724a 4429fec Merged master:55de46f3b2c5 into amd-gfx:25d7a92e704e 25d7a92 Merged master:7fb9de2c6f57 into amd-gfx:6eb6fff44da8 6eb6fff Merged master:f4ba7a100a56 into amd-gfx:365715cceaad 365715c Merged master:c8a282bcf7b6 into amd-gfx:8e9497fe1a50 8e9497f Merged master:aa57cabae2fc into amd-gfx:d45c1991868a d45c199 Merged master:c9bcc237a284 into amd-gfx:416665bc31ac 416665b Merged master:96c2d5e99e32 into amd-gfx:4ed9040d2bbb 4ed9040 Merged master:518a27e5591 into amd-gfx:2131d013575 2131d01 Merged master:6c7f640bf7a into amd-gfx:42258fe7804 42258fe Merged master:5a07490d761 into amd-gfx:db8dac0c1c5 db8dac0 Manual merge master:d3a9807674c1 into amd-gfx:e9d299d163e7 e9d299d Merged master:105608a4c28 into amd-gfx:cdfd20c1d24 cdfd20c Merged master:6780d5675b7 into amd-gfx:622f7bf088c 622f7bf Merged master:47cfffe893f into amd-gfx:b2844a88b1d b2844a8 Merged master:d21ce408218 into amd-gfx:18b46285c42 18b4628 Merged master:f2675ab45fb into amd-gfx:b07d614d687 b07d614 Merged master:4cd923784e9 into amd-gfx:9dbb9cfd3c1 9dbb9cf Merged master:f2916636f83d into amd-gfx:1c894b7c8014 1c894b7 Manually merged master:47f7174ffa71 into amd-gfx:4240f11c6570 4240f11 Manually merged master:160ff83765ac2 into amd-gfx:5bda552142400 5bda552 Merged master:b6635b5b15c into amd-gfx:5500f455383 5500f45 Merged master:142d0d3ed8e0 into amd-gfx:4cc47b88ab72 4cc47b8 Merged master:05b17346614 into amd-gfx:e81498ce299 e81498c Revert "Reinstate createCFGSimplificationPass" c5bad94 Merged master:3aab320557e7 into amd-gfx:d447dfd3eb40 d447dfd Merged master:629467eb981 into amd-gfx:413ecb3e590 413ecb3 Merged master:f71deb43abea into amd-gfx:c40b2286b7d3 c40b228 Merged master:7d0b32c268a into amd-gfx:02853004026 0285300 Merged master:71059257bd4 into amd-gfx:be729eb2277 be729eb Merged master:6700f4b9fe6 into amd-gfx:7dd816f37b8 7dd816f Merged master:8dbea4785c10 into amd-gfx:a616d205027b a616d20 Merged master:58743040ff5 into amd-gfx:cbe83ccf52b cbe83cc Merged master:a4ade9ed21e into amd-gfx:5e1c79f714b 5e1c79f Merged master:ad793ed9037 into amd-gfx:fe454753874 fe45475 Merged master:aec38c619df into amd-gfx:40f4b0ae278 40f4b0a Merged master:2f98eff3457 into amd-gfx:f54189c5a33 f54189c Merged master:1f4aa30a4f8 into amd-gfx:8f0efafe9ec 8f0efaf Merged master:b1e398920f7 into amd-gfx:bc9ad25f5df bc9ad25 Merged master:d50d4c3d440 into amd-gfx:b0efeab4481 b0efeab Merged master:db0d636e52c into amd-gfx:cda84d7337b cda84d7 Merged master:fb22678cd67 into amd-gfx:94be4d77337 94be4d7 Merged master:417d3d495f1 into amd-gfx:b5eefa940d4 b5eefa9 Merged master:16bcd545703 into amd-gfx:4544040be49 4544040 Merged master:22ec861d28c into amd-gfx:4e065bed1fe 4e065be Merged master:d3557ecede8 into amd-gfx:8626f584ba1 8626f58 Merged master:536736995bf5 into amd-gfx:572b5725a74b Added AMD modification notices and removed some GPL files. Change-Id: I271858387edf3f02f6769816c9cddb28bc461c35
Configuration menu - View commit details
-
Copy full SHA for c2ea9a1 - Browse repository at this point
Copy the full SHA c2ea9a1View commit details
Commits on Aug 14, 2020
-
Revert "AMDGPU: Fix verifier error on spilling partially defined SGPRs"
This reverts commit 592f2e8. Change-Id: I0045c5ed660ee6664267593a89051b8d363b5ef4
Configuration menu - View commit details
-
Copy full SHA for 5ad0302 - Browse repository at this point
Copy the full SHA 5ad0302View commit details -
Overwritten with: 5ad0302 Revert "AMDGPU: Fix verifier error on spill…
…ing partially defined SGPRs" Based on upstream llvm : 8119d6c [lldb][NFC] Remove dead code in BreakpointResolverAddress Local changes since c2ea9a1: 5ad0302 Revert "AMDGPU: Fix verifier error on spilling partially defined SGPRs" Added AMD modification notices and removed some GPL files. Change-Id: I89446e47f3c8d96d56e28d5774eaa7a3909f2cd8
Configuration menu - View commit details
-
Copy full SHA for ea979e9 - Browse repository at this point
Copy the full SHA ea979e9View commit details
Commits on Aug 20, 2020
-
Overwritten with: a77b6e9 Merged master:1454018dc1d9 into amd-gfx:3fd…
…59da059f0 Based on upstream llvm : 1454018 Revert "[libc++] Use CMake interface targets to setup benchmark flags" Local changes since ea979e9: a77b6e9 Merged master:1454018dc1d9 into amd-gfx:3fd59da059f0 3fd59da Merged master:03127f795b82 into amd-gfx:2052ff69de01 2052ff6 Merged master:98e01f56b0a1 into amd-gfx:0faf255c57f9 0faf255 Merged master:a275acc4a9c8 into amd-gfx:a8f0f462af04 a8f0f46 Merged master:75966ee241a2 into amd-gfx:ef48fb9dfd56 ef48fb9 Merged master:9c4825ce282d into amd-gfx:676863267727 6768632 Merged master:c135a68d426f into amd-gfx:35fe0c30d0db 35fe0c3 Merged master:24c74f5e8c2c into amd-gfx:6083d1110df4 6083d11 Merged master:24fc3177c176 into amd-gfx:ff3a17708b84 ff3a177 Merged master:aa61e4304049 into amd-gfx:e6039cd90733 e6039cd Merged master:fcd2969da9e0 into amd-gfx:3e378fbf48e8 3e378fb Merged master:e10e7829bf6f into amd-gfx:0db76176e796 0db7617 Merged master:9860e68450cd into amd-gfx:c5a502ac4725 c5a502a Merged master:0ec1f0f332c7 into amd-gfx:350123aa4ac0 350123a Merged master:5272d29e2cb7 into amd-gfx:cba62a96b2ab cba62a9 Merged master:fef260712407 into amd-gfx:041f8033781a 041f803 Merged master:f25d47b7ed3e into amd-gfx:2448a89cc6df 2448a89 Merged master:3ffb751f3dbf into amd-gfx:b0ff4a9889a7 b0ff4a9 Merged master:47552a614a8c into amd-gfx:028045aab0b9 028045a Merged master:402b063c8067 into amd-gfx:5a833493398a 5a83349 Merged master:12b4df991950 into amd-gfx:ecc5f403d29c ecc5f40 Merged master:1bc298aa125c into amd-gfx:5ffe73cf47b5 5ffe73c Merged master:d0b312955f12 into amd-gfx:4c4f72e10e54 4c4f72e Merged master:22cbe40fa997 into amd-gfx:b419d0d534fb b419d0d Merged master:93c761f5e5b0 into amd-gfx:584255ba88cf 584255b Merged master:160c133be5e1 into amd-gfx:aeb433f6a474 aeb433f Merged master:b7448a348bb8 into amd-gfx:4569d334fbce 4569d33 Merged master:85d381eb02a2 into amd-gfx:a871b73bce74 a871b73 Merged master:3aecf4bdf3f8 into amd-gfx:55d5ba92c162 55d5ba9 Merged master:25ee851746df into amd-gfx:a35835192b4e a358351 Merged master:3e7403a1346f into amd-gfx:5f789c6d8d10 5f789c6 Merged master:1621c004da7b into amd-gfx:573483bc2f35 573483b Merged master:43a38dc25173 into amd-gfx:bd3fdd8bf9e9 bd3fdd8 Merged master:05e3ab41e418 into amd-gfx:a06305b415c2 a06305b Merged master:6dbf0cfcf789 into amd-gfx:873eb5d3a8f7 873eb5d Merged master:fc4fd898522a into amd-gfx:12ae09d839a9 12ae09d Merged master:40a142fa57d6 into amd-gfx:745aa2c38fb6 745aa2c Merged master:ce439cb1c962 into amd-gfx:d2658fcb2edb d2658fc Revert "AMDGPU: Fix verifier error on spilling partially defined SGPRs" da0f63f Merged master:4c30d4b4e5f2 into amd-gfx:a078d802dea9 a078d80 Merged master:397b3cc9e5aa into amd-gfx:ecc0462b1bbe ecc0462 Merged master:909a851dbffe into amd-gfx:845a4b68fe55 845a4b6 Merged master:48cd5b72b13c into amd-gfx:fff0414d537a fff0414 Merged master:800f0eda5b15 into amd-gfx:3bb5d8efedce 3bb5d8e Merged master:b182ccfc2d6a into amd-gfx:5f4901f0c4e9 5f4901f Merged master:21810b0e1428 into amd-gfx:99aa69d1fa46 99aa69d Merged master:612b4dda7667 into amd-gfx:6a82f7b231e2 6a82f7b Merged master:98cf77e33786 into amd-gfx:470e37ff54c5 470e37f Merged master:2916dd5669e7 into amd-gfx:785ec1b704c7 785ec1b Merged master:a31d20e67e2b into amd-gfx:4fd18a5db4d2 4fd18a5 Merged master:3b0878a37005 into amd-gfx:68fe5b911a09 68fe5b9 [AMDGPU][GlobalISel] Select waterfall intrinsics with TableGen patterns 80700d1 Merged master:0e70a127a942 into amd-gfx:d22791a719e9 d22791a Merged master:3651658bdd11 into amd-gfx:9fb40d163aad 9fb40d1 Merged master:fccf4c6115a8 into amd-gfx:a67c54661cb9 a67c546 Merged master:511d5aaca37a into amd-gfx:3291c93460cb 3291c93 Merged master:88bbd3073656 into amd-gfx:f0de6323b87e f0de632 Merged master:31e5f7120bdd into amd-gfx:81f4fd729542 81f4fd7 Merged master:b0b95dab1ce2 into amd-gfx:b49b4e72112a b49b4e7 Merged master:c6f51377e12b into amd-gfx:4a16eb27d030 4a16eb2 Merged master:06d100a69a08 into amd-gfx:9bd98790e775 9bd9879 Merged master:254e0abf5be2 into amd-gfx:ad883734e3bc ad88373 Merged master:cf715717aa8c into amd-gfx:b935d4513c07 b935d45 Merged master:034b95e2839e into amd-gfx:712b9ec4fc09 712b9ec Merged master:031738a56118 into amd-gfx:2a691f810b57 2a691f8 Merged master:d6f710fd46dc into amd-gfx:1bfeb137fb97 1bfeb13 Merged master:c6d2078a35d5 into amd-gfx:274ff371947a 274ff37 Merged master:a22301ef9899 into amd-gfx:3d0e37098161 3d0e370 Merged master:02af25df2be7 into amd-gfx:db6f372dc7aa db6f372 Merged master:49fb1c2e9018 into amd-gfx:1e18df557928 1e18df5 Merged master:fb04d7b4a698 into amd-gfx:0f98b7a0bd24 0f98b7a Merged master:aae349e2760e into amd-gfx:b2a0e7264b38 b2a0e72 Merged master:7bc03f55539f into amd-gfx:c5a8d66d784a c5a8d66 Merged master:6fe6b29c294e into amd-gfx:49849cf359eb 49849cf Merged master:e2d61ae57333 into amd-gfx:46e8e3c2c623 46e8e3c Merged master:891ddfc64380 into amd-gfx:862f3dac7a1b Added AMD modification notices and removed some GPL files. Change-Id: I0c334c8956295f18bf8ef465dcf7bf09be8d400e
Configuration menu - View commit details
-
Copy full SHA for ccbc834 - Browse repository at this point
Copy the full SHA ccbc834View commit details
Commits on Sep 2, 2020
-
Overwritten with: b4be3a0 Update llvm.amdgcn.wqm.demote.ll
Based on upstream llvm : 7139736 Revert "[libfuzzer] Reduce default verbosity when printing large mutation sequences" Local changes since ccbc834: b4be3a0 Update llvm.amdgcn.wqm.demote.ll 5fae63e Merged master:7139736261e0 into amd-gfx:e569ed168e56 e569ed1 Merged master:a57fdcdd404b into amd-gfx:7b20432503d8 7b20432 Merged master:061182b7baf8 into amd-gfx:dcd304b046c1 dcd304b Merged master:3d90a61cf2ed into amd-gfx:d2809b43860a d2809b4 Revert "Revert "AMDGPU: Fix verifier error on spilling partially defined SGPRs"" 1f91527 Merged master:722db5c0b4e8 into amd-gfx:11191d6d82c0 11191d6 Merged master:03812041d8d9 into amd-gfx:e74d787250fc e74d787 Manually merged master:9fbb113247a5 into amd-gfx:a0550f47f72e a0550f4 Merged master:b9b954b8bbf0 into amd-gfx:59c50047705d 59c5004 Manually merged master:f4257c5832aa into amd-gfx:e7bf03cf04ed e7bf03c Merged master:dce72dc87040 into amd-gfx:5c7b2b0373fd 5c7b2b0 Merged master:43aa7227dfab into amd-gfx:fbf817481c51 fbf8174 [AMDGPU][GlobalISel] Select wqm.demote and wqm.helper intrinsics 7189d5e Merged master:2d13693bfce9 into amd-gfx:f4ee59a53095 f4ee59a Merged master:71f3169e1bae into amd-gfx:88e66714f50a 88e6671 Merged master:9936455204fd into amd-gfx:6877e932e322 6877e93 Merged master:09288bcbf5f1 into amd-gfx:7095da9190c1 7095da9 Merged master:60db26a66d53 into amd-gfx:97ddfe1656e5 97ddfe1 Merged master:5078825aa982 into amd-gfx:e081759f3e5c e081759 Merged master:99d18f79646c into amd-gfx:67f09f7a0ee9 67f09f7 Merged master:30507137986a into amd-gfx:4075ffb32ad6 4075ffb Merged master:47849870278c into amd-gfx:60ae67882921 60ae678 Merged master:72bdb41a06a2 into amd-gfx:05d46b7654ff 05d46b7 Merged master:1d1515a9e28c into amd-gfx:b7b799da5db5 b7b799d Merged master:8839e278ffca into amd-gfx:1dd2fbccbf8c 1dd2fbc Merged master:7cfcecece0e0 into amd-gfx:259ceb5e20d2 259ceb5 Merged master:f753f5b05033 into amd-gfx:e9003c201939 e9003c2 Merged master:78e4aeb7839e into amd-gfx:9ce6257e540b 9ce6257 Merged master:f8454d60b829 into amd-gfx:1fe58ede4cad 1fe58ed Merged master:0d2fe90063e9 into amd-gfx:43b9ac8878b2 43b9ac8 Merged master:4d90ff59ac45 into amd-gfx:8832016e5a77 8832016 Merged master:4dec8ec33d68 into amd-gfx:029ad24856bc 029ad24 Merged master:116affb18dfc into amd-gfx:82df69f7b607 82df69f Merged master:3cd8d7b1727f into amd-gfx:59caf3eadbd2 59caf3e Merged master:e1644a377996 into amd-gfx:568c74a3bc4a 568c74a Merged master:6a44edb8da33 into amd-gfx:b3b0d224fe25 b3b0d22 Merged master:3d1b0000f9da into amd-gfx:705782cee308 705782c Merged master:7a4e26adc8c2 into amd-gfx:d26dce3aa605 d26dce3 Merged master:3137c299269d into amd-gfx:b4105232fca7 b410523 Merged master:1bc45b2fd808 into amd-gfx:febc1534688d febc153 Merged master:f93b42a629ae into amd-gfx:5a888c923f81 5a888c9 Merged master:f6615b2ddb3d into amd-gfx:0449ca698739 0449ca6 Merged master:51a82828fb29 into amd-gfx:5e368ad43539 5e368ad Merged master:bef684154d40 into amd-gfx:895b723f9dff 895b723 Merged master:55208f5a2126 into amd-gfx:ab7c83b392c2 ab7c83b Merged master:1ce07cd614be into amd-gfx:8f5e508b220a 8f5e508 Partially revert 264afb9 [NFC][llvm] Make the contructors of `ElementCount` private. e1b555e Fix test checks after merge from upstream 372b3a4 Merge master:5e3fd471acb into amd-gfx 1eeb55b Revert "AMDGPU: Implement waterfall loop for MIMG instructions with 256-bit SRsrc" cf3dbb2 Merge master:d29d1e2ffd6 into amd-gfx 58d7da9 Merge master:d14cf45735b into amd-gfx Added AMD modification notices and removed some GPL files. Change-Id: I36357ce8c2a24aa58adbd9bd682169e0e411895d
Configuration menu - View commit details
-
Copy full SHA for 1826337 - Browse repository at this point
Copy the full SHA 1826337View commit details -
Overwritten with: a77b6e9 Merged master:1454018dc1d9 into amd-gfx:3fd…
…59da059f0 Based on upstream llvm : 1454018 Revert "[libc++] Use CMake interface targets to setup benchmark flags" This reverts back to the previous version from Aug 20th, as the Sep 2nd version causes multiple CTS failures. Added AMD modification notices and removed some GPL files. Change-Id: Ic219f7e21fa1c494b12944205b305ae6d4cfda02
Configuration menu - View commit details
-
Copy full SHA for c72fe64 - Browse repository at this point
Copy the full SHA c72fe64View commit details
Commits on Sep 10, 2020
-
Overwritten with: 4ef4636 [AMDGPU] Set DS alignment requirements to b…
…e more strict. Based on upstream llvm : be35264 Wordsmith RegionBranchOpInterface verification errors Local changes since c72fe64: 4ef4636 [AMDGPU] Set DS alignment requirements to be more strict. ddceb7e Merged master:be35264ab5a3 into amd-gfx:216acf9b338d 216acf9 Merged master:ba5b1371ecc5 into amd-gfx:b30d94ec0250 b30d94e Merged master:6e45b9893406 into amd-gfx:7d35190ec298 7d35190 Merged master:95b7040e4384 into amd-gfx:fafdb1f630bc fafdb1f Merged master:edf244217a48 into amd-gfx:a464d1bd6a9d a464d1b Revert "Revert "[AMDGPU] Fix offset for REL32_HI relocs"" c354f0c Merged master:8427885e2781 into amd-gfx:300befc3bdb2 300befc [AMDGPU] Avoid calling expandUnalignedLoad/Store and spilling when possible 007e8d2 Merged master:7e5dab5fca4b into amd-gfx:2cb92ad0376c 2cb92ad Merged master:4b530f75199d into amd-gfx:6c5d93ec9d8b 6c5d93e Merged master:3097427f93dd into amd-gfx:aacb97b51eb5 aacb97b Revert "[AMDGPU] Fix offset for REL32_HI relocs" 4cd77b3 Merge master:7403e3ee3240 into amd-gfx 704156f [AMDGPU] Fix scratch bounds bugs found by fuzzing 57cfefc Merged master:3445ec9ba718 into amd-gfx:efacedeed550 efacede Merged master:5d1347957454 into amd-gfx:b4be3a06d7aa Added AMD modification notices and removed some GPL files. Change-Id: I67baaf184d016f94d22a12d20a1e62a7fe8fecb1
Configuration menu - View commit details
-
Copy full SHA for 240f3dd - Browse repository at this point
Copy the full SHA 240f3ddView commit details
Commits on Sep 16, 2020
-
Overwritten with: c08be3d Merged master:cb9528a0420e into amd-gfx:2a3…
…30c47ba7d Based on upstream llvm : cb9528a [DSE] Add another test cases with loop carried dependence. Local changes since 240f3dd: c08be3d Merged master:cb9528a0420e into amd-gfx:2a330c47ba7d 2a330c4 Merged master:1c421046d742 into amd-gfx:a8b4052ff67e a8b4052 Merged master:a8d02015fcb7 into amd-gfx:43f430b3eb08 43f430b Fix AMDGPUConditionalDiscard crashes with "unreachable" 6277d98 Manually merged master:9868ea764f31 into amd-gfx:3e9081ae5006 3e9081a Merged master:412b417bfa79 into amd-gfx:ea7744e97a5c ea7744e Revert "[AMDGPU] intrinsics for byte/short load/store" 0be4f04 Merged master:687e1d712164 into amd-gfx:d4c310eb5e87 d4c310e Merged master:15bff4dec436 into amd-gfx:2bd365f723db 2bd365f Merged master:88690a965892 into amd-gfx:92dbd8e993d3 92dbd8e Merged master:783ba64a8950 into amd-gfx:dda4929b8aec dda4929 Merged master:cb3e1dd6c31e into amd-gfx:2cb8ebf0f9e1 2cb8ebf Merged master:8889faaed0b7 into amd-gfx:4997fc11ee05 4997fc1 Merged master:c0bcd11068fc into amd-gfx:86c8a30c61c8 86c8a30 Merged master:9237fde48139 into amd-gfx:45bcf58938d0 45bcf58 Merged master:e2dee9af8db6 into amd-gfx:2ee0ada5f927 2ee0ada Merged master:bec81dc67d93 into amd-gfx:1a98fd0f4c13 1a98fd0 Merged master:5f4e9bf6416e into amd-gfx:9cc2f53c368b 9cc2f53 Merged master:f086e85eea94 into amd-gfx:42084812293f 4208481 Merged master:758732a34ed0 into amd-gfx:06cd7639f3d6 06cd763 Merged master:9d300bc8d2f3 into amd-gfx:06aab2055889 06aab20 Merged master:70daa353e2ae into amd-gfx:fee17dbf125a fee17db Merged master:d6fadc49e3d7 into amd-gfx:02b636828dde 02b6368 Merged master:7d3825ed954a into amd-gfx:aa304b9c5565 aa304b9 Merged master:74760bb00fb9 into amd-gfx:bcc672e3fdb6 bcc672e Merged master:3170d5484265 into amd-gfx:21fa2f093bc5 21fa2f0 Merged master:78de7297abe2 into amd-gfx:eba5b48183eb eba5b48 Merged master:4ede83c06831 into amd-gfx:9b09fedad35c 9b09fed Merged master:b3f364e8561c into amd-gfx:c465085fd962 c465085 Merged master:0680a3d56d8b into amd-gfx:a2f43e05acd2 a2f43e0 Merged master:12a281d368e3 into amd-gfx:deb0de058064 deb0de0 Merged master:a8503b87f739 into amd-gfx:565b50a231f6 565b50a Merged master:e3e3d6eecfa5 into amd-gfx:c9607fa5e52c c9607fa Merged master:59fc86779038 into amd-gfx:ec51c0b57588 ec51c0b Merged master:40b72c9c7920 into amd-gfx:b1dd8d87a662 b1dd8d8 Merged master:f980ed4184f9 into amd-gfx:411720708275 4117207 Merged master:8da6ae4ce1b6 into amd-gfx:38db3e0ab8cc 38db3e0 Merged master:7527898fef47 into amd-gfx:a52b07df8f51 a52b07d Fix incomplete phi generated by AMDGPUConditionalDiscard 9820fc4 Revert "Partially revert 264afb9 [NFC][llvm] Make the contructors of `ElementCount` private." b39f544 Merged master:d380b582f7f0 into amd-gfx:0228fcc59645 0228fcc Merged master:e45b0708ae81 into amd-gfx:1e589fb96e5c 1e589fb Merged master:41e68f7ee7b3 into amd-gfx:310574702f25 3105747 Merged master:4934127e627d into amd-gfx:6bd5a7369e20 6bd5a73 Merged master:54fcea86b165 into amd-gfx:6b0cdcb65a4f 6b0cdcb Manual merge test fix 007fb0c Manual merge master:8a08740db6e1 onto amd-gfx:4ef4636769e7 Added AMD modification notices and removed some GPL files. Change-Id: Ic9efff76e38ea1c6b686646b58c5e37af7a692b1
Configuration menu - View commit details
-
Copy full SHA for ff1e992 - Browse repository at this point
Copy the full SHA ff1e992View commit details
Commits on Sep 25, 2020
-
Overwritten with: 82555a6 Merged master:625761825620 into amd-gfx:d9d…
…b95ee77fb Based on upstream llvm : 6257618 [ASTMatchers] Avoid recursion in ancestor matching to save stack space. Local changes since ff1e992: 82555a6 Merged master:625761825620 into amd-gfx:d9db95ee77fb d9db95e Merged master:703d3f25976c into amd-gfx:48d97b608ba9 48d97b6 Merged master:bf202b8ce77c into amd-gfx:e43067c199dc e43067c Merged master:b5e49e91cb90 into amd-gfx:6c61577619cb 6c61577 Merge master:892ef2e3c0b6 into amd-gfx 092d77f Merge master:a0c1dcc31827 into amd-gfx b82b3cc Merged master:1e6b240d7d33 into amd-gfx:a60fc2d73edc a60fc2d Merged master:96e52c13640b into amd-gfx:b4af738b3ef0 b4af738 [SplitKit] In addDeadDef tolerate parent range that defines more lanes 5e44e4d Merged master:df3e903655e2 into amd-gfx:85dcc941054b 85dcc94 Merged master:87f0b51d68de into amd-gfx:362d799bb7d7 362d799 Merged master:ffdd4a46a9a9 into amd-gfx:4f06d763d1d7 4f06d76 Merged master:349af8054218 into amd-gfx:8db42361a28e 8db4236 Merged master:a1aa330b202f into amd-gfx:046007c5b8e1 046007c Merged master:22dde1f92f68 into amd-gfx:606e09770817 606e097 Merged master:5d1f8395be94 into amd-gfx:0b4255fb2027 0b4255f Merge remote-tracking branch 'llvm.org/master' into merge-candidate 657879f Revert "[AMDGPU] Set DS alignment requirements to be more strict." 63ba5fe Merged master:09a3737384ec into amd-gfx:e3eb9e9bbcdb e3eb9e9 [AMDGPU] Ensure waterfall inserts RFL in-place d63df0c [AMDGPU] Improve waterfall uniform detection 04a8829 Merged master:67ae46c820fa into amd-gfx:656d292e7f8b 656d292 Revert "[AMDGPU] Add v3f16/v3i16 support to SDag" a41e667 Manual merge master:347d59b16c71 into amd-gfx:c08be3ddc85a Added AMD modification notices and removed some GPL files. Change-Id: I58a03b67a8069e7cfe6d7684ff2b713b89aba98a
Configuration menu - View commit details
-
Copy full SHA for d3f03b3 - Browse repository at this point
Copy the full SHA d3f03b3View commit details
Commits on Sep 30, 2020
-
Overwritten with: aa7b191 [AMDGPU] Correctly update uses of waterfall…
….readfirstlane Based on upstream llvm : 7fcad55 [InstCombine] Remove %tmp variable names from bswap tests Local changes since d3f03b3: aa7b191 [AMDGPU] Correctly update uses of waterfall.readfirstlane 8d4d8d3 Merged master:7fcad5583a12 into amd-gfx:26656ef803b2 26656ef Merged master:0eab9d582381 into amd-gfx:9a9ec94ec7f5 9a9ec94 Merged master:8c05c7c8d87c into amd-gfx:1cc7c9fb5e62 1cc7c9f Merged master:834b6470d9f1 into amd-gfx:91da1c469586 91da1c4 Merged master:4e4f926e83cf into amd-gfx:6885293b00fc 6885293 Merged master:e6e73712ddfa into amd-gfx:2aaac3689e79 2aaac36 Merged master:1d54e75cf26a into amd-gfx:4632cf3ab52c 4632cf3 Merged master:984744a1314c into amd-gfx:93def576d34e 93def57 Merged master:b5543063e1bf into amd-gfx:8850eb8d16e6 8850eb8 Merged master:5d19eb542db4 into amd-gfx:5e4ec881ba11 5e4ec88 Merged master:543922cd3630 into amd-gfx:dc9d87346342 dc9d873 Merged master:119274748bce into amd-gfx:d2145be64b29 d2145be Merged master:074ab233ed62 into amd-gfx:da1446efad0c da1446e Merged master:c5a4900e1a00 into amd-gfx:a62392bc83d8 a62392b Merged master:9100bd772d4f into amd-gfx:e28cb5ae5057 e28cb5a Merge remote-tracking branch 'llvm.org/master' into amd-gfx 59c13c9 Merged master:4c41fb5ad70c into amd-gfx:6063c3f98ed8 6063c3f Merge remote-tracking branch 'llvm.org/master' into amd-gfx 5f4947d Merged master:d3a8e333ec9d into amd-gfx:5e6c78e3944a 5e6c78e Merged master:0ad793f321ed into amd-gfx:5743f65431c1 5743f65 Merge remote-tracking branch 'llvm.org/master' into amd-gfx 18be55f Merged master:645c53a9d923 into amd-gfx:060b66d88b11 060b66d Merged master:ababcd2ab491 into amd-gfx:b3784523579f b378452 Merged master:5811d723998a into amd-gfx:f8c9b6a1d1e1 f8c9b6a Merged master:ba950ad0a510 into amd-gfx:42611bd8554c 42611bd Merged master:c8f6c0f961ee into amd-gfx:b17d18cd6ab0 b17d18c Merged master:55f727306e72 into amd-gfx:7db64841a553 7db6484 Merged master:6d374cf78c8a into amd-gfx:75c3a90abed8 75c3a90 Merged master:c2921d148e7b into amd-gfx:84afc21c89eb 84afc21 Merged master:915310bf14cb into amd-gfx:1dfb8a899d02 1dfb8a8 Merged master:93628ea9d162 into amd-gfx:185cc7fd8dfc 185cc7f Merged master:a61272a90029 into amd-gfx:01dbde096260 01dbde0 Merged master:8d5b289a4681 into amd-gfx:cf1a3e847a68 cf1a3e8 Merged master:c6c5629f2fb4 into amd-gfx:e0ad6afbb206 e0ad6af Merged master:96318f64a786 into amd-gfx:c913e2606339 c913e26 Merged master:63c58c2b9345 into amd-gfx:5fcc1d28e3aa 5fcc1d2 Merged master:546e460a00a9 into amd-gfx:5fc9b9614455 5fc9b96 Merged master:a000580a8971 into amd-gfx:9f58c9ba57c4 9f58c9b Merged master:a83eb048cb9a into amd-gfx:edec44630eba edec446 Merged master:2a0ca17f66f7 into amd-gfx:10b69f966560 10b69f9 Merged master:6cb0d23f2ea6 into amd-gfx:9013ebb7f638 9013ebb Merged master:85cea77ecb7f into amd-gfx:6180a6beec76 6180a6b Merged master:f330d9f163f6 into amd-gfx:e6f7d959be13 e6f7d95 Merged master:7af12015ad44 into amd-gfx:93bf630eaf4b 93bf630 Merged master:a399d1880bc6 into amd-gfx:3c5f340b9e99 3c5f340 Manually merged master:ada1e2ffa117 into amd-gfx:4baa63b509c7 698ee93 Revert "Revert "[AMDGPU] Add v3f16/v3i16 support to SDag"" 4baa63b Merged master:8e712807e484 into amd-gfx:3bd64024f646 3bd6402 Merged master:4da6927de470 into amd-gfx:82555a629c63 Added AMD modification notices and removed some GPL files. Change-Id: I559abb064e92d885c781929ebb8b79ade3684d95
Configuration menu - View commit details
-
Copy full SHA for 0510352 - Browse repository at this point
Copy the full SHA 0510352View commit details
Commits on Oct 6, 2020
-
Overwritten with: eb04fb8 Temporarily revert commits that caused hangs
Based on upstream llvm : 25692b7 [flang][NFC] Remove redundant `;` Local changes since 0510352: eb04fb8 Temporarily revert commits that caused hangs fce51b8 Merge remote-tracking branch 'llvm.org/master' into amd-gfx 9803d06 Merged master:d5a6da84a346 into amd-gfx:742c166a3543 742c166 Merged master:348d85a6c795 into amd-gfx:e95e7df41834 e95e7df Merged master:d52211e38477 into amd-gfx:f3e8848d81eb f3e8848 Merged master:2cd75f738ec6 into amd-gfx:bf830322100c bf83032 Merged master:b113fa451061 into amd-gfx:9f9a094215df 9f9a094 Merged master:045a620c455d into amd-gfx:898736e1787a 898736e Merged master:86b14d0969eb into amd-gfx:55b47f4dc7ae 55b47f4 Merged master:fe1f0a1a1901 into amd-gfx:ae984c5eb8b4 ae984c5 Merged master:8825fec37e73 into amd-gfx:f2aa04fae003 f2aa04f Merged master:e3de249a4c94 into amd-gfx:2bc9ee2e9a05 2bc9ee2 Merged master:542523a61a21 into amd-gfx:2fe244daaf8c 2fe244d Merged master:79fbcbff4173 into amd-gfx:3abdbc4a02d0 3abdbc4 Merged master:bc730b5e43ad into amd-gfx:1ad924232559 1ad9242 Merged master:8931c3d68276 into amd-gfx:3d273a9632c8 3d273a9 Merge master:456974ac78f into amd-gfx Added AMD modification notices and removed some GPL files. Change-Id: If68e93889a2346edcfafaf845bb5f542e73fce6f
Configuration menu - View commit details
-
Copy full SHA for bf98770 - Browse repository at this point
Copy the full SHA bf98770View commit details
Commits on Oct 12, 2020
-
Overwritten with: 19563a6 Merged master:9237e73ae8a3 into amd-gfx:ced…
…5b8fb9ffe Based on upstream llvm : 9237e73 [Hexagon] Replace HexagonISD::VSPLAT with ISD::SPLAT_VECTOR Local changes since bf98770: 19563a6 Merged master:9237e73ae8a3 into amd-gfx:ced5b8fb9ffe ced5b8f Merged master:a8682554c666 into amd-gfx:4a7e6e583ecf 4a7e6e5 Merged master:702ccb40e2d7 into amd-gfx:121871dddd87 121871d Merged master:5d330f435e12 into amd-gfx:3c5789a6ff0c 3c5789a Merged master:d48b249b7162 into amd-gfx:c3298b9d57eb c3298b9 Merged master:cb27006a9461 into amd-gfx:829bdbbc7e29 829bdbb Merged master:6d8eea61b18b into amd-gfx:84bbaf171625 84bbaf1 Merged master:e1c38dd55d9d into amd-gfx:defd97e34596 defd97e Merged master:2bd4730850cc into amd-gfx:8a3feeb388f0 8a3feeb Merged master:f6fa4d07dcb4 into amd-gfx:201734f69835 201734f Merged master:9b5b3050237d into amd-gfx:02a8883052a4 02a8883 Merged master:e0dc3dba3bd1 into amd-gfx:ae92c01db53a ae92c01 Merged master:3a6bfcf2f902 into amd-gfx:664c2001cf10 664c200 Merged master:dcd9be43e5c7 into amd-gfx:7b679a506c24 7b679a5 Merged master:8f56e382f782 into amd-gfx:e77b9b12d836 e77b9b1 Merged master:027e7a772175 into amd-gfx:2c4157561dac 2c41575 Merged master:32f2f0d78aa0 into amd-gfx:659cf3677a52 659cf36 Merged master:efd8c9ed726d into amd-gfx:bcba47ddb667 bcba47d Merged master:0a34492f36d7 into amd-gfx:6a77a9daa4d7 6a77a9d Merged master:1ceaffd95a6b into amd-gfx:8b9b4c5a940a 8b9b4c5 Merged master:137da82b8682 into amd-gfx:27e5f37749f4 27e5f37 Merged master:caedf7937c59 into amd-gfx:b063dd7fddcf b063dd7 Merged master:19119dda1662 into amd-gfx:f10bf2ff338e f10bf2f Merged master:69efcd03bdb9 into amd-gfx:c9263bb70a7a c9263bb Merged master:295d4e420fd0 into amd-gfx:9423a9135143 9423a91 Merged master:79809f58b024 into amd-gfx:42dde2b449a6 42dde2b Merged master:e547b1e2431f into amd-gfx:314f7fcdbcd3 314f7fc Merged master:5415fef3abef into amd-gfx:55fcdb42a5d9 55fcdb4 Revert "[AMDGPU] Avoid calling expandUnalignedLoad/Store and spilling when possible" 0e3f0fd Merged master:a96bcfb19674 into amd-gfx:08047a594363 08047a5 Merged master:b4ffc40d622b into amd-gfx:0a7be8195e1b 0a7be81 Merged master:93db4a8ce626 into amd-gfx:6f010c8a5dd6 6f010c8 Merged master:c10248829357 into amd-gfx:c6d4fa64b723 c6d4fa6 Merged master:297655c123b3 into amd-gfx:774f38e38f9d 774f38e Merged master:a85e43e99676 into amd-gfx:c6eb012f954a c6eb012 Merged master:69daa368cad3 into amd-gfx:030d8a56d386 030d8a5 Merged master:ddf1864ace48 into amd-gfx:4a02f3131539 4a02f31 Merged master:4a7e7620d6c6 into amd-gfx:4335f444a11d 4335f44 Merged master:dce03e3059f0 into amd-gfx:af34bc12c690 af34bc1 Merged master:1aa8e6a51a0e into amd-gfx:a69e55732a61 a69e557 Merged master:31dc90801746 into amd-gfx:eb04fb8d2acb Added AMD modification notices and removed some GPL files. Change-Id: I9c4e42098329f350832ea2a60cc67200e5047b90
Configuration menu - View commit details
-
Copy full SHA for 1598ada - Browse repository at this point
Copy the full SHA 1598adaView commit details
Commits on Oct 22, 2020
-
Overwritten with: 2f0ca85 [AMDGPU] Use WQM Live Mask to Early Termina…
…te Pixel Shaders Based on upstream llvm : 529ecd1 [NPM] port -unify-loop-exits to NPM Local changes since 1598ada: 2f0ca85 [AMDGPU] Use WQM Live Mask to Early Terminate Pixel Shaders 7028452 Merged master:529ecd19df1f into amd-gfx:6210b77c9d82 6210b77 Merged master:ec228fbfc0fc into amd-gfx:1b6104d6ec38 1b6104d Merged master:b78045c2ce2d into amd-gfx:9fd31e22f3e6 9fd31e2 Revert "[DAGCombiner][PowerPC] Remove isMulhCheaperThanMulShift TLI hook, Use isOperationLegalOrCustom directly instead." 7ee0c53 Merged master:ae3625d7526f into amd-gfx:2c7bdb1e17c8 2c7bdb1 Update expand-scalar-carry-out-select-user.ll 1085b47 Merged master:1d90e5304424 into amd-gfx:80dbad88ce20 80dbad8 Merged master:f2fd42098cfb into amd-gfx:64b7a5c063be 64b7a5c Merged master:a71a0d6d219a into amd-gfx:7e7f25793a94 7e7f257 Merged master:f402e682d0ef into amd-gfx:ba721ee79db8 ba721ee Merged master:094e9f4779eb into amd-gfx:bac148f43ef0 bac148f Merged master:7928d40c6b89 into amd-gfx:a32f1a47d4b7 a32f1a4 Merged master:98797a5fc06c into amd-gfx:b100493c9f39 b100493 Merged master:65e94cc946b0 into amd-gfx:44cc4ec6ae1c 44cc4ec Merged master:2a75e956e5ce into amd-gfx:9653dc41b75b 9653dc4 Merged master:53e92b4c0efc into amd-gfx:20722fb27f2e 20722fb Merged master:50cc9a0e6124 into amd-gfx:0438057f7745 0438057 Merged master:b93d74ac9c4e into amd-gfx:ceef23db0218 ceef23d Merged master:ae4fe1984f0e into amd-gfx:b9404d6baa28 b9404d6 Merged master:62a0ec1612bd into amd-gfx:428da186456d 428da18 Merged master:0538353b3be3 into amd-gfx:cefcd6abf519 cefcd6a Merged master:dc9713812355 into amd-gfx:97eda0c842bb 97eda0c Merged master:4ad459997e65 into amd-gfx:5efa00aba612 5efa00a Merged master:552c6c232872 into amd-gfx:28482ff9f121 28482ff Merged master:32f77eea2d0f into amd-gfx:a9377682fb5c a937768 Merged master:7dff6b818b1c into amd-gfx:83a2798a92c7 83a2798 Merged master:952f43cb431c into amd-gfx:a3165bf1e7b8 a3165bf Merged master:ef0ab3cdfe20 into amd-gfx:01cf3095e4bb 01cf309 Merged master:55991b44b7f9 into amd-gfx:11d9db147428 11d9db1 Merged master:51ff04567b2f into amd-gfx:340537749c25 3405377 Merged master:3cfd9384bff4 into amd-gfx:4f03f357fef1 4f03f35 [AMDGPU] Remove calcSubRegIdx bfa38bd Merged master:6771b98c4e4d into amd-gfx:8c6f592a80dc 8c6f592 Merged master:2bf423b0218c into amd-gfx:5fb0954ccdeb 5fb0954 Merged master:6754caa9bf21 into amd-gfx:d51eb44028f6 d51eb44 Merged master:67f189e93ce3 into amd-gfx:b2ae0114a629 b2ae011 Merged master:e9df9028a7ca into amd-gfx:dfd5c08faba1 dfd5c08 Merged master:09be7623e4e8 into amd-gfx:adbf4b157df9 adbf4b1 Merged master:88ce27c39c5e into amd-gfx:83b2caabc60f 83b2caa Merged master:196bee9648a9 into amd-gfx:2d673cddc23e 2d673cd Merged master:d8bb30c55180 into amd-gfx:a59fae97c89e a59fae9 Merged master:a7b209a6d40d into amd-gfx:45250cd1b7e3 45250cd Merged master:220de1f32add into amd-gfx:e5f653eaa249 e5f653e Merged master:78ccb0359d8d into amd-gfx:5894e00a0f69 5894e00 Merged master:e7b4feea8e1b into amd-gfx:f99c1c4e1ba6 f99c1c4 Merged master:633f9fcb820b into amd-gfx:7af372bc8c89 7af372b Merged master:adfb5415010f into amd-gfx:b2b452e5a617 b2b452e Merged master:ef748583c24d into amd-gfx:ffaf4aaa460d ffaf4aa Revert "[AMDGPU] Insert waterfall loops for divergent calls" fca46d9 Merged master:7f2a641aad28 into amd-gfx:7d8613e27f8f 7d8613e Merged master:974ddb54c9ad into amd-gfx:50f1f527b5ee 50f1f52 Revert "[AMDGPU] Temporary fix to get previous intrinsic cost" 3a3234b Merged master:6bf25f45a9b6 into amd-gfx:19563a6be683 Added AMD modification notices and removed some GPL files. Change-Id: I3482a129caffaceec6c74743834c57d3378162e5
Configuration menu - View commit details
-
Copy full SHA for 145729e - Browse repository at this point
Copy the full SHA 145729eView commit details
Commits on Oct 23, 2020
-
Overwritten with: b19d6f8 CfgInterface: rename interface() to getInte…
…rface() Based on upstream llvm : 529ecd1 [NPM] port -unify-loop-exits to NPM Local changes since 145729e: b19d6f8 CfgInterface: rename interface() to getInterface() 95bf6d0 Revert "Temporarily revert commits that caused hangs" Added AMD modification notices and removed some GPL files. Change-Id: I14229c5cec7a74553dcc08b6dff1ff4e542eaa4a
Configuration menu - View commit details
-
Copy full SHA for 1825096 - Browse repository at this point
Copy the full SHA 1825096View commit details
Commits on Oct 26, 2020
-
Overwritten with: 6f46063 Update llvm.amdgcn.waterfall.ll
Based on upstream llvm : 1cab3bf [InstCombine] matchBSwapOrBitReverse - expose bswap/bitreverse matching flags. Local changes since 1825096: 6f46063 Update llvm.amdgcn.waterfall.ll 89a5b55 Merged master:1cab3bf00461 into amd-gfx:b19d6f8966ea Added AMD modification notices and removed some GPL files. Change-Id: Iec872881c870fb3a7297ad302cf48e94e5852f67
Configuration menu - View commit details
-
Copy full SHA for f7d2903 - Browse repository at this point
Copy the full SHA f7d2903View commit details -
Overwritten with: 7666303 [AMDGPU] Extend waterfall support to begin …
…- begin-cont form Based on upstream llvm : 1cab3bf [InstCombine] matchBSwapOrBitReverse - expose bswap/bitreverse matching flags. Local changes since f7d2903: 7666303 [AMDGPU] Extend waterfall support to begin - begin-cont form Added AMD modification notices and removed some GPL files. Change-Id: I22f35367fdf617354eb719651859817529a76381
Configuration menu - View commit details
-
Copy full SHA for 5cb4dc4 - Browse repository at this point
Copy the full SHA 5cb4dc4View commit details
Commits on Oct 29, 2020
-
Overwritten with: 68d3270 Merged master:20a3931f8fad into amd-gfx:9e4…
…c96697575 Based on upstream llvm : 20a3931 Revert "[NFC][TSAN] Logs to debug test script on bot" Local changes since 5cb4dc4: 68d3270 Merged master:20a3931f8fad into amd-gfx:9e4c96697575 9e4c966 Merged master:1df8d7b4f23d into amd-gfx:513ba23e7467 513ba23 Merged master:5be50d79c0b8 into amd-gfx:6eb7d17bb40e 6eb7d17 Merged master:39856d5d0b65 into amd-gfx:6a4df4c90621 6a4df4c Merged master:77973f8dee6d into amd-gfx:921ffe6ea851 921ffe6 Merged master:864b3a336b60 into amd-gfx:71b4898c0fb4 71b4898 Merged master:818bd31906ba into amd-gfx:3054a3c25d15 3054a3c Merged master:31e944556f54 into amd-gfx:88456c1a7b47 88456c1 Merged master:ae73091f3024 into amd-gfx:1a8972ab337a 1a8972a Revert "[AMDGPU][CostModel] Refine cost model for half- and quarter-rate instructions." 2ab16fa Manually merged master:b7e219d0f368 to amd-gfx:65a5fb256cf0 65a5fb2 Manually merged master:a4fc18e6410f into amd-gfx:b7a4112fc2b5 b7a4112 Un-revert upstream waterfall related commits 268ff0a Revert "Revert "[DAGCombiner][PowerPC] Remove isMulhCheaperThanMulShift TLI hook, Use isOperationLegalOrCustom directly instead."" Added AMD modification notices and removed some GPL files. Change-Id: Ia74b1fe6e5407dc449aa46ba772f3b9bf81e11ce
Configuration menu - View commit details
-
Copy full SHA for e09ed8b - Browse repository at this point
Copy the full SHA e09ed8bView commit details
Commits on Nov 3, 2020
-
Overwritten with: 1c7c56d Merged master:6e008cb554b3 into amd-gfx:2e2…
…54597ecd9 Based on upstream llvm : 6e008cb [AMDGPU] Precommit globalisel tests for ds_read2_b64 with large offset Local changes since e09ed8b: 1c7c56d Merged master:6e008cb554b3 into amd-gfx:2e254597ecd9 2e25459 Merged master:71041a8b6bc4 into amd-gfx:765d9ac68d66 765d9ac Revert "[amdgpu] Add the late codegen preparation pass." d9ddf82 Merged master:992516857691 into amd-gfx:0c4f040292b0 0c4f040 Merged master:952ddc9866dc into amd-gfx:24e58ba22db5 24e58ba Merged master:f847094c2468 into amd-gfx:9005424148df 9005424 Merged master:98031b664c94 into amd-gfx:2931e6bc4ec5 2931e6b Merged master:dd6f7ee05e90 into amd-gfx:a8898f9cf70f a8898f9 Merged master:c0a922b3db2d into amd-gfx:19a374d63eaf 19a374d Merged master:c938b4a1ed43 into amd-gfx:4dee369a5451 4dee369 Merged master:773ad135a30d into amd-gfx:c5e2ee8977a0 c5e2ee8 Merged master:e59726220f3d into amd-gfx:698aeb64ba6d 698aeb6 Merged master:7142ec3aaf55 into amd-gfx:fde2223c78f1 fde2223 Merged master:e3645fdff463 into amd-gfx:92ee9cdf725a 92ee9cd Merged master:f03be9df37bf into amd-gfx:cc8bae54be9e cc8bae5 Merged master:1ed2ca68191f into amd-gfx:3a9a669b4cd8 3a9a669 Merged master:7979f24954ed into amd-gfx:c0143b8db6c2 c0143b8 Merged master:1800b44651c1 into amd-gfx:ac615d4ba684 ac615d4 Merged master:e03ba2198dbb into amd-gfx:3dc65cbc7b0c 3dc65cb Merged master:aab71d44431e into amd-gfx:304d7dcc173f 304d7dc Merged master:09662eeb46f7 into amd-gfx:83ab1eda747d 83ab1ed Merged master:ef6f6d1c1a28 into amd-gfx:8c369117c743 8c36911 Merged master:d915d403d741 into amd-gfx:1979a05520ab 1979a05 Merged master:5963e028e714 into amd-gfx:f9f961080e9f f9f9610 Merged master:6021cbea4d34 into amd-gfx:7e9078ffd348 7e9078f Merged master:5c31b8b94fdd into amd-gfx:84156f83019c 84156f8 Merged master:3eaec1fead4d into amd-gfx:d56063d98a2c d56063d Merged master:d11710dae6c1 into amd-gfx:3911a3927067 3911a39 Merged master:dd8297b0669f into amd-gfx:9e007aaa13a0 9e007aa Merged master:b093eba08478 into amd-gfx:bc2cc69d93e7 bc2cc69 Merged master:fccf4f6addc8 into amd-gfx:ee7c7aaecf7c ee7c7aa Merged master:00da38ce2d36 into amd-gfx:d88083461c06 d880834 Merged master:4dfe014a1291 into amd-gfx:0ceb1bc2c82e 0ceb1bc Merged master:52ff86d25598 into amd-gfx:783a629c71ff 783a629 Merged master:a4f7e4264cfc into amd-gfx:5d77d8ab1f54 5d77d8a Revert "[llvm] Export LLVM_LIT_ARGS in LLVMConfig.cmake" fd9dc6d Manually merged master:16ab0b6778be into amd-gfx:8fb378fe2aa8 8fb378f Merged master:dbae3d50f114 into amd-gfx:318f34c7ff2a 318f34c Merged master:8cc49bec2e06 into amd-gfx:7c4e68106766 7c4e681 Merged master:930a8c60b608 into amd-gfx:68d3270fef04 Added AMD modification notices and removed some GPL files. Change-Id: I695a7acf66ac735c802e9621b5ee22e6b0ea0398
Configuration menu - View commit details
-
Copy full SHA for f46f369 - Browse repository at this point
Copy the full SHA f46f369View commit details -
Overwritten with: 1c7c56d Merged master:6e008cb554b3 into amd-gfx:2e2…
Configuration menu - View commit details
-
Copy full SHA for 5b944bf - Browse repository at this point
Copy the full SHA 5b944bfView commit details
Commits on Nov 5, 2020
-
Overwritten with: 6612326 Merged master:35d625125465 into amd-gfx:7ef…
…2a04a9be8 Based on upstream llvm : 35d6251 Add default value for MachineInstr::modifiesRegister. NFC. Local changes since 5b944bf: 6612326 Merged master:35d625125465 into amd-gfx:7ef2a04a9be8 7ef2a04 Merged master:2c2eb5e6702b into amd-gfx:23e8ff695c93 23e8ff6 Merged master:26a8e8502b59 into amd-gfx:8e202fa63587 8e202fa Merged master:a7bcb3b9eb76 into amd-gfx:a97870a7d652 a97870a Merge master:23657d9cc332 into amd-gfx 26716e7 Merged master:6706342f48be into amd-gfx:e4f21cfa2d95 e4f21cf Merged master:aa662f61deca into amd-gfx:c37639dfce92 c37639d Merged master:1664462d70cc into amd-gfx:bd043dc64110 bd043dc Merged master:985a5d970aa9 into amd-gfx:55055611cf69 5505561 Merged master:9c31e12609e1 into amd-gfx:d382ea182aab d382ea1 Merged master:8260db752c91 into amd-gfx:362b06229d79 362b062 Merged master:7ba3293691be into amd-gfx:f2bcfb477c22 f2bcfb4 Merged master:c298824f9caf into amd-gfx:c54224fe9b38 c54224f Merged master:29d1fba7b533 into amd-gfx:f9db9f3f47d4 f9db9f3 Merged master:7f059a258a1d into amd-gfx:194fc973caf8 194fc97 Merged master:107c3a12d627 into amd-gfx:c198fccc05c7 c198fcc Merged master:e1af54296c52 into amd-gfx:1c7c56ddc669 Added AMD modification notices and removed some GPL files. Change-Id: I9974c5f93e04c810dae52c184f50117b7ac6de12
Configuration menu - View commit details
-
Copy full SHA for c9860f1 - Browse repository at this point
Copy the full SHA c9860f1View commit details
Commits on Nov 10, 2020
-
[AMDGPU] Fix live mask tracking with conditional kill live lanes
If a conditional kill or demote is based on a value representing live lanes then this must be combined with the exec mask to make sure we do not mark lanes dead just because they are currently inactive due to branching control flow. This code will become tidier demote support is upstreamed and kill lowering is moved to WQM pass. Change-Id: Ib317401f9e7faff30c772a957aca2565724ab6f3
Configuration menu - View commit details
-
Copy full SHA for 84d2d98 - Browse repository at this point
Copy the full SHA 84d2d98View commit details -
Overwritten with: 84d2d98 [AMDGPU] Fix live mask tracking with condit…
…ional kill live lanes Based on upstream llvm : 35d6251 Add default value for MachineInstr::modifiesRegister. NFC. Local changes since c9860f1: 84d2d98 [AMDGPU] Fix live mask tracking with conditional kill live lanes Added AMD modification notices and removed some GPL files. Change-Id: I4e16f407519beb007df353cede9c9d0dbd43074d
Configuration menu - View commit details
-
Copy full SHA for 88613f6 - Browse repository at this point
Copy the full SHA 88613f6View commit details
Commits on Nov 17, 2020
-
Overwritten with: adf0596 Change waterfall begin for multi-begin
Based on upstream llvm : af0d607 [clang-tidy] Fix an abseil-redundant-strcat-calls crash on 0-parameter StrCat(). Local changes since 88613f6: adf0596 Change waterfall begin for multi-begin a408f9e Merged master:af0d607e7275 into amd-gfx:7d324e9dc6bb 7d324e9 Merge remote-tracking branch 'llvm.org/master' into amd-gfx dda78e3 Merged master:47fd19f22eb5 into amd-gfx:4d3469bdb33b 4d3469b Merged master:83ac18205ec6 into amd-gfx:67a45da6120a 67a45da Revert "Revert "[amdgpu] Add the late codegen preparation pass."" 16f181f Merged master:ca2e7e59994d into amd-gfx:202115b46108 202115b Merged master:1c00d096a608 into amd-gfx:ec1abe3201ce ec1abe3 Merged master:147ccc848a55 into amd-gfx:d3b8b5809e03 d3b8b58 Merged master:0888eaf3fde6 into amd-gfx:df1dcf35202f df1dcf3 Merged master:c22dc71b120b into amd-gfx:874dbe853d60 874dbe8 Merged master:6ddc23776692 into amd-gfx:1c08cad927d4 1c08cad Merged master:e56103d25016 into amd-gfx:33ce16c41ea2 33ce16c Merged master:7fa8b629208c into amd-gfx:3c4445307114 3c44453 Merged master:d2acf2292792 into amd-gfx:44f50f53f836 44f50f5 Merged master:fb58142e00ad into amd-gfx:ae34a791d649 ae34a79 Merged master:906220b5e9b3 into amd-gfx:74ec107a73e1 74ec107 Merged master:581ebf44d28b into amd-gfx:bf0f513d8d8c bf0f513 Merged master:1ec6e1eb8a08 into amd-gfx:4998edf6a86d 4998edf Merged master:dd0b8b94d079 into amd-gfx:f389b5e4a2fc f389b5e Merged master:23cc838099e1 into amd-gfx:6915ea6e536e 6915ea6 Merged master:a70b511e7802 into amd-gfx:f635e0030b6a f635e00 Merged master:2104783d024c into amd-gfx:5adf44be80e9 5adf44b Merged master:5a2febb31af7 into amd-gfx:826bee7dd3cf 826bee7 Merged master:0a6e051a9b30 into amd-gfx:73d2905e2efa 73d2905 Merged master:db6f7e0e9ec2 into amd-gfx:a3d230106c39 a3d2301 Merged master:6861d938e5c9 into amd-gfx:fd0ff17ffcc9 fd0ff17 Merged master:c8f4e06b29f4 into amd-gfx:21cc0393fbff 21cc039 Merged master:6ef07111a402 into amd-gfx:ed9982e88406 ed9982e Merged master:ac06b1af402e into amd-gfx:6fabed927daf 6fabed9 Merged master:e7ed27653292 into amd-gfx:551e5b0eb003 551e5b0 Merged master:703ef17e7a0a into amd-gfx:5a0cbb904e31 5a0cbb9 Merged master:c9821cec7492 into amd-gfx:31cd21d3e722 31cd21d Merged master:835c462eae73 into amd-gfx:94cbe4b7a423 94cbe4b Merged master:3f78605a8cb1 into amd-gfx:b9ea5f1983f8 b9ea5f1 Merged master:c87c37509692 into amd-gfx:3c5ddab8ce09 3c5ddab Merged master:2728293bbc34 into amd-gfx:3e52121a5527 3e52121 Merged master:8920ef06a138 into amd-gfx:44df6ffdf403 44df6ff Merged master:c2bccd66f63d into amd-gfx:cf10a0160d05 cf10a01 Merged master:d0ba6c4002e4 into amd-gfx:5b170e5ef9e4 5b170e5 Merged master:3a7b57b7cad3 into amd-gfx:d2c3df5bcfc0 d2c3df5 Merged master:ba906eb16cdf into amd-gfx:6bbbbee07e26 6bbbbee Merged master:a088766508aa into amd-gfx:f3f542496cf0 f3f5424 Merged master:a72d3842495d into amd-gfx:a427513af78e a427513 Merge master:3225fcf11eb7 into amd-gfx 1a96385 Merged master:3df3b62018c0 into amd-gfx:e56f984c3e68 e56f984 Merged master:30fded75b48b into amd-gfx:e41d79a6a5be e41d79a Merged master:09e34048bf7e into amd-gfx:a19e5acf4bf6 a19e5ac Merged master:d1ff394ee27e into amd-gfx:d03e22dfa5dc d03e22d Merged master:b8a8ef32762b into amd-gfx:e954a3f4a4cb e954a3f Merged master:9922dded4737 into amd-gfx:26fcbe6abe1b 26fcbe6 Merged master:c43f8c772886 into amd-gfx:14b4412cd39c 14b4412 Merged master:dc14542a71f8 into amd-gfx:007b34496367 007b344 Merged master:58c586e70188 into amd-gfx:8988583afc06 8988583 Merged master:7f34b9ddf817 into amd-gfx:c4699df8d15a c4699df Merged master:9b0578d54631 into amd-gfx:bd1ebe497adc bd1ebe4 Merged master:543b30db06bf into amd-gfx:afa110055cbd afa1100 Merged master:a45a903a2133 into amd-gfx:7ee1df421c03 7ee1df4 Merged master:3035e676a388 into amd-gfx:242c915a4920 242c915 Reintroduce "[AMDGPU][CostModel] Refine cost model for half- and quarter-rate instructions." af97e00 Merged master:3ec69c16c3ec into amd-gfx:e3373b6002ed e3373b6 Merged master:d93287cac89f into amd-gfx:b9d9036e5f69 b9d9036 Merged master:1cbf8e89b54d into amd-gfx:a7154fc04d58 a7154fc [AMDGPU] Fix live mask tracking with conditional kill live lanes dd95dbd Merged master:2319c49339b9 into amd-gfx:9b076a871c1a 9b076a8 Merged master:35716f1b7d49 into amd-gfx:750ee93eb0aa 750ee93 Merged master:a41ea782c8e1 into amd-gfx:ed8fcdbdc1a7 ed8fcdb Merged master:b31d78794998 into amd-gfx:e6833c90e71d e6833c9 Merged master:65c489852c4e into amd-gfx:01c4f02f038f 01c4f02 Merge remote-tracking branch 'llvm.org/master' into amd-gfx c360d7c Merged master:a585228027a0 into amd-gfx:a82651c8a200 a82651c Merged master:80fe2f61fac9 into amd-gfx:c86553261963 c865532 Merged master:7efe07a12b69 into amd-gfx:0cf2de3b97d3 0cf2de3 Merged master:179d91b37631 into amd-gfx:3a0ab31f1b2a 3a0ab31 Merged master:43df29e20622 into amd-gfx:72ec2482f727 72ec248 Merge master:5e312e004197 into amd-gfx 5ca3404 Merged master:defe11866a32 into amd-gfx:6612326f4f49 Added AMD modification notices and removed some GPL files. Change-Id: I28b48a9bb44aae839c2b8fae5c45904abdd3bde9
Configuration menu - View commit details
-
Copy full SHA for 6d7376c - Browse repository at this point
Copy the full SHA 6d7376cView commit details
Commits on Nov 19, 2020
-
Overwritten with: c6553e1 Merged master:bd4662cd3f37 into amd-gfx:98c…
…87d9b5654 Based on upstream llvm : bd4662c [AST] Enhance the const expression evaluator to support error-dependent exprs. Local changes since 6d7376c: c6553e1 Merged master:bd4662cd3f37 into amd-gfx:98c87d9b5654 98c87d9 Merged master:871fe71f2951 into amd-gfx:64897df3e8ca 64897df Merged master:5e696d895bde into amd-gfx:12b9e03c12c5 12b9e03 Merged master:c173f1b8ebba into amd-gfx:fc40e2434742 fc40e24 Merged master:94e4ec6499a2 into amd-gfx:45db5159fc98 45db515 [AMDGPU] Update phi-node incoming value in conditional-discard 16cc4dc Merged master:b13415b59b1f into amd-gfx:96e6faf2ec8f 96e6faf Merged master:8e923ec2a803 into amd-gfx:b929df8dbe51 b929df8 Merged master:792f8e1114af into amd-gfx:f57647c915d6 f57647c Merged master:a200d6cdf0f7 into amd-gfx:d959ced38786 d959ced Merged master:4cadb66b490e into amd-gfx:adf059689f90 Added AMD modification notices and removed some GPL files. Change-Id: Ib89fe2b93f3072be467906c42b3df01707bbdcfd
Configuration menu - View commit details
-
Copy full SHA for 15bf319 - Browse repository at this point
Copy the full SHA 15bf319View commit details -
Overwritten with: c6553e1 Merged master:bd4662cd3f37 into amd-gfx:98c…
Configuration menu - View commit details
-
Copy full SHA for fde3d4e - Browse repository at this point
Copy the full SHA fde3d4eView commit details
Commits on Dec 3, 2020
-
Overwritten with: e39dc60 [AMDGPU] Waterfall loop insertion after las…
…t begin intrinsic Based on upstream llvm : e987fbd [BasicAA] Generalize recursive phi alias analysis Local changes since fde3d4e: e39dc60 [AMDGPU] Waterfall loop insertion after last begin intrinsic 8562b22 Merged master:e987fbdd85d6 into amd-gfx:1b2c77119be5 1b2c771 Merged master:d9da4c3e7372 into amd-gfx:8d15a8e8f5ef 8d15a8e Merged master:6dd9596b19d7 into amd-gfx:2ffb68a32fd1 2ffb68a Merged master:f502b14d40e7 into amd-gfx:ec1f53c31ab4 ec1f53c Merged master:acb69f3b7c83 into amd-gfx:d162b3ea0f06 d162b3e Merged master:1dea8ed8b7dd into amd-gfx:ee2ed3abef34 ee2ed3a Merged master:6ee22ca6ceb7 into amd-gfx:8eec92f00388 8eec92f Merged master:530c69e90964 into amd-gfx:a95ee4c32f45 a95ee4c Merged master:03ee46127621 into amd-gfx:872406fea363 872406f Merged master:8709d9d8724a into amd-gfx:ecd3aacf4bfe ecd3aac Merged master:851779652a3b into amd-gfx:68a238769f95 68a2387 Merged master:8e0148dff703 into amd-gfx:2465734a7a44 2465734 Merged master:e4c74fd9ddd9 into amd-gfx:e3891904d0e2 e389190 Merged master:b215198bb05b into amd-gfx:ef9fdcc2109f ef9fdcc Merged master:68ed64478556 into amd-gfx:c873681bb780 c873681 Merged master:5535696c386b into amd-gfx:05be99db5469 05be99d Merged master:9178c630c341 into amd-gfx:fcf804535f20 fcf8045 Merged master:faf183874cb6 into amd-gfx:bcf85dfd98b8 bcf85df Merged master:4d83aba4228e into amd-gfx:37f3d80e617b 37f3d80 Merged master:5836e5206376 into amd-gfx:6612e70835e9 6612e70 Merged master:f095ac11a955 into amd-gfx:56cee8c9a1cf 56cee8c Merged master:8166ed1a7a26 into amd-gfx:b5788070684a b578807 Merged master:17df5373e617 into amd-gfx:518c72adb33f 518c72a Merged master:20c926e0797e into amd-gfx:14c209a16d0d 14c209a Merged master:9549abcbb824 into amd-gfx:f01e7f4e154c f01e7f4 Merged master:4dd5f79f0702 into amd-gfx:2f9216f6d7ef 2f9216f Merged master:f690986f314f into amd-gfx:e05028dd2848 e05028d Merged master:14f2ad0e3cc5 into amd-gfx:3a621c8a0e85 3a621c8 Merged master:f78ad68b6d8c into amd-gfx:56092a7834d6 56092a7 Merged master:48ddf5e182c6 into amd-gfx:4d6e647240ec 4d6e647 Merged master:75f50e15bf8f into amd-gfx:40142cb34d81 40142cb Merged master:c9eae09251e3 into amd-gfx:25baf9cd436a 25baf9c Merged master:5654a3dd0add into amd-gfx:ea589931b2ea ea58993 Merged master:572d18397cf0 into amd-gfx:45f606d9808e 45f606d Merged master:6588592684ff into amd-gfx:aec1257919dc aec1257 Merged master:ecabb39ca11c into amd-gfx:823ae141034e 823ae14 Merged master:0cb38699a09d into amd-gfx:534cfb420e64 534cfb4 Merged master:3d2c681f2835 into amd-gfx:3f5633983086 3f56339 Merged master:9130651126b7 into amd-gfx:02301f694469 02301f6 Merged master:28d7ba15435f into amd-gfx:b20f02ee5a0a b20f02e Merged master:10ddb927c1c3 into amd-gfx:e8442293e545 e844229 Merged master:07f234be1ccb into amd-gfx:d297d238073e d297d23 Merged master:28de0fb4863a into amd-gfx:c0ba7c0c3df6 c0ba7c0 Merged master:4f5355ee7362 into amd-gfx:4017436367d1 4017436 Merged master:075468621c0f into amd-gfx:7785d463b30e 7785d46 Merged master:1a036e9cc82a into amd-gfx:d5a33af7087a d5a33af Merged master:a8de412f516c into amd-gfx:3189b1f523d1 3189b1f Merged master:ca1f2f2716b3 into amd-gfx:e69addf5385b e69addf Merged master:fd92c5dbeeeb into amd-gfx:cce1d9477dc1 cce1d94 Merged master:245052ac3080 into amd-gfx:6e9a64e83199 6e9a64e Merged master:5e9e335a2470 into amd-gfx:7ca564012231 7ca5640 Merged master:51994f90b618 into amd-gfx:92afb1f00f09 92afb1f Merged master:9194aa88676f into amd-gfx:1256d83c6060 1256d83 Merged master:e42021d5cc25 into amd-gfx:e49582238535 e495822 Merged master:f7d033f4d80f into amd-gfx:f84e0c6d39ad f84e0c6 Merged master:b4902bcd986d into amd-gfx:4eafab3013bc 4eafab3 Merged master:b23e84ffcff8 into amd-gfx:e698bb0f79b1 e698bb0 Merged master:5e1801813d93 into amd-gfx:752461b14e7a 752461b Merged master:e4effef33059 into amd-gfx:d325f4c6d276 d325f4c Merged master:3c696a212ba4 into amd-gfx:b2608d183762 b2608d1 Merged master:18e4272a4fe4 into amd-gfx:e981ff111987 e981ff1 Merged master:85d6af393c6e into amd-gfx:bf9db3286343 bf9db32 Merged master:186d129320c8 into amd-gfx:9ae20437d491 9ae2043 Merged master:95956c1c9aae into amd-gfx:36d49cd86e25 36d49cd Merged master:c8c3a411c50f into amd-gfx:ee555fbc4f83 ee555fb Merged master:655360096f27 into amd-gfx:098c66d6089f 098c66d Merged master:221c2b8862b1 into amd-gfx:fee51f748c26 fee51f7 Merged master:29dffb0c8a5d into amd-gfx:df1dac976d9b df1dac9 Merged master:82c22f124816 into amd-gfx:f4786eb0ecfe f4786eb Merged master:1c0941e1524f into amd-gfx:2cf3a511be62 2cf3a51 Merged master:c2309ff3d50c into amd-gfx:6233a2a00728 6233a2a Merged master:914f6c4ff8a4 into amd-gfx:4747909ae15c 4747909 Merged master:def7cfb7ffd4 into amd-gfx:ceea8dd131e0 ceea8dd Merged master:dcc06597b1d6 into amd-gfx:0b88b13edc1c 0b88b13 Merged master:3324fd8a7b1a into amd-gfx:67fd73c2c6d1 67fd73c Merged master:4629afa101d4 into amd-gfx:4d6cda3e2ed8 4d6cda3 Merged master:8aea95f3cb4e into amd-gfx:2aaf8676d0e3 2aaf867 Merged master:d4f1a3c6e2c6 into amd-gfx:d7e3da106d59 d7e3da1 Merged master:4a1d230fa6f4 into amd-gfx:0c885f9d960e 0c885f9 Merged master:da886bf471e7 into amd-gfx:d91b2d4303af d91b2d4 Merged master:a2dc4ac86b8e into amd-gfx:b05be4847398 b05be48 Merged master:41083267a9d7 into amd-gfx:9e25124ce9ee 9e25124 Merged master:08d90f72cebd into amd-gfx:60bad94c08b6 60bad94 Merged master:0196b45ceaf8 into amd-gfx:caca11248a23 caca112 Merged master:2c7e24c4b689 into amd-gfx:fbc426b1c73d fbc426b Merged master:6a1d8b91ed73 into amd-gfx:dfe14115f500 dfe1411 Merged master:1b749c0cb5c0 into amd-gfx:b0c49b5d37c9 b0c49b5 Merged master:6af81ea1d6d3 into amd-gfx:3a41fc55fff6 3a41fc5 Merged master:7a18bdb350e4 into amd-gfx:3cb71f1d313b 3cb71f1 Merged master:32dd5870ee31 into amd-gfx:2ea6c16ed1ee 2ea6c16 Merged master:0f9f0a4046e1 into amd-gfx:768eb3db0e77 768eb3d Merged master:b2f663073917 into amd-gfx:ada90d0b5123 ada90d0 Merged master:0fd04337a171 into amd-gfx:8b48af57af1b 8b48af5 Merged master:7fa14a7c690e into amd-gfx:b54ac9ef73ce b54ac9e Merged master:b14ea01f3bfa into amd-gfx:3e30482bb527 3e30482 Merged master:74170a3aeff1 into amd-gfx:cb1a5dc53e92 cb1a5dc Merged master:ab77fa515583 into amd-gfx:ef113cf4b2c1 ef113cf Merge master:a1de391dae8b into amd-gfx Added AMD modification notices and removed some GPL files. Change-Id: I62801eb32871be13eb2c850e225c288f8d0182ed
Configuration menu - View commit details
-
Copy full SHA for 529059d - Browse repository at this point
Copy the full SHA 529059dView commit details
Commits on Dec 7, 2020
-
Overwritten with: 8954ca6 Merge main:3d381a710220 into amd-gfx
Based on upstream llvm : 3d381a7 [llvm-nm][MachO] Don't call getFlags on redacted symbols Local changes since 529059d: 8954ca6 Merge main:3d381a710220 into amd-gfx 6768469 Merge main:8eedd18fcb9d into amd-gfx 91ad5e2 Merge master:1365718778b4 into amd-gfx Added AMD modification notices and removed some GPL files. Change-Id: I7f94f9261915c3d064d0a19675d19da5ad52c4ee
Configuration menu - View commit details
-
Copy full SHA for ae9a45d - Browse repository at this point
Copy the full SHA ae9a45dView commit details
Commits on Dec 17, 2020
-
Overwritten with: 352ac64 Merged main:dbfdb139f754 into amd-gfx:7af17…
…486f26a Based on upstream llvm : dbfdb13 [lldb] [POSIX-DYLD] Update the cached exe path after attach Local changes since ae9a45d: 352ac64 Merged main:dbfdb139f754 into amd-gfx:7af17486f26a 7af1748 Merged main:a906e3eccd1e into amd-gfx:a41f8084775a a41f808 Merged main:fce9dd6b2521 into amd-gfx:d697cf024dfc d697cf0 Merged main:f333736757e9 into amd-gfx:f590b57df705 f590b57 Merged main:4c8c6368710e into amd-gfx:b0130cb8e30b b0130cb Merged main:09d0e7a7c153 into amd-gfx:e73e167c66fb e73e167 Merged main:e72802480871 into amd-gfx:4a50bca95a48 4a50bca Merged main:70bd75426e5c into amd-gfx:9e86972b8431 9e86972 Merged main:b607837c75d0 into amd-gfx:e52924087542 e529240 Merged main:e5039aad4574 into amd-gfx:81245c8cf516 81245c8 Merged main:dad07baf123e into amd-gfx:714863fe3fd0 714863f Merged main:407d42002904 into amd-gfx:07ae5c51801c 07ae5c5 Merged main:02220f320498 into amd-gfx:0ef01b0bac0d 0ef01b0 Merged main:5aafdd7b88f5 into amd-gfx:29c4b66a5c55 29c4b66 Merged main:cfa1010c4242 into amd-gfx:7321b45c88d7 7321b45 Merged main:a00290ed10a6 into amd-gfx:87836d41bf16 87836d4 Merged main:7ea3932ab1de into amd-gfx:402e2f2057e1 402e2f2 Merged main:ffe84d90e9a7 into amd-gfx:f3c1f789611a f3c1f78 Merged main:bd0709266911 into amd-gfx:e1cb572b2dc2 e1cb572 Merged main:9c328e7afafd into amd-gfx:554bdce29aee 554bdce Merged main:8b330f1f6919 into amd-gfx:cf15849e81d4 cf15849 Merged main:dc82890a77fe into amd-gfx:738ee4837572 738ee48 Merged main:ce0c0013d8b1 into amd-gfx:bdc55c25369a bdc55c2 Merged main:ee43dcaad75b into amd-gfx:4d7163f98445 4d7163f Merged main:d50d7c37a159 into amd-gfx:1e7a931d181a 1e7a931 Merged main:045304701bc6 into amd-gfx:7596d56af686 7596d56 Merged main:87d7757bbe14 into amd-gfx:d618af10e479 d618af1 Merged main:d0797e62fa8a into amd-gfx:70a849b7d3dd 70a849b Merged main:fac7c7ec3ccd into amd-gfx:c7ccfc4baf10 c7ccfc4 Merged main:af4570cd3ab9 into amd-gfx:262c99449048 262c994 Merged main:4e2e785ddd35 into amd-gfx:6a5ee55760ba 6a5ee55 Merged main:7de9c61f3111 into amd-gfx:682ec2a7106f 682ec2a Merged main:ee5b5b7a35d0 into amd-gfx:26f6b4d2d543 26f6b4d Merged main:04795ab8368a into amd-gfx:4a55f88474ed 4a55f88 Merged main:fef242c32e83 into amd-gfx:661043e3fc39 661043e Merged main:0261ce9e17bd into amd-gfx:ccce20cae2a7 ccce20c Merged main:f99b4f5241a3 into amd-gfx:21e62802cf23 21e6280 Merged main:8bdfc1222f7c into amd-gfx:08107762b852 0810776 Merged main:36306403d492 into amd-gfx:71d65f4312ad 71d65f4 Merged main:bb939ebfd7f4 into amd-gfx:8897dd087fc0 8897dd0 Merged main:0cd8686043f9 into amd-gfx:7a17ebfe42ea 7a17ebf Merged main:a44e630353b8 into amd-gfx:af58e9538f9b af58e95 Merged main:ba3bc2fd41b8 into amd-gfx:b7a09dea9090 b7a09de Merged main:7beee561e23d into amd-gfx:dd34befa1149 dd34bef Merged main:a4823377fd2f into amd-gfx:21a2c4086495 21a2c40 Merged main:ab97c9bdb747 into amd-gfx:89f031ec9f94 89f031e Merged main:0e5bfffb1361 into amd-gfx:c9cce5cbe6fe c9cce5c Merged main:6baa9769ed57 into amd-gfx:07677c924b45 07677c9 Merged main:6f26a6de489e into amd-gfx:6106c5a3a92c 6106c5a Merged main:eb44682d671d into amd-gfx:bd6b8bb61d19 bd6b8bb Merged main:e007b3286429 into amd-gfx:b0c247a55684 b0c247a Merged main:7698a0180822 into amd-gfx:fe1da467196d fe1da46 Merged main:42f628c84269 into amd-gfx:97fa27a2220e 97fa27a Merged main:997d286f2d0f into amd-gfx:8b029cfadfd2 8b029cf Merged main:b5ad32ef5c68 into amd-gfx:bc2c136877e2 bc2c136 Merged main:658dc21c2df4 into amd-gfx:7ae1ef4af3cb 7ae1ef4 Merged main:cf638f84a4ba into amd-gfx:d9c1eff45e48 d9c1eff AMDGPU/GlobalISel: Add waterfall intrinsic combiner c58a2c1 Merged main:da97d12cc05a into amd-gfx:8e49abc295b1 8e49abc Merged main:fd78012b9e59 into amd-gfx:abc5c0adcb2a abc5c0a Merged main:0f1f13fcb17f into amd-gfx:b7ad48cdf1ae b7ad48c Merged main:8d396acac3bc into amd-gfx:47ff52ead290 47ff52e Merged main:4564553b8d8a into amd-gfx:ca4735522f1c ca47355 Merged main:75eca67c1c4b into amd-gfx:57dffbe52491 57dffbe Merged main:ac25e8628c44 into amd-gfx:3083a61407d4 3083a61 Merged main:5abbf20f0fe5 into amd-gfx:2f1f2c28c29e 2f1f2c2 Merged main:09f717b929ae into amd-gfx:4708702c57fa 4708702 Merged main:e954ba28bcac into amd-gfx:d8707e064e8f d8707e0 Merged main:d6f5e08199f6 into amd-gfx:9efa81533b1b 9efa815 Merged main:7adcacda0686 into amd-gfx:db667e891e72 db667e8 Merged main:ee74d1b42036 into amd-gfx:c3ce838e4580 c3ce838 Merged main:55ea639d3c57 into amd-gfx:2952e2d2963c 2952e2d Merged main:e6a1187dd867 into amd-gfx:7c4b5ced68d3 7c4b5ce Merged main:f9a27df16bc4 into amd-gfx:ae2f4ca2df7a ae2f4ca Merged main:03a77d04b412 into amd-gfx:b0317bca00da b0317bc Merged main:163c223161b8 into amd-gfx:26ab039577cd 26ab039 Merged main:4167a0259ec3 into amd-gfx:f23b536b3a0c f23b536 Merged main:ce14ffa1bba2 into amd-gfx:ed890a83c0d3 ed890a8 Merged main:aaa925795f93 into amd-gfx:fb87ca9b9678 fb87ca9 Merged main:846f576bea4d into amd-gfx:d290e5595cf8 d290e55 Merged main:64e768536889 into amd-gfx:ccafbf7a12fb ccafbf7 Merged main:86436a434362 into amd-gfx:937d9dc6f76d 937d9dc Merged main:a65dc08d105e into amd-gfx:ce73b585b571 ce73b58 Merged main:3bd2ad5a0828 into amd-gfx:655807befc95 655807b Merged main:9935b0fc9023 into amd-gfx:e448aeec0a4c e448aee Merged main:083e035c47f6 into amd-gfx:44479e6b06ab 44479e6 Merged main:c54d827fdb12 into amd-gfx:8954ca68dadc Added AMD modification notices and removed some GPL files. Change-Id: Ib8fb25a3947469a96e96f34de23957752c1c9e4e
Configuration menu - View commit details
-
Copy full SHA for 0472e03 - Browse repository at this point
Copy the full SHA 0472e03View commit details
Commits on Dec 23, 2020
-
Overwritten with: a2e8254 Merged main:ad0a7ad950fe into amd-gfx:a6377…
…05ce652 Based on upstream llvm : ad0a7ad [RISCV] Add intrinsics for vf[n]macc/vf[n]msac/vf[n]madd/vf[n]msub instructions Local changes since 0472e03: a2e8254 Merged main:ad0a7ad950fe into amd-gfx:a637705ce652 a637705 Merged main:d15119a02d92 into amd-gfx:edd8bb353cd4 edd8bb3 Merged main:75a3f326c3d8 into amd-gfx:e5e111cf62ac e5e111c Merged main:7ec7788ac175 into amd-gfx:52b101124f00 52b1011 Merged main:ae8f4b2178c4 into amd-gfx:050a073d7e98 050a073 Merged main:0955d8df0635 into amd-gfx:e6226f754f5c e6226f7 Merged main:5b37f0d97087 into amd-gfx:30a3e79da025 30a3e79 Merged main:c4fc8a21d1db into amd-gfx:c1b970ee7769 c1b970e Merged main:554eb1f6dc49 into amd-gfx:1a3dda5a9257 1a3dda5 Merged main:e0963ae274be into amd-gfx:de3ec7b8690b de3ec7b Merged main:f314bcffa3c6 into amd-gfx:6a03356a35ab 6a03356 Merged main:72e75ca343c6 into amd-gfx:ee99e9976e17 ee99e99 Merged main:4dce7c2e2092 into amd-gfx:53dd9e7ae707 53dd9e7 Merged main:01d1de81963d into amd-gfx:6081a1a21dac 6081a1a Merged main:64e475720020 into amd-gfx:ce8db8ba4702 ce8db8b Merged main:d86a00d8febd into amd-gfx:76fc271216eb 76fc271 Merged main:7e84aa1b81e7 into amd-gfx:c8fd52af75e8 c8fd52a Merged main:99562332e3de into amd-gfx:23e52d67d639 23e52d6 Merged main:c1d6de41a9d9 into amd-gfx:27bfa6aeef61 27bfa6a Merged main:0985a8bfea46 into amd-gfx:3cb46f4bdd32 3cb46f4 Merged main:7c6f28a438b5 into amd-gfx:92c6ea3b3286 92c6ea3 Merged main:c043f5055e89 into amd-gfx:7353851354ed 7353851 Merged main:c52bcf3a9b2d into amd-gfx:00f1b204ca1c 00f1b20 Merged main:56edfcada900 into amd-gfx:b9064ef59c93 b9064ef Merged main:1e785e92624b into amd-gfx:999f44c47316 999f44c Merged main:9c895aea118a into amd-gfx:4c669e1d84bf 4c669e1 Merged main:df8ed3928377 into amd-gfx:614bda13626a 614bda1 Merged main:805d59593f50 into amd-gfx:028085b475c1 028085b Merged main:a913a583f00a into amd-gfx:c81f48db78be c81f48d Merged main:af83b74dc2e5 into amd-gfx:e737d1ebac88 e737d1e Merged main:f5cef870d116 into amd-gfx:7797ed95dd67 7797ed9 Merged main:9c978dd6e12e into amd-gfx:f93171f456c8 f93171f Merged main:06d5b1c9ad52 into amd-gfx:824579b45cda 824579b Merged main:47aaa99c0e1e into amd-gfx:ee399b00535f ee399b0 Merged main:e35f9229dcb2 into amd-gfx:c1224cacd15c c1224ca Merged main:98993193e903 into amd-gfx:7250656b3cfe 7250656 Merged main:aec2991d083a into amd-gfx:b5b8e23bfbdd b5b8e23 Merged main:fdd6ed8e9341 into amd-gfx:e2efdf228fae e2efdf2 Merged main:d4ec3346b1ba into amd-gfx:ad4eacb9ea61 ad4eacb Merged main:ee2cb90e3bbe into amd-gfx:e1e3606ea86a e1e3606 Merged main:13261f4c0349 into amd-gfx:6d5c01e78160 6d5c01e Merged main:118a71565462 into amd-gfx:1b32793450da 1b32793 Merged main:49c248bd62a3 into amd-gfx:0b1cb6ed36a1 0b1cb6e Merged main:e22d802e587b into amd-gfx:492ab548fcaf 492ab54 Merged main:122a4ebde3f4 into amd-gfx:2e8df37e34a1 2e8df37 Merged main:b9890ae1976b into amd-gfx:bba750f5a128 bba750f Merged main:1fd3a0477597 into amd-gfx:f9b3c3f53d94 f9b3c3f Merged main:b8338983e6f6 into amd-gfx:352ac6432b9e Added AMD modification notices and removed some GPL files. Change-Id: Ic939fc2f325cd12093c39a9243f609c9a17e636e
Configuration menu - View commit details
-
Copy full SHA for 4ad3460 - Browse repository at this point
Copy the full SHA 4ad3460View commit details
Commits on Jan 5, 2021
-
Overwritten with: 273a500 Update bitcast-vec-canon-inseltpoison.ll
Based on upstream llvm : e43b3d1 Revert "[Sema] Fix deleted function problem in implicitly movable test" Local changes since 4ad3460: 273a500 Update bitcast-vec-canon-inseltpoison.ll ff485d5 Merged main:e43b3d1f5e05 into amd-gfx:a2e82546366c Added AMD modification notices and removed some GPL files. Change-Id: I73d154e438a1aa369b9ca1ce8d7725c86d2742b3
Configuration menu - View commit details
-
Copy full SHA for 9ef380b - Browse repository at this point
Copy the full SHA 9ef380bView commit details
Commits on Jan 7, 2021
-
Overwritten with: ee8e7ff Merged main:5471b1fa4013 into amd-gfx:5a673…
…28b3f94 Based on upstream llvm : 5471b1f [gn build] Port d2ddc69 Local changes since 9ef380b: ee8e7ff Merged main:5471b1fa4013 into amd-gfx:5a67328b3f94 5a67328 Merged main:238dbeb1e7ba into amd-gfx:578e90088656 578e900 Merged main:25bf4a8f4285 into amd-gfx:d8030f7eb81d d8030f7 Merged main:3505d8dc0742 into amd-gfx:1ba35b4ee8bf 1ba35b4 Merged main:37e83bc6db3a into amd-gfx:cb2b919330e6 cb2b919 Merged main:fb1c52852690 into amd-gfx:8a4e2494e40a 8a4e249 Merged main:0e874fc014be into amd-gfx:abefc15690ba abefc15 Merged main:1ca5e68aa07e into amd-gfx:8b5343c48207 8b5343c Merged main:0a3cf7f4762e into amd-gfx:ab07f2cc37e7 ab07f2c Merged main:4e0e79dd349a into amd-gfx:edf208676d23 edf2086 Merged main:ce8c59e6af48 into amd-gfx:33a7a3576da9 33a7a35 Merged main:979228f120f4 into amd-gfx:4da302fb8562 4da302f Merged main:7f7b0dc4e15f into amd-gfx:4da34311e394 4da3431 Merged main:c1cd42d69848 into amd-gfx:784cdf03f5db 784cdf0 Merged main:8444a2494d3d into amd-gfx:8416743e8944 8416743 Merged main:a39b19821b6b into amd-gfx:1fb289de71aa 1fb289d Merged main:cb5b52a06eeb into amd-gfx:7092d3ce882a 7092d3c Merged main:65cd3cbb3fc9 into amd-gfx:81ea74a95cce 81ea74a Merged main:86d68e288585 into amd-gfx:ebfd6644a317 ebfd664 Merged main:9eb2284f6039 into amd-gfx:d8c2161d55d3 d8c2161 Merged main:c73ae747cb0c into amd-gfx:9e2279be6db6 9e2279b Merged main:89ae5b5b6a47 into amd-gfx:c46db56b4c1a c46db56 Merged main:9a1ac97d3af5 into amd-gfx 02d2ce9 Merged main:f784be0777f3 into amd-gfx:273a500bfd31 Added AMD modification notices and removed some GPL files. Change-Id: I9f5237d2f352a16046b9c121018c6fcb4a343e51
Configuration menu - View commit details
-
Copy full SHA for 294f18d - Browse repository at this point
Copy the full SHA 294f18dView commit details
Commits on Jan 13, 2021
-
Overwritten with: d7af18d Merged main:f8cece186305 into amd-gfx:db362…
…2e02849 Based on upstream llvm : f8cece1 [ValueTracking] Fix one s/dyn_cast/dyn_cast_or_null/ Local changes since 294f18d: d7af18d Merged main:f8cece186305 into amd-gfx:db3622e02849 db3622e Merged main:ad85e3967067 into amd-gfx:6b9e471f7e7e 6b9e471 Manually merged main:6d3098e7ff96 into amd-gfx:b16080cd2f97 b16080c Manually merged main:1730b0f66ada into amd-gfx:8c001b46dda3 8c001b4 Merged main:c8a914db5c60 into amd-gfx:7f859d7ffae1 7f859d7 Merged main:b1c304c49465 into amd-gfx:760f63c318c2 760f63c Merged main:e5b4dbab041f into amd-gfx:85a9a508277b 85a9a50 Merged main:f75f391fc68c into amd-gfx:4be7439cc130 4be7439 Merged main:0a23fbd28c75 into amd-gfx:20116589434f 2011658 Merged main:110775809ad1 into amd-gfx:3a5281b1149b 3a5281b Merged main:a90214760d04 into amd-gfx:2b258318cd75 2b25831 Merged main:e5eb5c8a7f30 into amd-gfx:7e5454982977 7e54549 Fix minor build issue (NFC) 9bfe630 Merge remote-tracking branch 'llvm.org/main' into amd-gfx 1510cc0 Manually merged remote-tracking branch 'llvm.org/main' into amd-gfx 708f729 Merged main:d9ce31ae7d1f into amd-gfx:10510ba7a489 10510ba Merged main:466df1718e41 into amd-gfx:61de092b3ee7 61de092 Merged main:6e2b6351d2cb into amd-gfx:8235c3a775ad 8235c3a Manually merged master:d1bf26fd943e into amd-gfx:e344f0557da2 e344f05 Merged main:048f184ee488 into amd-gfx:da77c7758356 da77c77 Merged main:213329d7c64f into amd-gfx:e4ebc2c5f768 e4ebc2c Merged main:a828fb463ed9 into amd-gfx:ee8e7ff0e8c7 Added AMD modification notices and removed some GPL files. Change-Id: Idee9d5d89ada29e444d34de4c013ce9b3198460f
Configuration menu - View commit details
-
Copy full SHA for 1d0178f - Browse repository at this point
Copy the full SHA 1d0178fView commit details
Commits on Jan 20, 2021
-
Overwritten with: 87fe2f5 Merged main:b62c7e047420 into amd-gfx:b0ae2…
…fdce90d Based on upstream llvm : b62c7e0 [mlir][python] Swap shape and element_type order for MemRefType. Local changes since 1d0178f: 87fe2f5 Merged main:b62c7e047420 into amd-gfx:b0ae2fdce90d b0ae2fd Merged main:22eb1cf89f38 into amd-gfx:a7423a7b05ac a7423a7 Manual merge of main:da986511fb9d into amd-gfx:d7e43a20327b d7e43a2 Merged main:9a60ad216d2f into amd-gfx:18eea3b6be9f 18eea3b Merged main:58bdfcfac048 into amd-gfx:14d669f58d57 14d669f Merged main:831a143e50ca into amd-gfx:561d822bfcf4 561d822 Merged main:9a0900dc4c6b into amd-gfx:dbdf3139632f dbdf313 Merged main:e147eccafa15 into amd-gfx:4568380eb7aa 4568380 Merged main:a9b3303a8847 into amd-gfx:0a9c586beca3 0a9c586 Merged main:2d89ebd5d17b into amd-gfx:e927f3b64d4d e927f3b Merged main:d27bb5c375ca into amd-gfx:4b212e426876 4b212e4 Merged main:d9b6e4d583c5 into amd-gfx:a18ca347561a a18ca34 Merged main:2c51bef76cbf into amd-gfx:bcfd67265df9 bcfd672 Merged main:275716d6db79 into amd-gfx:707935cc68ad 707935c Merged main:3dbbadb8ef53 into amd-gfx:67755b8f0509 67755b8 Merged main:f7443905af1e into amd-gfx:c7351261213f c735126 Merged main:3bd24574c7d0 into amd-gfx:e6033a0bb194 e6033a0 Merged main:6e75ee6b65c1 into amd-gfx:c056990a956c c056990 Merged main:383b6501ffed into amd-gfx:dd924d74d1bd dd924d7 Merged main:e5619065b8b8 into amd-gfx:96be1e6f8501 96be1e6 Merged main:95d146182fdf into amd-gfx:0297f746a839 0297f74 Merged main:a89242d874df into amd-gfx:bee6f062cde1 bee6f06 Merged main:9a7fb0848771 into amd-gfx:ef899f5bb13a ef899f5 Merged main:7e9e6ac526eb into amd-gfx:58646d400256 58646d4 Merged main:9abbc050974f into amd-gfx:b78cdb338078 b78cdb3 Merged main:00dc97f16708 into amd-gfx:81b8a3da9777 81b8a3d Merged main:0b84afa5fcb4 into amd-gfx:1a56045b754d 1a56045 Merged main:3809f4ebabde into amd-gfx:a0d6dcabb5f7 a0d6dca Merged main:3cbd476c5488 into amd-gfx:e39fa94175d0 e39fa94 Merged main:633c5afccfbb into amd-gfx:f2a7e479a277 f2a7e47 Merged main:a048ce13e32d into amd-gfx:32c39fafa202 32c39fa Merged main:5238e7b302ff into amd-gfx:7da10bfe5304 7da10bf Merged main:d8fc27301d18 into amd-gfx:ce7959863533 ce79598 Merged main:63bedc80da36 into amd-gfx:c26ff42c0ae7 c26ff42 Merged main:bca16e2fbb45 into amd-gfx:4bb996d53d7e 4bb996d Merged main:25c1578a46ff into amd-gfx:237762389aa0 2377623 Merged main:f0a0ec2d085b into amd-gfx:b41aabe36e1a b41aabe Merged main:e0a979ccadd8 into amd-gfx:2f169bba494a 2f169bb Merged main:668827b64856 into amd-gfx:0510a18a75d0 0510a18 Merged main:a61e42efbb73 into amd-gfx:c40e345e152a c40e345 Merged main:e8049dc3c8a4 into amd-gfx:dd8c670c5230 dd8c670 Merged main:aa3d4d993959 into amd-gfx:1a04b3485db2 1a04b34 Merged main:a1500105ee60 into amd-gfx:8fd163607beb 8fd1636 Merged main:a14c36fe27f5 into amd-gfx:559b6f1b04d9 559b6f1 Merged main:cc90d41945f6 into amd-gfx:25c8d10ff391 25c8d10 Merged main:be69e66b1cd8 into amd-gfx:8d75e54ab8cb 8d75e54 Merged main:5183a13d3782 into amd-gfx:aec8dbcd7738 aec8dbc Merged main:6edc3fe598af into amd-gfx:d607423df52a d607423 Merged main:45ef053bd709 into amd-gfx:074de8ae48d3 074de8a Merged main:33be50daa9ce into amd-gfx:ed8c71575d36 ed8c715 Merged main:5508516b0663 into amd-gfx:33090e83332c 33090e8 Merged main:7dc3575ef2dc into amd-gfx:b2004a9a0490 b2004a9 Merged main:214387c2c694 into amd-gfx:47fd8032da63 47fd803 Merged main:036bc798f2ae into amd-gfx:c0ee6187e65d c0ee618 Merged main:a55a0a3056b8 into amd-gfx:4c42c8f9af2a 4c42c8f Merged main:e2d7d3cb0ead into amd-gfx:47ed92e4cdd6 47ed92e Merged main:202d359753d1 into amd-gfx:e2ab3cde433e e2ab3cd Merged main:7c9c2a2ea5e3 into amd-gfx:357c325e0649 357c325 Merged main:0b46f19a9ecd into amd-gfx:978a6104758f 978a610 Merged main:fa2fe9608c1c into amd-gfx:8eff8b2c9df5 8eff8b2 Merged main:d58512b2e31a into amd-gfx:56124e34625d 56124e3 Merged main:2b1e25befefc into amd-gfx:27f3456142ab 27f3456 Merged main:4b284b9ca809 into amd-gfx:f12986ba074f f12986b Merged main:6ed3083a9654 into amd-gfx:1c8672849f8a 1c86728 Merged main:260a856c2abc into amd-gfx:07f887fbf91c 07f887f Merged main:eec856848ccc into amd-gfx:3aae2758e676 3aae275 Merged main:3de92ca78cd4 into amd-gfx:580679d40098 580679d Merged main:82c4153e66fa into amd-gfx:d24dab268902 d24dab2 Merged main:01c3135850d1 into amd-gfx:255939cf39b7 255939c Merged main:123674a81674 into amd-gfx:23926e148cb6 23926e1 Merged main:17863614da1e into amd-gfx:d7af18dfc774 Added AMD modification notices and removed some GPL files. Change-Id: I3efcea9d95db344ddb941b8389e77ea9747ab22c
Configuration menu - View commit details
-
Copy full SHA for bcd2fe4 - Browse repository at this point
Copy the full SHA bcd2fe4View commit details
Commits on Jan 26, 2021
-
ELF note types for LLPC cache hash
This commit adds two new note types: NT_AMD_LLPC_CACHE_HASH and NT_AMD_LLPC_VERSION. They will be used for note entries for LLPC cache hash and LLPC version. This commit updates ELFDumper to show two note types clearly.
Configuration menu - View commit details
-
Copy full SHA for 9625120 - Browse repository at this point
Copy the full SHA 9625120View commit details