[SYCL] Change matrix type #5221
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
AlexeySotkin
previously approved these changes
Dec 27, 2021
bader
reviewed
Dec 27, 2021
bader
reviewed
Dec 27, 2021
bader
reviewed
Dec 27, 2021
|
restarting the pre-commit to find out whether it's test/product issue or sporadic tool issue. |
|
intel/llvm-test-suite#684 and intel/llvm-test-suite#683 resolved test issue. |
bader
reviewed
Dec 27, 2021
Comment on lines
3
to
8
| // CHECK-DAG: %"struct.__spv::__spirv_JointMatrixINTEL" = | ||
| // CHECK-DAG: type { [12 x [48 x [1 x [4 x i8]]]] addrspace(4)* } | ||
| // CHECK-DAG: %"struct.__spv::__spirv_JointMatrixINTEL.[[#]]" = | ||
| // CHECK-DAG: type { [12 x [12 x [1 x [4 x i32]]]] addrspace(4)* } | ||
| // CHECK-DAG: %"struct.__spv::__spirv_JointMatrixINTEL.[[#]]" = | ||
| // CHECK-DAG: type { [48 x [12 x [4 x [4 x i8]]]] addrspace(4)* } |
There was a problem hiding this comment.
This is not the right way to handle clang-format issues.
We agreed ignore FileCheck comments, so you should update https://github.com/intel/llvm/blob/sycl/sycl/test/.clang-format to ignore CHECK-DAG: .
AlexeySotkin
previously approved these changes
Dec 28, 2021
MrSidims
commented
Dec 28, 2021
AlexeySotkin
previously approved these changes
Dec 28, 2021
MrSidims
force-pushed
the
private/MrSidims/FixMatrixTy
branch
from
26183cb to
de3cf25
Compare
|
@MrSidims, please, fix linter check. |
Previously we relied on the structure type (which represented matrix
type) mangling to obtain its layout. Now, when DPCPP magling scheme is
aligned with C++, thus the structure lost their usual mangling. Yet we
want to preserve the desired information within the matrix type, coming
from DPCPP headers. To achive this the 'Matrix structure' was changed
form:
template <typename T, int R, int C, int L, int S>
struct __spirv_JointMatrixINTEL;
to
template <typename T, int R, int C, int L, int S>
struct __spirv_JointMatrixINTEL {
T (*Value)[R][C][L + 1][S + 1];
};
so it's no longer an opaque structure and now it look like this in LLVM
IR:
%struct.__spirv_JointMatrixINTEL = type { [42 x [6 x [2 x [1 x i32]]]]* }
Here we encode the number of Rows, Cols, Layout and Scope as sizes of an
array (which element type is the same as the base matrix's type), which
is a bit odd, but it's probably the best way we can preserve the
information now without having the matrix type itself in LLVM.
Signed-off-by: Dmitry Sidorov <dmitry.sidorov@intel.com>
Signed-off-by: Dmitry Sidorov <dmitry.sidorov@intel.com>
Signed-off-by: Dmitry Sidorov <dmitry.sidorov@intel.com>
This reverts commit 1764dac76364ad8b93b5b417950e0f81d7763923.
MrSidims
force-pushed
the
private/MrSidims/FixMatrixTy
branch
from
de3cf25 to
0b7f602
Compare
bader
removed
the
disable-lint
bader
approved these changes
Jan 11, 2022
|
@intel/llvm-reviewers-runtime could you please take a look? |
|
@vladimirlaz @steffenlarsen @s-kanaev could you please take a look at PR from runtime point of view? |
steffenlarsen
approved these changes
Jan 12, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Previously we relied on the structure type (which represented matrix
type) mangling to obtain its layout. Now, when DPCPP mangling scheme is
aligned with C++, thus the structure lost their usual mangling. Yet we
want to preserve the desired information within the matrix type, coming
from DPCPP headers. To achive this the 'Matrix structure' was changed
form:
template <typename T, int R, int C, int L, int S>
struct __spirv_JointMatrixINTEL;
to
template <typename T, int R, int C, int L, int S>
struct __spirv_JointMatrixINTEL {
T (*Value)[R][C][L + 1][S + 1];
};
so it's no longer an opaque structure and now it look like this in LLVM
IR:
%struct.__spirv_JointMatrixINTEL = type { [42 x [6 x [2 x [1 x i32]]]]* }
Here we encode the number of Rows, Cols, Layout and Scope as sizes of an
array (which element type is the same as the base matrix's type), which
is a bit odd, but it's probably the best way we can preserve the
information now without having the matrix type itself in LLVM.
Signed-off-by: Dmitry Sidorov dmitry.sidorov@intel.com