Skip to content

AMDGPU/GlobalISel: Add tests for missing readanylane combines #142788

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

AMDGPU/GlobalISel: Add tests for missing readanylane combines #142788

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions llvm/lib/Target/AMDGPU/AMDGPURegBankLegalizeRules.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -646,6 +646,7 @@ RegBankLegalizeRules::RegBankLegalizeRules(const GCNSubtarget &_ST,
.Any({{{UniB256, UniP1}, isAlign4 && isUL}, {{SgprB256}, {SgprP1}}})
.Any({{{UniB512, UniP1}, isAlign4 && isUL}, {{SgprB512}, {SgprP1}}})
.Any({{{UniB32, UniP1}, !isAlign4 || !isUL}, {{UniInVgprB32}, {SgprP1}}})
.Any({{{UniB64, UniP1}, !isAlign4 || !isUL}, {{UniInVgprB64}, {SgprP1}}})
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The PR title says it only adds tests but it also adds code, can you either rename the PR or split this off into a separate patch?

.Any({{{UniB256, UniP1}, !isAlign4 || !isUL}, {{UniInVgprB256}, {VgprP1}, SplitLoad}})
.Any({{{UniB512, UniP1}, !isAlign4 || !isUL}, {{UniInVgprB512}, {VgprP1}, SplitLoad}})

Expand Down
166 changes: 166 additions & 0 deletions llvm/test/CodeGen/AMDGPU/GlobalISel/readanylane-combines.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,166 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 -new-reg-bank-select < %s | FileCheck %s

define amdgpu_ps void @readanylane_to_virtual_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; CHECK-LABEL: readanylane_to_virtual_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v0, 0
; CHECK-NEXT: global_load_dword v1, v0, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_store_dword v0, v1, s[2:3]
; CHECK-NEXT: s_endpgm
%load = load volatile float, ptr addrspace(1) %ptr0
store float %load, ptr addrspace(1) %ptr1
ret void
}

define amdgpu_ps float @readanylane_to_physical_vgpr(ptr addrspace(1) inreg %ptr) {
; CHECK-LABEL: readanylane_to_physical_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v0, 0
; CHECK-NEXT: global_load_dword v0, v0, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_readfirstlane_b32 s0, v0
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: ; return to shader part epilog
%load = load volatile float, ptr addrspace(1) %ptr
ret float %load
}

define amdgpu_ps void @readanylane_to_bitcast_to_virtual_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; CHECK-LABEL: readanylane_to_bitcast_to_virtual_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v0, 0
; CHECK-NEXT: global_load_dword v1, v0, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_readfirstlane_b32 s0, v1
; CHECK-NEXT: v_mov_b32_e32 v1, s0
; CHECK-NEXT: global_store_dword v0, v1, s[2:3]
; CHECK-NEXT: s_endpgm
%load = load volatile <2 x i16>, ptr addrspace(1) %ptr0
%bitcast = bitcast <2 x i16> %load to i32
store i32 %bitcast, ptr addrspace(1) %ptr1
ret void
}

define amdgpu_ps float @readanylane_to_bitcast_to_physical_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; CHECK-LABEL: readanylane_to_bitcast_to_physical_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v0, 0
; CHECK-NEXT: global_load_dword v0, v0, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_readfirstlane_b32 s0, v0
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: ; return to shader part epilog
%load = load volatile <2 x i16>, ptr addrspace(1) %ptr0
%bitcast = bitcast <2 x i16> %load to float
ret float %bitcast
}

define amdgpu_ps void @unmerge_readanylane_merge_to_virtual_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; CHECK-LABEL: unmerge_readanylane_merge_to_virtual_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v2, 0
; CHECK-NEXT: global_load_dwordx2 v[0:1], v2, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_readfirstlane_b32 s0, v0
; CHECK-NEXT: v_readfirstlane_b32 s1, v1
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: v_mov_b32_e32 v1, s1
; CHECK-NEXT: global_store_dwordx2 v2, v[0:1], s[2:3]
; CHECK-NEXT: s_endpgm
%load = load volatile i64, ptr addrspace(1) %ptr0
store i64 %load, ptr addrspace(1) %ptr1
ret void
}

;define amdgpu_ps double @unmerge_readanylane_merge_to_physical_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; %load = load volatile double, ptr addrspace(1) %ptr0
; ret double %load
;}

define amdgpu_ps void @unmerge_readanylane_merge_bitcast_to_virtual_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; CHECK-LABEL: unmerge_readanylane_merge_bitcast_to_virtual_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v2, 0
; CHECK-NEXT: global_load_dwordx2 v[0:1], v2, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_readfirstlane_b32 s0, v0
; CHECK-NEXT: v_readfirstlane_b32 s1, v1
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: v_mov_b32_e32 v1, s1
; CHECK-NEXT: global_store_dwordx2 v2, v[0:1], s[2:3]
; CHECK-NEXT: s_endpgm
%load = load volatile <2 x i32>, ptr addrspace(1) %ptr0
%bitcast = bitcast <2 x i32> %load to double
store double %bitcast, ptr addrspace(1) %ptr1
ret void
}

;define amdgpu_ps double @unmerge_readanylane_merge_bitcast_to_physical_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; %load = load volatile <2 x i32>, ptr addrspace(1) %ptr0
; %bitcast = bitcast <2 x i32> %load to double
; ret double %bitcast
;}

define amdgpu_ps void @unmerge_readanylane_merge_extract_to_virtual_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; CHECK-LABEL: unmerge_readanylane_merge_extract_to_virtual_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v2, 0
; CHECK-NEXT: global_load_dwordx2 v[0:1], v2, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_readfirstlane_b32 s0, v1
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: global_store_dword v2, v0, s[2:3]
; CHECK-NEXT: s_endpgm
%load = load volatile <2 x i32>, ptr addrspace(1) %ptr0
%extracted = extractelement <2 x i32> %load, i32 1
store i32 %extracted, ptr addrspace(1) %ptr1
ret void
}

define amdgpu_ps float @unmerge_readanylane_merge_extract_to_physical_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; CHECK-LABEL: unmerge_readanylane_merge_extract_to_physical_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v0, 0
; CHECK-NEXT: global_load_dwordx2 v[0:1], v0, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_readfirstlane_b32 s0, v1
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: ; return to shader part epilog
%load = load volatile <2 x float>, ptr addrspace(1) %ptr0
%extracted = extractelement <2 x float> %load, i32 1
ret float %extracted
}

define amdgpu_ps void @unmerge_readanylane_merge_extract_bitcast_to_virtual_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; CHECK-LABEL: unmerge_readanylane_merge_extract_bitcast_to_virtual_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v2, 0
; CHECK-NEXT: global_load_dwordx2 v[0:1], v2, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_readfirstlane_b32 s0, v0
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: global_store_dword v2, v0, s[2:3]
; CHECK-NEXT: s_endpgm
%load = load volatile <4 x i16>, ptr addrspace(1) %ptr0
%extracted = shufflevector <4 x i16> %load, <4 x i16> %load, <2 x i32> <i32 0, i32 1>
%bitcast = bitcast <2 x i16> %extracted to float
store float %bitcast, ptr addrspace(1) %ptr1
ret void
}

define amdgpu_ps float @unmerge_readanylane_merge_extract_bitcast_to_physical_vgpr(ptr addrspace(1) inreg %ptr0, ptr addrspace(1) inreg %ptr1) {
; CHECK-LABEL: unmerge_readanylane_merge_extract_bitcast_to_physical_vgpr:
; CHECK: ; %bb.0:
; CHECK-NEXT: v_mov_b32_e32 v0, 0
; CHECK-NEXT: global_load_dwordx2 v[0:1], v0, s[0:1] glc dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_readfirstlane_b32 s0, v0
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: ; return to shader part epilog
%load = load volatile <4 x i16>, ptr addrspace(1) %ptr0
%extracted = shufflevector <4 x i16> %load, <4 x i16> %load, <2 x i32> <i32 0, i32 1>
%bitcast = bitcast <2 x i16> %extracted to float
ret float %bitcast
}
Loading