Skip to content

[AMDGPU] Fix llvm.amdgcn.workitem.id-unsupported-calling-convention.ll #127041

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

Merged
merged 2 commits into from
Feb 13, 2025
Merged

[AMDGPU] Fix llvm.amdgcn.workitem.id-unsupported-calling-convention.ll #127041

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c8f6769
[AMDGPU] Fix llvm.amdgcn.workitem.id-unsupported-calling-convention.ll
ro-i Feb 13, 2025
086f67c
implement feedback
ro-i Feb 13, 2025
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
59 changes: 14 additions & 45 deletions llvm/test/CodeGen/AMDGPU/llvm.amdgcn.workitem.id-unsupported-calling-convention.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,55 +1,24 @@
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn -mcpu=gfx942 -O0 -stop-after=amdgpu-isel -o - %s | FileCheck --check-prefix=SelDAG %s
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx942 -stop-after=legalizer -o - %s | FileCheck --check-prefix=GlobalISel %s
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn -mcpu=gfx942 -o - %s | FileCheck --check-prefix=SELDAG %s
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx942 -o - %s | FileCheck --check-prefix=GLOBALISEL %s
Copy link
Contributor

@arsenm arsenm Feb 13, 2025

Choose a reason for hiding this comment

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

Use explicit -global-isel=0 for the dag run line. Should also use a common prefix, they both have the same output


declare i32 @llvm.amdgcn.workitem.id.x()
declare i32 @llvm.amdgcn.workitem.id.y()
declare i32 @llvm.amdgcn.workitem.id.z()

define amdgpu_ps void @undefined_workitems(ptr %p, ptr %q, ptr %r) {
; SelDAG-LABEL: name: undefined_workitems
; SelDAG: bb.0 (%ir-block.0):
; SelDAG-NEXT: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
; SelDAG-NEXT: {{ $}}
; SelDAG-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr5
; SelDAG-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr4
; SelDAG-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; SelDAG-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; SelDAG-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; SelDAG-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; SelDAG-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY]], %subreg.sub1
; SelDAG-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY2]], %subreg.sub1
; SelDAG-NEXT: [[REG_SEQUENCE2:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY4]], %subreg.sub1
; SelDAG-NEXT: [[COPY6:%[0-9]+]]:vreg_64_align2 = COPY [[REG_SEQUENCE]]
; SelDAG-NEXT: [[COPY7:%[0-9]+]]:vreg_64_align2 = COPY [[REG_SEQUENCE1]]
; SelDAG-NEXT: [[COPY8:%[0-9]+]]:vreg_64_align2 = COPY [[REG_SEQUENCE2]]
; SelDAG-NEXT: S_ENDPGM 0
;
; GlobalISel-LABEL: name: undefined_workitems
; GlobalISel: bb.1 (%ir-block.0):
; GlobalISel-NEXT: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
; GlobalISel-NEXT: {{ $}}
; GlobalISel-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GlobalISel-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GlobalISel-NEXT: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; GlobalISel-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GlobalISel-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
; GlobalISel-NEXT: [[MV1:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
; GlobalISel-NEXT: [[COPY4:%[0-9]+]]:_(s32) = COPY $vgpr4
; GlobalISel-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr5
; GlobalISel-NEXT: [[MV2:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY4]](s32), [[COPY5]](s32)
; GlobalISel-NEXT: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
; GlobalISel-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY [[DEF]](s32)
; GlobalISel-NEXT: G_STORE [[COPY6]](s32), [[MV]](p0) :: (store (s32) into %ir.p)
; GlobalISel-NEXT: [[COPY7:%[0-9]+]]:_(s32) = COPY [[DEF]](s32)
; GlobalISel-NEXT: G_STORE [[COPY7]](s32), [[MV1]](p0) :: (store (s32) into %ir.q)
; GlobalISel-NEXT: G_STORE [[DEF]](s32), [[MV2]](p0) :: (store (s32) into %ir.r)
; GlobalISel-NEXT: S_ENDPGM 0
define amdgpu_ps void @undefined_workitems(ptr addrspace(1) %p, ptr addrspace(1) %q, ptr addrspace(1) %r) {
; SELDAG-LABEL: undefined_workitems:
; SELDAG: ; %bb.0:
; SELDAG-NEXT: s_endpgm
;
; GLOBALISEL-LABEL: undefined_workitems:
; GLOBALISEL: ; %bb.0:
; GLOBALISEL-NEXT: s_endpgm
%id.x = call i32 @llvm.amdgcn.workitem.id.x()
store i32 %id.x, ptr %p
store i32 %id.x, ptr addrspace(1) %p
%id.y = call i32 @llvm.amdgcn.workitem.id.y()
store i32 %id.y, ptr %q
store i32 %id.y, ptr addrspace(1) %q
%id.z = call i32 @llvm.amdgcn.workitem.id.z()
store i32 %id.z, ptr %r
store i32 %id.z, ptr addrspace(1) %r
ret void
}