shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

AMDGPU: Remove -stress-regalloc arguments from mfma selection tests (#150890)

Browse Source 
I'm not really sure what the point of these was, but they originated
in the base support commit for gfx942 mfma support. These don't impact
the selection at all, so don't belong in this test. These were causing
allocation failure depending on whether or not the AGPR or VGPR form
was used.
This commit is contained in:
Matt Arsenault 2025-07-29 00:30:01 +09:00 committed by GitHub
parent 6fb8e58565
commit a496a985d9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 0 additions and 127 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx942.ll
View File

@ -1,13 +1,9 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck --check-prefixes=GFX942,GFX942-VGPRCD,GFX942-SDAG,GFX942-VGPRCD-SDAG %s
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck --check-prefixes=GFX942,GFX942-VGPRCD,GFX942-GISEL,GFX942-VGPRCD-GISEL %s
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx942 -stress-regalloc=10 < %s | FileCheck --check-prefixes=GFX942,GFX942-AGPRCD,GFX942-SDAG,GFX942-AGPRCD-SDAG %s
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx942 -stress-regalloc=10 < %s | FileCheck --check-prefixes=GFX942,GFX942-AGPRCD,GFX942-GISEL,GFX942-AGPRCD-GISEL %s
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx950 < %s | FileCheck --check-prefixes=GFX950,GFX950-VGPRCD,GFX950-SDAG,GFX950-VGPRCD-SDAG %s
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx950 < %s | FileCheck --check-prefixes=GFX950,GFX950-VGPRCD,GFX950-GISEL,GFX950-VGPRCD-GISEL %s
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx950 -stress-regalloc=10 < %s | FileCheck --check-prefixes=GFX950,GFX950-AGPRCD,GFX950-SDAG,GFX950-AGPRCD-SDAG %s
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx950 -stress-regalloc=10 < %s | FileCheck --check-prefixes=GFX950,GFX950-AGPRCD,GFX950-GISEL,GFX950-AGPRCD-GISEL %s
declare <4 x i32> @llvm.amdgcn.mfma.i32.16x16x32.i8(i64, i64, <4 x i32>, i32, i32, i32)
declare <16 x i32> @llvm.amdgcn.mfma.i32.32x32x16.i8(i64, i64, <16 x i32>, i32, i32, i32)

123
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.xf32.gfx942.ll
View File

@ -1,8 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck --check-prefixes=GFX942,GFX942-SDAG %s
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck --check-prefixes=GFX942,GFX942-GISEL %s
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx942 -stress-regalloc=10 < %s | FileCheck --check-prefixes=GFX942-STRESS,GFX942-SDAG-STRESS %s
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx942 -stress-regalloc=10 < %s | FileCheck --check-prefixes=GFX942-STRESS,GFX942-GISEL-STRESS %s
declare <4 x float> @llvm.amdgcn.mfma.f32.16x16x8.xf32(<2 x float>, <2 x float>, <4 x float>, i32, i32, i32)
declare <16 x float> @llvm.amdgcn.mfma.f32.32x32x4.xf32(<2 x float>, <2 x float>, <16 x float>, i32, i32, i32)
@ -51,50 +49,6 @@ define amdgpu_kernel void @test_mfma_f32_16x16x8xf32(ptr addrspace(1) %arg) #0 {
; GFX942-GISEL-NEXT: s_nop 5
; GFX942-GISEL-NEXT: global_store_dwordx4 v0, a[0:3], s[6:7]
; GFX942-GISEL-NEXT: s_endpgm
;
; GFX942-SDAG-STRESS-LABEL: test_mfma_f32_16x16x8xf32:
; GFX942-SDAG-STRESS: ; %bb.0: ; %bb
; GFX942-SDAG-STRESS-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x24
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v0, 1.0
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v1, 2.0
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v2, 0x40400000
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v3, 4.0
; GFX942-SDAG-STRESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-SDAG-STRESS-NEXT: s_load_dwordx4 s[0:3], s[6:7], 0x0
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v4, 0
; GFX942-SDAG-STRESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a0, s0
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a1, s1
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a2, s2
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a3, s3
; GFX942-SDAG-STRESS-NEXT: s_nop 1
; GFX942-SDAG-STRESS-NEXT: v_mfma_f32_16x16x8_xf32 a[0:3], v[0:1], v[2:3], a[0:3] cbsz:1 abid:2 blgp:3
; GFX942-SDAG-STRESS-NEXT: s_nop 6
; GFX942-SDAG-STRESS-NEXT: global_store_dwordx4 v4, a[0:3], s[6:7]
; GFX942-SDAG-STRESS-NEXT: s_endpgm
;
; GFX942-GISEL-STRESS-LABEL: test_mfma_f32_16x16x8xf32:
; GFX942-GISEL-STRESS: ; %bb.0: ; %bb
; GFX942-GISEL-STRESS-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x24
; GFX942-GISEL-STRESS-NEXT: s_mov_b32 s0, 1.0
; GFX942-GISEL-STRESS-NEXT: s_mov_b32 s2, 0x40400000
; GFX942-GISEL-STRESS-NEXT: s_mov_b32 s1, 2.0
; GFX942-GISEL-STRESS-NEXT: s_mov_b32 s3, 4.0
; GFX942-GISEL-STRESS-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX942-GISEL-STRESS-NEXT: v_mov_b64_e32 v[2:3], s[2:3]
; GFX942-GISEL-STRESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-GISEL-STRESS-NEXT: s_load_dwordx4 s[0:3], s[6:7], 0x0
; GFX942-GISEL-STRESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a0, s0
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a1, s1
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a2, s2
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a3, s3
; GFX942-GISEL-STRESS-NEXT: s_nop 1
; GFX942-GISEL-STRESS-NEXT: v_mfma_f32_16x16x8_xf32 a[0:3], v[0:1], v[2:3], a[0:3] cbsz:1 abid:2 blgp:3
; GFX942-GISEL-STRESS-NEXT: v_mov_b32_e32 v0, 0
; GFX942-GISEL-STRESS-NEXT: s_nop 5
; GFX942-GISEL-STRESS-NEXT: global_store_dwordx4 v0, a[0:3], s[6:7]
; GFX942-GISEL-STRESS-NEXT: s_endpgm
bb:
%in.1 = load <4 x float>, ptr addrspace(1) %arg
%mai.1 = tail call <4 x float> @llvm.amdgcn.mfma.f32.16x16x8.xf32(<2 x float> <float 1.0, float 2.0>, <2 x float> <float 3.0, float 4.0>, <4 x float> %in.1, i32 1, i32 2, i32 3)
@ -178,82 +132,6 @@ define amdgpu_kernel void @test_mfma_f32_32x32x4xf32(ptr addrspace(1) %arg) #0 {
; GFX942-GISEL-NEXT: global_store_dwordx4 v0, a[8:11], s[16:17] offset:32
; GFX942-GISEL-NEXT: global_store_dwordx4 v0, a[12:15], s[16:17] offset:48
; GFX942-GISEL-NEXT: s_endpgm
;
; GFX942-SDAG-STRESS-LABEL: test_mfma_f32_32x32x4xf32:
; GFX942-SDAG-STRESS: ; %bb.0: ; %bb
; GFX942-SDAG-STRESS-NEXT: s_load_dwordx2 s[16:17], s[4:5], 0x24
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v0, 1.0
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v1, 2.0
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v2, 0x40400000
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v3, 4.0
; GFX942-SDAG-STRESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-SDAG-STRESS-NEXT: s_load_dwordx16 s[0:15], s[16:17], 0x0
; GFX942-SDAG-STRESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a0, s0
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a1, s1
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a2, s2
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a3, s3
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a4, s4
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a5, s5
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a6, s6
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a7, s7
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a8, s8
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a9, s9
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a10, s10
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a11, s11
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a12, s12
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a13, s13
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a14, s14
; GFX942-SDAG-STRESS-NEXT: v_accvgpr_write_b32 a15, s15
; GFX942-SDAG-STRESS-NEXT: s_nop 1
; GFX942-SDAG-STRESS-NEXT: v_mfma_f32_32x32x4_xf32 a[0:15], v[0:1], v[2:3], a[0:15] cbsz:1 abid:2 blgp:3
; GFX942-SDAG-STRESS-NEXT: v_mov_b32_e32 v0, 0
; GFX942-SDAG-STRESS-NEXT: s_nop 7
; GFX942-SDAG-STRESS-NEXT: s_nop 1
; GFX942-SDAG-STRESS-NEXT: global_store_dwordx4 v0, a[12:15], s[16:17] offset:48
; GFX942-SDAG-STRESS-NEXT: global_store_dwordx4 v0, a[8:11], s[16:17] offset:32
; GFX942-SDAG-STRESS-NEXT: global_store_dwordx4 v0, a[4:7], s[16:17] offset:16
; GFX942-SDAG-STRESS-NEXT: global_store_dwordx4 v0, a[0:3], s[16:17]
; GFX942-SDAG-STRESS-NEXT: s_endpgm
;
; GFX942-GISEL-STRESS-LABEL: test_mfma_f32_32x32x4xf32:
; GFX942-GISEL-STRESS: ; %bb.0: ; %bb
; GFX942-GISEL-STRESS-NEXT: s_load_dwordx2 s[16:17], s[4:5], 0x24
; GFX942-GISEL-STRESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-GISEL-STRESS-NEXT: s_load_dwordx16 s[0:15], s[16:17], 0x0
; GFX942-GISEL-STRESS-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a0, s0
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a1, s1
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a2, s2
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a3, s3
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a4, s4
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a5, s5
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a6, s6
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a7, s7
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a8, s8
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a9, s9
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a10, s10
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a11, s11
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a12, s12
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a13, s13
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a14, s14
; GFX942-GISEL-STRESS-NEXT: v_accvgpr_write_b32 a15, s15
; GFX942-GISEL-STRESS-NEXT: s_mov_b32 s0, 1.0
; GFX942-GISEL-STRESS-NEXT: s_mov_b32 s1, 2.0
; GFX942-GISEL-STRESS-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX942-GISEL-STRESS-NEXT: s_mov_b32 s0, 0x40400000
; GFX942-GISEL-STRESS-NEXT: s_mov_b32 s1, 4.0
; GFX942-GISEL-STRESS-NEXT: v_mov_b64_e32 v[2:3], s[0:1]
; GFX942-GISEL-STRESS-NEXT: s_nop 1
; GFX942-GISEL-STRESS-NEXT: v_mfma_f32_32x32x4_xf32 a[0:15], v[0:1], v[2:3], a[0:15] cbsz:1 abid:2 blgp:3
; GFX942-GISEL-STRESS-NEXT: v_mov_b32_e32 v0, 0
; GFX942-GISEL-STRESS-NEXT: s_nop 7
; GFX942-GISEL-STRESS-NEXT: s_nop 1
; GFX942-GISEL-STRESS-NEXT: global_store_dwordx4 v0, a[0:3], s[16:17]
; GFX942-GISEL-STRESS-NEXT: global_store_dwordx4 v0, a[4:7], s[16:17] offset:16
; GFX942-GISEL-STRESS-NEXT: global_store_dwordx4 v0, a[8:11], s[16:17] offset:32
; GFX942-GISEL-STRESS-NEXT: global_store_dwordx4 v0, a[12:15], s[16:17] offset:48
; GFX942-GISEL-STRESS-NEXT: s_endpgm
bb:
%in.1 = load <16 x float>, ptr addrspace(1) %arg
%mai.1 = tail call <16 x float> @llvm.amdgcn.mfma.f32.32x32x4.xf32(<2 x float> <float 1.0, float 2.0>, <2 x float> <float 3.0, float 4.0>, <16 x float> %in.1, i32 1, i32 2, i32 3)
@ -264,4 +142,3 @@ bb:
attributes #0 = { "amdgpu-flat-work-group-size"="1,256" }
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; GFX942: {{.*}}
; GFX942-STRESS: {{.*}}