[llvm] [AMDGPU] Add hazard tests for cvt scale of fp4. (PR #118813)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Dec 5 06:38:09 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Pravin Jagtap (pravinjagtap)
<details>
<summary>Changes</summary>
---
Patch is 24.69 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/118813.diff
1 Files Affected:
- (modified) llvm/test/CodeGen/AMDGPU/hazards-gfx950.mir (+380-12)
``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/hazards-gfx950.mir b/llvm/test/CodeGen/AMDGPU/hazards-gfx950.mir
index e2ee117bdd5c26..9c69101d9cdb93 100644
--- a/llvm/test/CodeGen/AMDGPU/hazards-gfx950.mir
+++ b/llvm/test/CodeGen/AMDGPU/hazards-gfx950.mir
@@ -530,11 +530,33 @@ body: |
...
---
-name: test_cvt_scale_fp4_f32_hazard
+name: test_cvt_scale_fp4_f32_neg_hazard_opsel0
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
- ; GCN-LABEL: name: test_cvt_scale_fp4_f32_hazard
+ ; GCN-LABEL: name: test_cvt_scale_fp4_f32_neg_hazard_opsel0
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr1 = V_AND_B32_e32 2147483647, killed $vgpr1, implicit $exec
+ ; GCN-NEXT: renamable $vgpr2 = V_XOR_B32_e32 -2147483648, killed $vgpr2, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_CVT_SCALEF32_PK_FP4_F32_e64 0, killed $vgpr1, 0, killed $vgpr2, 0, killed $vgpr3, killed $vgpr0, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr1 = V_AND_B32_e32 2147483647, killed $vgpr1, implicit $exec
+ renamable $vgpr2 = V_XOR_B32_e32 -2147483648, killed $vgpr2, implicit $exec
+ renamable $vgpr0 = V_CVT_SCALEF32_PK_FP4_F32_e64 0, killed $vgpr1, 0, killed $vgpr2, 0, killed $vgpr3, killed $vgpr0, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_cvt_scale_fp4_f32_opsel3_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GCN-LABEL: name: test_cvt_scale_fp4_f32_opsel3_hazard
; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
; GCN-NEXT: {{ $}}
; GCN-NEXT: S_WAITCNT 0
@@ -552,6 +574,50 @@ body: |
S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
...
+---
+name: test_cvt_scale_fp4_f32_opsel0_neg_fp4_as_src_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GCN-LABEL: name: test_cvt_scale_fp4_f32_opsel0_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr1 = V_AND_B32_e32 2147483647, killed $vgpr1, implicit $exec
+ ; GCN-NEXT: renamable $vgpr2 = V_XOR_B32_e32 -2147483648, killed $vgpr2, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_CVT_SCALEF32_PK_FP4_F32_e64 0, killed $vgpr1, 0, killed $vgpr2, 0, killed $vgpr3, killed $vgpr0, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr1 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr1 = V_AND_B32_e32 2147483647, killed $vgpr1, implicit $exec
+ renamable $vgpr2 = V_XOR_B32_e32 -2147483648, killed $vgpr2, implicit $exec
+ renamable $vgpr0 = V_CVT_SCALEF32_PK_FP4_F32_e64 0, killed $vgpr1, 0, killed $vgpr2, 0, killed $vgpr3, killed $vgpr0, 0, implicit $mode, implicit $exec
+ renamable $vgpr1 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_cvt_scale_fp4_f32_opsel3_neg_fp4_as_src_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GCN-LABEL: name: test_cvt_scale_fp4_f32_opsel3_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr1 = V_AND_B32_e32 2147483647, killed $vgpr1, implicit $exec
+ ; GCN-NEXT: renamable $vgpr2 = V_XOR_B32_e32 -2147483648, killed $vgpr2, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_CVT_SCALEF32_PK_FP4_F32_e64 8, killed $vgpr1, 0, killed $vgpr2, 4, killed $vgpr3, killed $vgpr0, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr1 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr1 = V_AND_B32_e32 2147483647, killed $vgpr1, implicit $exec
+ renamable $vgpr2 = V_XOR_B32_e32 -2147483648, killed $vgpr2, implicit $exec
+ renamable $vgpr0 = V_CVT_SCALEF32_PK_FP4_F32_e64 8, killed $vgpr1, 0, killed $vgpr2, 4, killed $vgpr3, killed $vgpr0, 0, implicit $mode, implicit $exec
+ renamable $vgpr1 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
---
name: test_scalef32_sr_pk_fp4_f16_hazard
body: |
@@ -576,11 +642,33 @@ body: |
...
---
-name: test_scalef32_sr_pk_fp4_bf16_hazard
+name: test_scalef32_sr_pk_fp4_bf16_neg_opsel0_hazard
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
- ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_bf16_hazard
+ ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_bf16_neg_opsel0_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ ; GCN-NEXT: S_WAITCNT 3952
+ ; GCN-NEXT: early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_BF16_e64 0, killed $vgpr2, 0, killed $vgpr3, 0, killed $vgpr4, killed $vgpr0, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ S_WAITCNT 3952
+ early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_BF16_e64 0, killed $vgpr2, 0, killed $vgpr3, 0, killed $vgpr4, killed $vgpr0, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_scalef32_sr_pk_fp4_bf16_opsel3_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
+ ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_bf16_opsel3_hazard
; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
; GCN-NEXT: {{ $}}
; GCN-NEXT: S_WAITCNT 0
@@ -599,11 +687,77 @@ body: |
...
---
-name: test_scalef32_sr_pk_fp4_f32_hazard
+name: test_scalef32_sr_pk_fp4_bf16_opsel0_neg_fp4_as_src_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
+ ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_bf16_opsel0_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ ; GCN-NEXT: S_WAITCNT 3952
+ ; GCN-NEXT: early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_BF16_e64 0, killed $vgpr2, 0, killed $vgpr3, 0, killed $vgpr4, killed $vgpr0, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ S_WAITCNT 3952
+ early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_BF16_e64 0, killed $vgpr2, 0, killed $vgpr3, 0, killed $vgpr4, killed $vgpr0, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_scalef32_sr_pk_fp4_bf16_opsel3_neg_fp4_as_src_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
+ ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_bf16_opsel3_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ ; GCN-NEXT: S_WAITCNT 3952
+ ; GCN-NEXT: early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_BF16_e64 8, killed $vgpr2, 0, killed $vgpr3, 4, killed $vgpr4, killed $vgpr0, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ S_WAITCNT 3952
+ early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_BF16_e64 8, killed $vgpr2, 0, killed $vgpr3, 4, killed $vgpr4, killed $vgpr0, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_scalef32_sr_pk_fp4_f32_neg_opsel0_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
+ ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_f32_neg_opsel0_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ ; GCN-NEXT: S_WAITCNT 3952
+ ; GCN-NEXT: early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_F32_e64 0, killed $vgpr2_vgpr3, 0, killed $vgpr4, 0, killed $vgpr5, killed $vgpr0, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ S_WAITCNT 3952
+ early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_F32_e64 0, killed $vgpr2_vgpr3, 0, killed $vgpr4, 0, killed $vgpr5, killed $vgpr0, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_scalef32_sr_pk_fp4_f32_opsel3_hazard
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
- ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_f32_hazard
+ ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_f32_opsel3_hazard
; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
; GCN-NEXT: {{ $}}
; GCN-NEXT: S_WAITCNT 0
@@ -622,11 +776,73 @@ body: |
...
---
-name: test_cvt_scalef32_fp4_f16_hazard
+name: test_scalef32_sr_pk_fp4_f32_opsel0_neg_fp4_as_src_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
+ ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_f32_opsel0_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ ; GCN-NEXT: S_WAITCNT 3952
+ ; GCN-NEXT: early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_F32_e64 0, killed $vgpr2_vgpr3, 0, killed $vgpr4, 0, killed $vgpr5, killed $vgpr0, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ S_WAITCNT 3952
+ early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_F32_e64 0, killed $vgpr2_vgpr3, 0, killed $vgpr4, 0, killed $vgpr5, killed $vgpr0, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_scalef32_sr_pk_fp4_f32_opsel3_neg_fp4_as_src_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
+ ; GCN-LABEL: name: test_scalef32_sr_pk_fp4_f32_opsel3_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ ; GCN-NEXT: S_WAITCNT 3952
+ ; GCN-NEXT: early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_F32_e64 8, killed $vgpr2_vgpr3, 0, killed $vgpr4, 4, killed $vgpr5, killed $vgpr0, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr0 = GLOBAL_LOAD_DWORD killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec
+ S_WAITCNT 3952
+ early-clobber renamable $vgpr1 = V_CVT_SCALEF32_SR_PK_FP4_F32_e64 8, killed $vgpr2_vgpr3, 0, killed $vgpr4, 4, killed $vgpr5, killed $vgpr0, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_cvt_scalef32_fp4_f16_neg_opsel0_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-LABEL: name: test_cvt_scalef32_fp4_f16_neg_opsel0_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_F16_e64 0, killed $vgpr0, 0, killed $vgpr1, 0, killed $vgpr2, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr2, $vgpr2, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_F16_e64 0, killed $vgpr0, 0, killed $vgpr1, 0, killed $vgpr2, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr2, $vgpr2, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_cvt_scalef32_fp4_f16_opsel3_hazard
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
- ; GCN-LABEL: name: test_cvt_scalef32_fp4_f16_hazard
+ ; GCN-LABEL: name: test_cvt_scalef32_fp4_f16_opsel3_hazard
; GCN: liveins: $vgpr0, $vgpr1, $vgpr2
; GCN-NEXT: {{ $}}
; GCN-NEXT: S_WAITCNT 0
@@ -641,11 +857,65 @@ body: |
...
---
-name: test_cvt_scalef32_fp4_bf16_hazard
+name: test_cvt_scalef32_fp4_f16_opsel0_neg_fp4_as_src_hazard
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
- ; GCN-LABEL: name: test_cvt_scalef32_fp4_bf16_hazard
+ ; GCN-LABEL: name: test_cvt_scalef32_fp4_f16_opsel0_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_F16_e64 0, killed $vgpr0, 0, killed $vgpr1, 0, killed $vgpr2, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_F16_e64 0, killed $vgpr0, 0, killed $vgpr1, 0, killed $vgpr2, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_cvt_scalef32_fp4_f16_opsel3_neg_fp4_as_src_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-LABEL: name: test_cvt_scalef32_fp4_f16_opsel3_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_F16_e64 8, killed $vgpr0, 0, killed $vgpr1, 4, killed $vgpr2, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_F16_e64 8, killed $vgpr0, 0, killed $vgpr1, 4, killed $vgpr2, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr1, $vgpr1, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_cvt_scalef32_fp4_bf16_neg_opsel0_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-LABEL: name: test_cvt_scalef32_fp4_bf16_neg_opsel0_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_BF16_e64 0, killed $vgpr0, 0, killed $vgpr1, 0, killed $vgpr2, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr2, $vgpr2, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_BF16_e64 0, killed $vgpr0, 0, killed $vgpr1, 0, killed $vgpr2, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr2, $vgpr2, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_cvt_scalef32_fp4_bf16_opsel3_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-LABEL: name: test_cvt_scalef32_fp4_bf16_opsel3_hazard
; GCN: liveins: $vgpr0, $vgpr1, $vgpr2
; GCN-NEXT: {{ $}}
; GCN-NEXT: S_WAITCNT 0
@@ -659,6 +929,42 @@ body: |
S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
...
+---
+name: test_cvt_scalef32_fp4_bf16_opsel0_neg_fp4_as_src_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-LABEL: name: test_cvt_scalef32_fp4_bf16_opsel0_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_BF16_e64 0, killed $vgpr0, 0, killed $vgpr1, 0, killed $vgpr2, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_BF16_e64 0, killed $vgpr0, 0, killed $vgpr1, 0, killed $vgpr2, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+...
+
+---
+name: test_cvt_scalef32_fp4_bf16_opsel3_neg_fp4_as_src_hazard
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-LABEL: name: test_cvt_scalef32_fp4_bf16_opsel3_neg_fp4_as_src_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: S_WAITCNT 0
+ ; GCN-NEXT: renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_BF16_e64 8, killed $vgpr0, 0, killed $vgpr1, 4, killed $vgpr2, 0, implicit $mode, implicit $exec
+ ; GCN-NEXT: renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31, implicit killed $vgpr0
+ S_WAITCNT 0
+ renamable $vgpr2 = V_CVT_SCALEF32_PK_FP4_BF16_e64 8, killed $vgpr0, 0, killed $vgpr1, 4, killed $vgpr2, 0, implicit $mode, implicit $exec
+ renamable $vgpr0 = V_ADD_U32_e32 killed $vgpr0, $vgpr0, implicit $exec
+ S_SETPC_B64_return undef $sgpr...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/118813
More information about the llvm-commits
mailing list