[llvm] AMDGPU: Add a few missing mfma rewrite tests (PR #152434)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Aug 6 20:55:51 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
<details>
<summary>Changes</summary>
Test other splitting situations that appear in greedy.
This includes ensuring we have a case that hits a local split
and instruction split (most of the tests hit the region split path).
Also test a few cases where the final result isn't fully used, resulting
in partial copy bundles instead of a simple full copy. Test physreg
and virtreg agpr interference with a reassignment candidate.
I'm accumulating too many failure cases, and MIR tests are very prone
to painful merge conflicts, so I've added a few more tests and extracted
new tests from #<!-- -->147975.
Closes #<!-- -->149026
---
Patch is 142.36 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/152434.diff
2 Files Affected:
- (modified) llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-agpr-negative-tests.mir (+607)
- (modified) llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-av-with-load-source.mir (+842-95)
``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-agpr-negative-tests.mir b/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-agpr-negative-tests.mir
index c7767cb832078..5cb7fbb74b46e 100644
--- a/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-agpr-negative-tests.mir
+++ b/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-agpr-negative-tests.mir
@@ -20,11 +20,36 @@
ret void
}
+ define amdgpu_kernel void @inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_physreg_src2() #0 {
+ ret void
+ }
+
define amdgpu_kernel void @inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_src2_different_subreg() #0 {
ret void
}
+ define amdgpu_kernel void @inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_mac_vgprcd_e64_two_chained_uses_cannot_rewrite_final_use() #0 {
+ ret void
+ }
+
+ define amdgpu_kernel void @inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_chain_no_agprs_first() #1 {
+ ret void
+ }
+
+ define amdgpu_kernel void @inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_chain_no_agprs_second() #1 {
+ ret void
+ }
+
+ define amdgpu_kernel void @inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_chain_no_agprs_first_physreg() #1 {
+ ret void
+ }
+
+ define amdgpu_kernel void @inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_chain_no_agprs_second_physreg() #1 {
+ ret void
+ }
+
attributes #0 = { "amdgpu-wave-limiter"="true" "amdgpu-waves-per-eu"="8,8" }
+ attributes #1 = { "amdgpu-wave-limiter"="true" "amdgpu-waves-per-eu"="10,10" }
...
# Inflate pattern, except the defining instruction isn't an MFMA.
@@ -403,6 +428,89 @@ body: |
...
+# Non-mac variant, src2 is a physical register
+---
+name: inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_physreg_src2
+tracksRegLiveness: true
+machineFunctionInfo:
+ isEntryFunction: true
+ stackPtrOffsetReg: '$sgpr32'
+ occupancy: 10
+ sgprForEXECCopy: '$sgpr100_sgpr101'
+body: |
+ ; CHECK-LABEL: name: inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_physreg_src2
+ ; CHECK: bb.0:
+ ; CHECK-NEXT: successors: %bb.1(0x80000000)
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: S_NOP 0, implicit-def $agpr0
+ ; CHECK-NEXT: renamable $sgpr0 = S_MOV_B32 0
+ ; CHECK-NEXT: renamable $vgpr8 = V_MOV_B32_e32 0, implicit $exec
+ ; CHECK-NEXT: renamable $sgpr1 = COPY renamable $sgpr0
+ ; CHECK-NEXT: renamable $vgpr0_vgpr1 = COPY killed renamable $sgpr0_sgpr1
+ ; CHECK-NEXT: renamable $vcc = S_AND_B64 $exec, -1, implicit-def dead $scc
+ ; CHECK-NEXT: dead renamable $vgpr9 = COPY renamable $vgpr8
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: bb.1:
+ ; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
+ ; CHECK-NEXT: liveins: $vcc, $vgpr0_vgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: early-clobber renamable $vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17 = V_MFMA_F32_32X32X8F16_vgprcd_e64 $vgpr0_vgpr1, $vgpr0_vgpr1, undef $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, 0, 0, 0, implicit $mode, implicit $exec
+ ; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
+ ; CHECK-NEXT: S_BRANCH %bb.2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: bb.2:
+ ; CHECK-NEXT: liveins: $vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17:0x00000000FFFFFFFF
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: renamable $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15 = COPY killed renamable $vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63
+ ; CHECK-NEXT: renamable $vgpr0 = V_MOV_B32_e32 0, implicit $exec
+ ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR renamable $vgpr0, renamable $agpr8_agpr9_agpr10_agpr11, undef $sgpr0_sgpr1, 32, 0, implicit $exec :: (store (s128), align 32, addrspace 1)
+ ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR renamable $vgpr0, renamable $agpr12_agpr13_agpr14_agpr15, undef $sgpr0_sgpr1, 48, 0, implicit $exec :: (store (s128), addrspace 1)
+ ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR renamable $vgpr0, renamable $agpr0_agpr1_agpr2_agpr3, undef $sgpr0_sgpr1, 0, 0, implicit $exec :: (store (s128), align 128, addrspace 1)
+ ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR killed renamable $vgpr0, killed renamable $agpr4_agpr5_agpr6_agpr7, killed undef $sgpr0_sgpr1, 16, 0, implicit $exec :: (store (s128), addrspace 1)
+ ; CHECK-NEXT: S_ENDPGM 0
+ bb.0:
+ S_NOP 0, implicit-def $agpr0
+ renamable $sgpr0 = S_MOV_B32 0
+ undef %0.sub8:vreg_512_align2 = V_MOV_B32_e32 0, implicit $exec
+ renamable $sgpr1 = COPY renamable $sgpr0
+ %1:vreg_64_align2 = COPY killed renamable $sgpr0_sgpr1
+ renamable $vcc = S_AND_B64 $exec, -1, implicit-def dead $scc
+ %0.sub9:vreg_512_align2 = COPY %0.sub8
+
+ bb.1:
+ liveins: $vcc
+
+ %0:vreg_512_align2 = V_MFMA_F32_32X32X8F16_vgprcd_e64 %1, %1, undef $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, 0, 0, 0, implicit $mode, implicit $exec
+ S_CBRANCH_VCCNZ %bb.1, implicit $vcc
+ S_BRANCH %bb.2
+
+ bb.2:
+ ; No VGPRs available for %0
+ S_NOP 0, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
+ S_NOP 0, implicit-def $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+ S_NOP 0, implicit-def $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23
+ S_NOP 0, implicit-def $vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31
+ S_NOP 0, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39
+ S_NOP 0, implicit-def $vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47
+ S_NOP 0, implicit-def $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55
+ S_NOP 0, implicit-def $vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63
+ %2:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+ GLOBAL_STORE_DWORDX4_SADDR %2, %0.sub8_sub9_sub10_sub11, undef $sgpr0_sgpr1, 32, 0, implicit $exec :: (store (s128), align 32, addrspace 1)
+ GLOBAL_STORE_DWORDX4_SADDR %2, %0.sub12_sub13_sub14_sub15, undef $sgpr0_sgpr1, 48, 0, implicit $exec :: (store (s128), addrspace 1)
+ GLOBAL_STORE_DWORDX4_SADDR %2, %0.sub0_sub1_sub2_sub3, undef $sgpr0_sgpr1, 0, 0, implicit $exec :: (store (s128), align 128, addrspace 1)
+ GLOBAL_STORE_DWORDX4_SADDR %2, %0.sub4_sub5_sub6_sub7, killed undef $sgpr0_sgpr1, 16, 0, implicit $exec :: (store (s128), addrspace 1)
+ S_ENDPGM 0
+
+...
+
# Non-mac variant, src2 is the same VGPR, but a different subregister.
---
name: inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_src2_different_subreg
@@ -489,3 +597,502 @@ body: |
S_ENDPGM 0
...
+
+---
+name: inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_mac_vgprcd_e64_two_chained_uses_cannot_rewrite_final_use
+tracksRegLiveness: true
+machineFunctionInfo:
+ isEntryFunction: true
+ stackPtrOffsetReg: '$sgpr32'
+ occupancy: 10
+ sgprForEXECCopy: '$sgpr100_sgpr101'
+body: |
+ ; CHECK-LABEL: name: inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_mac_vgprcd_e64_two_chained_uses_cannot_rewrite_final_use
+ ; CHECK: bb.0:
+ ; CHECK-NEXT: successors: %bb.1(0x80000000)
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: S_NOP 0, implicit-def $agpr0
+ ; CHECK-NEXT: renamable $sgpr0 = S_MOV_B32 0
+ ; CHECK-NEXT: renamable $vgpr8 = V_MOV_B32_e32 0, implicit $exec
+ ; CHECK-NEXT: renamable $sgpr1 = COPY renamable $sgpr0
+ ; CHECK-NEXT: renamable $vgpr0_vgpr1 = COPY killed renamable $sgpr0_sgpr1
+ ; CHECK-NEXT: renamable $vcc = S_AND_B64 $exec, -1, implicit-def dead $scc
+ ; CHECK-NEXT: dead renamable $vgpr9 = COPY renamable $vgpr8
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: bb.1:
+ ; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
+ ; CHECK-NEXT: liveins: $vcc, $vgpr0_vgpr1
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: renamable $vgpr2_vgpr3 = GLOBAL_LOAD_DWORDX2 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s64), addrspace 1)
+ ; CHECK-NEXT: renamable $vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17 = V_MFMA_F32_32X32X8F16_mac_vgprcd_e64 $vgpr0_vgpr1, $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17, 0, 0, 0, implicit $mode, implicit $exec
+ ; CHECK-NEXT: renamable $vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17 = V_MFMA_F32_32X32X8F16_mac_vgprcd_e64 $vgpr0_vgpr1, $vgpr0_vgpr1, killed $vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17, 0, 0, 0, implicit $mode, implicit $exec
+ ; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
+ ; CHECK-NEXT: S_BRANCH %bb.2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: bb.2:
+ ; CHECK-NEXT: liveins: $vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17:0x00000000FFFFFFFF
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: renamable $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15 = COPY killed renamable $vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63
+ ; CHECK-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = COPY killed renamable $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15
+ ; CHECK-NEXT: INLINEASM &"; use $0 ", 1 /* sideeffect attdialect */, 27983881 /* reguse:VReg_512_Align2 */, killed renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+ ; CHECK-NEXT: S_ENDPGM 0
+ bb.0:
+ S_NOP 0, implicit-def $agpr0
+ renamable $sgpr0 = S_MOV_B32 0
+ undef %0.sub8:vreg_512_align2 = V_MOV_B32_e32 0, implicit $exec
+ renamable $sgpr1 = COPY renamable $sgpr0
+ %1:vreg_64_align2 = COPY killed renamable $sgpr0_sgpr1
+ renamable $vcc = S_AND_B64 $exec, -1, implicit-def dead $scc
+ %0.sub9:vreg_512_align2 = COPY %0.sub8
+
+ bb.1:
+ liveins: $vcc
+
+ undef %0.sub0_sub1:vreg_512_align2 = GLOBAL_LOAD_DWORDX2 undef %3:vreg_64_align2, 0, 0, implicit $exec :: (load (s64), addrspace 1)
+ %0:vreg_512_align2 = V_MFMA_F32_32X32X8F16_mac_vgprcd_e64 %1, %1, %0, 0, 0, 0, implicit $mode, implicit $exec
+ %0:vreg_512_align2 = V_MFMA_F32_32X32X8F16_mac_vgprcd_e64 %1, %1, %0, 0, 0, 0, implicit $mode, implicit $exec
+ S_CBRANCH_VCCNZ %bb.1, implicit $vcc
+ S_BRANCH %bb.2
+
+ bb.2:
+ ; No VGPRs available for %0
+ S_NOP 0, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
+ S_NOP 0, implicit-def $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+ S_NOP 0, implicit-def $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23
+ S_NOP 0, implicit-def $vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31
+ S_NOP 0, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39
+ S_NOP 0, implicit-def $vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47
+ S_NOP 0, implicit-def $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55
+ S_NOP 0, implicit-def $vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63
+ INLINEASM &"; use $0 ", 1 /* sideeffect attdialect */, 27983881 /* reguse:VReg_512_Align2 */, %0:vreg_512_align2
+ S_ENDPGM 0
+
+...
+
+# There isn't an assignable AGPR around the first MFMA.
+---
+name: inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_chain_no_agprs_first
+tracksRegLiveness: true
+machineFunctionInfo:
+ isEntryFunction: true
+ stackPtrOffsetReg: '$sgpr32'
+ occupancy: 10
+ sgprForEXECCopy: '$sgpr100_sgpr101'
+body: |
+ ; CHECK-LABEL: name: inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_chain_no_agprs_first
+ ; CHECK: bb.0:
+ ; CHECK-NEXT: successors: %bb.1(0x80000000)
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: S_NOP 0, implicit-def $agpr0
+ ; CHECK-NEXT: renamable $sgpr0 = S_MOV_B32 0
+ ; CHECK-NEXT: renamable $vgpr8 = V_MOV_B32_e32 0, implicit $exec
+ ; CHECK-NEXT: renamable $sgpr1 = COPY renamable $sgpr0
+ ; CHECK-NEXT: renamable $vgpr18_vgpr19 = COPY killed renamable $sgpr0_sgpr1
+ ; CHECK-NEXT: renamable $vcc = S_AND_B64 $exec, -1, implicit-def dead $scc
+ ; CHECK-NEXT: dead renamable $vgpr9 = COPY renamable $vgpr8
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: bb.1:
+ ; CHECK-NEXT: successors: %bb.1(0x40000000), %bb.2(0x40000000)
+ ; CHECK-NEXT: liveins: $vcc, $vgpr18_vgpr19
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: renamable $vgpr16_vgpr17 = GLOBAL_LOAD_DWORDX2 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s64), addrspace 1)
+ ; CHECK-NEXT: S_NOP 0, implicit-def renamable $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, implicit-def renamable $agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31, implicit-def renamable $agpr32_agpr33_agpr34_agpr35_agpr36_agpr37_agpr38_agpr39_agpr40_agpr41_agpr42_agpr43_agpr44_agpr45_agpr46_agpr47, implicit-def renamable $agpr48_agpr49_agpr50_agpr51_agpr52_agpr53_agpr54_agpr55_agpr56_agpr57_agpr58_agpr59_agpr60_agpr61_agpr62_agpr63
+ ; CHECK-NEXT: early-clobber renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = V_MFMA_F32_32X32X8F16_vgprcd_e64 $vgpr18_vgpr19, $vgpr18_vgpr19, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, 0, 0, 0, implicit $mode, implicit $exec
+ ; CHECK-NEXT: S_NOP 0, implicit killed renamable $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15, implicit killed renamable $agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31, implicit killed renamable $agpr32_agpr33_agpr34_agpr35_agpr36_agpr37_agpr38_agpr39_agpr40_agpr41_agpr42_agpr43_agpr44_agpr45_agpr46_agpr47, implicit killed renamable $agpr48_agpr49_agpr50_agpr51_agpr52_agpr53_agpr54_agpr55_agpr56_agpr57_agpr58_agpr59_agpr60_agpr61_agpr62_agpr63
+ ; CHECK-NEXT: early-clobber renamable $vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31_vgpr32_vgpr33_vgpr34_vgpr35 = V_MFMA_F32_32X32X8F16_vgprcd_e64 $vgpr18_vgpr19, $vgpr18_vgpr19, killed $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, 0, 0, 0, implicit $mode, implicit $exec
+ ; CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit $vcc
+ ; CHECK-NEXT: S_BRANCH %bb.2
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: bb.2:
+ ; CHECK-NEXT: liveins: $vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31_vgpr32_vgpr33_vgpr34_vgpr35:0x00000000FFFFFFFF
+ ; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+ ; CHECK-NEXT: renamable $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15 = COPY killed renamable $vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31_vgpr32_vgpr33_vgpr34_vgpr35
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55
+ ; CHECK-NEXT: S_NOP 0, implicit-def $vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63
+ ; CHECK-NEXT: renamable $vgpr0 = V_MOV_B32_e32 0, implicit $exec
+ ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR renamable $vgpr0, renamable $agpr8_agpr9_agpr10_agpr11, undef $sgpr0_sgpr1, 32, 0, implicit $exec :: (store (s128), align 32, addrspace 1)
+ ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR renamable $vgpr0, renamable $agpr12_agpr13_agpr14_agpr15, undef $sgpr0_sgpr1, 48, 0, implicit $exec :: (store (s128), addrspace 1)
+ ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR renamable $vgpr0, renamable $agpr0_agpr1_agpr2_agpr3, undef $sgpr0_sgpr1, 0, 0, implicit $exec :: (store (s128), align 128, addrspace 1)
+ ; CHECK-NEXT: GLOBAL_STORE_DWORDX4_SADDR killed renamable $vgpr0, killed renamable $agpr4_agpr5_agpr6_agpr7, killed undef $sgpr0_sgpr1, 16, 0, implicit $exec :: (store (s128), addrspace 1)
+ ; CHECK-NEXT: S_ENDPGM 0
+ bb.0:
+ S_NOP 0, implicit-def $agpr0
+ renamable $sgpr0 = S_MOV_B32 0
+ undef %0.sub8:vreg_512_align2 = V_MOV_B32_e32 0, implicit $exec
+ renamable $sgpr1 = COPY renamable $sgpr0
+ %1:vreg_64_align2 = COPY killed renamable $sgpr0_sgpr1
+ renamable $vcc = S_AND_B64 $exec, -1, implicit-def dead $scc
+ %0.sub9:vreg_512_align2 = COPY %0.sub8
+
+ bb.1:
+ liveins: $vcc
+
+ undef %0.sub0_sub1:vreg_512_align2 = GLOBAL_LOAD_DWORDX2 undef %2:vreg_64_align2, 0, 0, implicit $exec :: (load (s64), addrspace 1)
+ S_NOP 0, implicit-def %6:areg_512_align2, implicit-def %7:areg_512_align2, implicit-def %8:areg_512_align2, implicit-def %9:areg_512_align2
+ %3:vreg_512_align2 = V_MFMA_F32_32X32X8F16_vgprcd_e64 %1, %1, %0, 0, 0, 0, implicit $mode, implicit $exec
+ S_NOP 0, implicit %6, implicit %7, implicit %8, implicit %9
+ %4:vreg_512_align2 = V_MFMA_F32_32X32X8F16_vgprcd_e64 %1, %1, %3, 0, 0, 0, implicit $mode, implicit $exec
+ S_CBRANCH_VCCNZ %bb.1, implicit $vcc
+ S_BRANCH %bb.2
+
+ bb.2:
+ ; No VGPRs available for %0 or %4
+ S_NOP 0, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
+ S_NOP 0, implicit-def $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+ S_NOP 0, implicit-def $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23
+ S_NOP 0, implicit-def $vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31
+ S_NOP 0, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39
+ S_NOP 0, implicit-def $vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47
+ S_NOP 0, implicit-def $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55
+ S_NOP 0, implicit-def $vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63
+ %5:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
+ GLOBAL_STORE_DWORDX4_SADDR %5, %4.su...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/152434
More information about the llvm-commits
mailing list