[llvm] AMDGPU: Fix asserting on non-register mfma src2 (PR #150552)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Thu Jul 24 16:55:36 PDT 2025


https://github.com/arsenm created https://github.com/llvm/llvm-project/pull/150552

Also validate the subregister, although for the moment this
is redundant since we currently only process full copies.

>From 5ff0ad39041219eaed85728a6794de6be43b30c5 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault at amd.com>
Date: Fri, 25 Jul 2025 00:25:20 +0900
Subject: [PATCH] AMDGPU: Fix asserting on non-register mfma src2

Also validate the subregister, although for the moment this
is redundant since we currently only process full copies.
---
 .../AMDGPU/AMDGPURewriteAGPRCopyMFMA.cpp      |   3 +-
 ...class-vgpr-mfma-to-agpr-negative-tests.mir | 178 ++++++++++++++++++
 ...class-vgpr-mfma-to-av-with-load-source.mir |  90 +++++++++
 3 files changed, 270 insertions(+), 1 deletion(-)

diff --git a/llvm/lib/Target/AMDGPU/AMDGPURewriteAGPRCopyMFMA.cpp b/llvm/lib/Target/AMDGPU/AMDGPURewriteAGPRCopyMFMA.cpp
index a8e1967116d19..f580f4368110f 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPURewriteAGPRCopyMFMA.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURewriteAGPRCopyMFMA.cpp
@@ -159,7 +159,8 @@ bool AMDGPURewriteAGPRCopyMFMAImpl::run(MachineFunction &MF) const {
 
       // If the inputs are tied and the same register, we can shortcut and
       // directly replace the register.
-      if (Src2->getReg() != CopySrcReg) {
+      if (!Src2->isReg() || Src2->getReg() != CopySrcReg ||
+          Src2->getSubReg() != DefMI->getOperand(1).getSubReg()) {
         LLVM_DEBUG(
             dbgs()
             << "Replacing untied VGPR MFMAs with AGPR form not yet handled\n");
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 cf1546625b80c..c7767cb832078 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
@@ -16,6 +16,14 @@
     ret void
   }
 
+  define amdgpu_kernel void @inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_imm_src2() #0 {
+    ret void
+  }
+
+  define amdgpu_kernel void @inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_src2_different_subreg() #0 {
+    ret void
+  }
+
   attributes #0 = { "amdgpu-wave-limiter"="true" "amdgpu-waves-per-eu"="8,8" }
 ...
 
@@ -311,3 +319,173 @@ body:             |
     $agpr0 = COPY %0
 
 ...
+
+# Non-mac variant, src2 is an immediate.
+---
+name:            inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_imm_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_imm_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, 0, 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, 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
+    %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 $exec :: (store (s128), addrspace 1)
+    S_ENDPGM 0
+
+...
+
+# Non-mac variant, src2 is the same VGPR, but a different subregister.
+---
+name:            inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_src2_different_subreg
+tracksRegLiveness: true
+machineFunctionInfo:
+  isEntryFunction: true
+  stackPtrOffsetReg: '$sgpr32'
+  occupancy:       10
+  sgprForEXECCopy: '$sgpr100_sgpr101'
+body:             |
+  ; CHECK-LABEL: name: inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_vgprcd_e64_src2_different_subreg
+  ; 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 $vgpr0_vgpr1 = GLOBAL_LOAD_DWORDX2 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s64), addrspace 1)
+  ; CHECK-NEXT:   renamable $vgpr16_vgpr17 = GLOBAL_LOAD_DWORDX2 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s64), addrspace 1)
+  ; 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:   renamable $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15 = COPY killed renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15
+  ; CHECK-NEXT:   S_CBRANCH_VCCNZ %bb.1, implicit $vcc
+  ; CHECK-NEXT:   S_BRANCH %bb.2
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2:
+  ; CHECK-NEXT:   liveins: $agpr0_agpr1_agpr2_agpr3_agpr4_agpr5_agpr6_agpr7_agpr8_agpr9_agpr10_agpr11_agpr12_agpr13_agpr14_agpr15_agpr16_agpr17_agpr18_agpr19_agpr20_agpr21_agpr22_agpr23_agpr24_agpr25_agpr26_agpr27_agpr28_agpr29_agpr30_agpr31:0x00000000FFFFFFFF
+  ; 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:   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_1024_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_1024_align2 = COPY %0.sub8
+
+  bb.1:
+    liveins: $vcc
+
+    undef %0.sub0_sub1:vreg_1024_align2 = GLOBAL_LOAD_DWORDX2 undef %3:vreg_64_align2, 0, 0, implicit $exec :: (load (s64), addrspace 1)
+    %0.sub16_sub17:vreg_1024_align2 = GLOBAL_LOAD_DWORDX2 undef %3:vreg_64_align2, 0, 0, implicit $exec :: (load (s64), addrspace 1)
+    %0.sub0_sub1_sub2_sub3_sub4_sub5_sub6_sub7_sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15:vreg_1024_align2 = V_MFMA_F32_32X32X8F16_vgprcd_e64 %1, %1, %0.sub16_sub17_sub18_sub19_sub20_sub21_sub22_sub23_sub24_sub25_sub26_sub27_sub28_sub29_sub30_sub31, 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
+
+...
diff --git a/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-av-with-load-source.mir b/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-av-with-load-source.mir
index 87184018be942..b907c134d06b1 100644
--- a/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-av-with-load-source.mir
+++ b/llvm/test/CodeGen/AMDGPU/inflate-reg-class-vgpr-mfma-to-av-with-load-source.mir
@@ -970,3 +970,93 @@ body:             |
     S_ENDPGM 0
 
 ...
+
+---
+name:            inflate_result_to_agpr__V_MFMA_F32_32X32X8F16_mac_vgprcd_e64_same_subreg
+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_same_subreg
+  ; 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 $vgpr10 = 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:   renamable $vgpr11 = COPY renamable $vgpr10
+  ; 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_vgpr4_vgpr5 = GLOBAL_LOAD_DWORDX4 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s128), addrspace 1)
+  ; CHECK-NEXT:   renamable $vgpr6_vgpr7_vgpr8_vgpr9 = GLOBAL_LOAD_DWORDX4 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s128), addrspace 1)
+  ; CHECK-NEXT:   renamable $vgpr10_vgpr11_vgpr12_vgpr13 = GLOBAL_LOAD_DWORDX4 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s128), addrspace 1)
+  ; CHECK-NEXT:   renamable $vgpr14_vgpr15_vgpr16_vgpr17 = GLOBAL_LOAD_DWORDX4 undef renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (load (s128), 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:   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_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31_vgpr32_vgpr33:0x00000000FFFFFFFF
+  ; 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_1024_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_1024_align2 = COPY %0.sub8
+
+  bb.1:
+    liveins: $vcc
+
+    %0.sub0_sub1_sub2_sub3:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4 undef %3:vreg_64_align2, 0, 0, implicit $exec :: (load (s128), addrspace 1)
+    %0.sub4_sub5_sub6_sub7:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4 undef %3:vreg_64_align2, 0, 0, implicit $exec :: (load (s128), addrspace 1)
+    %0.sub8_sub9_sub10_sub11:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4 undef %3:vreg_64_align2, 0, 0, implicit $exec :: (load (s128), addrspace 1)
+    %0.sub12_sub13_sub14_sub15:vreg_1024_align2 = GLOBAL_LOAD_DWORDX4 undef %3:vreg_64_align2, 0, 0, implicit $exec :: (load (s128), addrspace 1)
+    %0.sub0_sub1_sub2_sub3_sub4_sub5_sub6_sub7_sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15:vreg_1024_align2 = V_MFMA_F32_32X32X8F16_mac_vgprcd_e64 %1, %1, %0.sub0_sub1_sub2_sub3_sub4_sub5_sub6_sub7_sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15, 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
+
+...



More information about the llvm-commits mailing list