llvm/test/CodeGen/AMDGPU/si-fold-operands-bundle.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 6
# RUN: llc -mtriple=amdgcn -mcpu=gfx908 -run-pass=si-fold-operands -o - %s | FileCheck %s

# When SIFoldOperands folds a COPY source into a use inside a BUNDLE, it
# must also update the BUNDLE header's matching implicit operand.
# Without it, for example after folding %5.sub1 into the bundle
#
#   %8:vgpr_32 = COPY killed %5.sub1:vreg_128
#   BUNDLE implicit killed %8:vgpr_32, ... {
#     DS_GWS_INIT %5.sub1:vreg_128, ...
#   }
#
# the header still uses %8, so the COPY can't be deleted. Its `killed %5.sub1`
# is now stale and MachineVerifier reports "Using a killed virtual register".
# Updating the header's implicit operand from %8 to %5.sub1 lets the dead-COPY
# cleanup remove the COPY and its stale kill flag.


---
name: fold_into_bundled_use
tracksRegLiveness: true
body: |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3

    ; CHECK-LABEL: name: fold_into_bundled_use
    ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
    ; CHECK-NEXT: {{  $}}
    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
    ; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
    ; CHECK-NEXT: $m0 = S_MOV_B32 0
    ; CHECK-NEXT: BUNDLE implicit [[REG_SEQUENCE]].sub0, implicit $m0, implicit $exec :: (store (s32) into custom "GWSResource") {
    ; CHECK-NEXT:   DS_GWS_INIT [[REG_SEQUENCE]].sub0, 0, implicit $m0, implicit $exec :: (store (s32) into custom "GWSResource")
    ; CHECK-NEXT:   S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
    ; CHECK-NEXT: }
    ; CHECK-NEXT: BUNDLE implicit [[REG_SEQUENCE]].sub1, implicit $m0, implicit $exec :: (store (s32) into custom "GWSResource") {
    ; CHECK-NEXT:   DS_GWS_INIT [[REG_SEQUENCE]].sub1, 0, implicit $m0, implicit $exec :: (store (s32) into custom "GWSResource")
    ; CHECK-NEXT:   S_WAITCNT .Vmcnt_0_Expcnt_0_Lgkmcnt_0
    ; CHECK-NEXT: }
    ; CHECK-NEXT: S_ENDPGM 0
    %0:vgpr_32 = COPY $vgpr0
    %1:vgpr_32 = COPY $vgpr1
    %2:vgpr_32 = COPY $vgpr2
    %3:vgpr_32 = COPY $vgpr3
    %4:vreg_128 = REG_SEQUENCE %0:vgpr_32, %subreg.sub0, %1:vgpr_32, %subreg.sub1, %2:vgpr_32, %subreg.sub2, %3:vgpr_32, %subreg.sub3
    %5:vgpr_32 = COPY %4.sub0:vreg_128
    %6:vgpr_32 = COPY %4.sub1:vreg_128
    $m0 = S_MOV_B32 0
    BUNDLE implicit %5:vgpr_32, implicit $m0, implicit $exec :: (store (s32) into custom "GWSResource") {
      DS_GWS_INIT %5:vgpr_32, 0, implicit $m0, implicit $exec :: (store (s32) into custom "GWSResource")
      S_WAITCNT 0
    }
    BUNDLE implicit %6:vgpr_32, implicit $m0, implicit $exec :: (store (s32) into custom "GWSResource") {
      DS_GWS_INIT %6:vgpr_32, 0, implicit $m0, implicit $exec :: (store (s32) into custom "GWSResource")
      S_WAITCNT 0
    }
    S_ENDPGM 0
...