llvm-project/llvm/test/CodeGen/AMDGPU/fold-vgpr-copy.mir

54 lines
1.8 KiB
YAML

# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=si-fold-operands,dead-mi-elimination -verify-machineinstrs %s -o - | FileCheck -check-prefix=GCN %s
# GCN-LABEL: name: fold_vgpr_to_vgpr_copy
# GCN: %0:vreg_64 = IMPLICIT_DEF
# GCN-NEXT: %1:vgpr_32 = IMPLICIT_DEF
# GCN-NEXT: %2:vgpr_32 = IMPLICIT_DEF
# GCN-NEXT: DS_WRITE2_B32_gfx9 %0.sub0, killed %1, killed %2, 0, 1, 0, implicit $exec
---
name: fold_vgpr_to_vgpr_copy
body: |
bb.0:
%0:vreg_64 = IMPLICIT_DEF
%4:vgpr_32 = IMPLICIT_DEF
%3:vgpr_32 = IMPLICIT_DEF
%1:vgpr_32 = COPY %0.sub0
%2:vgpr_32 = COPY %1
DS_WRITE2_B32_gfx9 %2, killed %4, killed %3, 0, 1, 0, implicit $exec
...
# GCN-LABEL: name: fold_sgpr_to_vgpr_copy
# GCN: %0:sreg_64 = IMPLICIT_DEF
# GCN-NEXT: %1:vgpr_32 = IMPLICIT_DEF
# GCN-NEXT: %2:vgpr_32 = IMPLICIT_DEF
# GCN-NEXT: %4:vgpr_32 = COPY %0.sub0
# GCN-NEXT: DS_WRITE2_B32_gfx9 %4, killed %1, killed %2, 0, 1, 0, implicit $exec
name: fold_sgpr_to_vgpr_copy
body: |
bb.0:
%0:sreg_64 = IMPLICIT_DEF
%4:vgpr_32 = IMPLICIT_DEF
%3:vgpr_32 = IMPLICIT_DEF
%1:sgpr_32 = COPY %0.sub0
%2:vgpr_32 = COPY %1
DS_WRITE2_B32_gfx9 %2, killed %4, killed %3, 0, 1, 0, implicit $exec
...
# GCN-LABEL: name: fma_sgpr_use
# GCN: %0:sreg_64_xexec = IMPLICIT_DEF
# GCN-NEXT: %4:vgpr_32 = nnan ninf nsz arcp contract afn reassoc V_FMA_F32 2, %0.sub0, 0, 1073741824, 0, %0.sub1, 0, 0, implicit $exec
---
name: fma_sgpr_use
body: |
bb.0:
%0:sreg_64_xexec = IMPLICIT_DEF
%1:sgpr_32 = COPY %0.sub0
%2:sgpr_32 = COPY %0.sub1
%3:vgpr_32 = COPY %2
%4:vgpr_32 = nnan ninf nsz arcp contract afn reassoc V_FMAC_F32_e64 2, %1, 0, 1073741824, 0, %3, 0, 0, implicit $exec
DS_WRITE2_B32_gfx9 undef %5:vgpr_32, killed %4, undef %6:vgpr_32, 0, 1, 0, implicit $exec
...