Files
clang-p2996/llvm/test/CodeGen/AMDGPU/fold-sgpr-copy.mir
Stanislav Mekhanoshin 3bffb1cd0e [AMDGPU] Use single cache policy operand
Replace individual operands GLC, SLC, and DLC with a single cache_policy
bitmask operand. This will reduce the number of operands in MIR and I hope
the amount of code. These operands are mostly 0 anyway.

Additional advantage that parser will accept these flags in any order unlike
now.

Differential Revision: https://reviews.llvm.org/D96469
2021-03-15 13:00:59 -07:00

49 lines
1.3 KiB
YAML

# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=si-fold-operands,dead-mi-elimination -verify-machineinstrs %s -o - | FileCheck -check-prefix=GCN %s
---
# GCN-LABEL: name: fold_sgpr_to_sgpr_copy_full
# GCN: %0:sgpr_32 = IMPLICIT_DEF
# GCN-NEXT: S_STORE_DWORD_IMM %0, undef $sgpr10_sgpr11, 0, 0
name: fold_sgpr_to_sgpr_copy_full
body: |
bb.0:
%0:sgpr_32 = IMPLICIT_DEF
%1:sgpr_32 = COPY %0
%2:sgpr_32 = COPY %1
S_STORE_DWORD_IMM %2, undef $sgpr10_sgpr11, 0, 0
...
# GCN-LABEL: name: fold_sgpr_to_sgpr_copy_subreg
# GCN: %0:sreg_64 = IMPLICIT_DEF
# GCN-NEXT: %2:sgpr_32 = COPY %0.sub0
# GCN-NEXT: S_STORE_DWORD_IMM %2, undef $sgpr10_sgpr11, 0, 0
name: fold_sgpr_to_sgpr_copy_subreg
body: |
bb.0:
%0:sreg_64 = IMPLICIT_DEF
%1:sgpr_32 = COPY %0.sub0
%2:sgpr_32 = COPY %1
S_STORE_DWORD_IMM %2, undef $sgpr10_sgpr11, 0, 0
...
# GCN-LABEL: name: fold_sgpr_to_sgpr_copy_subreg2
# GCN: %0:sreg_64 = IMPLICIT_DEF
# GCN-NEXT: %3:sreg_32_xm0_xexec = COPY %0.sub0
# GCN-NEXT: S_STORE_DWORD_IMM %3, undef $sgpr10_sgpr11, 0, 0
name: fold_sgpr_to_sgpr_copy_subreg2
body: |
bb.0:
%0:sreg_64 = IMPLICIT_DEF
%1:sgpr_32 = COPY %0.sub0
%2:sgpr_32 = COPY %1
%3:sreg_32_xm0_xexec = COPY %2
S_STORE_DWORD_IMM %3, undef $sgpr10_sgpr11, 0, 0
...