1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
llvm-mirror/test/CodeGen/AMDGPU/fold-sgpr-copy.mir
Stanislav Mekhanoshin 40bb4ec570 [AMDGPU] Enable SGPR copy folding
That used to fail in the last testcase function because after
%0:sreg_64.sub0 was folded into %3:sreg_32_xm0_xexec COPY, it
was further folded into S_STORE_DWORD_IMM. Its legal effective
subreg class is SReg_32 while instruction expects more restricted
SReg_32_XM0_EXEC. However, SIInstrInfo::isLegalRegOperand()
passed the legality check and it was caught in the verifier.

Borrowed code from the verifier to check for RC legality.

Differential Revision: https://reviews.llvm.org/D69445
2019-10-25 15:08:30 -07:00

49 lines
1.4 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, 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, 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, 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, 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, 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, 0
...