llvm-project/llvm/test/CodeGen/AMDGPU/omod-nsz-flag.mir

72 lines
1.8 KiB
YAML

# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-fold-operands %s -o - | FileCheck -check-prefix=GCN %s
--- |
define amdgpu_ps void @omod_inst_flag_nsz_src() {
unreachable
}
define amdgpu_ps void @omod_inst_flag_nsz_result() {
unreachable
}
define amdgpu_ps void @omod_inst_flag_nsz_both() {
unreachable
}
...
---
# FIXME: Is it OK to fold omod for this?
# GCN-LABEL: name: omod_inst_flag_nsz_src
# GCN: %0:vgpr_32 = nsz V_ADD_F32_e64 0, $vgpr0, 0, $vgpr1, 0, 0, implicit $exec
# GCN-NEXT: %1:vgpr_32 = V_MUL_F32_e64 0, %0, 0, 1073741824, 0, 0, implicit $exec
# GCN-NEXT: S_ENDPGM implicit %1
name: omod_inst_flag_nsz_src
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1
%0:vgpr_32 = nsz V_ADD_F32_e64 0, $vgpr0, 0, $vgpr1, 0, 0, implicit $exec
%1:vgpr_32 = V_MUL_F32_e64 0, %0, 0, 1073741824, 0, 0, implicit $exec
S_ENDPGM implicit %1
...
---
# GCN-LABEL: name: omod_inst_flag_nsz_result
# GCN: %0:vgpr_32 = V_ADD_F32_e64 0, $vgpr0, 0, $vgpr1, 0, 1, implicit $exec
# GCN-NEXT: S_ENDPGM implicit %0
name: omod_inst_flag_nsz_result
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1
%0:vgpr_32 = V_ADD_F32_e64 0, $vgpr0, 0, $vgpr1, 0, 0, implicit $exec
%1:vgpr_32 = nsz V_MUL_F32_e64 0, %0, 0, 1073741824, 0, 0, implicit $exec
S_ENDPGM implicit %1
...
---
# GCN-LABEL: name: omod_inst_flag_nsz_both
# GCN: %0:vgpr_32 = nsz V_ADD_F32_e64 0, $vgpr0, 0, $vgpr1, 0, 1, implicit $exec
# GCN-NEXT: S_ENDPGM implicit %0
name: omod_inst_flag_nsz_both
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1
%0:vgpr_32 = nsz V_ADD_F32_e64 0, $vgpr0, 0, $vgpr1, 0, 0, implicit $exec
%1:vgpr_32 = nsz V_MUL_F32_e64 0, %0, 0, 1073741824, 0, 0, implicit $exec
S_ENDPGM implicit %1
...