llvm-project/llvm/test/CodeGen/AMDGPU/sdwa-gfx9.mir

89 lines
3.4 KiB
YAML

# RUN: llc -march=amdgcn -mcpu=kaveri -run-pass=si-peephole-sdwa -o - %s | FileCheck -check-prefix=CI -check-prefix=GCN %s
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=si-peephole-sdwa -o - %s | FileCheck -check-prefix=VI -check-prefix=GCN %s
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=si-peephole-sdwa -o - %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
# GCN-LABEL: {{^}}name: add_shr_i32
# GCN: [[SMOV:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 123
# CI: [[SHIFT:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 16, %{{[0-9]+}}, implicit $exec
# CI: %{{[0-9]+}}:vgpr_32 = V_ADD_I32_e32 [[SMOV]], killed [[SHIFT]], implicit-def $vcc, implicit $exec
# VI: [[VMOV:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 [[SMOV]], implicit $exec
# VI: %{{[0-9]+}}:vgpr_32 = V_ADD_I32_sdwa 0, [[VMOV]], 0, %{{[0-9]+}}, 0, 6, 0, 6, 5, implicit-def $vcc, implicit $exec
# GFX9: %{{[0-9]+}}:vgpr_32 = V_ADD_I32_sdwa 0, [[SMOV]], 0, %{{[0-9]+}}, 0, 6, 0, 6, 5, implicit-def $vcc, implicit $exec
---
name: add_shr_i32
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_64 }
- { id: 1, class: vreg_64 }
- { id: 2, class: sreg_64 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_32_xm0 }
- { id: 5, class: sreg_32_xm0 }
- { id: 6, class: sreg_32 }
- { id: 7, class: sreg_32_xm0 }
- { id: 8, class: sreg_32 }
- { id: 9, class: vgpr_32 }
- { id: 10, class: vgpr_32 }
- { id: 11, class: vgpr_32 }
- { id: 12, class: sreg_32_xm0 }
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $sgpr30_sgpr31
%2 = COPY $sgpr30_sgpr31
%1 = COPY $vgpr2_vgpr3
%0 = COPY $vgpr0_vgpr1
%3 = FLAT_LOAD_DWORD %1, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4)
%12 = S_MOV_B32 123
%10 = V_LSHRREV_B32_e64 16, %3, implicit $exec
%11 = V_ADD_I32_e32 %12, killed %10, implicit-def $vcc, implicit $exec
FLAT_STORE_DWORD %0, %11, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4)
$sgpr30_sgpr31 = COPY %2
S_SETPC_B64_return $sgpr30_sgpr31
...
# GCN-LABEL: {{^}}name: trunc_shr_f32
# CI: [[SHIFT:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 16, %{{[0-9]+}}, implicit $exec
# CI: %{{[0-9]+}}:vgpr_32 = V_TRUNC_F32_e64 0, killed [[SHIFT]], 1, 2, implicit-def $vcc, implicit $exec
# VI: [[SHIFT:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 16, %{{[0-9]+}}, implicit $exec
# VI: %{{[0-9]+}}:vgpr_32 = V_TRUNC_F32_e64 0, killed [[SHIFT]], 1, 2, implicit-def $vcc, implicit $exec
#GFX9: %{{[0-9]+}}:vgpr_32 = V_TRUNC_F32_sdwa 0, %{{[0-9]+}}, 1, 2, 6, 0, 5, implicit $exec
---
name: trunc_shr_f32
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_64 }
- { id: 1, class: vreg_64 }
- { id: 2, class: sreg_64 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_32_xm0 }
- { id: 5, class: sreg_32_xm0 }
- { id: 6, class: sreg_32 }
- { id: 7, class: sreg_32_xm0 }
- { id: 8, class: sreg_32 }
- { id: 9, class: vgpr_32 }
- { id: 10, class: vgpr_32 }
- { id: 11, class: vgpr_32 }
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $sgpr30_sgpr31
%2 = COPY $sgpr30_sgpr31
%1 = COPY $vgpr2_vgpr3
%0 = COPY $vgpr0_vgpr1
%3 = FLAT_LOAD_DWORD %1, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4)
%10 = V_LSHRREV_B32_e64 16, %3, implicit $exec
%11 = V_TRUNC_F32_e64 0, killed %10, 1, 2, implicit-def $vcc, implicit $exec
FLAT_STORE_DWORD %0, %11, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4)
$sgpr30_sgpr31 = COPY %2
S_SETPC_B64_return $sgpr30_sgpr31