llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-trunc.v2s16.mir

66 lines
3.2 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=tahiti -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX6 %s
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX8 %s
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX8 %s
---
name: trunc_sgpr_v2s32_to_v2s16
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $sgpr0_sgpr1
; GFX6-LABEL: name: trunc_sgpr_v2s32_to_v2s16
; GFX6: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
; GFX6: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
; GFX6: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; GFX6: [[S_LSHL_B32_:%[0-9]+]]:sreg_32 = S_LSHL_B32 [[COPY2]], 16, implicit-def $scc
; GFX6: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 65535
; GFX6: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def $scc
; GFX6: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[S_LSHL_B32_]], [[S_AND_B32_]], implicit-def $scc
; GFX6: S_ENDPGM 0, implicit [[S_OR_B32_]]
; GFX8-LABEL: name: trunc_sgpr_v2s32_to_v2s16
; GFX8: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
; GFX8: [[COPY1:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub0
; GFX8: [[COPY2:%[0-9]+]]:sreg_32 = COPY [[COPY]].sub1
; GFX8: [[S_LSHL_B32_:%[0-9]+]]:sreg_32 = S_LSHL_B32 [[COPY2]], 16, implicit-def $scc
; GFX8: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 65535
; GFX8: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 [[COPY1]], [[S_MOV_B32_]], implicit-def $scc
; GFX8: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 [[S_LSHL_B32_]], [[S_AND_B32_]], implicit-def $scc
; GFX8: S_ENDPGM 0, implicit [[S_OR_B32_]]
%0:sgpr(<2 x s32>) = COPY $sgpr0_sgpr1
%1:sgpr(<2 x s16>) = G_TRUNC %0
S_ENDPGM 0, implicit %1
...
---
name: trunc_vgpr_v2s32_to_v2s16
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $vgpr0_vgpr1
; GFX6-LABEL: name: trunc_vgpr_v2s32_to_v2s16
; GFX6: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX6: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
; GFX6: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
; GFX6: [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 16, [[COPY2]], implicit $exec
; GFX6: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 65535, implicit $exec
; GFX6: [[V_AND_B32_e64_:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 [[COPY1]], [[V_MOV_B32_e32_]], implicit $exec
; GFX6: [[V_OR_B32_e64_:%[0-9]+]]:vgpr_32 = V_OR_B32_e64 [[V_LSHLREV_B32_e64_]], [[V_AND_B32_e64_]], implicit $exec
; GFX6: S_ENDPGM 0, implicit [[V_OR_B32_e64_]]
; GFX8-LABEL: name: trunc_vgpr_v2s32_to_v2s16
; GFX8: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
; GFX8: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
; GFX8: [[V_MOV_B32_sdwa:%[0-9]+]]:vgpr_32 = V_MOV_B32_sdwa 0, [[COPY2]], 0, 5, 2, 4, implicit $exec, implicit [[COPY1]](tied-def 0)
; GFX8: S_ENDPGM 0, implicit [[V_MOV_B32_sdwa]]
%0:vgpr(<2 x s32>) = COPY $vgpr0_vgpr1
%1:vgpr(<2 x s16>) = G_TRUNC %0
S_ENDPGM 0, implicit %1
...