llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-atomicrmw-fadd-...

117 lines
5.6 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX8 %s
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX9 %s
# RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX9 %s
# GFX6/7 selection should fail.
# RUN: llc -march=amdgcn -mcpu=tahiti -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -disable-gisel-legality-check -o - %s | FileCheck -check-prefix=GFX6 %s
# RUN: llc -march=amdgcn -mcpu=hawaii -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -disable-gisel-legality-check -o - %s | FileCheck -check-prefix=GFX6 %s
---
name: atomicrmw_fadd_s32_local
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX8-LABEL: name: atomicrmw_fadd_s32_local
; GFX8: liveins: $vgpr0, $vgpr1
; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX8: $m0 = S_MOV_B32 -1
; GFX8: [[DS_ADD_RTN_F32_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32 [[COPY]], [[COPY1]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst (s32), addrspace 3)
; GFX8: $vgpr0 = COPY [[DS_ADD_RTN_F32_]]
; GFX9-LABEL: name: atomicrmw_fadd_s32_local
; GFX9: liveins: $vgpr0, $vgpr1
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX9: [[DS_ADD_RTN_F32_gfx9_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32_gfx9 [[COPY]], [[COPY1]], 0, 0, implicit $exec :: (load store seq_cst (s32), addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_ADD_RTN_F32_gfx9_]]
; GFX6-LABEL: name: atomicrmw_fadd_s32_local
; GFX6: liveins: $vgpr0, $vgpr1
; GFX6: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[ATOMICRMW_FADD:%[0-9]+]]:vgpr_32(s32) = G_ATOMICRMW_FADD [[COPY]](p3), [[COPY1]] :: (load store seq_cst (s32), addrspace 3)
; GFX6: $vgpr0 = COPY [[ATOMICRMW_FADD]](s32)
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = G_ATOMICRMW_FADD %0(p3), %1 :: (load store seq_cst (s32), addrspace 3)
$vgpr0 = COPY %2
...
---
name: atomicrmw_fadd_s32_local_noret
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX8-LABEL: name: atomicrmw_fadd_s32_local_noret
; GFX8: liveins: $vgpr0, $vgpr1
; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX8: $m0 = S_MOV_B32 -1
; GFX8: [[DS_ADD_RTN_F32_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32 [[COPY]], [[COPY1]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst (s32), addrspace 3)
; GFX9-LABEL: name: atomicrmw_fadd_s32_local_noret
; GFX9: liveins: $vgpr0, $vgpr1
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX9: [[DS_ADD_RTN_F32_gfx9_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32_gfx9 [[COPY]], [[COPY1]], 0, 0, implicit $exec :: (load store seq_cst (s32), addrspace 3)
; GFX6-LABEL: name: atomicrmw_fadd_s32_local_noret
; GFX6: liveins: $vgpr0, $vgpr1
; GFX6: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[ATOMICRMW_FADD:%[0-9]+]]:vgpr(s32) = G_ATOMICRMW_FADD [[COPY]](p3), [[COPY1]] :: (load store seq_cst (s32), addrspace 3)
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = G_ATOMICRMW_FADD %0(p3), %1 :: (load store seq_cst (s32), addrspace 3)
...
---
name: atomicrmw_fadd_s32_local_gep4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX8-LABEL: name: atomicrmw_fadd_s32_local_gep4
; GFX8: liveins: $vgpr0, $vgpr1
; GFX8: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX8: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX8: $m0 = S_MOV_B32 -1
; GFX8: [[DS_ADD_RTN_F32_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32 [[COPY]], [[COPY1]], 4, 0, implicit $m0, implicit $exec :: (load store seq_cst (s32), addrspace 3)
; GFX8: $vgpr0 = COPY [[DS_ADD_RTN_F32_]]
; GFX9-LABEL: name: atomicrmw_fadd_s32_local_gep4
; GFX9: liveins: $vgpr0, $vgpr1
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX9: [[DS_ADD_RTN_F32_gfx9_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32_gfx9 [[COPY]], [[COPY1]], 4, 0, implicit $exec :: (load store seq_cst (s32), addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_ADD_RTN_F32_gfx9_]]
; GFX6-LABEL: name: atomicrmw_fadd_s32_local_gep4
; GFX6: liveins: $vgpr0, $vgpr1
; GFX6: [[COPY:%[0-9]+]]:vgpr(p3) = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
; GFX6: [[C:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 4
; GFX6: [[PTR_ADD:%[0-9]+]]:vgpr(p3) = G_PTR_ADD [[COPY]], [[C]](s32)
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[ATOMICRMW_FADD:%[0-9]+]]:vgpr_32(s32) = G_ATOMICRMW_FADD [[PTR_ADD]](p3), [[COPY1]] :: (load store seq_cst (s32), addrspace 3)
; GFX6: $vgpr0 = COPY [[ATOMICRMW_FADD]](s32)
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = G_CONSTANT i32 4
%3:vgpr(p3) = G_PTR_ADD %0, %2
%4:vgpr(s32) = G_ATOMICRMW_FADD %3(p3), %1 :: (load store seq_cst (s32), addrspace 3)
$vgpr0 = COPY %4
...