llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-atomic-cmpxchg-...

174 lines
8.7 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 -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX6 %s
# RUN: llc -march=amdgcn -mcpu=hawaii -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX7 %s
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX7 %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
---
name: atomic_cmpxchg_s32_local
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: atomic_cmpxchg_s32_local
; GFX6: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX6: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_CMPST_RTN_B32_:%[0-9]+]]:vgpr_32 = DS_CMPST_RTN_B32 [[COPY]], [[COPY1]], [[COPY2]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_CMPST_RTN_B32_]]
; GFX7-LABEL: name: atomic_cmpxchg_s32_local
; GFX7: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_CMPST_RTN_B32_:%[0-9]+]]:vgpr_32 = DS_CMPST_RTN_B32 [[COPY]], [[COPY1]], [[COPY2]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_CMPST_RTN_B32_]]
; GFX9-LABEL: name: atomic_cmpxchg_s32_local
; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX9: [[DS_CMPST_RTN_B32_gfx9_:%[0-9]+]]:vgpr_32 = DS_CMPST_RTN_B32_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 0, 0, implicit $exec :: (load store seq_cst 4, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_CMPST_RTN_B32_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = COPY $vgpr2
%3:vgpr(s32) = G_ATOMIC_CMPXCHG %0, %1, %2 :: (load store seq_cst 4, addrspace 3)
$vgpr0 = COPY %3
...
---
name: atomic_cmpxchg_s32_local_gep4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: atomic_cmpxchg_s32_local_gep4
; GFX6: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX6: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX6: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4, implicit $exec
; GFX6: %4:vgpr_32, dead %6:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_CMPST_RTN_B32_:%[0-9]+]]:vgpr_32 = DS_CMPST_RTN_B32 %4, [[COPY1]], [[COPY2]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3)
; GFX6: $vgpr0 = COPY [[DS_CMPST_RTN_B32_]]
; GFX7-LABEL: name: atomic_cmpxchg_s32_local_gep4
; GFX7: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX7: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_CMPST_RTN_B32_:%[0-9]+]]:vgpr_32 = DS_CMPST_RTN_B32 [[COPY]], [[COPY1]], [[COPY2]], 4, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3)
; GFX7: $vgpr0 = COPY [[DS_CMPST_RTN_B32_]]
; GFX9-LABEL: name: atomic_cmpxchg_s32_local_gep4
; GFX9: liveins: $vgpr0, $vgpr1, $vgpr2
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX9: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX9: [[DS_CMPST_RTN_B32_gfx9_:%[0-9]+]]:vgpr_32 = DS_CMPST_RTN_B32_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 4, 0, implicit $exec :: (load store seq_cst 4, addrspace 3)
; GFX9: $vgpr0 = COPY [[DS_CMPST_RTN_B32_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(s32) = COPY $vgpr2
%3:vgpr(s32) = G_CONSTANT i32 4
%4:vgpr(p3) = G_PTR_ADD %0, %3
%5:vgpr(s32) = G_ATOMIC_CMPXCHG %4, %1, %2 :: (load store seq_cst 4, addrspace 3)
$vgpr0 = COPY %5
...
---
name: atomic_cmpxchg_s64_local
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
; GFX6-LABEL: name: atomic_cmpxchg_s64_local
; GFX6: liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr1_vgpr2
; GFX6: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3_vgpr4
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_CMPST_RTN_B64_:%[0-9]+]]:vreg_64 = DS_CMPST_RTN_B64 [[COPY]], [[COPY1]], [[COPY2]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 8, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[DS_CMPST_RTN_B64_]]
; GFX7-LABEL: name: atomic_cmpxchg_s64_local
; GFX7: liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr1_vgpr2
; GFX7: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3_vgpr4
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_CMPST_RTN_B64_:%[0-9]+]]:vreg_64 = DS_CMPST_RTN_B64 [[COPY]], [[COPY1]], [[COPY2]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 8, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[DS_CMPST_RTN_B64_]]
; GFX9-LABEL: name: atomic_cmpxchg_s64_local
; GFX9: liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr1_vgpr2
; GFX9: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3_vgpr4
; GFX9: [[DS_CMPST_RTN_B64_gfx9_:%[0-9]+]]:vreg_64 = DS_CMPST_RTN_B64_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 0, 0, implicit $exec :: (load store seq_cst 8, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[DS_CMPST_RTN_B64_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s64) = COPY $vgpr1_vgpr2
%2:vgpr(s64) = COPY $vgpr3_vgpr4
%3:vgpr(s64) = G_ATOMIC_CMPXCHG %0, %1, %2 :: (load store seq_cst 8, addrspace 3)
$vgpr0_vgpr1 = COPY %3
...
---
name: atomic_cmpxchg_s64_local_gep4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
; GFX6-LABEL: name: atomic_cmpxchg_s64_local_gep4
; GFX6: liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr1_vgpr2
; GFX6: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3_vgpr4
; GFX6: $m0 = S_MOV_B32 -1
; GFX6: [[DS_CMPST_RTN_B64_:%[0-9]+]]:vreg_64 = DS_CMPST_RTN_B64 [[COPY]], [[COPY1]], [[COPY2]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 8, addrspace 3)
; GFX6: $vgpr0_vgpr1 = COPY [[DS_CMPST_RTN_B64_]]
; GFX7-LABEL: name: atomic_cmpxchg_s64_local_gep4
; GFX7: liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX7: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr1_vgpr2
; GFX7: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3_vgpr4
; GFX7: $m0 = S_MOV_B32 -1
; GFX7: [[DS_CMPST_RTN_B64_:%[0-9]+]]:vreg_64 = DS_CMPST_RTN_B64 [[COPY]], [[COPY1]], [[COPY2]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 8, addrspace 3)
; GFX7: $vgpr0_vgpr1 = COPY [[DS_CMPST_RTN_B64_]]
; GFX9-LABEL: name: atomic_cmpxchg_s64_local_gep4
; GFX9: liveins: $vgpr0, $vgpr1_vgpr2, $vgpr3_vgpr4
; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr1_vgpr2
; GFX9: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr3_vgpr4
; GFX9: [[DS_CMPST_RTN_B64_gfx9_:%[0-9]+]]:vreg_64 = DS_CMPST_RTN_B64_gfx9 [[COPY]], [[COPY1]], [[COPY2]], 0, 0, implicit $exec :: (load store seq_cst 8, addrspace 3)
; GFX9: $vgpr0_vgpr1 = COPY [[DS_CMPST_RTN_B64_gfx9_]]
%0:vgpr(p3) = COPY $vgpr0
%1:vgpr(s64) = COPY $vgpr1_vgpr2
%2:vgpr(s64) = COPY $vgpr3_vgpr4
%3:vgpr(s32) = G_CONSTANT i32 4
%4:vgpr(p3) = G_PTR_ADD %0, %3
%5:vgpr(s64) = G_ATOMIC_CMPXCHG %0, %1, %2 :: (load store seq_cst 8, addrspace 3)
$vgpr0_vgpr1 = COPY %5
...