forked from OSchip/llvm-project
64 lines
2.6 KiB
YAML
64 lines
2.6 KiB
YAML
# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck %s
|
|
--- |
|
|
define amdgpu_ps <4 x float> @exp_done_waitcnt(<4 x i32> inreg, <4 x
|
|
i32> inreg, i32 inreg %w, float %v) #0 {
|
|
%a = load volatile float, float addrspace(1)* undef
|
|
%b = load volatile float, float addrspace(1)* undef
|
|
%c = load volatile float, float addrspace(1)* undef
|
|
%d = load volatile float, float addrspace(1)* undef
|
|
call void @llvm.amdgcn.exp.f32(i32 15, i32 1, float %a, float %b, float %c, float %d, i1 true, i1 false)
|
|
ret <4 x float> <float 5.000000e-01, float 1.000000e+00, float 2.000000e+00, float 4.000000e+00>
|
|
}
|
|
|
|
declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #0
|
|
|
|
attributes #0 = { nounwind }
|
|
|
|
...
|
|
---
|
|
|
|
# CHECK-LABEL: name: exp_done_waitcnt{{$}}
|
|
# CHECK: EXP_DONE
|
|
# CHECK-NEXT: S_WAITCNT 3855
|
|
# CHECK: $vgpr0 = V_MOV_B32
|
|
# CHECK: $vgpr1 = V_MOV_B32
|
|
# CHECK: $vgpr2 = V_MOV_B32
|
|
# CHECK: $vgpr3 = V_MOV_B32
|
|
name: exp_done_waitcnt
|
|
alignment: 0
|
|
exposesReturnsTwice: false
|
|
legalized: false
|
|
regBankSelected: false
|
|
selected: false
|
|
tracksRegLiveness: true
|
|
frameInfo:
|
|
isFrameAddressTaken: false
|
|
isReturnAddressTaken: false
|
|
hasStackMap: false
|
|
hasPatchPoint: false
|
|
stackSize: 0
|
|
offsetAdjustment: 0
|
|
maxAlignment: 0
|
|
adjustsStack: false
|
|
hasCalls: false
|
|
maxCallFrameSize: 0
|
|
hasOpaqueSPAdjustment: false
|
|
hasVAStart: false
|
|
hasMustTailInVarArgFunc: false
|
|
body: |
|
|
bb.0 (%ir-block.2):
|
|
$sgpr3 = S_MOV_B32 61440
|
|
$sgpr2 = S_MOV_B32 -1
|
|
$vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, 0, implicit $exec :: (volatile load 4 from `float addrspace(1)* undef`)
|
|
$vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, 0, implicit $exec :: (volatile load 4 from `float addrspace(1)* undef`)
|
|
$vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, 0, implicit $exec :: (volatile load 4 from `float addrspace(1)* undef`)
|
|
$vgpr3 = BUFFER_LOAD_DWORD_OFFSET killed $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, 0, implicit $exec :: (volatile load 4 from `float addrspace(1)* undef`)
|
|
EXP_DONE 0, killed $vgpr0, killed $vgpr1, killed $vgpr2, killed $vgpr3, -1, -1, 15, implicit $exec
|
|
$vgpr0 = V_MOV_B32_e32 1056964608, implicit $exec
|
|
$vgpr1 = V_MOV_B32_e32 1065353216, implicit $exec
|
|
$vgpr2 = V_MOV_B32_e32 1073741824, implicit $exec
|
|
$vgpr3 = V_MOV_B32_e32 1082130432, implicit $exec
|
|
SI_RETURN_TO_EPILOG killed $vgpr0, killed $vgpr1, killed $vgpr2, killed $vgpr3
|
|
|
|
...
|