forked from OSchip/llvm-project
101 lines
5.2 KiB
YAML
101 lines
5.2 KiB
YAML
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -run-pass=none %s -o - | FileCheck --check-prefix=GCN %s
|
|
|
|
--- |
|
|
; ModuleID = '<stdin>'
|
|
source_filename = "<stdin>"
|
|
target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
|
|
target triple = "amdgcn-amd-amdhsa"
|
|
|
|
define void @syncscopes(i32 %agent, i32 addrspace(4)* %agent_out, i32 %workgroup, i32 addrspace(4)* %workgroup_out, i32 %wavefront, i32 addrspace(4)* %wavefront_out) #0 {
|
|
entry:
|
|
store atomic i32 %agent, i32 addrspace(4)* %agent_out syncscope("agent") seq_cst, align 4, !nontemporal !0
|
|
store atomic i32 %workgroup, i32 addrspace(4)* %workgroup_out syncscope("workgroup") seq_cst, align 4, !nontemporal !0
|
|
store atomic i32 %wavefront, i32 addrspace(4)* %wavefront_out syncscope("wavefront") seq_cst, align 4, !nontemporal !0
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: convergent nounwind
|
|
declare { i1, i64 } @llvm.amdgcn.if(i1) #1
|
|
|
|
; Function Attrs: convergent nounwind
|
|
declare { i1, i64 } @llvm.amdgcn.else(i64) #1
|
|
|
|
; Function Attrs: convergent nounwind readnone
|
|
declare i64 @llvm.amdgcn.break(i64) #2
|
|
|
|
; Function Attrs: convergent nounwind readnone
|
|
declare i64 @llvm.amdgcn.if.break(i1, i64) #2
|
|
|
|
; Function Attrs: convergent nounwind readnone
|
|
declare i64 @llvm.amdgcn.else.break(i64, i64) #2
|
|
|
|
; Function Attrs: convergent nounwind
|
|
declare i1 @llvm.amdgcn.loop(i64) #1
|
|
|
|
; Function Attrs: convergent nounwind
|
|
declare void @llvm.amdgcn.end.cf(i64) #1
|
|
|
|
attributes #0 = { "target-cpu"="gfx803" }
|
|
attributes #1 = { convergent nounwind }
|
|
attributes #2 = { convergent nounwind readnone }
|
|
|
|
!0 = !{i32 1}
|
|
|
|
# GCN-LABEL: name: syncscopes
|
|
# GCN: FLAT_STORE_DWORD killed $vgpr0_vgpr1, killed $vgpr2, 0, -1, 0, implicit $exec, implicit $flat_scr :: (volatile non-temporal store syncscope("agent") seq_cst 4 into %ir.agent_out, addrspace 4)
|
|
# GCN: FLAT_STORE_DWORD killed $vgpr0_vgpr1, killed $vgpr2, 0, -1, 0, implicit $exec, implicit $flat_scr :: (volatile non-temporal store syncscope("workgroup") seq_cst 4 into %ir.workgroup_out, addrspace 4)
|
|
# GCN: FLAT_STORE_DWORD killed $vgpr0_vgpr1, killed $vgpr2, 0, -1, 0, implicit $exec, implicit $flat_scr :: (volatile non-temporal store syncscope("wavefront") seq_cst 4 into %ir.wavefront_out, addrspace 4)
|
|
...
|
|
---
|
|
name: syncscopes
|
|
alignment: 0
|
|
exposesReturnsTwice: false
|
|
legalized: false
|
|
regBankSelected: false
|
|
selected: false
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '$sgpr4_sgpr5' }
|
|
frameInfo:
|
|
isFrameAddressTaken: false
|
|
isReturnAddressTaken: false
|
|
hasStackMap: false
|
|
hasPatchPoint: false
|
|
stackSize: 0
|
|
offsetAdjustment: 0
|
|
maxAlignment: 0
|
|
adjustsStack: false
|
|
hasCalls: false
|
|
hasOpaqueSPAdjustment: false
|
|
hasVAStart: false
|
|
hasMustTailInVarArgFunc: false
|
|
body: |
|
|
bb.0.entry:
|
|
liveins: $sgpr4_sgpr5
|
|
|
|
S_WAITCNT 0
|
|
$sgpr0_sgpr1 = S_LOAD_DWORDX2_IMM $sgpr4_sgpr5, 8, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(4)* undef`)
|
|
$sgpr6 = S_LOAD_DWORD_IMM $sgpr4_sgpr5, 0, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
|
|
$sgpr2_sgpr3 = S_LOAD_DWORDX2_IMM $sgpr4_sgpr5, 24, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(4)* undef`)
|
|
$sgpr7 = S_LOAD_DWORD_IMM $sgpr4_sgpr5, 16, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
|
|
$sgpr8 = S_LOAD_DWORD_IMM $sgpr4_sgpr5, 32, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
|
|
S_WAITCNT 127
|
|
$vgpr0 = V_MOV_B32_e32 $sgpr0, implicit $exec, implicit-def $vgpr0_vgpr1, implicit $sgpr0_sgpr1
|
|
$sgpr4_sgpr5 = S_LOAD_DWORDX2_IMM killed $sgpr4_sgpr5, 40, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(4)* undef`)
|
|
$vgpr1 = V_MOV_B32_e32 killed $sgpr1, implicit $exec, implicit killed $sgpr0_sgpr1, implicit $sgpr0_sgpr1, implicit $exec
|
|
$vgpr2 = V_MOV_B32_e32 killed $sgpr6, implicit $exec, implicit $exec
|
|
FLAT_STORE_DWORD killed $vgpr0_vgpr1, killed $vgpr2, 0, -1, 0, implicit $exec, implicit $flat_scr :: (volatile non-temporal store syncscope("agent") seq_cst 4 into %ir.agent_out)
|
|
S_WAITCNT 112
|
|
$vgpr0 = V_MOV_B32_e32 $sgpr2, implicit $exec, implicit-def $vgpr0_vgpr1, implicit $sgpr2_sgpr3
|
|
$vgpr1 = V_MOV_B32_e32 killed $sgpr3, implicit $exec, implicit killed $sgpr2_sgpr3, implicit $sgpr2_sgpr3, implicit $exec
|
|
$vgpr2 = V_MOV_B32_e32 killed $sgpr7, implicit $exec, implicit $exec
|
|
FLAT_STORE_DWORD killed $vgpr0_vgpr1, killed $vgpr2, 0, -1, 0, implicit $exec, implicit $flat_scr :: (volatile non-temporal store syncscope("workgroup") seq_cst 4 into %ir.workgroup_out)
|
|
S_WAITCNT 112
|
|
$vgpr0 = V_MOV_B32_e32 $sgpr4, implicit $exec, implicit-def $vgpr0_vgpr1, implicit $sgpr4_sgpr5
|
|
$vgpr1 = V_MOV_B32_e32 killed $sgpr5, implicit $exec, implicit killed $sgpr4_sgpr5, implicit $sgpr4_sgpr5, implicit $exec
|
|
$vgpr2 = V_MOV_B32_e32 killed $sgpr8, implicit $exec, implicit $exec
|
|
FLAT_STORE_DWORD killed $vgpr0_vgpr1, killed $vgpr2, 0, -1, 0, implicit $exec, implicit $flat_scr :: (volatile non-temporal store syncscope("wavefront") seq_cst 4 into %ir.wavefront_out)
|
|
S_ENDPGM
|
|
|
|
...
|