forked from OSchip/llvm-project
123 lines
4.3 KiB
YAML
123 lines
4.3 KiB
YAML
# RUN: llc -march=amdgcn -mcpu=gfx803 -run-pass si-memory-legalizer %s -o - | FileCheck %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"
|
|
|
|
; Function Attrs: nounwind readnone
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #0
|
|
|
|
; Function Attrs: nounwind
|
|
define amdgpu_kernel void @atomic_max_i32_noret(
|
|
i32 addrspace(1)* %out,
|
|
i32 addrspace(1)* addrspace(1)* %in,
|
|
i32 addrspace(1)* %x,
|
|
i32 %y) #1 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%idxprom = sext i32 %tid to i64
|
|
%tid.gep = getelementptr i32 addrspace(1)*, i32 addrspace(1)* addrspace(1)* %in, i64 %idxprom
|
|
%ptr = load volatile i32 addrspace(1)*, i32 addrspace(1)* addrspace(1)* %tid.gep
|
|
%xor = xor i32 %tid, 1
|
|
%cmp = icmp ne i32 %xor, 0
|
|
%1 = call { i1, i64 } @llvm.amdgcn.if(i1 %cmp)
|
|
%2 = extractvalue { i1, i64 } %1, 0
|
|
%3 = extractvalue { i1, i64 } %1, 1
|
|
br i1 %2, label %atomic, label %exit
|
|
|
|
atomic: ; preds = %0
|
|
%gep = getelementptr i32, i32 addrspace(1)* %ptr, i32 100
|
|
%ret = atomicrmw max i32 addrspace(1)* %gep, i32 %y seq_cst
|
|
br label %exit
|
|
|
|
exit: ; preds = %atomic, %0
|
|
call void @llvm.amdgcn.end.cf(i64 %3)
|
|
ret void
|
|
}
|
|
|
|
declare { i1, i64 } @llvm.amdgcn.if(i1)
|
|
|
|
declare void @llvm.amdgcn.end.cf(i64)
|
|
|
|
; Function Attrs: nounwind
|
|
declare void @llvm.stackprotector(i8*, i8**) #3
|
|
|
|
attributes #0 = { nounwind readnone "target-cpu"="tahiti" }
|
|
attributes #1 = { nounwind "target-cpu"="tahiti" }
|
|
attributes #2 = { readnone }
|
|
attributes #3 = { nounwind }
|
|
|
|
...
|
|
---
|
|
|
|
# CHECK-LABEL: name: atomic_max_i32_noret
|
|
|
|
# CHECK-LABEL: bb.1.atomic:
|
|
# CHECK: BUFFER_ATOMIC_SMAX_ADDR64
|
|
# CHECK-NEXT: S_WAITCNT 3952
|
|
# CHECK-NEXT: BUFFER_WBINVL1_VOL
|
|
|
|
name: atomic_max_i32_noret
|
|
alignment: 0
|
|
exposesReturnsTwice: false
|
|
legalized: false
|
|
regBankSelected: false
|
|
selected: false
|
|
tracksRegLiveness: true
|
|
liveins:
|
|
- { reg: '%sgpr0_sgpr1' }
|
|
- { reg: '%vgpr0' }
|
|
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.0):
|
|
successors: %bb.1.atomic(0x40000000), %bb.2.exit(0x40000000)
|
|
liveins: %vgpr0, %sgpr0_sgpr1
|
|
|
|
%sgpr4_sgpr5 = S_LOAD_DWORDX2_IMM %sgpr0_sgpr1, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%vgpr1 = V_ASHRREV_I32_e32 31, %vgpr0, implicit %exec
|
|
%vgpr1_vgpr2 = V_LSHL_B64 %vgpr0_vgpr1, 3, implicit %exec
|
|
%sgpr7 = S_MOV_B32 61440
|
|
%sgpr6 = S_MOV_B32 0
|
|
S_WAITCNT 127
|
|
%vgpr1_vgpr2 = BUFFER_LOAD_DWORDX2_ADDR64 killed %vgpr1_vgpr2, %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 8 from %ir.tid.gep)
|
|
%vgpr0 = V_XOR_B32_e32 1, killed %vgpr0, implicit %exec
|
|
V_CMP_NE_U32_e32 0, killed %vgpr0, implicit-def %vcc, implicit %exec
|
|
%sgpr2_sgpr3 = S_AND_SAVEEXEC_B64 killed %vcc, implicit-def %exec, implicit-def %scc, implicit %exec
|
|
%sgpr2_sgpr3 = S_XOR_B64 %exec, killed %sgpr2_sgpr3, implicit-def dead %scc
|
|
SI_MASK_BRANCH %bb.2.exit, implicit %exec
|
|
|
|
bb.1.atomic:
|
|
successors: %bb.2.exit(0x80000000)
|
|
liveins: %sgpr4_sgpr5_sgpr6_sgpr7:0x0000000C, %sgpr0_sgpr1, %sgpr2_sgpr3, %vgpr1_vgpr2_vgpr3_vgpr4:0x00000003
|
|
|
|
%sgpr0 = S_LOAD_DWORD_IMM killed %sgpr0_sgpr1, 15, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(2)* undef`)
|
|
dead %vgpr0 = V_MOV_B32_e32 -1, implicit %exec
|
|
dead %vgpr0 = V_MOV_B32_e32 61440, implicit %exec
|
|
%sgpr4_sgpr5 = S_MOV_B64 0
|
|
S_WAITCNT 127
|
|
%vgpr0 = V_MOV_B32_e32 killed %sgpr0, implicit %exec, implicit %exec
|
|
S_WAITCNT 3952
|
|
BUFFER_ATOMIC_SMAX_ADDR64 killed %vgpr0, killed %vgpr1_vgpr2, killed %sgpr4_sgpr5_sgpr6_sgpr7, 0, 400, 0, implicit %exec :: (volatile load seq_cst 4 from %ir.gep)
|
|
|
|
bb.2.exit:
|
|
liveins: %sgpr2_sgpr3
|
|
|
|
%exec = S_OR_B64 %exec, killed %sgpr2_sgpr3, implicit-def %scc
|
|
S_ENDPGM
|
|
|
|
...
|
|
|