llvm-project/llvm/test/CodeGen/AMDGPU/memory-legalizer-multiple-m...

164 lines
6.8 KiB
YAML

# RUN: llc -march=amdgcn -mcpu=gfx803 -run-pass si-memory-legalizer %s -o - | FileCheck %s
--- |
; ModuleID = 'memory-legalizer-multiple-mem-operands.ll'
source_filename = "memory-legalizer-multiple-mem-operands.ll"
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-A5"
define amdgpu_kernel void @multiple_mem_operands(i32 addrspace(1)* %out, i32 %cond, i32 %if_offset, i32 %else_offset) #0 {
entry:
%scratch0 = alloca [8192 x i32], addrspace(5)
%scratch1 = alloca [8192 x i32], addrspace(5)
%scratchptr01 = bitcast [8192 x i32] addrspace(5)* %scratch0 to i32 addrspace(5)*
store i32 1, i32 addrspace(5)* %scratchptr01
%scratchptr12 = bitcast [8192 x i32] addrspace(5)* %scratch1 to i32 addrspace(5)*
store i32 2, i32 addrspace(5)* %scratchptr12
%cmp = icmp eq i32 %cond, 0
br i1 %cmp, label %if, label %else, !structurizecfg.uniform !0, !amdgpu.uniform !0
if: ; preds = %entry
%if_ptr = getelementptr [8192 x i32], [8192 x i32] addrspace(5)* %scratch0, i32 0, i32 %if_offset, !amdgpu.uniform !0
%if_value = load i32, i32 addrspace(5)* %if_ptr, align 4, !nontemporal !1
br label %done, !structurizecfg.uniform !0
else: ; preds = %entry
%else_ptr = getelementptr [8192 x i32], [8192 x i32] addrspace(5)* %scratch1, i32 0, i32 %else_offset, !amdgpu.uniform !0
%else_value = load i32, i32 addrspace(5)* %else_ptr, align 4
br label %done, !structurizecfg.uniform !0
done: ; preds = %else, %if
%value = phi i32 [ %if_value, %if ], [ %else_value, %else ]
store i32 %value, i32 addrspace(1)* %out
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 = !{}
!1 = !{i32 1}
...
---
# CHECK-LABEL: name: multiple_mem_operands
# CHECK-LABEL: bb.3.done:
# CHECK: BUFFER_LOAD_DWORD_OFFEN killed $vgpr0, killed $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 0, 0, 0, 0
name: multiple_mem_operands
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
liveins:
- { reg: '$sgpr0_sgpr1', virtual-reg: '' }
- { reg: '$sgpr3', virtual-reg: '' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 65540
offsetAdjustment: 0
maxAlignment: 4
adjustsStack: false
hasCalls: false
stackProtector: ''
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
savePoint: ''
restorePoint: ''
fixedStack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 4, stack-id: 0,
isImmutable: false, isAliased: false, callee-saved-register: '' }
stack:
- { id: 0, name: scratch0, type: default, offset: 4, size: 32768, alignment: 4,
stack-id: 0, callee-saved-register: '', local-offset: 0,
debug-info-variable: '', debug-info-expression: '',
debug-info-location: '' }
- { id: 1, name: scratch1, type: default, offset: 32772, size: 32768,
alignment: 4, stack-id: 0, callee-saved-register: '', local-offset: 32768,
debug-info-variable: '', debug-info-expression: '',
debug-info-location: '' }
constants:
body: |
bb.0.entry:
successors: %bb.1.if(0x30000000), %bb.2.else(0x50000000)
liveins: $sgpr0_sgpr1, $sgpr3
$sgpr2 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 44, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(2)* undef`)
$sgpr8 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
$sgpr4_sgpr5 = S_LOAD_DWORDX2_IMM $sgpr0_sgpr1, 36, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
$sgpr9 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
$sgpr10 = S_MOV_B32 4294967295, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
$sgpr11 = S_MOV_B32 15204352, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
$vgpr0 = V_MOV_B32_e32 1, implicit $exec
BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 4, 0, 0, 0, implicit $exec :: (store 4 into %ir.scratchptr01)
S_WAITCNT 127
S_CMP_LG_U32 killed $sgpr2, 0, implicit-def $scc
S_WAITCNT 3855
$vgpr0 = V_MOV_B32_e32 2, implicit $exec
$vgpr1 = V_MOV_B32_e32 32772, implicit $exec
BUFFER_STORE_DWORD_OFFEN killed $vgpr0, killed $vgpr1, $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 0, 0, 0, 0, implicit $exec :: (store 4 into %ir.scratchptr12)
S_CBRANCH_SCC0 %bb.1.if, implicit killed $scc
bb.2.else:
successors: %bb.3.done(0x80000000)
liveins: $sgpr0_sgpr1, $sgpr4_sgpr5, $sgpr3, $sgpr8_sgpr9_sgpr10_sgpr11
$sgpr0 = S_LOAD_DWORD_IMM killed $sgpr0_sgpr1, 52, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(2)* undef`)
S_WAITCNT 3855
$vgpr0 = V_MOV_B32_e32 32772, implicit $exec
S_BRANCH %bb.3.done
bb.1.if:
successors: %bb.3.done(0x80000000)
liveins: $sgpr0_sgpr1, $sgpr4_sgpr5, $sgpr3, $sgpr8_sgpr9_sgpr10_sgpr11
$sgpr0 = S_LOAD_DWORD_IMM killed $sgpr0_sgpr1, 48, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(2)* undef`)
S_WAITCNT 3855
$vgpr0 = V_MOV_B32_e32 4, implicit $exec
bb.3.done:
liveins: $sgpr3, $sgpr4_sgpr5, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0, $sgpr0
S_WAITCNT 127
$sgpr0 = S_LSHL_B32 killed $sgpr0, 2, implicit-def dead $scc
$vgpr0 = V_ADD_I32_e32 killed $sgpr0, killed $vgpr0, implicit-def dead $vcc, implicit $exec
$vgpr0 = BUFFER_LOAD_DWORD_OFFEN killed $vgpr0, killed $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 0, 0, 0, 0, implicit $exec :: (load 4 from %ir.else_ptr), (non-temporal load 4 from %ir.if_ptr)
$vgpr1 = V_MOV_B32_e32 $sgpr4, implicit $exec, implicit-def $vgpr1_vgpr2, implicit $sgpr4_sgpr5
$vgpr2 = V_MOV_B32_e32 killed $sgpr5, implicit $exec, implicit $sgpr4_sgpr5, implicit $exec
S_WAITCNT 3952
FLAT_STORE_DWORD killed $vgpr1_vgpr2, killed $vgpr0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %ir.out)
S_ENDPGM
...