forked from OSchip/llvm-project
117 lines
3.3 KiB
Plaintext
117 lines
3.3 KiB
Plaintext
|
# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-load-store-opt -o - %s | FileCheck %s
|
||
|
|
||
|
# Check that SILoadStoreOptimizer honors physregs defs/uses between moved
|
||
|
# instructions.
|
||
|
#
|
||
|
# The following IR snippet would usually be optimized by the peephole optimizer.
|
||
|
# However, an equivalent situation can occur with buffer instructions as well.
|
||
|
|
||
|
# CHECK-LABEL: name: scc_def_and_use_no_dependency
|
||
|
# CHECK: S_ADD_U32
|
||
|
# CHECK: S_ADDC_U32
|
||
|
# CHECK: DS_READ2_B32
|
||
|
--- |
|
||
|
define amdgpu_kernel void @scc_def_and_use_no_dependency(i32 addrspace(3)* %ptr.0) nounwind {
|
||
|
%ptr.4 = getelementptr i32, i32 addrspace(3)* %ptr.0, i32 1
|
||
|
%ptr.64 = getelementptr i32, i32 addrspace(3)* %ptr.0, i32 16
|
||
|
ret void
|
||
|
}
|
||
|
|
||
|
define amdgpu_kernel void @scc_def_and_use_dependency(i32 addrspace(3)* %ptr.0) nounwind {
|
||
|
%ptr.4 = getelementptr i32, i32 addrspace(3)* %ptr.0, i32 1
|
||
|
%ptr.64 = getelementptr i32, i32 addrspace(3)* %ptr.0, i32 16
|
||
|
ret void
|
||
|
}
|
||
|
...
|
||
|
---
|
||
|
name: scc_def_and_use_no_dependency
|
||
|
alignment: 0
|
||
|
exposesReturnsTwice: false
|
||
|
legalized: false
|
||
|
regBankSelected: false
|
||
|
selected: false
|
||
|
tracksRegLiveness: false
|
||
|
liveins:
|
||
|
- { reg: '$vgpr0' }
|
||
|
- { reg: '$sgpr0' }
|
||
|
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:
|
||
|
liveins: $vgpr0, $sgpr0
|
||
|
|
||
|
%1:vgpr_32 = COPY $vgpr0
|
||
|
%10:sgpr_32 = COPY $sgpr0
|
||
|
|
||
|
$m0 = S_MOV_B32 -1
|
||
|
%2:vgpr_32 = DS_READ_B32 %1, 0, 0, implicit $m0, implicit $exec :: (load 4 from %ir.ptr.0)
|
||
|
|
||
|
%11:sgpr_32 = S_ADD_U32 %10, 4, implicit-def $scc
|
||
|
%12:sgpr_32 = S_ADDC_U32 %10, 0, implicit-def dead $scc, implicit $scc
|
||
|
|
||
|
%3:vgpr_32 = DS_READ_B32 %1, 64, 0, implicit $m0, implicit $exec :: (load 4 from %ir.ptr.64)
|
||
|
S_ENDPGM
|
||
|
|
||
|
...
|
||
|
|
||
|
# CHECK-LABEL: name: scc_def_and_use_dependency
|
||
|
# CHECK: DS_READ2_B32
|
||
|
# CHECK: S_ADD_U32
|
||
|
# CHECK: S_ADDC_U32
|
||
|
---
|
||
|
name: scc_def_and_use_dependency
|
||
|
alignment: 0
|
||
|
exposesReturnsTwice: false
|
||
|
legalized: false
|
||
|
regBankSelected: false
|
||
|
selected: false
|
||
|
tracksRegLiveness: false
|
||
|
liveins:
|
||
|
- { reg: '$vgpr0' }
|
||
|
- { reg: '$sgpr0' }
|
||
|
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:
|
||
|
liveins: $vgpr0, $sgpr0
|
||
|
|
||
|
%1:vgpr_32 = COPY $vgpr0
|
||
|
%10:sgpr_32 = COPY $sgpr0
|
||
|
|
||
|
$m0 = S_MOV_B32 -1
|
||
|
%2:vgpr_32 = DS_READ_B32 %1, 0, 0, implicit $m0, implicit $exec :: (load 4 from %ir.ptr.0)
|
||
|
%20:sgpr_32 = V_READFIRSTLANE_B32 %2, implicit $exec
|
||
|
|
||
|
%21:sgpr_32 = S_ADD_U32 %20, 4, implicit-def $scc
|
||
|
; The S_ADDC_U32 depends on the first DS_READ_B32 only via SCC
|
||
|
%11:sgpr_32 = S_ADDC_U32 %10, 0, implicit-def dead $scc, implicit $scc
|
||
|
|
||
|
%3:vgpr_32 = DS_READ_B32 %1, 64, 0, implicit $m0, implicit $exec :: (load 4 from %ir.ptr.64)
|
||
|
S_ENDPGM
|
||
|
|
||
|
...
|