maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU/GlobalISel: Fix using wrong addrspace for aperture 

This was always passing the destination flat address space, when it
should be picking between the two valid source options.

llvm-svn: 373716
This commit is contained in:
Matt Arsenault 2019-10-04 08:35:38 +00:00
parent 412e0bf8f3
commit d7cad4fb41
2 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
View File

@ -1085,6 +1085,8 @@ Register AMDGPULegalizerInfo::getSegmentAperture(
const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
const LLT S32 = LLT::scalar(32);
assert(AS == AMDGPUAS::LOCAL_ADDRESS || AS == AMDGPUAS::PRIVATE_ADDRESS);
if (ST.hasApertureRegs()) {
// FIXME: Use inline constants (src_{shared, private}_base) instead of
// getreg.
@ -1231,7 +1233,7 @@ bool AMDGPULegalizerInfo::legalizeAddrSpaceCast(
auto FlatNull =
B.buildConstant(DstTy, TM.getNullPointerValue(DestAS));
Register ApertureReg = getSegmentAperture(DestAS, MRI, B);
Register ApertureReg = getSegmentAperture(SrcAS, MRI, B);
if (!ApertureReg.isValid())
return false;

16
llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-addrspacecast.mir
View File

@ -259,9 +259,9 @@ body: |
; VI: [[C:%[0-9]+]]:_(p3) = G_CONSTANT i32 -1
; VI: [[C1:%[0-9]+]]:_(p0) = G_CONSTANT i64 0
; VI: [[COPY2:%[0-9]+]]:_(p4) = COPY [[COPY]](p4)
; VI: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 68
; VI: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 64
; VI: [[GEP:%[0-9]+]]:_(p4) = G_GEP [[COPY2]], [[C2]](s64)
; VI: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[GEP]](p4) :: (dereferenceable invariant load 4 from `i8 addrspace(4)* undef` + 68, addrspace 4)
; VI: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[GEP]](p4) :: (dereferenceable invariant load 4 from `i8 addrspace(4)* undef` + 64, align 64, addrspace 4)
; VI: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[COPY1]](p3), [[C]]
; VI: [[PTRTOINT:%[0-9]+]]:_(s32) = G_PTRTOINT [[COPY1]](p3)
; VI: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[PTRTOINT]](s32), [[LOAD]](s32)
@ -271,7 +271,7 @@ body: |
; GFX9: [[COPY:%[0-9]+]]:_(p3) = COPY $vgpr0
; GFX9: [[C:%[0-9]+]]:_(p3) = G_CONSTANT i32 -1
; GFX9: [[C1:%[0-9]+]]:_(p0) = G_CONSTANT i64 0
; GFX9: [[S_GETREG_B32_:%[0-9]+]]:sreg_32(s32) = S_GETREG_B32 30735
; GFX9: [[S_GETREG_B32_:%[0-9]+]]:sreg_32(s32) = S_GETREG_B32 31759
; GFX9: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX9: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[S_GETREG_B32_]], [[C2]](s32)
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[COPY]](p3), [[C]]
@ -465,16 +465,16 @@ body: |
; VI: [[C:%[0-9]+]]:_(p3) = G_CONSTANT i32 -1
; VI: [[C1:%[0-9]+]]:_(p0) = G_CONSTANT i64 0
; VI: [[COPY2:%[0-9]+]]:_(p4) = COPY [[COPY]](p4)
; VI: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 68
; VI: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 64
; VI: [[GEP:%[0-9]+]]:_(p4) = G_GEP [[COPY2]], [[C2]](s64)
; VI: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[GEP]](p4) :: (dereferenceable invariant load 4 from `i8 addrspace(4)* undef` + 68, addrspace 4)
; VI: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[GEP]](p4) :: (dereferenceable invariant load 4 from `i8 addrspace(4)* undef` + 64, align 64, addrspace 4)
; VI: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UV]](p3), [[C]]
; VI: [[PTRTOINT:%[0-9]+]]:_(s32) = G_PTRTOINT [[UV]](p3)
; VI: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[PTRTOINT]](s32), [[LOAD]](s32)
; VI: [[SELECT:%[0-9]+]]:_(p0) = G_SELECT [[ICMP]](s1), [[MV]], [[C1]]
; VI: [[COPY3:%[0-9]+]]:_(p4) = COPY [[COPY]](p4)
; VI: [[GEP1:%[0-9]+]]:_(p4) = G_GEP [[COPY3]], [[C2]](s64)
; VI: [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[GEP1]](p4) :: (dereferenceable invariant load 4 from `i8 addrspace(4)* undef` + 68, addrspace 4)
; VI: [[LOAD1:%[0-9]+]]:_(s32) = G_LOAD [[GEP1]](p4) :: (dereferenceable invariant load 4 from `i8 addrspace(4)* undef` + 64, align 64, addrspace 4)
; VI: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UV1]](p3), [[C]]
; VI: [[PTRTOINT1:%[0-9]+]]:_(s32) = G_PTRTOINT [[UV1]](p3)
; VI: [[MV1:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[PTRTOINT1]](s32), [[LOAD1]](s32)
@ -486,14 +486,14 @@ body: |
; GFX9: [[UV:%[0-9]+]]:_(p3), [[UV1:%[0-9]+]]:_(p3) = G_UNMERGE_VALUES [[COPY]](<2 x p3>)
; GFX9: [[C:%[0-9]+]]:_(p3) = G_CONSTANT i32 -1
; GFX9: [[C1:%[0-9]+]]:_(p0) = G_CONSTANT i64 0
; GFX9: [[S_GETREG_B32_:%[0-9]+]]:sreg_32(s32) = S_GETREG_B32 30735
; GFX9: [[S_GETREG_B32_:%[0-9]+]]:sreg_32(s32) = S_GETREG_B32 31759
; GFX9: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX9: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[S_GETREG_B32_]], [[C2]](s32)
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UV]](p3), [[C]]
; GFX9: [[PTRTOINT:%[0-9]+]]:_(s32) = G_PTRTOINT [[UV]](p3)
; GFX9: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[PTRTOINT]](s32), [[SHL]](s32)
; GFX9: [[SELECT:%[0-9]+]]:_(p0) = G_SELECT [[ICMP]](s1), [[MV]], [[C1]]
; GFX9: [[S_GETREG_B32_1:%[0-9]+]]:sreg_32(s32) = S_GETREG_B32 30735
; GFX9: [[S_GETREG_B32_1:%[0-9]+]]:sreg_32(s32) = S_GETREG_B32 31759
; GFX9: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[S_GETREG_B32_1]], [[C2]](s32)
; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UV1]](p3), [[C]]
; GFX9: [[PTRTOINT1:%[0-9]+]]:_(s32) = G_PTRTOINT [[UV1]](p3)