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

AMDGPU: Fix assert on alloca of array of struct 

llvm-svn: 313282
This commit is contained in:
Matt Arsenault 2017-09-14 18:02:29 +00:00
parent 6819a7a1cb
commit 37ab4cf8b8
2 changed files with 14 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
View File

@ -285,9 +285,9 @@ Value *AMDGPUPromoteAlloca::getWorkitemID(IRBuilder<> &Builder, unsigned N) {
return CI;
}
static VectorType *arrayTypeToVecType(Type *ArrayTy) {
return VectorType::get(ArrayTy->getArrayElementType(),
ArrayTy->getArrayNumElements());
static VectorType *arrayTypeToVecType(ArrayType *ArrayTy) {
return VectorType::get(ArrayTy->getElementType(),
ArrayTy->getNumElements());
}
static Value *
@ -346,10 +346,9 @@ static bool tryPromoteAllocaToVector(AllocaInst *Alloca, AMDGPUAS AS) {
// FIXME: We also reject alloca's of the form [ 2 x [ 2 x i32 ]] or equivalent. Potentially these
// could also be promoted but we don't currently handle this case
if (!AllocaTy ||
AllocaTy->getElementType()->isVectorTy() ||
AllocaTy->getElementType()->isArrayTy() ||
AllocaTy->getNumElements() > 4 ||
AllocaTy->getNumElements() < 2) {
AllocaTy->getNumElements() < 2 ||
!VectorType::isValidElementType(AllocaTy->getElementType())) {
DEBUG(dbgs() << " Cannot convert type to vector\n");
return false;
}

9
llvm/test/CodeGen/AMDGPU/promote-alloca-array-aggregate.ll
View File

@ -11,6 +11,7 @@
%Block = type { [1 x float], i32 }
%gl_PerVertex = type { <4 x float>, float, [1 x float], [1 x float] }
%struct = type { i32, i32 }
@block = external addrspace(1) global %Block
@pv = external addrspace(1) global %gl_PerVertex
@ -129,3 +130,11 @@ define amdgpu_ps void @promote_double_aggr() #0 {
store <4 x float> %tmp21, <4 x float> addrspace(1)* @frag_color
ret void
}
; Don't crash on a type that isn't a valid vector element.
; OPT-LABEL: @alloca_struct(
define amdgpu_kernel void @alloca_struct() #0 {
entry:
%alloca = alloca [2 x %struct], align 4
ret void
}