RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 10:42:39 +01:00
Code Issues Projects Releases Wiki Activity

AMDGPU: Add an option -disable-promote-alloca-to-lds

Browse Source 
Add this option for debugging and providing workaround.

By default it is off so no behavior change in backend.

Differential Revision: https://reviews.llvm.org/D54158

llvm-svn: 346267
This commit is contained in:
Yaxun Liu 2018-11-06 21:28:17 +00:00
parent 155b10f347
commit c32fcd8c26
2 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
View File

@ -70,6 +70,11 @@ static cl::opt<bool> DisablePromoteAllocaToVector(
cl::desc("Disable promote alloca to vector"),
cl::init(false));
static cl::opt<bool> DisablePromoteAllocaToLDS(
"disable-promote-alloca-to-lds",
cl::desc("Disable promote alloca to LDS"),
cl::init(false));
// FIXME: This can create globals so should be a module pass.
class AMDGPUPromoteAlloca : public FunctionPass {
private:
@ -706,6 +711,9 @@ bool AMDGPUPromoteAlloca::handleAlloca(AllocaInst &I, bool SufficientLDS) {
if (tryPromoteAllocaToVector(&I))
return true; // Promoted to vector.
if (DisablePromoteAllocaToLDS)
return false;
const Function &ContainingFunction = *I.getParent()->getParent();
CallingConv::ID CC = ContainingFunction.getCallingConv();

3
test/CodeGen/AMDGPU/promote-alloca-to-lds-icmp.ll
View File

@ -1,8 +1,11 @@
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -amdgpu-promote-alloca < %s | FileCheck %s
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -amdgpu-promote-alloca -disable-promote-alloca-to-lds< %s | FileCheck -check-prefix=NOLDS %s
; This normally would be fixed by instcombine to be compare to the GEP
; indices
; NOLDS-NOT: addrspace(3)
; CHECK-LABEL: @lds_promoted_alloca_icmp_same_derived_pointer(
; CHECK: [[ARRAYGEP:%[0-9]+]] = getelementptr inbounds [256 x [16 x i32]], [256 x [16 x i32]] addrspace(3)* @lds_promoted_alloca_icmp_same_derived_pointer.alloca, i32 0, i32 %{{[0-9]+}}
; CHECK: %ptr0 = getelementptr inbounds [16 x i32], [16 x i32] addrspace(3)* [[ARRAYGEP]], i32 0, i32 %a