[PATCH] D18358: AMDGPU: Account for globals in AMDGPUPromoteAlloca pass
Bas Nieuwenhuizen via llvm-commits
llvm-commits at lists.llvm.org
Tue Mar 22 10:13:53 PDT 2016
bnieuwenhuizen created this revision.
bnieuwenhuizen added reviewers: arsenm, tstellarAMD.
bnieuwenhuizen added a subscriber: llvm-commits.
Herald added a subscriber: arsenm.
http://reviews.llvm.org/D18358
Files:
lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
test/CodeGen/AMDGPU/promote-alloca-globals.ll
Index: test/CodeGen/AMDGPU/promote-alloca-globals.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/promote-alloca-globals.ll
@@ -0,0 +1,26 @@
+; RUN: opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-promote-alloca < %s | FileCheck %s
+
+; CHECK: alloca [5 x i32]
+
+ at promote_alloca_size_1500.stack = internal unnamed_addr addrspace(3) global [1500 x [5 x i32]] undef, align 4
+
+define void @promote_alloca_size_256(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) {
+entry:
+ %stack = alloca [5 x i32], align 4
+ %0 = load i32, i32 addrspace(1)* %in, align 4
+ %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
+ store i32 4, i32* %arrayidx1, align 4
+ %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
+ %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
+ %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
+ store i32 5, i32* %arrayidx3, align 4
+ %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
+ %2 = load i32, i32* %arrayidx10, align 4
+ store i32 %2, i32 addrspace(1)* %out, align 4
+ %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
+ %3 = load i32, i32* %arrayidx12
+ %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
+ store i32 %3, i32 addrspace(1)* %arrayidx13
+ %v = getelementptr inbounds [1500 x [5 x i32]], [1500 x [5 x i32]] addrspace(3)* @promote_alloca_size_1500.stack, i32 0, i32 0
+ ret void
+}
Index: lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
+++ lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
@@ -126,13 +126,15 @@
continue;
for (Use &U : GV.uses()) {
- Instruction *Use = dyn_cast<Instruction>(U);
+ Instruction *Use = dyn_cast<Instruction>(U.getUser());
if (!Use)
continue;
- if (Use->getParent()->getParent() == &F)
+ if (Use->getParent()->getParent() == &F){
LocalMemAvailable -=
Mod->getDataLayout().getTypeAllocSize(GV.getValueType());
+ break;
+ }
}
}
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D18358.51296.patch
Type: text/x-patch
Size: 2245 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160322/4e85dc8b/attachment.bin>
More information about the llvm-commits
mailing list