RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2025-01-30 07:14:53 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Call the potentially costly isAnnotatedParallel() only once.

Browse Source 
Made the uniform write test's checks a bit stricter.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180119 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Pekka Jaaskelainen 2013-04-23 16:44:43 +00:00
parent 13aba14eb5
commit 2e59a125fc
2 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -2556,6 +2556,8 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
PtrRtCheck.Pointers.clear();
PtrRtCheck.Need = false;
const bool IsAnnotatedParallel = TheLoop->isAnnotatedParallel();
// For each block.
for (Loop::block_iterator bb = TheLoop->block_begin(),
be = TheLoop->block_end(); bb != be; ++bb) {
@ -2570,7 +2572,7 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
if (it->mayReadFromMemory()) {
LoadInst *Ld = dyn_cast<LoadInst>(it);
if (!Ld) return false;
if (!Ld->isSimple() && !TheLoop->isAnnotatedParallel()) {
if (!Ld->isSimple() && !IsAnnotatedParallel) {
DEBUG(dbgs() << "LV: Found a non-simple load.\n");
return false;
}
@ -2582,7 +2584,7 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
if (it->mayWriteToMemory()) {
StoreInst *St = dyn_cast<StoreInst>(it);
if (!St) return false;
if (!St->isSimple() && !TheLoop->isAnnotatedParallel()) {
if (!St->isSimple() && !IsAnnotatedParallel) {
DEBUG(dbgs() << "LV: Found a non-simple store.\n");
return false;
}
@ -2629,7 +2631,7 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
ReadWrites.insert(std::make_pair(Ptr, ST));
}
if (TheLoop->isAnnotatedParallel()) {
if (IsAnnotatedParallel) {
DEBUG(dbgs()
<< "LV: A loop annotated parallel, ignore memory dependency "
<< "checks.\n");

3
test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
View File

@ -4,7 +4,8 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3
target triple = "x86_64-unknown-linux-gnu"
;CHECK: @foo
;CHECK-NOT: <4 x
;CHECK-NOT: <4 x i32>
;CHECK: ret void
; Function Attrs: nounwind uwtable
define void @foo(i32* nocapture %a, i32* nocapture %b, i32 %k, i32 %m) #0 {