RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-12-12 05:56:28 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

SLP Vectorier: Don't vectorize really short chains because they are already handled by the SelectionDAG store-vectorizer, which does a better job in deciding when to vectorize.

Browse Source 
llvm-svn: 187267
This commit is contained in:
Nadav Rotem 2013-07-26 23:07:55 +00:00
parent 965db2159b
commit 9bebda1517
2 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -898,8 +898,12 @@ int BoUpSLP::getTreeCost() {
DEBUG(dbgs() << "SLP: Calculating cost for tree of size " <<
VectorizableTree.size() << ".\n");
if (!VectorizableTree.size()) {
assert(!ExternalUses.size() && "We should not have any external users");
// Don't vectorize tiny trees. Small load/store chains or consecutive stores
// of constants will be vectoried in SelectionDAG in MergeConsecutiveStores.
if (VectorizableTree.size() < 3) {
if (!VectorizableTree.size()) {
assert(!ExternalUses.size() && "We should not have any external users");
}
return 0;
}

4
test/Transforms/SLPVectorizer/X86/reduction2.ll
View File

@ -16,11 +16,13 @@ define double @foo(double* nocapture %D) {
%3 = getelementptr inbounds double* %D, i32 %2
%4 = load double* %3, align 4
%A4 = fmul double %4, %4
%A42 = fmul double %A4, %A4
%5 = or i32 %2, 1
%6 = getelementptr inbounds double* %D, i32 %5
%7 = load double* %6, align 4
%A7 = fmul double %7, %7
%8 = fadd double %A4, %A7
%A72 = fmul double %A7, %A7
%8 = fadd double %A42, %A72
%9 = fadd double %sum.01, %8
%10 = add nsw i32 %i.02, 1
%exitcond = icmp eq i32 %10, 100