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

Vectorize a reduction chain feeding into a 'return' statement. 

e.x 
return (a[0]+b[0]) + (a[1]+b[1])

Differential Revision: http://reviews.llvm.org/D6227

llvm-svn: 222364
This commit is contained in:
Suyog Sarda 2014-11-19 16:07:38 +00:00
parent efa443429d
commit aba97f4aba
2 changed files with 69 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View File

@ -3696,6 +3696,21 @@ bool SLPVectorizer::vectorizeChainsInBlock(BasicBlock *BB, BoUpSLP &R) {
}
}
// Try to vectorize horizontal reductions feeding into a return.
if (ReturnInst *RI = dyn_cast<ReturnInst>(it))
if (RI->getNumOperands() != 0)
if (BinaryOperator *BinOp =
dyn_cast<BinaryOperator>(RI->getOperand(0))) {
DEBUG(dbgs() << "SLP: Found a return to vectorize.\n");
if (tryToVectorizePair(BinOp->getOperand(0),
BinOp->getOperand(1), R)) {
Changed = true;
it = BB->begin();
e = BB->end();
continue;
}
}
// Try to vectorize trees that start at compare instructions.
if (CmpInst *CI = dyn_cast<CmpInst>(it)) {
if (tryToVectorizePair(CI->getOperand(0), CI->getOperand(1), R)) {

54
llvm/test/Transforms/SLPVectorizer/X86/return.ll Normal file
View File

@ -0,0 +1,54 @@
; RUN: opt < %s -basicaa -slp-vectorizer -S | FileCheck %s
target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
target triple = "x86_64--linux-gnu"
@a = common global [4 x double] zeroinitializer, align 8
@b = common global [4 x double] zeroinitializer, align 8
; [4], b[4];
; double foo() {
; double sum =0;
; sum = (a[0]+b[0]) + (a[1]+b[1]);
; return sum;
; }
; CHECK-LABEL: @return1
; CHECK: %0 = load <2 x double>*
; CHECK: %1 = load <2 x double>*
; CHECK: %2 = fadd <2 x double>
define double @return1() {
entry:
%a0 = load double* getelementptr inbounds ([4 x double]* @a, i32 0, i32 0), align 8
%b0 = load double* getelementptr inbounds ([4 x double]* @b, i32 0, i32 0), align 8
%add0 = fadd double %a0, %b0
%a1 = load double* getelementptr inbounds ([4 x double]* @a, i32 0, i32 1), align 8
%b1 = load double* getelementptr inbounds ([4 x double]* @b, i32 0, i32 1), align 8
%add1 = fadd double %a1, %b1
%add2 = fadd double %add0, %add1
ret double %add2
}
; double hadd(double *x) {
; return ((x[0] + x[2]) + (x[1] + x[3]));
; }
; CHECK-LABEL: @return2
; CHECK: %1 = load <2 x double>*
; CHECK: %3 = load <2 x double>* %2
; CHECK: %4 = fadd <2 x double> %1, %3
define double @return2(double* nocapture readonly %x) {
entry:
%x0 = load double* %x, align 4
%arrayidx1 = getelementptr inbounds double* %x, i32 2
%x2 = load double* %arrayidx1, align 4
%add3 = fadd double %x0, %x2
%arrayidx2 = getelementptr inbounds double* %x, i32 1
%x1 = load double* %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds double* %x, i32 3
%x3 = load double* %arrayidx3, align 4
%add4 = fadd double %x1, %x3
%add5 = fadd double %add3, %add4
ret double %add5
}