maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopVectorize/no_idiv_reduction.ll

25 lines
806 B
LLVM
Raw Normal View History

LoopVectorizer: integer division is not a reduction operation Don't classify idiv/udiv as a reduction operation. Integer division is lossy. For example : (1 / 2) * 4 != 4/2. Example: int a[] = { 2, 5, 2, 2} int x = 80; for() x /= a[i]; Scalar: x /= 2 // = 40 x /= 5 // = 8 x /= 2 // = 4 x /= 2 // = 2 Vectorized: <80, 1> / <2,5> //= <40,0> <40, 0> / <2,2> //= <20,0> 20*0 = 0 radar://13640654 llvm-svn: 179381
2013-04-12 23:15:19 +08:00
; RUN: opt -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 -S < %s | FileCheck %s
@a = common global [128 x i32] zeroinitializer, align 16
;; Must not vectorize division reduction. Division is lossy.
define i32 @g() {
entry:
br label %for.body
for.body:
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @g(
LoopVectorizer: integer division is not a reduction operation Don't classify idiv/udiv as a reduction operation. Integer division is lossy. For example : (1 / 2) * 4 != 4/2. Example: int a[] = { 2, 5, 2, 2} int x = 80; for() x /= a[i]; Scalar: x /= 2 // = 40 x /= 5 // = 8 x /= 2 // = 4 x /= 2 // = 2 Vectorized: <80, 1> / <2,5> //= <40,0> <40, 0> / <2,2> //= <20,0> 20*0 = 0 radar://13640654 llvm-svn: 179381
2013-04-12 23:15:19 +08:00
; CHECK-NOT: sdiv <2 x i32>
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%r.05 = phi i32 [ 80, %entry ], [ %div, %for.body ]
%arrayidx = getelementptr inbounds [128 x i32]* @a, i64 0, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%div = sdiv i32 %r.05, %0
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, 1024
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret i32 %div
}