mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-30 23:42:52 +01:00
48b1c3e915
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
25 lines
799 B
LLVM
25 lines
799 B
LLVM
; 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:
|
|
; CHECK: @g
|
|
; 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
|
|
}
|