1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt %s -loop-vectorize -debug-only=loop-vectorize -S 2>&1 | FileCheck %s
; REQUIRES: asserts
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"
; CHECK: Found an estimated cost of 4 for VF 1 For instruction: %neg = fneg float %{{.*}}
; CHECK: Found an estimated cost of 4 for VF 2 For instruction: %neg = fneg float %{{.*}}
; CHECK: Found an estimated cost of 4 for VF 4 For instruction: %neg = fneg float %{{.*}}
define void @fneg_cost(float* %a, i64 %n) {
entry:
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds float, float* %a, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%neg = fneg float %0
store float %neg, float* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%cmp = icmp eq i64 %indvars.iv.next, %n
br i1 %cmp, label %for.end, label %for.body
for.end:
ret void
}
|
