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
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
|
; RUN: opt -S -passes=loop-vectorize < %s 2>&1 -pass-remarks-analysis=.* | FileCheck %s
; Test the optimization remark emitter for recognition
; of a mathlib function vs. an arbitrary function.
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.14.0"
@data = external local_unnamed_addr global [32768 x float], align 16
; CHECK: loop not vectorized: library call cannot be vectorized
define void @libcall_blocks_vectorization() {
entry:
br label %for.body
for.cond.cleanup:
ret void
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds [32768 x float], ptr @data, i64 0, i64 %indvars.iv
%t0 = load float, ptr %arrayidx, align 4
%sqrtf = tail call float @sqrtf(float %t0)
store float %sqrtf, ptr %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 32768
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
; CHECK: loop not vectorized: call instruction cannot be vectorized
define void @arbitrary_call_blocks_vectorization() {
entry:
br label %for.body
for.cond.cleanup:
ret void
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds [32768 x float], ptr @data, i64 0, i64 %indvars.iv
%t0 = load float, ptr %arrayidx, align 4
%sqrtf = tail call float @arbitrary(float %t0)
store float %sqrtf, ptr %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 32768
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
declare float @sqrtf(float)
declare float @arbitrary(float)
|
