File: prefer-fixed-if-equal-to-scalable.ll

package info (click to toggle)
swiftlang 6.1.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 2,791,604 kB
  • sloc: cpp: 9,901,740; ansic: 2,201,431; asm: 1,091,827; python: 308,252; objc: 82,166; f90: 80,126; lisp: 38,358; pascal: 25,559; sh: 20,429; ml: 5,058; perl: 4,745; makefile: 4,484; awk: 3,535; javascript: 3,018; xml: 918; fortran: 664; cs: 573; ruby: 396
file content (60 lines) | stat: -rw-r--r-- 2,325 bytes parent folder | download | duplicates (4)
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
53
54
55
56
57
58
59
60
; RUN: opt -S < %s -passes=loop-vectorize -force-target-instruction-cost=1 | FileCheck %s

target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128-Fn32"
target triple = "aarch64-unknown-linux-gnu"

@a = dso_local local_unnamed_addr global [32000 x float] zeroinitializer, align 64
@b = dso_local local_unnamed_addr global [32000 x float] zeroinitializer, align 64

define void @NeoverseV2() #0 {
; CHECK-LABEL: define void @NeoverseV2(
; CHECK:       store <4 x float>
;
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 [32000 x float], ptr @a, i64 0, i64 %indvars.iv
  %0 = load float, ptr %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds [32000 x float], ptr @b, i64 0, i64 %indvars.iv
  %1 = load float, ptr %arrayidx2, align 4
  %add = fadd fast float %1, %0
  %2 = add nuw nsw i64 %indvars.iv, 16000
  %arrayidx5 = getelementptr inbounds [32000 x float], ptr @a, i64 0, i64 %2
  store float %add, ptr %arrayidx5, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond.not = icmp eq i64 %indvars.iv.next, 16000
  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}

define void @GenericCPU() #1 {
; CHECK-LABEL: define void @GenericCPU(
; CHECK:       store <vscale x 4 x float>
;
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 [32000 x float], ptr @a, i64 0, i64 %indvars.iv
  %0 = load float, ptr %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds [32000 x float], ptr @b, i64 0, i64 %indvars.iv
  %1 = load float, ptr %arrayidx2, align 4
  %add = fadd fast float %1, %0
  %2 = add nuw nsw i64 %indvars.iv, 16000
  %arrayidx5 = getelementptr inbounds [32000 x float], ptr @a, i64 0, i64 %2
  store float %add, ptr %arrayidx5, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond.not = icmp eq i64 %indvars.iv.next, 16000
  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}

attributes #0 = { vscale_range(1,16) "target-cpu"="neoverse-v2" "target-features"="+sve,+sve2,+v9a" }
attributes #1 = { vscale_range(1,16) "target-cpu"="generic" "target-features"="+sve,+v9a" }