File: strict-fadd-cost.ll

package info (click to toggle)
llvm-toolchain-13 1%3A13.0.1-6~deb11u1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 1,418,812 kB
  • sloc: cpp: 5,290,827; ansic: 996,570; asm: 544,593; python: 188,212; objc: 72,027; lisp: 30,291; f90: 25,395; sh: 24,900; javascript: 9,780; pascal: 9,398; perl: 7,484; ml: 5,432; awk: 3,523; makefile: 2,892; xml: 953; cs: 573; fortran: 539
file content (50 lines) | stat: -rw-r--r-- 2,013 bytes parent folder | download | duplicates (3)
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
; REQUIRES: asserts
; RUN: opt < %s -loop-vectorize -debug -disable-output -enable-strict-reductions=true -hints-allow-reordering=false \
; RUN:   -force-vector-width=4 -force-vector-interleave=1 -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF4
; RUN: opt < %s -loop-vectorize -debug -disable-output -enable-strict-reductions=true -hints-allow-reordering=false \
; RUN:   -force-vector-width=8 -force-vector-interleave=1 -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF8

target triple="aarch64-unknown-linux-gnu"

; CHECK-VF4: Found an estimated cost of 17 for VF 4 For instruction:   %add = fadd float %0, %sum.07
; CHECK-VF8: Found an estimated cost of 34 for VF 8 For instruction:   %add = fadd float %0, %sum.07

define float @fadd_strict32(float* noalias nocapture readonly %a, i64 %n) {
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %sum.07 = phi float [ 0.000000e+00, %entry ], [ %add, %for.body ]
  %arrayidx = getelementptr inbounds float, float* %a, i64 %iv
  %0 = load float, float* %arrayidx, align 4
  %add = fadd float %0, %sum.07
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, %n
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret float %add
}


; CHECK-VF4: Found an estimated cost of 14 for VF 4 For instruction:   %add = fadd double %0, %sum.07
; CHECK-VF8: Found an estimated cost of 28 for VF 8 For instruction:   %add = fadd double %0, %sum.07

define double @fadd_strict64(double* noalias nocapture readonly %a, i64 %n) {
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %sum.07 = phi double [ 0.000000e+00, %entry ], [ %add, %for.body ]
  %arrayidx = getelementptr inbounds double, double* %a, i64 %iv
  %0 = load double, double* %arrayidx, align 4
  %add = fadd double %0, %sum.07
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, %n
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret double %add
}