File: vecreduce-fmax-legalization.ll

package info (click to toggle)
llvm-toolchain-11 1%3A11.0.1-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 995,808 kB
  • sloc: cpp: 4,767,656; ansic: 760,916; asm: 477,436; python: 170,940; objc: 69,804; lisp: 29,914; sh: 23,855; f90: 18,173; pascal: 7,551; perl: 7,471; ml: 5,603; awk: 3,489; makefile: 2,573; xml: 915; cs: 573; fortran: 503; javascript: 452
file content (77 lines) | stat: -rw-r--r-- 2,709 bytes parent folder | download | duplicates (2)
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK

declare half @llvm.experimental.vector.reduce.fmax.v1f16(<1 x half> %a)
declare float @llvm.experimental.vector.reduce.fmax.v1f32(<1 x float> %a)
declare double @llvm.experimental.vector.reduce.fmax.v1f64(<1 x double> %a)
declare fp128 @llvm.experimental.vector.reduce.fmax.v1f128(<1 x fp128> %a)

declare float @llvm.experimental.vector.reduce.fmax.v3f32(<3 x float> %a)
declare fp128 @llvm.experimental.vector.reduce.fmax.v2f128(<2 x fp128> %a)
declare float @llvm.experimental.vector.reduce.fmax.v16f32(<16 x float> %a)

define half @test_v1f16(<1 x half> %a) nounwind {
; CHECK-LABEL: test_v1f16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ret
  %b = call nnan half @llvm.experimental.vector.reduce.fmax.v1f16(<1 x half> %a)
  ret half %b
}

define float @test_v1f32(<1 x float> %a) nounwind {
; CHECK-LABEL: test_v1f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    // kill: def $s0 killed $s0 killed $q0
; CHECK-NEXT:    ret
  %b = call nnan float @llvm.experimental.vector.reduce.fmax.v1f32(<1 x float> %a)
  ret float %b
}

define double @test_v1f64(<1 x double> %a) nounwind {
; CHECK-LABEL: test_v1f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ret
  %b = call nnan double @llvm.experimental.vector.reduce.fmax.v1f64(<1 x double> %a)
  ret double %b
}

define fp128 @test_v1f128(<1 x fp128> %a) nounwind {
; CHECK-LABEL: test_v1f128:
; CHECK:       // %bb.0:
; CHECK-NEXT:    ret
  %b = call nnan fp128 @llvm.experimental.vector.reduce.fmax.v1f128(<1 x fp128> %a)
  ret fp128 %b
}

define float @test_v3f32(<3 x float> %a) nounwind {
; CHECK-LABEL: test_v3f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mov w8, #-8388608
; CHECK-NEXT:    fmov s1, w8
; CHECK-NEXT:    mov v0.s[3], v1.s[0]
; CHECK-NEXT:    fmaxnmv s0, v0.4s
; CHECK-NEXT:    ret
  %b = call nnan float @llvm.experimental.vector.reduce.fmax.v3f32(<3 x float> %a)
  ret float %b
}

define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
; CHECK-LABEL: test_v2f128:
; CHECK:       // %bb.0:
; CHECK-NEXT:    b fmaxl
  %b = call nnan fp128 @llvm.experimental.vector.reduce.fmax.v2f128(<2 x fp128> %a)
  ret fp128 %b
}

define float @test_v16f32(<16 x float> %a) nounwind {
; CHECK-LABEL: test_v16f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fmaxnm v1.4s, v1.4s, v3.4s
; CHECK-NEXT:    fmaxnm v0.4s, v0.4s, v2.4s
; CHECK-NEXT:    fmaxnm v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    fmaxnmv s0, v0.4s
; CHECK-NEXT:    ret
  %b = call nnan float @llvm.experimental.vector.reduce.fmax.v16f32(<16 x float> %a)
  ret float %b
}