File: combine-smax.ll

package info (click to toggle)
llvm-toolchain-9 1%3A9.0.1-16
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 882,436 kB
  • sloc: cpp: 4,167,636; ansic: 714,256; asm: 457,610; python: 155,927; objc: 65,094; sh: 42,856; lisp: 26,908; perl: 7,786; pascal: 7,722; makefile: 6,881; ml: 5,581; awk: 3,648; cs: 2,027; xml: 888; javascript: 381; ruby: 156
file content (47 lines) | stat: -rw-r--r-- 2,664 bytes parent folder | download | duplicates (7)
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
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE42
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512BW

define <16 x i8> @test_v16i8_nosignbit(<16 x i8> %a, <16 x i8> %b) {
; SSE2-LABEL: test_v16i8_nosignbit:
; SSE2:       # %bb.0:
; SSE2-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSE2-NEXT:    pand %xmm2, %xmm0
; SSE2-NEXT:    pand %xmm2, %xmm1
; SSE2-NEXT:    pmaxub %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; SSE41-LABEL: test_v16i8_nosignbit:
; SSE41:       # %bb.0:
; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSE41-NEXT:    pand %xmm2, %xmm0
; SSE41-NEXT:    pand %xmm2, %xmm1
; SSE41-NEXT:    pmaxsb %xmm1, %xmm0
; SSE41-NEXT:    retq
;
; SSE42-LABEL: test_v16i8_nosignbit:
; SSE42:       # %bb.0:
; SSE42-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSE42-NEXT:    pand %xmm2, %xmm0
; SSE42-NEXT:    pand %xmm2, %xmm1
; SSE42-NEXT:    pmaxsb %xmm1, %xmm0
; SSE42-NEXT:    retq
;
; AVX-LABEL: test_v16i8_nosignbit:
; AVX:       # %bb.0:
; AVX-NEXT:    vmovdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX-NEXT:    vpand %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vpand %xmm2, %xmm1, %xmm1
; AVX-NEXT:    vpmaxsb %xmm1, %xmm0, %xmm0
; AVX-NEXT:    retq
  %1 = and <16 x i8> %a, <i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15>
  %2 = and <16 x i8> %b, <i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15, i8 15>
  %3 = icmp sgt <16 x i8> %1, %2
  %4 = select <16 x i1> %3, <16 x i8> %1, <16 x i8> %2
  ret <16 x i8> %4
}