File: insertps-from-constantpool.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 (20 lines) | stat: -rw-r--r-- 872 bytes parent folder | download | duplicates (20)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
; RUN: llc -mtriple=i686-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s --check-prefix=X32
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s --check-prefix=X64

; Test for case where insertps folds the load of an insertion element from a constant pool.

define <4 x float> @fold_from_constantpool(<4 x float> %a) {
; X32-LABEL: fold_from_constantpool:
; X32:       # %bb.0:
; X32-NEXT:    insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
; X32-NEXT:    retl
;
; X64-LABEL: fold_from_constantpool:
; X64:       # %bb.0:
; X64-NEXT:    insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
; X64-NEXT:    retq
  %1 = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> <float 0.0, float 1.0, float 0.0, float 0.0>, i8 64)
  ret <4 x float> %1
}

declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone