File: insertps-from-constantpool.ll

package info (click to toggle)
llvm-toolchain-18 1%3A18.1.8-20
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 1,909,296 kB
  • sloc: cpp: 6,667,975; ansic: 1,440,452; asm: 883,619; python: 230,549; objc: 76,880; f90: 74,238; lisp: 35,989; pascal: 16,571; sh: 10,229; perl: 7,459; ml: 5,047; awk: 3,523; makefile: 2,992; javascript: 2,149; xml: 892; fortran: 649; cs: 573
file content (20 lines) | stat: -rw-r--r-- 872 bytes parent folder | download | duplicates (21) 
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