| Simon Pilgrim | 2829c1c | 2015-11-21 21:42:26 +0000 | [diff] [blame] | 1 | ; RUN: llc -mtriple=i686-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s --check-prefix=X32 |
| 2 | ; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s --check-prefix=X64 |
| 3 | |
| 4 | ; Test for case where insertps folds the load of an insertion element from a constant pool. |
| 5 | |
| 6 | define <4 x float> @fold_from_constantpool(<4 x float> %a) { |
| 7 | ; X32-LABEL: fold_from_constantpool: |
| 8 | ; X32: # BB#0: |
| 9 | ; X32-NEXT: insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3] |
| 10 | ; X32-NEXT: retl |
| 11 | ; |
| 12 | ; X64-LABEL: fold_from_constantpool: |
| 13 | ; X64: # BB#0: |
| 14 | ; X64-NEXT: insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3] |
| 15 | ; X64-NEXT: retq |
| 16 | %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) |
| 17 | ret <4 x float> %1 |
| 18 | } |
| 19 | |
| 20 | declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone |