| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5 |
| ; RUN: llc < %s -mtriple=x86_64 -mattr=+fma | FileCheck %s |
| |
| define <4 x float> @pr138982(<4 x float> %in_vec) { |
| ; CHECK-LABEL: pr138982: |
| ; CHECK: # %bb.0: # %entry |
| ; CHECK-NEXT: vxorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1 |
| ; CHECK-NEXT: vrcpps %xmm0, %xmm2 |
| ; CHECK-NEXT: vrcpps %xmm1, %xmm1 |
| ; CHECK-NEXT: vxorps %xmm3, %xmm3, %xmm3 |
| ; CHECK-NEXT: vcmpneqps %xmm0, %xmm3, %xmm0 |
| ; CHECK-NEXT: vbroadcastss {{.*#+}} xmm4 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0] |
| ; CHECK-NEXT: vblendvps %xmm0, %xmm1, %xmm4, %xmm0 |
| ; CHECK-NEXT: vfnmadd231ps {{.*#+}} xmm0 = -(xmm3 * xmm2) + xmm0 |
| ; CHECK-NEXT: retq |
| entry: |
| %fneg = fneg <4 x float> %in_vec |
| %rcp = tail call <4 x float> @llvm.x86.sse.rcp.ps(<4 x float> %fneg) |
| %cmp = fcmp une <4 x float> zeroinitializer, %in_vec |
| %sel = select <4 x i1> %cmp, <4 x float> %rcp, <4 x float> splat (float 1.000000e+00) |
| %fma = call nsz <4 x float> @llvm.fma.v4f32(<4 x float> %rcp, <4 x float> zeroinitializer, <4 x float> %sel) |
| ret <4 x float> %fma |
| } |