diff options
| -rw-r--r-- | llvm/test/CodeGen/X86/scalarize-fp.ll | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/X86/scalarize-fp.ll b/llvm/test/CodeGen/X86/scalarize-fp.ll index 650b948..5c72d4b 100644 --- a/llvm/test/CodeGen/X86/scalarize-fp.ll +++ b/llvm/test/CodeGen/X86/scalarize-fp.ll @@ -773,3 +773,29 @@ define <8 x float> @splat0_fdiv_const_op0_v8f32(<8 x float> %vx) { %r = shufflevector <8 x float> %b, <8 x float> undef, <8 x i32> zeroinitializer ret <8 x float> %r } + +define <4 x float> @multi_use_binop(<4 x float> %x, <4 x float> %y) { +; SSE-LABEL: multi_use_binop: +; SSE: # %bb.0: +; SSE-NEXT: movaps %xmm0, %xmm2 +; SSE-NEXT: mulps %xmm1, %xmm2 +; SSE-NEXT: mulss %xmm1, %xmm0 +; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0,0,0] +; SSE-NEXT: movlhps {{.*#+}} xmm1 = xmm1[0],xmm2[0] +; SSE-NEXT: addps %xmm1, %xmm0 +; SSE-NEXT: retq +; +; AVX-LABEL: multi_use_binop: +; AVX: # %bb.0: +; AVX-NEXT: vmulps %xmm1, %xmm0, %xmm2 +; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm0 +; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0] +; AVX-NEXT: vmovddup {{.*#+}} xmm1 = xmm2[0,0] +; AVX-NEXT: vaddps %xmm1, %xmm0, %xmm0 +; AVX-NEXT: retq + %mul = fmul <4 x float> %x, %y + %mul0 = shufflevector <4 x float> %mul, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 undef, i32 0> + %mul1 = shufflevector <4 x float> %mul, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 undef, i32 1> + %r = fadd <4 x float> %mul0, %mul1 + ret <4 x float> %r +} |