From f9d74b7d33f7a4c50073b8eeebc21d05a6ad0876 Mon Sep 17 00:00:00 2001 From: Craig Topper Date: Tue, 6 Dec 2016 08:08:09 +0000 Subject: [PATCH] [X86] Add test case demonstrating a case where a vector sqrt being passed (scalar_to_vector loadf64) uses a scalar sqrt instruction. This occurs due to a pattern that uses sse_load_f32/f64 with vector sqrt/rcp/rsqrt operations and turns them into scalar instructions. Perhaps for the case were the upper bits come from undef this is ok. I believe a (vzmovl load64) would do the same thing but those seems to become vzload instead and selectScalarSSELoad doesn't handle that today. In that case we should be performing the vector operation on the zeros in the upper bits which is not equivalent to using a scalar instruction. I will remove this pattern in a follow up patch. There appears to be no other test content for it. llvm-svn: 288783 --- test/CodeGen/X86/avx-arith.ll | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/test/CodeGen/X86/avx-arith.ll b/test/CodeGen/X86/avx-arith.ll index edf2ef1cd82..0f3b0c93810 100644 --- a/test/CodeGen/X86/avx-arith.ll +++ b/test/CodeGen/X86/avx-arith.ll @@ -360,3 +360,15 @@ define <4 x float> @int_sqrt_ss() { %x2 = call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %x1) nounwind ret <4 x float> %x2 } + +define <2 x double> @vector_sqrt_scalar_load(double* %a0) optsize { +; CHECK-LABEL: vector_sqrt_scalar_load: +; CHECK: ## BB#0: +; CHECK-NEXT: vsqrtsd (%rdi), %xmm0, %xmm0 +; CHECK-NEXT: retq + %a1 = load double, double* %a0 + %a2 = insertelement <2 x double> undef, double %a1, i32 0 + %res = call <2 x double> @llvm.sqrt.v2f64(<2 x double> %a2) ; <<2 x double>> [#uses=1] + ret <2 x double> %res +} +declare <2 x double> @llvm.sqrt.v2f64(<2 x double>) nounwind readnone