From c0218923e1b0227fd030dd353d097437dfb9b209 Mon Sep 17 00:00:00 2001 From: Sanjay Patel Date: Sun, 19 Nov 2017 17:31:37 +0000 Subject: [PATCH] [x86] add sqrt tests for partially-inline-libcalls (PR31455) llvm-svn: 318630 --- llvm/test/CodeGen/X86/sqrt-partial.ll | 43 +++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 llvm/test/CodeGen/X86/sqrt-partial.ll diff --git a/llvm/test/CodeGen/X86/sqrt-partial.ll b/llvm/test/CodeGen/X86/sqrt-partial.ll new file mode 100644 index 0000000..b4b53f1 --- /dev/null +++ b/llvm/test/CodeGen/X86/sqrt-partial.ll @@ -0,0 +1,43 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s + +; PR31455 - https://bugs.llvm.org/show_bug.cgi?id=31455 +; We have to assume that errno can be set, so we have to make a libcall in that case. +; But it's better for perf to check that the argument is valid rather than the result of +; sqrtss/sqrtsd. +; Note: This is really a test of the -partially-inline-libcalls IR pass (and we have an IR test +; for that), but we're checking the final asm to make sure that comes out as expected too. + +define float @f(float %val) nounwind { +; CHECK-LABEL: f: +; CHECK: # BB#0: +; CHECK-NEXT: sqrtss %xmm0, %xmm1 +; CHECK-NEXT: ucomiss %xmm1, %xmm1 +; CHECK-NEXT: jp .LBB0_2 +; CHECK-NEXT: # BB#1: # %.split +; CHECK-NEXT: movaps %xmm1, %xmm0 +; CHECK-NEXT: retq +; CHECK-NEXT: .LBB0_2: # %call.sqrt +; CHECK-NEXT: jmp sqrtf # TAILCALL + %res = tail call float @sqrtf(float %val) + ret float %res +} + +define double @d(double %val) nounwind { +; CHECK-LABEL: d: +; CHECK: # BB#0: +; CHECK-NEXT: sqrtsd %xmm0, %xmm1 +; CHECK-NEXT: ucomisd %xmm1, %xmm1 +; CHECK-NEXT: jp .LBB1_2 +; CHECK-NEXT: # BB#1: # %.split +; CHECK-NEXT: movapd %xmm1, %xmm0 +; CHECK-NEXT: retq +; CHECK-NEXT: .LBB1_2: # %call.sqrt +; CHECK-NEXT: jmp sqrt # TAILCALL + %res = tail call double @sqrt(double %val) + ret double %res +} + +declare float @sqrtf(float) +declare double @sqrt(double) + -- 2.7.4