[llvm] r313869 - [X86] Adding a testpoint for fast-math flags propagation.

[Jatin Bhateja via llvm-commits]

Author: jbhateja
Date: Thu Sep 21 02:53:21 2017
New Revision: 313869

URL: http://llvm.org/viewvc/llvm-project?rev=313869&view=rev
Log:
[X86] Adding a testpoint for fast-math flags propagation.

Reviewers: jbhateja

Reviewed By: jbhateja

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D38127

Added:
    llvm/trunk/test/CodeGen/X86/fmf-flags.ll

Added: llvm/trunk/test/CodeGen/X86/fmf-flags.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/fmf-flags.ll?rev=313869&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/X86/fmf-flags.ll (added)
+++ llvm/trunk/test/CodeGen/X86/fmf-flags.ll Thu Sep 21 02:53:21 2017
@@ -0,0 +1,47 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s -check-prefix=X64
+; RUN: llc < %s -mtriple=i686-unknown   | FileCheck %s -check-prefix=X86
+
+declare float @llvm.sqrt.f32(float %x);
+
+define float @fast_recip_sqrt(float %x) {
+; X64-LABEL: fast_recip_sqrt:
+; X64:       # BB#0:
+; X64-NEXT:    sqrtss %xmm0, %xmm1
+; X64-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; X64-NEXT:    divss %xmm1, %xmm0
+; X64-NEXT:    retq
+;
+; X86-LABEL: fast_recip_sqrt:
+; X86:       # BB#0:
+; X86-NEXT:    flds {{[0-9]+}}(%esp)
+; X86-NEXT:    fsqrt
+; X86-NEXT:    fld1
+; X86-NEXT:    fdivp %st(1)
+; X86-NEXT:    retl
+  %y = call fast float @llvm.sqrt.f32(float %x)
+  %z = fdiv fast float 1.0,  %y
+  ret float %z
+}
+
+declare float @llvm.fmuladd.f32(float %a, float %b, float %c);
+
+define float @fast_fmuladd_opts(float %a , float %b , float %c) {
+; X64-LABEL: fast_fmuladd_opts:
+; X64:       # BB#0:
+; X64-NEXT:    movaps %xmm0, %xmm1
+; X64-NEXT:    addss %xmm1, %xmm1
+; X64-NEXT:    addss %xmm0, %xmm1
+; X64-NEXT:    movaps %xmm1, %xmm0
+; X64-NEXT:    retq
+;
+; X86-LABEL: fast_fmuladd_opts:
+; X86:       # BB#0:
+; X86-NEXT:    flds {{[0-9]+}}(%esp)
+; X86-NEXT:    fld %st(0)
+; X86-NEXT:    fadd %st(1)
+; X86-NEXT:    faddp %st(1)
+; X86-NEXT:    retl
+  %res = call fast float @llvm.fmuladd.f32(float %a, float 2.0, float %a)
+  ret float %res
+}