RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2024-12-13 23:18:58 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

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

Browse Source 
Reviewers: jbhateja

Reviewed By: jbhateja

Subscribers: llvm-commits

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

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313869 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Jatin Bhateja 2017-09-21 09:53:21 +00:00
parent 00cc3caa4d
commit 5713c8d1d3
1 changed files with 47 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
test/CodeGen/X86/fmf-flags.ll Normal file
View File

@ -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
}