diff options
| author | Sanjay Patel <spatel@rotateright.com> | 2015-05-22 21:10:06 +0000 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2015-05-22 21:10:06 +0000 |
| commit | ba2ba80302182bcf1773c560b592949cd9a1d501 (patch) | |
| tree | 925620c95192cb142122963aa9512b1676a00243 /llvm/test/CodeGen/X86/recip-fastmath.ll | |
| parent | b2f6afb30ac3285f2d2db310ed283398860f12fc (diff) | |
| download | bcm5719-llvm-ba2ba80302182bcf1773c560b592949cd9a1d501.tar.gz bcm5719-llvm-ba2ba80302182bcf1773c560b592949cd9a1d501.zip | |
make reciprocal estimate code generation more flexible by adding command-line options
This patch adds a class for processing many recip codegen possibilities.
The TargetRecip class is intended to handle both command-line options to llc as well
as options passed in from a front-end such as clang with the -mrecip option.
The x86 backend is updated to use the new functionality.
Only -mcpu=btver2 with -ffast-math should see a functional change from this patch.
All other CPUs continue to *not* use reciprocal estimates by default with -ffast-math.
Differential Revision: http://reviews.llvm.org/D8982
llvm-svn: 238051
Diffstat (limited to 'llvm/test/CodeGen/X86/recip-fastmath.ll')
| -rw-r--r-- | llvm/test/CodeGen/X86/recip-fastmath.ll | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/llvm/test/CodeGen/X86/recip-fastmath.ll b/llvm/test/CodeGen/X86/recip-fastmath.ll index fcd077092da..7f1521a83bc 100644 --- a/llvm/test/CodeGen/X86/recip-fastmath.ll +++ b/llvm/test/CodeGen/X86/recip-fastmath.ll @@ -1,6 +1,6 @@ ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 | FileCheck %s -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx,use-recip-est | FileCheck %s --check-prefix=RECIP -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx,use-recip-est -x86-recip-refinement-steps=2 | FileCheck %s --check-prefix=REFINE +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=divf,vec-divf | FileCheck %s --check-prefix=RECIP +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=divf:2,vec-divf:2 | FileCheck %s --check-prefix=REFINE ; If the target's divss/divps instructions are substantially ; slower than rcpss/rcpps with a Newton-Raphson refinement, |
