Evan Cheng 8ca29326e1 Don't dag combine floating point select to max and min intrinsics. Those ...

take v4f32 / v2f64 operands and may end up causing larger spills / restores.
Added X86 specific nodes X86ISD::FMAX, X86ISD::FMIN instead.

This fixes PR996.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@31645 91177308-0d34-0410-b5e6-96231b3b80d8

2006-11-10 21:43:37 +00:00

..

Analysis

Remove redundant <cmath>.

2006-11-08 19:16:44 +00:00

Archive

…

AsmParser

For PR950:

2006-11-08 06:47:33 +00:00

Bytecode

Bump the bytecode version number to 7. Implement upgrade of version 6 and

2006-11-08 21:27:54 +00:00

CodeGen

Fix a dag combiner bug exposed by my recent instcombine patch. This fixes

2006-11-10 21:37:15 +00:00

Debugger

For PR786:

2006-11-02 20:25:50 +00:00

ExecutionEngine

if lazy compilation is disabled, print an error message and abort if

2006-11-09 19:32:13 +00:00

Linker

silence warnings

2006-11-09 05:18:12 +00:00

Support

Remove redundant <cmath>.

2006-11-08 19:16:44 +00:00

System

Unbreak VC++ build.

2006-11-05 19:31:28 +00:00

Target

Don't dag combine floating point select to max and min intrinsics. Those

2006-11-10 21:43:37 +00:00

Transforms

second patch to fix PR992/993.

2006-11-09 23:36:08 +00:00

VMCore

s/PassManagerAnalysisHelper/CommonPassManagerImpl

2006-11-10 21:33:13 +00:00

Makefile

…