Lang Hames 5afba6f00c Add a new intrinsic: llvm.fmuladd. This intrinsic represents a multiply-add ...

expression (a * b + c) that can be implemented as a fused multiply-add (fma)
if the target determines that this will be more efficient. This intrinsic
will be used to implement FP_CONTRACT support and an aggressive FMA formation
mode.

If your target has a fast FMA instruction you should override the
isFMAFasterThanMulAndAdd method in TargetLowering to return true.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158014 91177308-0d34-0410-b5e6-96231b3b80d8

2012-06-05 19:07:46 +00:00

..

Analysis

Fix typos found by http://github.com/lyda/misspell-check

2012-06-02 10:20:22 +00:00

Archive

…

AsmParser

switch AttrListPtr::get to take an ArrayRef, simplifying a lot of clients.

2012-05-28 01:47:44 +00:00

Bitcode

PR1255: case ranges.

2012-06-02 09:42:43 +00:00

CodeGen

Add a new intrinsic: llvm.fmuladd. This intrinsic represents a multiply-add

2012-06-05 19:07:46 +00:00

DebugInfo

…

ExecutionEngine

Fix typos found by http://github.com/lyda/misspell-check

2012-06-02 10:20:22 +00:00

Linker

Supply a C interface to the "LinkModules" method.

2012-05-09 08:55:40 +00:00

MC

misched: Added MultiIssueItineraries.

2012-06-05 03:44:40 +00:00

Object

Mark some static arrays as const.

2012-05-24 06:35:32 +00:00

Support

Use access(2) instead of stat(2) to check if a file exists.

2012-06-02 16:28:09 +00:00

TableGen

Fix 80 columns.

2012-06-01 00:58:41 +00:00

Target

Fix header file include order in NVPTX backend NV_CONTRIB

2012-06-05 19:06:13 +00:00

Transforms

LoopUnroll: always check for NULL LoopPassManager

2012-06-05 17:51:05 +00:00

VMCore

Simplify the fma4 renaming code.

2012-06-03 16:48:52 +00:00

CMakeLists.txt

…

LLVMBuild.txt

…

Makefile

…