Chris Lattner 45de191b0b Spill/restore X86 floating point stack registers with 64-bits of precision ...

instead of 80-bits of precision.  This fixes PR467.

This change speeds up fldry on X86 with LLC from 7.32s on apoc to 4.68s.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@18433 91177308-0d34-0410-b5e6-96231b3b80d8

2004-12-02 18:17:31 +00:00

..

Analysis

Fix DeadStoreElimination/2004-11-28-LiveStoreDeleted.ll

2004-11-28 20:30:15 +00:00

Archive

Compute the firstFileOffset correctly after reading the LLVM symbol table.

2004-11-28 03:13:02 +00:00

AsmParser

Fix PR463

2004-11-28 16:45:45 +00:00

Bytecode

RevisionNum is read by error(), initialize it early.

2004-11-30 16:58:18 +00:00

CodeGen

Fix SingleSource/UnitTests/2004-11-28-GlobalBoolLayout.c, and hopefully

2004-11-28 17:56:47 +00:00

Debugger

…

ExecutionEngine

Remove unneeded cast.

2004-12-01 17:13:05 +00:00

Linker

PR466:

2004-12-02 09:52:10 +00:00

Support

Up the compression threshold to 64K so we avoid it for all but the largest

2004-11-30 07:13:34 +00:00

System

Fix seriously broken implementation of GetMagicNumber.

2004-12-02 09:09:48 +00:00

Target

Spill/restore X86 floating point stack registers with 64-bits of precision

2004-12-02 18:17:31 +00:00

Transforms

Implement a FIXME by checking to make sure that a malloc is not being used

2004-12-02 07:11:07 +00:00

VMCore

Get GEP's working with packed types. Contributed by Morten Ofstad!

2004-12-01 17:12:16 +00:00

Makefile

…