llvm/lib
Rafael Espindola 6b83b5d1ae call libc memcpy/memset if array size is bigger then threshold.
Coping 100MB array (after a warmup) shows that glibc 2.6.1 implementation on
x86-64 (core 2) is 30% faster (from 0.270917s to 0.188079s)



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@41479 91177308-0d34-0410-b5e6-96231b3b80d8
2007-08-27 10:18:20 +00:00
..
Analysis Use SmallVector. 2007-08-21 16:54:51 +00:00
Archive finishing touches of bytecode -> bitcode changes. also unbreak Windows 2007-07-06 20:28:40 +00:00
AsmParser regenerate 2007-08-06 21:00:46 +00:00
Bitcode Patch 10 for long double. Doing constants right needs expanding ConstantFP 2007-08-09 22:51:36 +00:00
CodeGen Revise per review comments. 2007-08-26 01:18:27 +00:00
Debugger switch this to bitcode instead of bytecode 2007-05-06 09:29:13 +00:00
ExecutionEngine rename APInt::toString -> toStringUnsigned for symmetry with toStringSigned() 2007-08-23 05:15:32 +00:00
Linker Fix PR1611 - Visibility should be ignored for a declaration 2007-08-19 22:22:54 +00:00
Support Poison APFloat::operator==. Replace existing uses with bitwiseIsEqual. 2007-08-24 22:09:56 +00:00
System Fix PR1581, patch by Timo Savola 2007-07-31 06:00:51 +00:00
Target call libc memcpy/memset if array size is bigger then threshold. 2007-08-27 10:18:20 +00:00
Transforms Don't promote volatile loads/stores. This is needed (for example) to handle setjmp/longjmp properly. 2007-08-26 21:43:30 +00:00
VMCore Poison APFloat::operator==. Replace existing uses with bitwiseIsEqual. 2007-08-24 22:09:56 +00:00
Makefile build lib/Archive instead of lib/Bytecode 2007-05-06 19:50:06 +00:00