Give full play to the gift of God.

Note: I think it is very rare to have the opportunity to do this project. I feel very grateful that I want to do it well, so I will use this title.

 

The comment from Linus is "the code looks clever and nice "!

 

A. memcpy in Linux Kernel

Patch: https://patchwork.kernel.org/patch/296282/

Commit ID: 59daa706fbec745684702741b9f5373142dd9fdc

First completely avoid Memory false dependence in CPU pipeline, which impacts all x86 CPU, the performance is improved up to 3x, pushed into Linux kernel release version, and replaced original one, which stayed for 8 years.

 

B. memmove in Linux Kernel

Patch: http://lkml.org/lkml/2010/9/16/502

Commit ID: 3b4b682becdfa9f42321aa024d5cc84f71f06d8c

Avoid long latency and some limitation from mov string instruction, which cost much time in decoding stage, and memory false dependence for unaligned cases.

H. J and I provide the below codes.

 

A. 64bit memcpy/memmove for atom, core2 and core i7

Http://article.gmane.org/gmane.comp.lib.glibc.alpha/15278

This patch already des optimized 64bit memcpy/memmove for atom, Core 2 and

Core i7. it improves memcpy up to 3x on Atom, up to 4x on Core 2 and

Up to 1x on core i7. it also improves memmove by up to 3x on Atom, up

4x on Core 2 and up to 2x on core i7.

 

B. 64bit memcmp for core i7

Http://sourceware.org/ml/libc-alpha/2010-04/msg00030.html

This is 64bit SSE4 optimized memcmp. It improves memcmp by up to 3X

on Intel Core i7.

 

C. 64bit strcmp

Http://sources.redhat.com/ml/libc-alpha/2009-07/msg00063.html

The code is checked in glibc and opensolaris library.

 

D. 64bit strcpy

Http://src.opensolaris.org/source/xref/onnv/onnv-gate/usr/src/lib/libc/amd64/gen/strcpy.s

The code is checked in glibc and opensolaris library.

 

E. 32bit memset/memcpy for atom, core2 and corei7

Http://sources.redhat.com/ml/libc-alpha/2010-01/msg00016.html

Their performances are all improved up to 3x ~ 4x, pushed into moblin libc successfully.

 

F. 32bit memcmp/strcmp/strncmp for atom, core2 and corei7.

Http://sourceware.org/ml/libc-alpha/2010-02/msg00028.html

The patch is to provide 32bit memcmp/strcmp/strncmp optimized

Ssse3/sss4.2. it can improve memcmp by up to 3x, strcmp by up to 7X