1 | |
1 | 3.6 Mon Feb 7 17:37:31 CET 2011 |
2 | - fixed hash calculation in C♯ version (Tiago Freitas Leal). |
2 | - fixed hash calculation in C♯ version (Tiago Freitas Leal). |
3 | - unroll copy for small sizes, use memcpy for larger sizes, |
3 | - unroll copy for small sizes, use memcpy for larger sizes, |
4 | greatly speeding up decompression in most cases. |
4 | greatly speeding up decompression in most cases. |
5 | - finally disable rep movsb - it's a big loss on modern intel cpus, |
5 | - finally disable rep movsb - it's a big loss on modern intel cpus, |
6 | and only a small win on amd cpus. |
6 | and only a small win on amd cpus. |
|
|
7 | - improve C++ compatibility of the code. |
|
|
8 | - slightly improve compressor speed. |
|
|
9 | - halved memory requirements for compressor on 64 bit architectures, |
|
|
10 | which can improve the speed quite a bit on older cpus. |
7 | |
11 | |
8 | 3.5 Fri May 1 02:28:42 CEST 2009 |
12 | 3.5 Fri May 1 02:28:42 CEST 2009 |
9 | - lzf_compress did sometimes write one octet past the given output |
13 | - lzf_compress did sometimes write one octet past the given output |
10 | buffer (analyzed and nice testcase by Salvatore Sanfilippo). |
14 | buffer (analyzed and nice testcase by Salvatore Sanfilippo). |
11 | |
15 | |