diff options
author | upstream source tree <ports@midipix.org> | 2015-03-15 20:14:05 -0400 |
---|---|---|
committer | upstream source tree <ports@midipix.org> | 2015-03-15 20:14:05 -0400 |
commit | 554fd8c5195424bdbcabf5de30fdc183aba391bd (patch) | |
tree | 976dc5ab7fddf506dadce60ae936f43f58787092 /zlib/contrib/asm586/README.586 | |
download | cbb-gcc-4.6.4-upstream.tar.bz2 cbb-gcc-4.6.4-upstream.tar.xz |
obtained gcc-4.6.4.tar.bz2 from upstream website;upstream
verified gcc-4.6.4.tar.bz2.sig;
imported gcc-4.6.4 source tree from verified upstream tarball.
downloading a git-generated archive based on the 'upstream' tag
should provide you with a source tree that is binary identical
to the one extracted from the above tarball.
if you have obtained the source via the command 'git clone',
however, do note that line-endings of files in your working
directory might differ from line-endings of the respective
files in the upstream repository.
Diffstat (limited to 'zlib/contrib/asm586/README.586')
-rw-r--r-- | zlib/contrib/asm586/README.586 | 43 |
1 files changed, 43 insertions, 0 deletions
diff --git a/zlib/contrib/asm586/README.586 b/zlib/contrib/asm586/README.586 new file mode 100644 index 000000000..6bb78f320 --- /dev/null +++ b/zlib/contrib/asm586/README.586 @@ -0,0 +1,43 @@ +This is a patched version of zlib modified to use +Pentium-optimized assembly code in the deflation algorithm. The files +changed/added by this patch are: + +README.586 +match.S + +The effectiveness of these modifications is a bit marginal, as the the +program's bottleneck seems to be mostly L1-cache contention, for which +there is no real way to work around without rewriting the basic +algorithm. The speedup on average is around 5-10% (which is generally +less than the amount of variance between subsequent executions). +However, when used at level 9 compression, the cache contention can +drop enough for the assembly version to achieve 10-20% speedup (and +sometimes more, depending on the amount of overall redundancy in the +files). Even here, though, cache contention can still be the limiting +factor, depending on the nature of the program using the zlib library. +This may also mean that better improvements will be seen on a Pentium +with MMX, which suffers much less from L1-cache contention, but I have +not yet verified this. + +Note that this code has been tailored for the Pentium in particular, +and will not perform well on the Pentium Pro (due to the use of a +partial register in the inner loop). + +If you are using an assembler other than GNU as, you will have to +translate match.S to use your assembler's syntax. (Have fun.) + +Brian Raiter +breadbox@muppetlabs.com +April, 1998 + + +Added for zlib 1.1.3: + +The patches come from +http://www.muppetlabs.com/~breadbox/software/assembly.html + +To compile zlib with this asm file, copy match.S to the zlib directory +then do: + +CFLAGS="-O3 -DASMV" ./configure +make OBJA=match.o |