[arch-general] imagemagick 18.104.22.168-1 is slower than 22.214.171.124-1
archlinux at cryptocrack.de
Fri Oct 17 18:58:22 UTC 2014
On Fri, 17 Oct 2014 at 04:39:33, Matthew Wynn wrote:
> After upgrading to imagemagick 126.96.36.199-1, I've found it to be a lot slower than 188.8.131.52-1. I only get this issue when downloading from the repositories or using the PKGBUILD, not when compiling using the instructions at imagemagic.org.
> I've discussed the issue with the ImageMagick developers, which you can find at http://www.imagemagick.org/discourse-server/viewtopic.php?f=3&t=26369&sid=a29400f51bd723e98da6b74c0819e9b3. Even when trying to convert a 500x500 image to 100x100, it appears that an image that is 2048x1536 is created.
> I've tried this on multiple Arch machines with the same result.
Anatol and I were able to reproduce this issue. It seems to be related
to __memcpy_avx_unaligned() in glibc which means that it only occurs on
architectures with the AVX extension.
If you have a look at the memcpy-avx-unaligned.S source code , you
will notice that there are several branches that copy blocks of
different sizes. Now, for some reason, 184.108.40.206-1 always (or almost
always) picks the L(less_32bytes) branch which means that only small
blocks are copied, while 220.127.116.11-1 copies larger blocks. I do not have
the time to debug this in detail but maybe you can add this information
to the upstream report?
More information about the arch-general