Svarychevski Michail Aleksandrovich put up a version of BarsWF for ATI BROOK not long ago, but the results were less than spectacular. I recently updated to CCC 9.5 and wanted to give it another shot. Here are my hardware specs for my Vista 64 box:
CPUZ – Stock clock speeds.
cpuz
GPUZ – Also stock speeds.
gpuz

And here is the BarsWF run.
barswf

This particular run is a demo of ideal circumstances. I know the passwords charset and length, so I specified it in the command line:

C:\sec\md5>BarsWF_Brook_x64.exe -h d19ff6fb09cafa03d51ecac250bf71a8 -c 0A -min_len 10

Here is the same run under less than ideal circumstances. I don’t know anything about the hash, so I will just run the defaults:
barswf-2

C:\sec\md5>BarsWF_Brook_x64.exe -h d19ff6fb09cafa03d51ecac250bf71a8 -c 0aA~

So, we can see that it is indeed quite fast when running the full charset, though it should be noted that the ETA is quite off. It will likely reset a few times before finding the hash. It’s great to know that ATI owners have a GPU bruteforce option now. I’d really like to see this tech developed further to include other hash methods as well.

**UPDATE**
Here’s a screen of its memory usage after about 5 hours of running.
taskmgr
Looks like it’s using around 100MB RAM per hour at this point. I’ll continue to watch it and hopefully have it finish before start paging every thing (which is a must-reboot scenario with Vista for some reason).

Just read a great howto on Perishable Press demonstrating a few ways to optimize PNG without losing image quality. I noticed that OptiPNG hadn’t been updated so I decided to compile it myself. I just got my build environment set up to compile x64 as well, so I decided to give that a shot while I was at it. I noticed a fairly significant decrease in optimization time with the x64 version on my hardware so I figured I’d share the binary. You mileage may vary, depending on your hardware, but here are my unscientific benchmarks based on a small 3DS rendering I did not long ago:

Source: 640×480 pixels, 4×16 bits/pixel, RGB+alpha

OptiPNG 0.6.2.1 x32:
Output IDAT size = 384602 bytes (10771 bytes decrease)
Output file size = 384659 bytes (11347 bytes = 2.87% decrease)

46.9 seconds

OptiPNG 0.6.2.1 x64:
Output IDAT size = 384602 bytes (10771 bytes decrease)
Output file size = 384659 bytes (11347 bytes = 2.87% decrease)

41.6 seconds

For very large and complex files, the time/size savings are marginal, but could be useful when processing a large batch of files. Another intersting feature of OptiPNG is it’s ability to work with 48bit PNG’s… a feature that many commercial tools seem to lack.

Source: 1920×1080 pixels, 4×16 bits/pixel, RGB+alpha

OptiPNG 0.6.2.1 x32:
Output IDAT size = 9816277 bytes (108632 bytes decrease)
Output file size = 9816334 bytes (123164 bytes = 1.24% decrease)

16 minutes, 46 seconds

OptiPNG 0.6.2.1 x64:
Output IDAT size = 9816277 bytes (108632 bytes decrease)
Output file size = 9816334 bytes (123164 bytes = 1.24% decrease)

16 minutes, 20 seconds

Here are the same files optimized by pngcrush for comparison *official win32 binary only as I was unable to get it compiled for either arch.

Small file (29.000 seconds):
Best pngcrush method = 124 (fm 5 zl 9 zs 1) for small.png
(2.65% IDAT reduction)
(2.80% filesize reduction)

CPU time used = 29.000 seconds (decoding 2.962,
encoding 25.868, other 0.170 seconds)

Large file (9.99835 minutes):
Best pngcrush method = 12 (fm 1 zl 2 zs 2) for large.png
(1.09% IDAT reduction)
(1.24% filesize reduction)

CPU time used = 599.901 seconds (decoding 25.295,
encoding 571.670, other 2.936 seconds)

Download OptiPNG 0.6.2.1 x64 Windows Binary

MD5: a7bb617dce7991b0814ed5c1534a0845
SHA1: 3d206584075b2ce555d2d7b3379e480101bccffd

This x64 package is not built or maintained by Cosmin TruĊ£a, the creator of OptiPNG. Please don’t bother him with bug reports or help requests unless you’ve confirmed the problem exists in his official packages as well.

© 2010 nukeitdotorg Suffusion WordPress theme by Sayontan Sinha