My best work is from 11pm to 4am but at around 5am I can start making serious mistakes. Within a few days I should get it to ~1kB per second vs 1kb per second in a non parallel non Linux non Cuda environment not from genius re tweaking or gen two but just cleaning the crap up and gutting calls that have no positive impact to this technique that works. Lots of calls all over the place since I was trying so many different techniques until I landed the MUCH more productive technique in terms of speed. In looking through my code I see that I should easily still be able to chop off some overhead and make it run even faster from removing calls that do not contribute to do anything. Only more recently in the last few weeks or so have I had a serious gain in speeds where it went from originally weeks to days to hours to seconds using various techniques. I did however compress encrypted files from AxCrypt at again 30% smaller. I can give it a try for for amusement and maybe it will hit 1% smaller if not have negative gains. I have not attempted to re-compress the output files as I do not expect any type of serious gains. With precomp I tried a few various other settings to optimize and ran it to compress it down to ~30% >~30% LESS NOT DOWN TO ~30%> was added after the post by me for clarity on March 19th 1pm ish EST Specifically used enwik8.rar and enwik8.zip and ran precomp048dev.exe default and precomp048dev.exe with -intense to create the pcf files for compression. I did a few optimizations and got it down to ~3 seconds per 1kb in the last 24 hours. I ran command line precomp with default settings and -intense and other optimizations and was able to chop off 30% of the resulting pcf files ~3 seconds per 1kb chunk. I assume I can get sub 1 second performance single thread from MASM I used to program in MASM and I will give that a go to increase speed further. Should be able to get it down to 1kb chunk processing in ~2 seconds in a single threaded 2.2Ghz windows environment. I think that is part of the entire process of compression/decompression and yes lossless as well. Decompressing to the original file is not an issue. The only problem I have with the Hutter prize is having to release the code at this point. This is not my site so I am happy to just be here. Oh I am able to compress Flac and FL4 ~50% which is not random data re: maybe moved to random data.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |