Just for fun, how long does it normally take to generate through 5 pieces? and then 6 pieces? If it is reasonable, I can give it a whirl just to see how this thing works, if your generator is available?syzygy wrote:Indeed...bob wrote:Would be one hell of a machine to generate endgame tables..
Interesting machine
Moderators: hgm, Rebel, chrisw
-
- Posts: 20943
- Joined: Mon Feb 27, 2006 7:30 pm
- Location: Birmingham, AL
Re: Interesting machine
-
- Posts: 5566
- Joined: Tue Feb 28, 2012 11:56 pm
Re: Interesting machine
5 pieces take about an hour on my machine (i7-3930K at 4.2Ghz, 6 cores / 12 threads). 6 pieces around 100x as long.bob wrote:Just for fun, how long does it normally take to generate through 5 pieces? and then 6 pieces? If it is reasonable, I can give it a whirl just to see how this thing works, if your generator is available?syzygy wrote:Indeed...bob wrote:Would be one hell of a machine to generate endgame tables..
My generator is available (see signature), but it expects a little endian machine and it uses a bit of x86 inline assembly for atomically doing updates to the tablebase arrays.
The inline assembly can now be replaced with C11 atomics (if you have a relatively recent gcc). That should not take me much time.
The endianness might be a non-issue, but that is not clear to me. What does the machine / the OS expect? But it can in any case be fixed and I should probably do that anyway at some point.
-
- Posts: 838
- Joined: Thu Jul 05, 2007 5:03 pm
- Location: British Columbia, Canada
Re: Interesting machine
Just an aside.. its awesome that we now live in a world where someone can generate 6-piece tablebases for chess in less than a week on a single machine costing only a few thousand dollars. (At least using a sufficiently-clever generator, which yours is)syzygy wrote:5 pieces take about an hour on my machine (i7-3930K at 4.2Ghz, 6 cores / 12 threads). 6 pieces around 100x as long.
-
- Posts: 113
- Joined: Mon Nov 28, 2011 10:17 am
Re: Interesting machine
Benchmark! Please Robert!
-
- Posts: 20943
- Joined: Mon Feb 27, 2006 7:30 pm
- Location: Birmingham, AL
Re: Interesting machine
It is about 80% as fast as the 2660 20 core box I have been using...hammerklavier wrote:Benchmark! Please Robert!
I have it running a LONG smp test. When that finishes I will post the bench output for that and the 2660 machine...
-
- Posts: 199
- Joined: Sun Nov 03, 2013 9:32 am
Re: Interesting machine
Hi bob,
I have an old commadore 64 you can also
I have an old commadore 64 you can also
-
- Posts: 199
- Joined: Sun Nov 03, 2013 9:32 am
Re: Interesting machine
Hi bob,
I have an old commadore 64 you can also
I have an old commadore 64 you can also
-
- Posts: 20943
- Joined: Mon Feb 27, 2006 7:30 pm
- Location: Birmingham, AL
Re: Interesting machine
This is a bit newer. 20 cores, 1 terabyte of DRAM. Got anything close?lauriet wrote:Hi bob,
I have an old commadore 64 you can also
-
- Posts: 199
- Joined: Sun Nov 03, 2013 9:32 am
Re: Interesting machine
Well the commadore comes with a nice shinny 5 1/4" drive.
Surely that sweatens the offer ?
Surely that sweatens the offer ?
-
- Posts: 5566
- Joined: Tue Feb 28, 2012 11:56 pm
Re: Interesting machine
OK, if you are interested, you could try this version:syzygy wrote:5 pieces take about an hour on my machine (i7-3930K at 4.2Ghz, 6 cores / 12 threads). 6 pieces around 100x as long.bob wrote:Just for fun, how long does it normally take to generate through 5 pieces? and then 6 pieces? If it is reasonable, I can give it a whirl just to see how this thing works, if your generator is available?syzygy wrote:Indeed...bob wrote:Would be one hell of a machine to generate endgame tables..
My generator is available (see signature), but it expects a little endian machine and it uses a bit of x86 inline assembly for atomically doing updates to the tablebase arrays.
The inline assembly can now be replaced with C11 atomics (if you have a relatively recent gcc). That should not take me much time.
The endianness might be a non-issue, but that is not clear to me. What does the machine / the OS expect? But it can in any case be fixed and I should probably do that anyway at some point.
https://github.com/syzygy1/tb/tree/c11
https://github.com/syzygy1/tb/archive/c11.zip
It requires a relatively recent gcc (with c11 atomics support).
- download the zip file and extract
- specify desired number of max threads in src/Makefile (-DMAX_THREADS=N)
- make all
- test, e.g. with 8 threads: ./rtbgen -t 8 KQvK
- see if probing of KQvK works: ./rtbgen -t 8 KQQvK
This should create four files:
Code: Select all
$ md5sum *.rtbw?
21070fc6c230cce12f6f6b615c9f1eb4 KQQvK.rtbw
fccaac715e6b2d5540db71ebe6284b49 KQQvK.rtbz
f06221548404795b6b33469e247b4560 KQvK.rtbw
ac866466e16eb19a4f8c796f8e1abd2b KQvK.rtbz
(If the md5sums do not match but the file sizes do, my attempt to port the internal (non-md5) checksum calculation to big endian was not yet fully successful.)
rtbgen creates pawnless tables, rtbgenp creates pawnful tables.
Create all 5-piece TBs:
Code: Select all
$ ./run.pl --generate --threads 160 --min 3 --max 5
Don't bother with rtbver and rtbverp (or with ./run.pl --verify).
Of course untested on a power 8 machine, so the above is likely to break down at some point .