Author: Robert Hyatt
Date: 18:02:56 05/07/04
Go up one level in this thread
On May 07, 2004 at 19:31:34, Vincent Diepeveen wrote: >On May 07, 2004 at 12:02:28, Robert Hyatt wrote: > >>On May 07, 2004 at 11:53:29, Andreas Guettinger wrote: >> >>>On May 07, 2004 at 04:38:00, Vincent Diepeveen wrote: >>> >>>>On May 06, 2004 at 19:03:48, martin fierz wrote: >>>> >>>>>aloha! >>>>> >>>>>bob posted some crafty logfiles running a 24-position test set on his ftp site >>>>>(for anyone else crazy enough to repeat what i did: >>>>>ftp.cis.uab.edu/pub/hyatt/smpdata) >>>>> >>>>>these are logfiles of crafty running as single CPU, dual, or quad; on opterons. >>>>>i took the last completed ply on the single CPU set for each position (marked by >>>>>-> in the logfile, i hope...), wrote down the time to complete this ply, and did >>>>>this for all logfiles. there are 9 of these, 4 repeats for 2 and 4 CPUs. i >>>>>computed the speedup for time-to-finish-ply-X for each of the multi-CPU runs >>>>>with the following results: >>>>> >>>>>2 CPUs: >>>>>1.961 +- 0.093 >>>>>1.888 +- 0.074 >>>>>1.846 +- 0.078 >>>>>1.763 +- 0.084 >>>>> >>>>>4 CPUs: >>>>>3.15 +- 0.15 >>>>>3.29 +- 0.20 >>>>>3.06 +- 0.12 >>>>>3.19 +- 0.13 >>>>> >>>>>now, is there any meaning to this, and if yes, what? >>>>> >>>>>point #1 to make is that the numbers here are mutually consistent with each >>>>>other, given the error margins quoted. which should show those skeptical of this >>>>>statistical approach that it makes sense to do it this way, rather than to just >>>>>write "i measured speedup 3.1". >>>>> >>>>>point #2 is that the speedup on 4 CPUs on average is 3.17 in this test, which >>>>>might be one point for bob in the duel with vincent; although i suspect that the >>>>>speedup depends on the hardware architecture - i will leave this question to the >>>>>parallel computing experts though... >>>> >>>>Bob has tested the SMP version 1 cpu versus SMP version 2 or 4 cpus. The single >>>>cpu version of crafty is just hardly existing because of a stupid thread pointer >>>>which is a constant. Optimizing that crafty is 5% faster for sure in time single >>>>cpu at opteron. >>> >>>I don't understand that. What does that mean? >>> >>>regards >>>Andy >> >>Ever heard of "the fog of war"? This is "the fog of vincent". >> >>In crafty, I pass a pointer to a "TREE struct" around so that each thread can >>use a different struct for their local tree state. This is done even with mt=0 >>or when Crafty is compiled with no SMP support. Vincent claims it would speed >>Crafty up by 5% if the pointer were removed. That would be neat as it didn't >>slow me down 5% when I added the pointer. >> >>But that's irrelevant because Vincent has said so... >> >>IE everywhere that I now say tree->something such as: >> >>tree->node_count++; >> >>could be replaced by a non-pointer: >> >>node_count++; >> >>It doesn't cost 5%... > >I have spoken to several commercial programmers and we all had similar results. >Such an optimization (just for single cpu) will save 5-10%. Most claim 10%. > >Whether it's 4 or 5 or 6% is irrelevant. > >You just compare apples to petatoes. Actually I compare reality to moron. Guess who's the moron? It is 2-3%. On opteron even less with the extra 8 registers. Try 14.x vs 15.0 if you can find one. That'll answer the question once and for all. It is _amazing_ how many different ways you want to attack Crafty's parallel search. First, it won't go 3x faster on 4 cpus. That gets shitcanned so you want to use a different test set. That gets shitcanned. Now you claim that 2-3% slower 1-cpu program is not fair. Just take the current 1cpu number and reduce by 3% and see what happens to the speedup numbers. That gets shitcanned. Why don't you post some of your outstanding results. Complete log files. Both you and GCP always demand _mine_. You _never_ produce any of your own. Either of you. Why is that? Got something to hide? I don't...
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.