ChessUSA.com TalkChess.com
Hosted by Your Move Chess & Games
 
 FAQFAQ   SearchSearch   MemberlistMemberlist   UsergroupsUsergroups   RegisterRegister 
 ProfileProfile   Log in to check your private messagesLog in to check your private messages   Log inLog in 

uct on gpu
Post new topic    TalkChess.com Forum Index -> Computer Chess Club: Programming and Technical Discussions Flat
View previous topic :: View next topic  
Author Message
Daniel Shawul



Joined: 14 Mar 2006
Posts: 3053
Location: Ethiopia

PostPost subject: Re: uct on gpu    Posted: Thu Mar 08, 2012 1:08 pm Reply to topic Reply with quote

A ton of very serious bugs were fixed. For starters the uct select was completely broken producing rather strange shallow and uniform tree. But after the many bug fixes, it starts producing good result as shown below. Also the occupancy of my last test was at 50% so I have a chance to increase that to 100% by simply changing configurations. Infact the occupancy has been slightly increased on my current gpu to 67% after the register usage reduced when the bugs are fixed. So that directly translated to performance increase. On capability >1.3 block size of 256 gives 100% occupancy so that will be doubled performance if everything goes well.
One other thing is that now there is absolutely no synchronization (__syncthreads) except for the inherent warp sync. A warp is the smallest working unit to fetch a node from DRAM; previously it was a block. The threads in a warp can diverge since each does its own monte carlo game on the same initial board. That has speeded up the code and simplified it as well.
On the initial position e4! (this is HEX btw!) is chosen as the best move and it was expanded to depth 7 after 45 mil simulation. Time is decreased to 5.375sec compared to previous ~5.5. Tree is also very selective.
Code:

0.h8     22323755     45989376     0.485411
        1.a1       148364       291840     0.508374
        1.b1        88821       177152     0.501383
        1.c1        10350        20992     0.493045
        1.d1         7756        15872     0.488659
        1.e1         8021        16384     0.489563
        1.f1        36382        75264     0.483392
        1.g1        54957       116224     0.472854
        1.h1          947         2048     0.462402
        1.a2        58208       116224     0.500826
        1.b2       254948       501248     0.508626
        1.c2       174206       344064     0.506319
        1.d2        59118       116736     0.506425
        1.e2        58413       116224     0.502590
        1.f2        57629       116736     0.493669
        1.g2         1467         3072     0.477539
        1.h2          680         1536     0.442708
        1.a3        58347       117760     0.495474
        1.b3       239661       470528     0.509345
        1.c3       185939       364032     0.510777
        1.d3       238775       470528     0.507462
        1.e3       174534       344576     0.506518
        1.f3        53076       105472     0.503224
        1.g3        57767       117248     0.492691
        1.h3         1972         4096     0.481445
        1.a4        54223       111616     0.485799
        1.b4       156572       313344     0.499681
        1.c4       259251       508928     0.509406
        1.d4       402122       789504     0.509335
        1.e4      1890305      3686400     0.512778
        1.f4       120209       241152     0.498478
        1.g4        54437       108544     0.501520
        1.h4        57571       119296     0.482590
        1.a5        37182        76800     0.484141
        1.b5        58508       116736     0.501199
        1.c5       172019       337408     0.509825
        1.d5       149083       292352     0.509943
        1.e5     15977301     30803968     0.518677
        1.f5       256793       503296     0.510223
        1.g5        59556       117248     0.507949
        1.h5        57704       118784     0.485789
        1.a6         1699         3584     0.474051
        1.b6        58560       118784     0.492996
        1.c6        59423       117760     0.504611
        1.d6       225991       443392     0.509687
        1.e6       177571       348160     0.510027
        1.f6       211449       414720     0.509860
        1.g6       115356       231424     0.498462
        1.h6        57993       117760     0.492468
        1.a7         2211         4608     0.479818
        1.b7         1935         4096     0.472412
        1.c7        57972       118272     0.490158
        1.d7        58431       117760     0.496187
        1.e7        60376       119296     0.506102
        1.f7       225979       445952     0.506734
        1.g7       130554       256000     0.509977
        1.h7        59264       118784     0.498922
        1.a8         1896         4096     0.462891
        1.b8         1966         4096     0.479980
        1.c8         2192         4608     0.475694
        1.d8        57759       119296     0.484165
        1.e8         1983         4096     0.484131
        1.f8        58658       119296     0.491701
        1.g8        58889       117760     0.500076
        1.h8       127233       249856     0.509225
Total nodes   : 31499
Leaf  nodes   : 30985
Maximum depth : 7
Average depth : 3.72
Errors: no error
time 5375

_________________
https://sites.google.com/site/dshawul/
https://github.com/dshawul
Back to top
View user's profile Send private message Visit poster's website Yahoo Messenger
Display posts from previous:   
Subject Author Date/Time
uct on gpu Daniel Shawul Fri Feb 24, 2012 5:52 am
      Re: uct on gpu Srdja Matovic Fri Feb 24, 2012 8:17 am
      Re: uct on gpu Srdja Matovic Fri Feb 24, 2012 8:45 am
            Re: uct on gpu Daniel Shawul Fri Feb 24, 2012 1:00 pm
                  Re: uct on gpu Srdja Matovic Fri Feb 24, 2012 1:44 pm
                        Re: uct on gpu Daniel Shawul Fri Feb 24, 2012 2:28 pm
                              Re: uct on gpu Srdja Matovic Fri Feb 24, 2012 3:04 pm
                                    Re: uct on gpu Daniel Shawul Fri Feb 24, 2012 3:53 pm
                  Re: uct on gpu david nash Sun Feb 26, 2012 12:42 am
                        Re: uct on gpu Daniel Shawul Thu Mar 08, 2012 1:26 pm
      Re: uct on gpu Daniel Shawul Sat Feb 25, 2012 8:30 pm
      100x speed up Daniel Shawul Mon Feb 27, 2012 8:02 pm
            Re: 100x speed up Robert Hyatt Thu Mar 15, 2012 2:13 pm
                  Re: 100x speed up Daniel Shawul Thu Mar 15, 2012 3:24 pm
                        Re: 100x speed up Robert Hyatt Thu Mar 15, 2012 4:35 pm
                              Re: 100x speed up Daniel Shawul Thu Mar 15, 2012 5:11 pm
                                    Table Daniel Shawul Thu Mar 15, 2012 5:51 pm
                                    Re: 100x speed up Robert Hyatt Thu Mar 15, 2012 7:36 pm
                                          Re: 100x speed up Daniel Shawul Thu Mar 15, 2012 8:21 pm
      Re: uct on gpu Daniel Shawul Thu Mar 08, 2012 1:08 pm
      uct for chess Daniel Shawul Mon Mar 12, 2012 10:30 pm
            Re: uct for chess Karlo Bala Jr. Mon Mar 12, 2012 11:14 pm
                  Re: uct for chess Daniel Shawul Tue Mar 13, 2012 12:13 am
                        Re: uct for chess Karlo Bala Jr. Tue Mar 13, 2012 12:52 pm
            Re: uct for chess Srdja Matovic Tue Mar 13, 2012 8:08 pm
                  Re: uct for chess Daniel Shawul Tue Mar 13, 2012 9:43 pm
                        Re: uct for chess Daniel Shawul Wed Mar 14, 2012 2:21 am
                        Re: uct for chess Srdja Matovic Wed Mar 14, 2012 11:56 am
                              Re: uct for chess Daniel Shawul Wed Mar 14, 2012 12:46 pm
                                    Re: uct for chess Srdja Matovic Wed Mar 14, 2012 1:00 pm
                        Re: uct for chess - move gen speedup by vector datatypes Srdja Matovic Mon Mar 19, 2012 3:04 pm
                              Re: uct for chess - move gen speedup by vector datatypes Daniel Shawul Mon Mar 19, 2012 8:01 pm
                                    Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Mon Mar 19, 2012 8:43 pm
                                          Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Mon Mar 19, 2012 9:01 pm
                                                Re: uct for chess - move gen speedup by vector datatypes Daniel Shawul Mon Mar 19, 2012 10:01 pm
                                                      Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Tue Mar 20, 2012 12:59 am
                                                            Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Tue Mar 20, 2012 1:04 am
                                                            Re: uct for chess - move gen speedup by vector datatypes Daniel Shawul Tue Mar 20, 2012 2:40 am
                                                                  Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Tue Mar 20, 2012 1:07 pm
                                                                        Re: uct for chess - MCS, YBW and 32 bit move gen Srdja Matovic Tue Mar 20, 2012 2:37 pm
                                                                              Re: uct for chess - MCS, YBW and 32 bit move gen Vincent Diepeveen Wed Mar 21, 2012 4:39 pm
                                                                                    Re: uct for chess - MCS, YBW and 32 bit move gen Srdja Matovic Wed Mar 21, 2012 5:53 pm
                                                                        Re: uct for chess - move gen speedup by vector datatypes Daniel Shawul Tue Mar 20, 2012 3:18 pm
                                                                              Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Wed Mar 21, 2012 2:13 pm
                                                                                    Re: uct for chess - move gen speedup by vector datatypes Daniel Shawul Wed Mar 21, 2012 4:00 pm
                              Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Mon Mar 19, 2012 8:33 pm
                                    Re: uct for chess - move gen speedup by vector datatypes Srdja Matovic Mon Mar 19, 2012 9:30 pm
                                          Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Tue Mar 20, 2012 12:54 am
                                          Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Tue Mar 20, 2012 12:45 pm
                              Re: uct for chess - move gen speedup by vector datatypes Srdja Matovic Tue Mar 20, 2012 2:38 am
                                    Re: uct for chess - move gen speedup by vector datatypes Vincent Diepeveen Tue Mar 20, 2012 1:13 pm
                                          Re: uct for chess - move gen speedup by vector datatypes Srdja Matovic Tue Mar 20, 2012 1:43 pm
                                                Re: uct for chess - move gen performance killers Srdja Matovic Tue Mar 20, 2012 4:45 pm
            intrinsic popcnt Daniel Shawul Wed Mar 14, 2012 5:21 am
                  Re: intrinsic popcnt Daniel Shawul Wed Mar 14, 2012 5:50 am
                        Re: intrinsic popcnt Robert Hyatt Thu Mar 15, 2012 5:12 pm
      Re: uct on gpu Vincent Diepeveen Thu Mar 15, 2012 8:14 pm
            Re: uct on gpu Daniel Shawul Thu Mar 15, 2012 8:27 pm
                  Re: uct on gpu Vincent Diepeveen Sat Mar 17, 2012 1:17 pm
Post new topic    TalkChess.com Forum Index -> Computer Chess Club: Programming and Technical Discussions

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum




Powered by phpBB © 2001, 2005 phpBB Group
Enhanced with Moby Threads