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: 2187
Location: Ethiopia
PostPost subject: Re: uct for chess - move gen speedup by vector datatypes    Posted: Tue Mar 20, 2012 2:40 am Reply to topic Reply with quote
Quote:

Daniel i disagree on the occupancy with you. You just need to be a good programmer to get to a high IPC and also you're using a dead old GPU. Less talented programmers already get 70% IPC at Fermi and newer, same thing for AMD by the way.

It is not about occupancy really rather performance. I can get to 70% occupancy by limiting register usage --maxrregcount during nvcc compilation. It does its best to reduce register usage at the cost of putting some variables , that it judges as least often used, in local memory. There are other tricks like using 'volatile' which boils down to the same thing: sacrificing speed for occupancy. I very much doubt it is my coding that is the problem because nvcc compiler does really optimize register usage even if you write a bad code. I don't write code that has lots of branches or with very big dependency chains, unless I have to. Maybe I will save some some if I work hard on it but I doubt it would be a significant improvement.

You should understand that what makes my occupancy so low is register pressure caused by design choices I made: that each thread does its own search,
and that it stores everything it needs on registers and shared mem. You talk about alpha-beta here but it is virtually impossible to have the move stacks
for each thread be on chip. I can implement a YBW or something similar if that is what I wanted but what is the point if it will be slow while everything is stored
on global memory. To put it in perspective, I can't even have one array of int[246] for each thread to generate its moves and remove the illegal ones (even on fermi).
So it really baffles me to think about doing any form of alpha-beta fast without incuring the 500 cycles latency everytime you pick up a move from uncached (barely cached) global memory..

Quote:

A = x + y; // it takes now 8 cycles for A to be available for further processing
b = A + c;

We have a different concept of latency here. On gpus simple instruction like add, mad and othesr typically take 24 cycles. This pipeline latency is hidden by at least having 192 threads (6 warps on tesla probably twice of that on fermi), so once you have that you need not worry about it this dependency issue. It requires atleast 25% occupancy. To hide global memory latency , you would need far more than that...
_________________
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