Release Rebel 15x2

x2 stands the multiplication of the neural net with a factor of 2 from 22Mb to 44Mb. Rebel 15x2 is not meant as a new elo bomb but as a final touch of Rebel 15 and investment for a future Rebel.

Because of the double sized network (based on 2.75 billion positions) Rebel has much more chess knowledge available which can be easily demonstrated by playing a match on depth instead of regular time control. The match ended in favor for the x2 version with a 58% score indicating a 56 elo increase.

However there is an important drawback, because of the bigger neural network the NPS has dropped significantly, depending on your PC with 25% - 35% which has to be compensated by the better chess knowledge hence the elo gain is not much. On the other hand it makes Rebel 15x2 much more suitable as an analysis engine and an excellent starting point for creating an even better neural network.

....

http://rebel13.nl/windows/rebel-15.html

Test results

[CCRL 40/2 elo pool of 3390] [Rebel-15 on CCRL 40/2 is 3368]

On my Intel I7

Code:

No. Name            Win Draw Loss Unf.  Score Games       %      
-----------------------------------------------------------    
  1 Rebel-15x2     +226 =541 -233   *0  496.5  1000   49.6%    
  2 Ethereal-12.75  +56 =107  -37   *0  109.5   200   54.8%    
  3 Stockfish-8     +52 =113  -35   *0  108.5   200   54.2%    
  4 Pedone-3.1      +48 =116  -36   *0  106.0   200   53.0%    
  5 Komodo-12       +48 =105  -47   *0  100.5   200   50.2%    
  6 Booot-6.5       +29 =100  -71   *0   79.0   200   39.5%    

On the Ryzen PC from Thorsten

Code:

No. Name            Win Draw Loss Unf.  Score Games       %
-----------------------------------------------------------
  1 Rebel-15x2     +236 =570 -194   *0  521.0  1000   52.1%
  2 Ethereal-12.75  +44 =121  -35   *0  104.5   200   52.2%
  3 Pedone-3.1      +52 =104  -44   *0  104.0   200   52.0%
  4 Stockfish-8     +37 =127  -36   *0  100.5   200   50.2%
  5 Komodo-12       +41 =114  -45   *0   98.0   200   49.0%
  6 Booot-6.5       +20 =104  -76   *0   72.0   200   36.0%

However, I don't dare to make an elo prediction.

Hi Ed

I have one small request.. Is it possible for you to make Rebel XP GUI compatible for Windows 10/11

Classics like Rebel 3/4 Century can not run on my AMD Ryzen Threadripper 3990X 64-Core Processor

2895MHz, (64 cores, 128 threads)

Damir Desevac wrote:

Hi Ed

I have one small request.. Is it possible for you to make Rebel XP GUI compatible for Windows 10/11

Classics like Rebel 3/4 Century can not run on my AMD Ryzen Threadripper 3990X 64-Core Processor

2895MHz, (64 cores, 128 threads)

All DOS Rebel's run fine under Defend-reloaded.

http://rebel13.nl/noomen/dos-rebels.html

Thanks a lot Ed!

Code:

No. Name        Win Draw Loss Unf.  Score Games       %
-------------------------------------------------------
  1 Rebel-15x2 +210 =629 -161   *0  524.5  1000   52.5%
  2 Rebel-15   +161 =629 -210   *0  475.5  1000   47.5%

A self play test (40/120) by Thorsten gave +17 elo.

Even better than expected.

I started the first test with Rebel 15x2 tonight, more results tomorrow evening.... It is clear to me that the larger network has to make up for the speed disadvantage regarding Rebel 15.

Rebel 15x2NN x64 1CPU

Pedone 3.1NN x64 1CPU          3335  43,0  3286 [J.B.] (+14 Elo compared with 15.0)

running...

Ed it appears that Chesspartner interface is no longer compatible with Rebel 12 on Windows 10/11...

https://www.lokasoft.nl/rebel12.aspx

I have bought several of Chesspartner interface in the past including Rebel 12 and none of them are

longer working in Windows 11.

Is there a way to make Chessparther compatible with Windows 10/11 ?

Damir Desevac wrote:

Ed it appears that Chesspartner interface is no longer compatible with Rebel 12 on Windows 10/11...

https://www.lokasoft.nl/rebel12.aspx

I have bought several of Chesspartner interface in the past including Rebel 12 and none of them are

longer working in Windows 11.

Is there a way to make Chessparther compatible with Windows 10/11 ?

Chessparther is running fine on my W10 systems and I don't have (nor planning) W11. Better ask Lex Loep from Lokasoft.

Thanks Ed. Somehow I managed to make it work.

+29 Elo after 1600 games, running..

Rebel 15x2NN x64 1CPU

Pedone 3.1NN x64 1CPU           3335  43,0  3286 [J.B.] 
Fritz 18NN x64 1CPU             3255  59,0  3318 [J.B.] 
Revenge 1.0NN x64 1CPU          3367  39,5  3293 [J.B.] 
Arasan 23.3NN x64 1CPU          3344  43,5  3299 [J.B.] 
Komodo 12.1.1 x64 1CPU          3335  43,0  3286 [J.B.] 
Zahak 10.0NN x64 1CPU           3218  59,5  3285 [J.B.]
Tucano 10.0NN x64 1CPU          3282  49,5  3279 [J.B.]
Booot 6.5 x64 1CPU              3224  57,0  3273 [J.B.] 
Hiarcs 15.1 x64 1CPU            3166  66,5  3285 [J.B.] 
Seer 2.5.0NN x64 1CPU           3434  32,5  3307 [J.B.] 
RofChade 3.0NN x64 1CPU         3453  00,0  xxxx [J.B.] 
LC0 0.28.2 DX12 Vega11 771721   3500  00,0  xxxx [W.B.]
RubiChess 20220223NN x64 1CPU   3437  31,5  3302 [W.B.]
Fire 8.2 x64 1CPU               3349  46,0  3321 [W.B.]
Clover 3.1NN x64 1CPU           3300  55,5  3338 [W.B.]
Wasp 5.50NN x64 1CPU            3263  57,5  3316 [W.B.]
Velvet 3.3.0NN x64 1CPU         3203  61,0  3281 [W.B.]
Weiss 2.0 x64 1CPU              3175  66,0  3290 [W.B.]
.
.
running...

Performance = ca. ELO 3297 / 1600 games => +29 to v15.0 (3268)

Surprise.......

Admin wrote:

Surprise.......

not to me, I predicted plus 30-40

Your are right Chris, +30 Elo after 1800 games..

Dio wrote:

Your are right Chris, +30 Elo after 1800 games..

There seems to be a PC specific issue with relative nps of the x1 and x2 versions. Ed’s system lost 35%, mine (same executables) 25%

Chris Whittington wrote:

Dio wrote:

Your are right Chris, +30 Elo after 1800 games..

There seems to be a PC specific issue with relative nps of the x1 and x2 versions. Ed’s system lost 35%, mine (same executables) 25%

On my system, the sse x2 version is about 35% slower.

BTW, I tried some of the options to prune more, but so far the results are not encouraging.

matejst wrote:

Chris Whittington wrote:

Dio wrote:

Your are right Chris, +30 Elo after 1800 games..

There seems to be a PC specific issue with relative nps of the x1 and x2 versions. Ed’s system lost 35%, mine (same executables) 25%

On my system, the sse x2 version is about 35% slower.

BTW, I tried some of the options to prune more, but so far the results are not encouraging.

First guess is that older systems have less cache memory

an unofficial test on my very old computer (built in 2014, but with avx2) TC 30s + 2s, all 2 threads, which started at the same time as the official test for CEGT. Again, Rebel 15x2 is ahead of Rebel 15 (about 28 Elo, head calculation due to score difference). According to my tests so far, the larger net scores very balanced against opponents of very different playing strength, no matter on which hardware, which is a good sign. Keep it up... !

Rank	Engine	Rating	Score	%	Dr	Ko	Ro	Se	Ko	Re	Lc	Wa	Fr	Re	Ko	Za	Lc	De	S-B
01	Dragon 3.0	2200	326.0/390	83.5	· ·· ·· ·	3-0-27	11-0-19	13-0-17	20-0-10	24-0-6	18-0-12	22-1-7	26-0-4	26-0-4	24-0-6	26-0-4	24-0-6	26-0-4	58351,00
02	Koivisto 8.0	2200	280.5/390	71.9	0-3-27	· ·· ·· ·	6-2-22	7-1-22	11-1-18	16-1-13	15-0-15	18-0-12	15-0-15	20-1-9	14-1-15	20-0-10	17-0-13	22-0-8	50501,50
03	RofChade 3.0	2200	263.5/390	67.5	0-11-19	2-6-22	· ·· ·· ·	4-3-23	15-4-11	15-2-13	15-0-15	16-2-12	16-0-14	15-1-14	19-0-11	16-1-13	14-1-15	21-0-9	46763,00
04	Seer 2.5.0	2200	243.0/390	62.3	0-13-17	1-7-22	3-4-23	· ·· ·· ·	9-4-17	7-2-21	13-1-16	15-1-14	12-0-18	13-0-17	16-3-11	15-1-14	11-0-19	17-0-13	43293,25
05	Komodo 13.02	2200	204.0/390	52.3	0-20-10	1-11-18	4-15-11	4-9-17	· ·· ·· ·	7-3-20	10-3-17	8-3-19	10-3-17	8-5-17	8-2-20	10-1-19	11-4-15	17-1-12	35996,00
06	Rebel 15x2	2200	177.0/390	45.3	0-24-6	1-16-13	2-15-13	2-7-21	3-7-20	· ·· ·· ·	6-4-20	5-6-19	4-5-21	5-0-25	10-8-12	12-4-14	9-3-18	7-3-20	31399,50
07	Lc0 791814	2200	168.5/390	43.2	0-18-12	0-15-15	0-15-15	1-13-16	3-10-17	4-6-20	· ·· ·· ·	7-8-15	8-5-17	5-7-18	10-6-14	7-10-13	7-0-23	11-3-16	30161,75
08	Wasp 5.50	2200	166.0/390	42.5	1-22-7	0-18-12	2-16-12	1-15-14	3-8-19	6-5-19	8-7-15	· ·· ·· ·	6-5-19	6-4-20	2-6-22	6-5-19	10-3-17	10-5-15	29466,00
09	Fritz 18NN	2200	164.5/390	42.1	0-26-4	0-15-15	0-16-14	0-12-18	3-10-17	5-4-21	5-8-17	5-6-19	· ·· ·· ·	8-7-15	11-6-13	5-3-22	8-11-11	17-4-9	28821,50
10	Rebel 15.0	2200	161.5/390	41.4	0-26-4	1-20-9	1-15-14	0-13-17	5-8-17	0-5-25	7-5-18	4-6-20	7-8-15	· ·· ·· ·	7-6-17	4-4-22	10-3-17	13-7-10	28339,25
11	Komodo 13.02 (MCTS)	2200	154.5/390	39.6	0-24-6	1-14-15	0-19-11	3-16-11	2-8-20	8-10-12	6-10-14	6-2-22	6-11-13	6-7-17	· ·· ·· ·	8-8-14	6-7-17	5-2-23	27642,50
12	Zahak 10.0	2200	149.0/390	38.2	0-26-4	0-20-10	1-16-13	1-15-14	1-10-19	4-12-14	10-7-13	5-6-19	3-5-22	4-4-22	8-8-14	· ·· ·· ·	8-5-17	4-7-19	26407,00
13	Lc0 771721	2200	147.0/390	37.6	0-24-6	0-17-13	1-14-15	0-11-19	4-11-15	3-9-18	0-7-23	3-10-17	11-8-11	3-10-17	7-6-17	5-8-17	· ·· ·· ·	8-6-16	26644,00
14	Deep Hiarcs 15.1	2200	125.0/390	32.0	0-26-4	0-22-8	0-21-9	0-17-13	1-17-12	3-7-20	3-11-16	5-10-15	4-17-9	7-13-10	2-5-23	7-4-19	6-8-16	· ·· ·· ·	22135,25

2730 games played / Tournament finished

Tournament start: 2022.04.26, 12:49:53
Latest update: 2022.05.20, 19:17:40
Site/ Country: isle of Rügen, Germany
Level: Blitz 0:30/2
Hardware: Intel(R) Core(TM) i3-7100 CPU @ 3.90GHz mit 7,9 GB Speicher
Operating system: Windows 10 Enterprise Professional (Build 9200) 64 bit
Table created with: Arena 3.5.1

Thank you for all your intensive tests. It looks like I am still on the right track, results give hope 1) it will better scale on longer time controls and 2) that the new net I am currently creating will be even better.

There have been no search changes in Rebel 15, it's only the neural net.

Ed, always learning and always producing better engines. Thank you very much.

I noticed that there are lots of blunders in the lines given by Rebel, already after a dozen plies: e.g. (from today) a missed mate on the first rank, a blundered rook, in relatively simple positions. While I think the net is very good (it gives solutions very similar to accepted theory or to SF at similar depth; I still have not tested it in endings but I will soon), there seem to be some hidden problems with the search.

I will agree with you search is the weak part and my unwillingness to do something about that. In the meantime the [GPL] engine deserves something better and I am looking for volunteers

OTOH Boban, you are probably using the double sized and SSE version and what me wonder is what the average NPS is doing on your laptop.

Amd A8 2Mhz, 115kn for Rebel 15x2, 175kn for Rebel 15, Ed, on one thread.

From Talkchess

Post by Wolfgang » Thu May 19, 2022 12:22 pm
https://cegt.forumieren.com/t1736-testi ... hade-3-0nn

2100 games played, +257 to v2.3 8-)
Best
Wolfgang
CEGT-Team
www.cegt.net
www.cegt.forumieren.com

-------

Would give Rofchade a CEGT rating of ~3.450, almost top-10

For a moment I had the illusion Rebel was the strongest dutch engine

matejst wrote:

Amd A8 2Mhz, 115kn for Rebel 15x2, 175kn for Rebel 15, Ed, on one thread.

That's what I meant, you can not expect too much from that, even with a 100 elo better search.