Cluster Toga based on Fruit Source Code

Discussion of anything and everything relating to chess playing software and machines.

Moderator: Ras

karger
Posts: 218
Joined: Tue Feb 02, 2010 2:27 am
Full name: John Karger

Re: Cluster Toga based on Fruit Source Code

Post by karger »

Thank you very much , Gentleman Jim :D
Jorge Garcia
Posts: 61
Joined: Thu Oct 22, 2009 1:50 am
Location: Barcelona Spain

Re: Cluster Toga based on Fruit Source Code

Post by Jorge Garcia »

Thanks for the information and the compiles, I will try clustertoga for fun.
Thank yoy Jim
Dann Corbit
Posts: 12777
Joined: Wed Mar 08, 2006 8:57 pm
Location: Redmond, WA USA

Re: Cluster Toga based on Fruit Source Code

Post by Dann Corbit »

KaiHimstedt wrote:From time to time people ask me about the availability of the Cluster Toga based on Fruit source code. I decided to publish the source code now. Cluster Toga is a Young Brothers Wait Concept (YBWC) parallelized version of Toga based on Fruit capable to run on a high performance cluster and participated for example in the 17th International Paderborn Computer Chess Championship (IPCCC) 2007 and the 16th World Computer-Chess Championship (WCCC) 2008 in Beijing. In fact Cluster Toga is a stand alone base engine of the GridChess system which participated for example in the 15th World Computer-Chess Championship (WCCC) 2007 in Amsterdam but is limited to use a single cluster. Up to now Cluster Toga has been tested under several Linux derivatives, Windows Server 2003 Compute Cluster Edition and Windows Clusters built from COTS (commodity off-the-shelf) components. If you are interested, a short description about my project and how to receive the source code can be found at

http://www.informatik.uni-hamburg.de/TI ... rojects/79

Have fun!

Kai Himstedt
Here is what I have found running on one machine with 4 CPUs and utililizing MPICH2 software. It scales well to 3 processors in such a circumstance and the last one is wasted. It is the same for SMP Scorpio, so perhaps it is a fundamental property of MPI interface. Due to this behavior, I suggest that running on single core machines might be a bit of a problem for scaling, but I did not bother to test that yet.

cluster toga info:

Code: Select all

1 cpu:
info depth 17
info currmove e2e4 currmovenumber 1
info time 31434 nodes 29180000 nps 928294 cpuload 1000
info hashfull 1000
info time 32448 nodes 30150000 nps 929179 cpuload 1000
info hashfull 1000
info time 33462 nodes 31200000 nps 932401 cpuload 1000
info hashfull 1000
info time 34476 nodes 32230000 nps 934853 cpuload 1000
info hashfull 1000
info time 35490 nodes 33180000 nps 934911 cpuload 1000
info hashfull 1000
info time 36504 nodes 34160000 nps 935788 cpuload 1000
info hashfull 1000
info time 37518 nodes 35100000 nps 935551 cpuload 1000
info hashfull 1000
info time 38532 nodes 36040000 nps 935326 cpuload 1000
info hashfull 1000
info time 39546 nodes 36970000 nps 934861 cpuload 1000
info hashfull 1000
info time 40560 nodes 37950000 nps 935651 cpuload 1000
info hashfull 1000
info time 41574 nodes 38890000 nps 935440 cpuload 1000
info hashfull 1000
info multipv 1 depth 17 seldepth 41 score cp 19 time 42120 nodes 39380377 pv e2e4 e7e5 g1f3 b8c6 d2d4 e5d4 f3d4 f8c5 c1e3 c5d4 e3d4 g8f6 b1c3 e8g8 f1b5 f8e8 d4f6 d8f6 e1g1 c6d4
info currmove b1c3 currmovenumber 2
info time 42588 nodes 39820000 nps 935005 cpuload 1000
info hashfull 1000

2 CPUs:

info depth 17
info currmove e2e4 currmovenumber 1
info time 10156 nodes 16701200 nps 1644466 cpuload 1000
info hashfull 1000
info time 11170 nodes 18527529 nps 1658687 cpuload 1000
info hashfull 1000
info time 12184 nodes 19420037 nps 1593897 cpuload 1000
info hashfull 1000
info time 13198 nodes 20330037 nps 1540388 cpuload 1000
info hashfull 1000
info time 14212 nodes 23400031 nps 1646498 cpuload 1000
info hashfull 1000
info time 15226 nodes 24808008 nps 1629319 cpuload 1000
info hashfull 1000
info time 16240 nodes 25698008 nps 1582390 cpuload 999
info hashfull 1000
info time 17254 nodes 26578008 nps 1540397 cpuload 1000
info hashfull 1000
info time 18268 nodes 27458008 nps 1503066 cpuload 999
info hashfull 1000
info time 19282 nodes 28308008 nps 1468105 cpuload 1000
info hashfull 1000
info time 20296 nodes 29148008 nps 1436145 cpuload 1000
info hashfull 1000
info time 21310 nodes 30028008 nps 1409104 cpuload 1000
info hashfull 1000
info time 22324 nodes 30988008 nps 1388103 cpuload 1000
info hashfull 1000
info time 23338 nodes 31988008 nps 1370641 cpuload 1000
info hashfull 1000
info time 24352 nodes 41701946 nps 1712465 cpuload 1000
info hashfull 1000
info time 25366 nodes 42611946 nps 1679884 cpuload 1000
info hashfull 1000
info time 26380 nodes 42942024 nps 1627825 cpuload 1000
info hashfull 1000
info time 27394 nodes 42942024 nps 1567570 cpuload 1000
info hashfull 1000
info time 28408 nodes 42942024 nps 1511617 cpuload 1000
info hashfull 1000
info time 29422 nodes 42942024 nps 1459521 cpuload 1000
info hashfull 1000
info time 30436 nodes 42942024 nps 1410896 cpuload 1000
info hashfull 1000
info multipv 1 depth 17 seldepth 37 score cp 22 time 30467 nodes 48671065 pv e2e4 e7e5 g1f3 b8c6 f1b5 g8f6 e1g1 f8c5 b1c3 e8g8 f3e5 c6e5 d2d4 c7c6 d4e5 c6b5 e5f6 d8f6
info currmove d2d4 currmovenumber 2
info time 31450 nodes 49520987 nps 1574594 cpuload 1000
info hashfull 1000

3 CPUs:
info depth 17
info currmove e2e4 currmovenumber 1
info time 12199 nodes 21365649 nps 1751426 cpuload 999
info hashfull 1000
info time 13213 nodes 23081450 nps 1746874 cpuload 999
info hashfull 1000
info time 14227 nodes 24752858 nps 1739851 cpuload 999
info hashfull 1000
info time 15241 nodes 27880096 nps 1829283 cpuload 1000
info hashfull 1000
info time 16255 nodes 29760778 nps 1830869 cpuload 999
info hashfull 1000
info time 17269 nodes 32077382 nps 1857512 cpuload 999
info hashfull 1000
info time 18283 nodes 33597611 nps 1837642 cpuload 1000
info hashfull 1000
info time 19297 nodes 36169260 nps 1874346 cpuload 1000
info hashfull 1000
info time 20311 nodes 38768154 nps 1908727 cpuload 1000
info hashfull 1000
info multipv 1 depth 17 seldepth 40 score cp 34 time 20530 nodes 39474381 pv e2e4 e7e5 g1f3 g8f6 f3e5 d7d6 e5f3 f6e4 f1b5 c7c6 b5d3 e4c5 d3e2 f8e7 b1c3 h7h5 e1g1
info currmove d2d4 currmovenumber 2
info time 21325 nodes 41112557 nps 1927904 cpuload 1000
info hashfull 1000

4 CPUs:
info depth 17
info currmove e2e4 currmovenumber 1
info time 22402 nodes 26939738 nps 1202560 cpuload 1000
info hashfull 1000
info time 23416 nodes 27987363 nps 1195224 cpuload 1000
info hashfull 1000
info time 24430 nodes 29238200 nps 1196815 cpuload 1000
info hashfull 1000
info time 25444 nodes 29903520 nps 1175268 cpuload 1000
info hashfull 1000
info time 26458 nodes 29903520 nps 1130226 cpuload 1000
info hashfull 1000
info time 27472 nodes 29903520 nps 1088509 cpuload 1000
info hashfull 1000
info time 28486 nodes 29903520 nps 1049762 cpuload 1000
info hashfull 1000
info time 29500 nodes 29903520 nps 1013679 cpuload 1000
info hashfull 1000
info time 30514 nodes 29903520 nps 979993 cpuload 1000
info hashfull 1000
info time 31528 nodes 29903520 nps 948475 cpuload 1000
info hashfull 1000
info time 32682 nodes 31609308 nps 967178 cpuload 1000
info hashfull 1000
info time 33696 nodes 33019341 nps 979919 cpuload 1000
info hashfull 1000
info time 34710 nodes 34076371 nps 981745 cpuload 1000
info hashfull 1000
info time 35724 nodes 34076371 nps 953879 cpuload 1000
info hashfull 1000
info time 36738 nodes 34076371 nps 927551 cpuload 1000
info hashfull 1000
info time 37752 nodes 34076371 nps 902638 cpuload 1000
info hashfull 1000
info time 38766 nodes 34076371 nps 879027 cpuload 1000
info hashfull 1000
info time 39905 nodes 35133369 nps 880425 cpuload 1000
info hashfull 1000
info time 40919 nodes 36389526 nps 889306 cpuload 1000
info hashfull 1000
info multipv 1 depth 17 seldepth 38 score cp 19 time 41294 nodes 36440523 pv e2e4 e7e5 g1f3 b8c6 f1b5 g8f6 e1g1 f8c5 b1c3 e8g8 d2d3 d7d6 c1e3 c5e3 f2e3 c8d7 b5c6 d7c6
info currmove b1c3 currmovenumber 2
info time 41933 nodes 36866197 nps 879169 cpuload 1000
info hashfull 1000
info time 42947 nodes 37616197 nps 875875 cpuload 1000
info hashfull 1000
Cluster Scorpio info:

Code: Select all

c:\chess\winboard\scorpio>"c:\Program Files\MPICH2\bin\mpiexec.exe" -np 1 c:\chess\winboard\scorpio\scorpioClusterParallel.exe
feature done=0
ht 4194304 X 64 = 256MB
eht 1048576 X 16 = 16MB
pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
Error (unknown command): mid
Error (unknown command): end
EgbbProbe 3.3 by Daniel Shawul
Egbbs loaded !
loading_time = 2s
Process [0/1] on dcorbit2008.corporate.connx.com : pid 10424
xboard
new
post
st 99
go
[st = 99000ms, mt = 99000ms , hply = 0]
2 0 0 44  e2-e4 e7-e5
2 41 0 58  e2-e3
2 41 0 73  e2-e3
3 43 0 251  e2-e3 e7-e5 Nb1-c3
3 49 0 411  e2-e4 d7-d5 Nb1-c3 d5xe4 Nc3xe4
3 50 0 599  Nb1-c3 e7-e5 e2-e4
3 50 0 662  Nb1-c3 e7-e5 e2-e4
4 -2 0 885  Nb1-c3 e7-e5 Ng1-f3 Nb8-c6
4 2 0 1906  e2-e4 Ng8-f6 Nb1-c3 Nb8-c6
4 50 0 2709  Ng1-f3 d7-d5 d2-d4
4 50 0 2739  Ng1-f3 d7-d5 d2-d4
5 43 0 4487  Ng1-f3 g7-g6 d2-d4 d7-d5
5 44 0 7262  d2-d4 f7-f5 Ng1-f3 Nb8-c6
5 44 1 7557  d2-d4 f7-f5 Ng1-f3 Nb8-c6
6 27 1 13218  d2-d4 Ng8-f6 Bc1-g5 Nb8-c6 Nb1-c3
6 14 1 21299  d2-d4 Nb8-c6 Qd1-d3 e7-e5 Ng1-f3
6 14 2 27515  d2-d4 Nb8-c6 Qd1-d3 e7-e5 Ng1-f3
7 24 2 37365  d2-d4
7 45 3 46010  d2-d4 Ng8-f6 Nb1-c3 b7-b6 e2-e4 Nb8-c6
7 45 3 47778  d2-d4 Ng8-f6 Nb1-c3 b7-b6 e2-e4 Nb8-c6
8 35 3 52346  d2-d4
8 11 5 76551  d2-d4 Ng8-f6 e2-e3 d7-d5 Ng1-f3 Bc8-f5 Nb1-c3
8 31 6 105579  Ng1-f3 d7-d5 e2-e3 Nb8-c6 Bf1-d3 Ng8-f6 Ke1-g1 Qd8-d6
8 31 7 111339  Ng1-f3 d7-d5 e2-e3 Nb8-c6 Bf1-d3 Ng8-f6 Ke1-g1 Qd8-d6
9 21 9 158661  Ng1-f3 d7-d5 e2-e3 Bc8-g4 h2-h3 Bg4-f5 Nb1-c3
9 26 10 177557  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Bf8-b4 Bf1-c4 Ng8-f6
9 26 11 195652  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Bf8-b4 Bf1-c4 Ng8-f6
10 34 14 253620  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Bf8-d6 e3-e4 Ng8-f6 Bf1-c4
10 34 16 282517  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Bf8-d6 e3-e4 Ng8-f6 Bf1-c4
11 29 22 401815  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Ng8-f6 d2-d4 e5-e4 Nf3-e5 d7-d5
11 29 27 483153  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Ng8-f6 d2-d4 e5-e4 Nf3-e5 d7-d5
12 19 33 608289  Ng1-f3
12 9 63 1155847  Ng1-f3 Ng8-f6 d2-d4 e7-e6 e2-e3 Nb8-c6 Bf1-d3 Bf8-d6 Nb1-c3 Ke8-g8 Ke1-g1 Nf6-g4
12 23 124 2273904  e2-e4 Ng8-f6 e4-e5 Nf6-d5 Nb1-c3 Nd5xc3 d2xc3 d7-d5 Bc1-g5 Nb8-c6 Ng1-f3 Bc8-f5 Nf3-d4
12 23 129 2363919  e2-e4 Ng8-f6 e4-e5 Nf6-d5 Nb1-c3 Nd5xc3 d2xc3 d7-d5 Bc1-g5 Nb8-c6 Ng1-f3 Bc8-f5 Nf3-d4
13 33 248 4522198  e2-e4
13 30 260 4729688  e2-e4 Ng8-f6 e4-e5 Nf6-d5 Ng1-f3 Nb8-c6 Bf1-b5 e7-e6 c2-c4 Nd5-b6 Ke1-g1 Bf8-c5
13 30 272 4950490  e2-e4 Ng8-f6 e4-e5 Nf6-d5 Ng1-f3 Nb8-c6 Bf1-b5 e7-e6 c2-c4 Nd5-b6 Ke1-g1 Bf8-c5
14 26 549 9864944  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Bf1-c4 Nb8-c6 Ke1-g1 Bf8-c5 c2-c3 Nf6xe4 Bc4-d5 f7-f5 Bd5xc6 b7xc6 Nf3xe5
14 26 603 10846812  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Bf1-c4 Nb8-c6 Ke1-g1 Bf8-c5 c2-c3 Nf6xe4 Bc4-d5 f7-f5 Bd5xc6 b7xc6 Nf3xe5
15 36 814 14596752  e2-e4
15 24 931 16656534  e2-e4 e7-e5 Ng1-f3 Ng8-f6 d2-d4 Nf6xe4 Bf1-d3 d7-d5 Bd3xe4 d5xe4 Nf3xe5 Nb8-d7 Bc1-f4 Nd7xe5 Bf4xe5
15 24 1019 18247427  e2-e4 e7-e5 Ng1-f3 Ng8-f6 d2-d4 Nf6xe4 Bf1-d3 d7-d5 Bd3xe4 d5xe4 Nf3xe5 Nb8-d7 Bc1-f4 Nd7xe5 Bf4xe5
16 21 1539 27540586  e2-e4 e7-e5 Nb1-c3 Ng8-f6 Bf1-c4 Bf8-b4 Ng1-e2 Ke8-g8 Ke1-g1 Nb8-c6 a2-a3 Bb4-a5 d2-d3 d7-d6
16 21 1723 30864497  e2-e4 e7-e5 Nb1-c3 Ng8-f6 Bf1-c4 Bf8-b4 Ng1-e2 Ke8-g8 Ke1-g1 Nb8-c6 a2-a3 Bb4-a5 d2-d3 d7-d6
17 19 2952 53216646  e2-e4 e7-e5 Nb1-c3 Ng8-f6 Bf1-c4 Bf8-b4 Ng1-e2 Ke8-g8 Ke1-g1 Nb8-c6 d2-d3 Nc6-a5 Bc4-d5 c7-c6 Bd5-b3 Na5xb3 a2xb3
17 19 3405 61393118  e2-e4 e7-e5 Nb1-c3 Ng8-f6 Bf1-c4 Bf8-b4 Ng1-e2 Ke8-g8 Ke1-g1 Nb8-c6 d2-d3 Nc6-a5 Bc4-d5 c7-c6 Bd5-b3 Na5xb3 a2xb3
18 29 5838 105856948  e2-e4
18 33 8741 158146909  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Bf1-c4 Nf6xe4 Nb1-c3 Ne4-d6 Bc4-d3 Nb8-c6 Ke1-g1 Bf8-e7 Qd1-e1 Be7-f6 Nc3-d5
18 33 9353 169461260  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Bf1-c4 Nf6xe4 Nb1-c3 Ne4-d6 Bc4-d3 Nb8-c6 Ke1-g1 Bf8-e7 Qd1-e1 Be7-f6 Nc3-d5
nodes = 169461260 <64 qnodes> time = 93537ms nps = 1811703
lazy_eval = 64 splits = 0 badsplits = 0 egbb_probes = 0
move e2e4
quit
Fatal error in MPI_Send: Other MPI error, error stack:
MPI_Send(174): MPI_Send(buf=0000000000000000, count=0, MPI_INT, dest=0, tag=9, MPI_COMM_WORLD) failed
MPID_Send(53): DEADLOCK: attempting to send a message to the local process without a prior matching receive

job aborted:
rank: node: exit code[: error message]
0: dcorbit2008.corporate.connx.com: 1: Fatal error in MPI_Send: Other MPI error, error stack:
MPI_Send(174): MPI_Send(buf=0000000000000000, count=0, MPI_INT, dest=0, tag=9, MPI_COMM_WORLD) failed
MPID_Send(53): DEADLOCK: attempting to send a message to the local process without a prior matching receive

c:\chess\winboard\scorpio>sc2.cmd

c:\chess\winboard\scorpio>"c:\Program Files\MPICH2\bin\mpiexec.exe" -np 2 c:\chess\winboard\scorpio\scorpioClusterParallel.exe
feature done=0
feature done=0
ht 4194304 X 64 = 256MB
eht 1048576 X 16 = 16MB
ht 4194304 X 64 = 256MB
pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
eht 1048576 X 16 = 16MB
Error (unknown command): mid
Error (unknown command): end
EgbbProbe 3.3 by Daniel Shawul
Loading egbbs....pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
Error (unknown command): mid
Error (unknown command): end
EgbbProbe 3.3 by Daniel Shawul
Egbbs loaded !
loading_time = 5s
Egbbs loaded !
loading_time = 5s
Process [1/2] on dcorbit2008.corporate.connx.com Process [0/2] on dcorbit2008.corporate.connx.com : pid 6016
: pid 10744
xboard
new
post
st 99
go
[st = 99000ms, mt = 99000ms , hply = 0]
2 0 0 44  e2-e4 e7-e5
2 41 0 58  e2-e3
2 41 0 73  e2-e3
3 43 0 251  e2-e3 e7-e5 Nb1-c3
3 49 0 411  e2-e4 d7-d5 Nb1-c3 d5xe4 Nc3xe4
3 50 0 599  Nb1-c3 e7-e5 e2-e4
3 50 0 662  Nb1-c3 e7-e5 e2-e4
4 -2 0 885  Nb1-c3 e7-e5 Ng1-f3 Nb8-c6
4 2 0 1906  e2-e4 Ng8-f6 Nb1-c3 Nb8-c6
4 50 0 2709  Ng1-f3 d7-d5 d2-d4
4 50 0 2739  Ng1-f3 d7-d5 d2-d4
5 43 0 4487  Ng1-f3 g7-g6 d2-d4 d7-d5
5 44 1 7262  d2-d4 f7-f5 Ng1-f3 Nb8-c6
5 44 1 7557  d2-d4 f7-f5 Ng1-f3 Nb8-c6
6 27 1 13218  d2-d4 Ng8-f6 Bc1-g5 Nb8-c6 Nb1-c3
6 14 2 21299  d2-d4 Nb8-c6 Qd1-d3 e7-e5 Ng1-f3
6 14 2 27515  d2-d4 Nb8-c6 Qd1-d3 e7-e5 Ng1-f3
7 24 4 40840  d2-d4
7 45 5 53925  d2-d4 Ng8-f6 Nb1-c3 b7-b6 e2-e4 Nb8-c6
7 45 5 55989  d2-d4 Ng8-f6 Nb1-c3 b7-b6 e2-e4 Nb8-c6
8 35 6 66885  d2-d4
8 9 9 118212  d2-d4 d7-d5 Bc1-f4 Bc8-f5 h2-h4 Nb8-c6 Nb1-c3
8 21 13 199128  Ng1-f3 e7-e6 d2-d4 Bf8-d6 h2-h3 Nb8-c6 Bc1-g5
8 21 14 209638  Ng1-f3 e7-e6 d2-d4 Bf8-d6 h2-h3 Nb8-c6 Bc1-g5
9 31 20 312104  Ng1-f3
9 29 23 379883  Ng1-f3 Nb8-c6 Nb1-c3 Ng8-f6 e2-e3 b7-b6 Bf1-d3 e7-e5
9 31 27 432565  e2-e3 Ng8-f6 Ng1-f3 Nb8-c6 Bf1-d3 d7-d5 Ke1-g1 Qd8-d6
9 31 28 438360  e2-e3 Ng8-f6 Ng1-f3 Nb8-c6 Bf1-d3 d7-d5 Ke1-g1 Qd8-d6
10 21 30 492770  e2-e3
10 23 35 572886  e2-e3 Ng8-f6 Ng1-f3 e7-e6 Nb1-c3 Bf8-b4 Bf1-d3 Ke8-g8 Ke1-g1 Nb8-c6
10 23 38 622340  e2-e3 Ng8-f6 Ng1-f3 e7-e6 Nb1-c3 Bf8-b4 Bf1-d3 Ke8-g8 Ke1-g1 Nb8-c6
11 18 46 864437  e2-e3 Ng8-f6 Ng1-f3 e7-e6 d2-d4 Bf8-b4 c2-c3 Bb4-e7 Bf1-d3 Ke8-g8 Ke1-g1 Nb8-c6
11 18 71 1353669  e2-e3 Ng8-f6 Ng1-f3 e7-e6 d2-d4 Bf8-b4 c2-c3 Bb4-e7 Bf1-d3 Ke8-g8 Ke1-g1 Nb8-c6
12 16 98 2092719  e2-e3 Ng8-f6 Nb1-c3 e7-e6 Bf1-d3 Bf8-c5 Nc3-a4 Bc5-f8 Ng1-f3 Nb8-c6
12 16 116 2487981  e2-e3 Ng8-f6 Nb1-c3 e7-e6 Bf1-d3 Bf8-c5 Nc3-a4 Bc5-f8 Ng1-f3 Nb8-c6
13 20 169 3940546  e2-e3 Ng8-f6 Ng1-f3 e7-e6 d2-d4 d7-d5 Nb1-c3 Bf8-d6 Bf1-d3 Ke8-g8 Ke1-g1 Nb8-c6 Bc1-d2
13 20 208 4825201  e2-e3 Ng8-f6 Ng1-f3 e7-e6 d2-d4 d7-d5 Nb1-c3 Bf8-d6 Bf1-d3 Ke8-g8 Ke1-g1 Nb8-c6 Bc1-d2
14 20 331 7619806  e2-e3 Ng8-f6 Ng1-f3 e7-e6 d2-d4 d7-d5 Bc1-d2 Nb8-c6 Bf1-d3 Bf8-d6 Ke1-g1 Ke8-g8 Nb1-c3
14 20 376 8728871  e2-e3 Ng8-f6 Ng1-f3 e7-e6 d2-d4 d7-d5 Bc1-d2 Nb8-c6 Bf1-d3 Bf8-d6 Ke1-g1 Ke8-g8 Nb1-c3
15 17 580 14306137  e2-e3 Ng8-f6 d2-d4 d7-d5 Ng1-f3 e7-e6 Bf1-d3 Nb8-c6 Nb1-c3 Bf8-d6 Ke1-g1 Ke8-g8 Bc1-d2 Nf6-g4 Qd1-e2
15 30 933 22040627  e2-e4
15 36 1517 35477448  e2-e4 Ng8-f6 e4-e5 Nf6-d5 Ng1-f3 Nb8-c6 d2-d4 e7-e6 Bf1-d3 Bf8-e7 Ke1-g1 Ke8-g8 c2-c4 Nd5-b6
15 36 1548 36168754  e2-e4 Ng8-f6 e4-e5 Nf6-d5 Ng1-f3 Nb8-c6 d2-d4 e7-e6 Bf1-d3 Bf8-e7 Ke1-g1 Ke8-g8 c2-c4 Nd5-b6
16 26 2297 55269076  e2-e4 d7-d5 e4xd5 Qd8xd5 Nb1-c3 Qd5-e6 Bf1-e2 Qe6-g6 Ng1-f3 Qg6xg2 Rh1-g1 Qg2-h3 d2-d4 Bc8-g4 Bc1-f4 Nb8-a6 Ke1-d2
16 21 2859 69340426  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Nf3xe5 Qd8-e7 d2-d4 d7-d6 Ne5-f3 Qe7xe4 Bc1-e3 Qe4-g6 h2-h4 Nb8-c6 Nb1-c3
16 21 3154 76464880  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Nf3xe5 Qd8-e7 d2-d4 d7-d6 Ne5-f3 Qe7xe4 Bc1-e3 Qe4-g6 h2-h4 Nb8-c6 Nb1-c3
17 31 4006 99016122  e2-e4
17 23 4691 117344266  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Nf3xe5 Qd8-e7 d2-d4 d7-d6 Ne5-f3 Qe7xe4 Bc1-e3 Qe4-g6 Nb1-c3 Nb8-c6 Nf3-h4 Qg6-g4 Nh4-f3
17 23 4933 123368673  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Nf3xe5 Qd8-e7 d2-d4 d7-d6 Ne5-f3 Qe7xe4 Bc1-e3 Qe4-g6 Nb1-c3 Nb8-c6 Nf3-h4 Qg6-g4 Nh4-f3
18 33 6972 175555267  e2-e4
18 32 9338 238275944  e2-e4 e7-e5 Bf1-c4 Ng8-f6 Ng1-f3 Nb8-c6 d2-d4 e5xd4 Ke1-g1 Nf6xe4 Bc4-d5 Ne4-f6 Bc1-g5 Bf8-e7 Bd5xc6 d7xc6 Nf3xd4
18 32 9747 248388918  e2-e4 e7-e5 Bf1-c4 Ng8-f6 Ng1-f3 Nb8-c6 d2-d4 e5xd4 Ke1-g1 Nf6xe4 Bc4-d5 Ne4-f6 Bc1-g5 Bf8-e7 Bd5xc6 d7xc6 Nf3xd4
nodes = 248388918 <64 qnodes> time = 97474ms nps = 2548258
lazy_eval = 64 splits = 1988 badsplits = 282 egbb_probes = 0
move e2e4
quit
Fatal error in MPI_Send: Other MPI error, error stack:
MPI_Send(174): MPI_Send(buf=0000000000000000, count=0, MPI_INT, dest=0, tag=9, MPI_COMM_WORLD) failed
MPID_Send(53): DEADLOCK: attempting to send a message to the local process without a prior matching receive

job aborted:
rank: node: exit code[: error message]
0: dcorbit2008.corporate.connx.com: 1: Fatal error in MPI_Send: Other MPI error, error stack:
MPI_Send(174): MPI_Send(buf=0000000000000000, count=0, MPI_INT, dest=0, tag=9, MPI_COMM_WORLD) failed
MPID_Send(53): DEADLOCK: attempting to send a message to the local process without a prior matching receive
1: dcorbit2008.corporate.connx.com: 1

c:\chess\winboard\scorpio>sc3.cmd

c:\chess\winboard\scorpio>"c:\Program Files\MPICH2\bin\mpiexec.exe" -np 3 c:\chess\winboard\scorpio\scorpioClusterParallel.exe
feature done=0
feature done=0
feature done=0
ht 4194304 X 64 = 256MB
eht 1048576 X 16 = 16MB
ht 4194304 X 64 = 256MB
pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
Error (unknown command): mid
Error (unknown command): end
eht 1048576 X 16 = 16MB
ht 4194304 X 64 = 256MB
EgbbProbe 3.3 by Daniel Shawul
Loading egbbs....pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
eht 1048576 X 16 = 16MB
Error (unknown command): mid
Error (unknown command): end
EgbbProbe 3.3 by Daniel Shawul
Loading egbbs....pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
Error (unknown command): mid
Error (unknown command): end
EgbbProbe 3.3 by Daniel Shawul
Egbbs loaded !
loading_time = 3s
Egbbs loaded !
loading_time = 6s
Egbbs loaded !
loading_time = 6s
Process [0/3] on dcorbit2008.corporate.connx.com : pid 10652
Process [2/3] on dcorbit2008.corporate.connx.com : pid 7872
Process [1/3] on dcorbit2008.corporate.connx.com : pid 2076
xboard
new
post
st 99
go
[st = 99000ms, mt = 99000ms , hply = 0]
2 0 0 44  e2-e4 e7-e5
2 41 0 58  e2-e3
2 41 0 73  e2-e3
3 43 0 251  e2-e3 e7-e5 Nb1-c3
3 49 0 411  e2-e4 d7-d5 Nb1-c3 d5xe4 Nc3xe4
3 50 0 599  Nb1-c3 e7-e5 e2-e4
3 50 0 662  Nb1-c3 e7-e5 e2-e4
4 -2 0 885  Nb1-c3 e7-e5 Ng1-f3 Nb8-c6
4 2 0 1906  e2-e4 Ng8-f6 Nb1-c3 Nb8-c6
4 50 0 2709  Ng1-f3 d7-d5 d2-d4
4 50 0 2739  Ng1-f3 d7-d5 d2-d4
5 43 0 4487  Ng1-f3 g7-g6 d2-d4 d7-d5
5 44 1 7262  d2-d4 f7-f5 Ng1-f3 Nb8-c6
5 44 1 7557  d2-d4 f7-f5 Ng1-f3 Nb8-c6
6 27 1 13218  d2-d4 Ng8-f6 Bc1-g5 Nb8-c6 Nb1-c3
6 14 1 21299  d2-d4 Nb8-c6 Qd1-d3 e7-e5 Ng1-f3
6 14 2 27515  d2-d4 Nb8-c6 Qd1-d3 e7-e5 Ng1-f3
7 15 3 42954  d2-d4 e7-e6 Nb1-c3 Nb8-c6 Bc1-f4 Ng8-f6
7 24 4 67683  Nb1-c3
7 46 5 94807  Nb1-c3 Nb8-c6 d2-d4 g7-g6 Bc1-f4 Ng8-f6
7 46 5 95710  Nb1-c3 Nb8-c6 d2-d4 g7-g6 Bc1-f4 Ng8-f6
8 36 5 107650  Nb1-c3
8 12 7 147274  Nb1-c3 Nb8-c6 d2-d4 d7-d5 Bc1-f4 Bc8-f5 Nc3-b5 Ra8-c8
8 28 10 217771  Ng1-f3 d7-d5 d2-d3 e7-e6 Bc1-d2 Bf8-c5 Nb1-c3
8 28 10 223916  Ng1-f3 d7-d5 d2-d3 e7-e6 Bc1-d2 Bf8-c5 Nb1-c3
9 38 15 382668  Ng1-f3
9 38 17 410076  Ng1-f3 d7-d5 e2-e3 Bc8-g4 h2-h3 Bg4-f5 Bf1-b5 c7-c6 Nf3-d4
9 38 19 426821  Ng1-f3 d7-d5 e2-e3 Bc8-g4 h2-h3 Bg4-f5 Bf1-b5 c7-c6 Nf3-d4
10 28 24 548577  Ng1-f3 d7-d5 e2-e3 Bc8-f5 Bf1-d3 Bf5xd3 c2xd3 Nb8-d7 Ke1-g1 e7-e5
10 19 29 659372  Ng1-f3 Nb8-c6 d2-d4 d7-d5 Qd1-d3 h7-h5 Bc1-f4 Ng8-f6
10 19 34 796519  Ng1-f3 Nb8-c6 d2-d4 d7-d5 Qd1-d3 h7-h5 Bc1-f4 Ng8-f6
11 29 43 1034613  Ng1-f3
11 29 47 1238879  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Ng8-f6 d2-d4 e5-e4 Nf3-e5 d7-d5
11 29 56 1470452  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Ng8-f6 d2-d4 e5-e4 Nf3-e5 d7-d5
12 26 72 1978457  Ng1-f3 Nb8-c6 e2-e3 Ng8-f6 Bf1-b5 e7-e6 Qd1-e2 Nf6-g4 Ke1-g1 Bf8-d6
12 26 85 2323364  Ng1-f3 Nb8-c6 e2-e3 Ng8-f6 Bf1-b5 e7-e6 Qd1-e2 Nf6-g4 Ke1-g1 Bf8-d6
13 20 152 4690284  Ng1-f3 Ng8-f6 d2-d4 d7-d5 e2-e3 e7-e6 Bf1-d3 Bf8-d6 Bc1-d2 Ke8-g8 Ke1-g1 Nb8-c6 Nb1-c3
13 20 214 6354944  Ng1-f3 Ng8-f6 d2-d4 d7-d5 e2-e3 e7-e6 Bf1-d3 Bf8-d6 Bc1-d2 Ke8-g8 Ke1-g1 Nb8-c6 Nb1-c3
14 10 274 8945421  Ng1-f3
14 16 366 11441161  Ng1-f3 Ng8-f6 d2-d4 Nb8-c6 Nb1-c3 d7-d5 Bc1-f4 e7-e6 e2-e3 Bf8-d6 Bf1-b5 Bd6xf4 e3xf4 Ke8-g8 Ke1-g1
14 30 501 14722451  e2-e4
14 31 785 24644827  e2-e4 Nb8-c6 Ng1-f3 Ng8-f6 e4-e5 Nf6-d5 c2-c4 Nd5-b4 Nb1-c3 d7-d6 a2-a3 Nb4-a6 d2-d4 d6xe5 d4xe5 Qd8xd1 Ke1xd1
14 31 821 25606316  e2-e4 Nb8-c6 Ng1-f3 Ng8-f6 e4-e5 Nf6-d5 c2-c4 Nd5-b4 Nb1-c3 d7-d6 a2-a3 Nb4-a6 d2-d4 d6xe5 d4xe5 Qd8xd1 Ke1xd1
15 27 1314 41624796  e2-e4 e7-e5 Bf1-c4 Nb8-c6 Ng1-f3 Bf8-c5 Ke1-g1 Ng8-f6 c2-c3 Nf6xe4 Bc4-d5 Ne4-g5 Bd5xc6 d7xc6 Nf3xe5
15 27 1392 43940873  e2-e4 e7-e5 Bf1-c4 Nb8-c6 Ng1-f3 Bf8-c5 Ke1-g1 Ng8-f6 c2-c3 Nf6xe4 Bc4-d5 Ne4-g5 Bd5xc6 d7xc6 Nf3xe5
16 37 1717 55797246  e2-e4
16 31 2443 86603677  e2-e4 e7-e5 Ng1-f3 Nb8-c6 Bf1-b5 Ng8-f6 Ke1-g1 Bf8-c5 d2-d3 Qd8-e7 Bb5-c4 Ke8-g8 Nb1-c3
16 31 2568 90531350  e2-e4 e7-e5 Ng1-f3 Nb8-c6 Bf1-b5 Ng8-f6 Ke1-g1 Bf8-c5 d2-d3 Qd8-e7 Bb5-c4 Ke8-g8 Nb1-c3
17 41 4387 151825522  e2-e4
17 21 4869 166389095  e2-e4
17 21 5303 177794832  e2-e4 e7-e5 Bf1-c4 Ng8-f6 Ng1-f3 Nf6xe4 Nb1-c3 Ne4-d6 Bc4-d3 Nb8-c6 Qd1-e2 f7-f6 Ke1-g1 Bf8-e7 Bd3-c4 Nd6xc4 Qe2xc4
17 21 5833 192902884  e2-e4 e7-e5 Bf1-c4 Ng8-f6 Ng1-f3 Nf6xe4 Nb1-c3 Ne4-d6 Bc4-d3 Nb8-c6 Qd1-e2 f7-f6 Ke1-g1 Bf8-e7 Bd3-c4 Nd6xc4 Qe2xc4
18 31 7886 256723858  e2-e4
nodes = 256723858 <64 qnodes> time = 78866ms nps = 3255190
lazy_eval = 64 splits = 1748 badsplits = 205 egbb_probes = 0
move e2e4
quit
Fatal error in MPI_Send: Other MPI error, error stack:
MPI_Send(174): MPI_Send(buf=0000000000000000, count=0, MPI_INT, dest=0, tag=9, MPI_COMM_WORLD) failed
MPID_Send(53): DEADLOCK: attempting to send a message to the local process without a prior matching receive

job aborted:
rank: node: exit code[: error message]
0: dcorbit2008.corporate.connx.com: 1: Fatal error in MPI_Send: Other MPI error, error stack:
MPI_Send(174): MPI_Send(buf=0000000000000000, count=0, MPI_INT, dest=0, tag=9, MPI_COMM_WORLD) failed
MPID_Send(53): DEADLOCK: attempting to send a message to the local process without a prior matching receive
1: dcorbit2008.corporate.connx.com: 1
2: dcorbit2008.corporate.connx.com: 1

c:\chess\winboard\scorpio>sc4.cmd

c:\chess\winboard\scorpio>"c:\Program Files\MPICH2\bin\mpiexec.exe" -np 4 c:\chess\winboard\scorpio\scorpioClusterParallel.exe
feature done=0
feature done=0
feature done=0
feature done=0
ht 4194304 X 64 = 256MB
eht 1048576 X 16 = 16MB
ht 4194304 X 64 = 256MB
pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
Error (unknown command): mid
Error (unknown command): end
EgbbProbe 3.3 by Daniel Shawul
eht 1048576 X 16 = 16MB
Loading egbbs....ht 4194304 X 64 = 256MB
pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
Error (unknown command): mid
Error (unknown command): end
ht 4194304 X 64 = 256MB
eht 1048576 X 16 = 16MB
EgbbProbe 3.3 by Daniel Shawul
Loading egbbs....pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
eht 1048576 X 16 = 16MB
Error (unknown command): mid
Error (unknown command): end
EgbbProbe 3.3 by Daniel Shawul
Loading egbbs....pht 349525 X 24 = 7MB
processors [1]
SMP_SPLIT_DEPTH = 4
CLUSTER_SPLIT_DEPTH = 4
Error (unknown command): multi_personality
Error (unknown command): opn
Error (unknown command): mid
Error (unknown command): end
EgbbProbe 3.3 by Daniel Shawul
Egbbs loaded !
loading_time = 5s
Egbbs loaded !
loading_time = 5s
Egbbs loaded !
loading_time = 7s
Egbbs loaded !
loading_time = 7s
Process [3/4] on dcorbit2008.corporate.conProcess [2/4] on dcorbit2008.corporate.connx.com : pid 868
Process [0/4] on dcorbit2008.corporate.connx.com : pid 5828
Process [1/4] on dcorbit2008.corporate.connx.com : pid 2868
nx.com : pid 10092
xboard
new
post
st 99
go
[st = 99000ms, mt = 99000ms , hply = 0]
2 0 0 44  e2-e4 e7-e5
2 41 0 58  e2-e3
2 41 0 73  e2-e3
3 43 0 251  e2-e3 e7-e5 Nb1-c3
3 49 0 411  e2-e4 d7-d5 Nb1-c3 d5xe4 Nc3xe4
3 50 0 599  Nb1-c3 e7-e5 e2-e4
3 50 0 662  Nb1-c3 e7-e5 e2-e4
4 -2 0 885  Nb1-c3 e7-e5 Ng1-f3 Nb8-c6
4 2 0 1906  e2-e4 Ng8-f6 Nb1-c3 Nb8-c6
4 50 0 2709  Ng1-f3 d7-d5 d2-d4
4 50 0 2739  Ng1-f3 d7-d5 d2-d4
5 43 0 4487  Ng1-f3 g7-g6 d2-d4 d7-d5
5 44 0 7262  d2-d4 f7-f5 Ng1-f3 Nb8-c6
5 44 1 7557  d2-d4 f7-f5 Ng1-f3 Nb8-c6
6 27 1 13218  d2-d4 Ng8-f6 Bc1-g5 Nb8-c6 Nb1-c3
6 14 1 21299  d2-d4 Nb8-c6 Qd1-d3 e7-e5 Ng1-f3
6 14 2 27515  d2-d4 Nb8-c6 Qd1-d3 e7-e5 Ng1-f3
7 15 2 48304  d2-d4 e7-e6 Nb1-c3 Nb8-c6 Bc1-f4 Ng8-f6
7 24 3 67390  Nb1-c3
7 46 4 83874  Nb1-c3 Nb8-c6 d2-d4 g7-g6 Bc1-f4 Ng8-f6
7 46 4 84777  Nb1-c3 Nb8-c6 d2-d4 g7-g6 Bc1-f4 Ng8-f6
8 36 4 94386  Nb1-c3
8 7 6 167692  Nb1-c3 d7-d5 d2-d4 Ng8-f6 Bc1-d2 Bc8-f5 Ng1-f3
8 15 10 293290  d2-d4 d7-d6 Bc1-d2 Ng8-f6 Ng1-f3 Bc8-f5 Nb1-c3
8 31 13 392843  Ng1-f3 d7-d5 e2-e3 Nb8-c6 Bf1-d3 Ng8-f6 Ke1-g1 Qd8-d6
8 31 13 394812  Ng1-f3 d7-d5 e2-e3 Nb8-c6 Bf1-d3 Ng8-f6 Ke1-g1 Qd8-d6
9 35 16 465511  Ng1-f3 d7-d5 e2-e3 Qd8-d6 Nb1-c3 Nb8-c6 Nc3-b5 Qd6-d8
9 35 17 493909  Ng1-f3 d7-d5 e2-e3 Qd8-d6 Nb1-c3 Nb8-c6 Nc3-b5 Qd6-d8
10 25 19 556458  Ng1-f3
10 42 24 679148  Ng1-f3 d7-d5 e2-e3 Nb8-c6 Bf1-b5 Ng8-f6 Ke1-g1 Bc8-g4 Bb5xc6 b7xc6 Nb1-c3 Qd8-d6
10 42 27 732539  Ng1-f3 d7-d5 e2-e3 Nb8-c6 Bf1-b5 Ng8-f6 Ke1-g1 Bc8-g4 Bb5xc6 b7xc6 Nb1-c3 Qd8-d6
11 32 33 995072  Ng1-f3 d7-d5 e2-e3 Qd8-d6 Nb1-c3 Ng8-f6 Bf1-b5 Nb8-c6 Ke1-g1 Bc8-f5 Nf3-d4
11 22 57 1713609  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Ng8-f6 Bf1-b5 e5-e4 Nf3-d4 Bf8-c5 Nd4-f5
11 22 72 2118331  Ng1-f3 Nb8-c6 e2-e3 e7-e5 Nb1-c3 Ng8-f6 Bf1-b5 e5-e4 Nf3-d4 Bf8-c5 Nd4-f5
12 12 91 2808371  Ng1-f3 Nb8-c6 d2-d4 Ng8-f6 Bc1-f4 d7-d5 Nb1-a3 a7-a6 e2-e3 Bc8-f5 Bf1-d3
12 15 115 3657160  Ng1-f3 Ng8-f6 Nb1-c3 Nb8-c6 d2-d4 e7-e6 e2-e4 Bf8-b4 Bf1-d3 d7-d5 e4-e5 Nf6-g4
12 15 272 6531035  Ng1-f3 Ng8-f6 Nb1-c3 Nb8-c6 d2-d4 e7-e6 e2-e4 Bf8-b4 Bf1-d3 d7-d5 e4-e5 Nf6-g4
13 15 313 7903866  Ng1-f3 Ng8-f6 Nb1-c3 Nb8-c6 e2-e4 d7-d5 e4xd5 Nf6xd5 Bf1-b5 Nd5xc3 d2xc3 Qd8xd1 Ke1xd1 Bc8-g4 Bb5xc6 b7xc6 Bc1-e3 Bg4xf3 g2xf3 Ra8-b8 Ra1-b1
13 19 373 9419722  e2-e4 Nb8-c6 Ng1-f3 Ng8-f6 Bf1-d3 d7-d5 e4xd5 Nc6-b4 Bd3-b5 Bc8-d7 Bb5xd7 Qd8xd7 Ke1-g1 Nb4xd5
13 19 382 9702270  e2-e4 Nb8-c6 Ng1-f3 Ng8-f6 Bf1-d3 d7-d5 e4xd5 Nc6-b4 Bd3-b5 Bc8-d7 Bb5xd7 Qd8xd7 Ke1-g1 Nb4xd5
14 27 621 16612583  e2-e4 d7-d5 e4xd5 Qd8xd5 Nb1-c3 Qd5-e6 Bf1-e2 Qe6-g6 Nc3-d5 Nb8-a6 Be2-f3 e7-e5 Qd1-e2 Bf8-d6 d2-d4
14 27 651 17524596  e2-e4 d7-d5 e4xd5 Qd8xd5 Nb1-c3 Qd5-e6 Bf1-e2 Qe6-g6 Nc3-d5 Nb8-a6 Be2-f3 e7-e5 Qd1-e2 Bf8-d6 d2-d4
15 32 1021 31260497  e2-e4 e7-e5 Ng1-f3 Nb8-c6 Bf1-b5 Ng8-f6 Ke1-g1 Bf8-c5 d2-d3 Qd8-e7 Nb1-c3 Ke8-g8 Bc1-e3 Bc5xe3 f2xe3 Rf8-d8
15 32 1072 32870032  e2-e4 e7-e5 Ng1-f3 Nb8-c6 Bf1-b5 Ng8-f6 Ke1-g1 Bf8-c5 d2-d3 Qd8-e7 Nb1-c3 Ke8-g8 Bc1-e3 Bc5xe3 f2xe3 Rf8-d8
16 22 1388 45235293  e2-e4
16 35 1710 55824767  e2-e4 e7-e5 Ng1-f3 Nb8-c6 Bf1-c4 Ng8-f6 Nb1-c3 Bf8-c5 Ke1-g1 Ke8-g8 d2-d3 d7-d6 Bc1-g5 h7-h6 Bg5-e3 Bc5xe3 f2xe3
16 35 1863 58830622  e2-e4 e7-e5 Ng1-f3 Nb8-c6 Bf1-c4 Ng8-f6 Nb1-c3 Bf8-c5 Ke1-g1 Ke8-g8 d2-d3 d7-d6 Bc1-g5 h7-h6 Bg5-e3 Bc5xe3 f2xe3
17 41 4333 141985725  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Bf1-c4 Nb8-c6 d2-d4 e5xd4 Ke1-g1 Nf6xe4 Bc4-d5 Ne4-f6 Bc1-g5 Bf8-e7 Bd5xc6 d7xc6 Nf3xd4
17 41 4524 147781171  e2-e4 e7-e5 Ng1-f3 Ng8-f6 Bf1-c4 Nb8-c6 d2-d4 e5xd4 Ke1-g1 Nf6xe4 Bc4-d5 Ne4-f6 Bc1-g5 Bf8-e7 Bd5xc6 d7xc6 Nf3xd4
18 31 5308 182145987  e2-e4
18 31 8026 263537317  e2-e4 e7-e5 Ng1-f3 Ng8-f6 d2-d4 Nf6xe4 Nf3xe5 d7-d6 Ne5-f3 Bf8-e7 Bf1-d3 d6-d5 Ke1-g1 Ke8-g8 Nb1-c3 f7-f5
18 31 9122 292038441  e2-e4 e7-e5 Ng1-f3 Ng8-f6 d2-d4 Nf6xe4 Nf3xe5 d7-d6 Ne5-f3 Bf8-e7 Bf1-d3 d6-d5 Ke1-g1 Ke8-g8 Nb1-c3 f7-f5
nodes = 292038441 <64 qnodes> time = 91227ms nps = 3201228
lazy_eval = 65 splits = 1686 badsplits = 203 egbb_probes = 0
move e2e4
quit
Fatal error in MPI_Send: Other MPI error, error stack:
MPI_Send(174): MPI_Send(buf=0000000000000000, count=0, MPI_INT, dest=0, tag=9, MPI_COMM_WORLD) failed
MPID_Send(53): DEADLOCK: attempting to send a message to the local process without a prior matching receive

job aborted:
rank: node: exit code[: error message]
0: dcorbit2008.corporate.connx.com: 1: Fatal error in MPI_Send: Other MPI error, error stack:
MPI_Send(174): MPI_Send(buf=0000000000000000, count=0, MPI_INT, dest=0, tag=9, MPI_COMM_WORLD) failed
MPID_Send(53): DEADLOCK: attempting to send a message to the local process without a prior matching receive
1: dcorbit2008.corporate.connx.com: 1
2: dcorbit2008.corporate.connx.com: 1
3: dcorbit2008.corporate.connx.com: 1

c:\chess\winboard\scorpio>
CRoberson
Posts: 2091
Joined: Mon Mar 13, 2006 2:31 am
Location: North Carolina, USA

Re: Cluster Toga based on Fruit Source Code

Post by CRoberson »

Hi Dann,

MPI allows you to overload a machine, so try -n 5 on the 4 proc machine.

I don't know exactly how they implemented their systems, but one process could be set up as a manager. The problem I've seen with Open MPI (not OpenMP) is that MPI_Recv is implemented as a busy loop, thus the manager processes burns CPU time when waiting on a Recv. It is possible that MPICH is not set up that way.