Commit 2bcdde67 authored by THIBAULT Samuel's avatar THIBAULT Samuel

Add sirocco sampling

parent c48c44ef
# GPU CPU0 CPU1 CPU2 CPU3 CPU4 CPU5 CPU6 CPU7 CPU8 CPU9 CPU10 CPU11 CPU12 CPU13 CPU14 CPU15 CPU16 CPU17 CPU18 CPU19 CPU20 CPU21 CPU22 CPU23
0 6 7 8 9 10 11 0 1 2 3 4 5 18 19 20 21 22 23 12 13 14 15 16 17
1 6 7 8 9 10 11 0 1 2 3 4 5 18 19 20 21 22 23 12 13 14 15 16 17
2 18 19 20 21 22 23 12 13 14 15 16 17 0 1 2 3 4 5 6 7 8 9 10 11
3 18 19 20 21 22 23 12 13 14 15 16 17 0 1 2 3 4 5 6 7 8 9 10 11
0 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
1 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
2 12 13 14 15 16 17 18 19 20 21 22 23 0 1 2 3 4 5 6 7 8 9 10 11
3 12 13 14 15 16 17 18 19 20 21 22 23 0 1 2 3 4 5 6 7 8 9 10 11
# to 0 to 1 to 2 to 3 to 4 to 5 to 6 to 7 to 8 to 9 to 10 to 11 to 12 to 13 to 14 to 15
0.000000e+00 1.051768e+04 1.051743e+04 1.051732e+04 1.051718e+04 7.997534e+03 7.978223e+03 8.025122e+03 8.002101e+03 nan nan nan nan nan nan nan
1.052170e+04 0.000000e+00 1.024409e+04 7.662719e+03 8.527736e+03 4.543798e+03 4.537558e+03 4.552690e+03 4.545272e+03 nan nan nan nan nan nan nan
1.052123e+04 1.024068e+04 0.000000e+00 7.630370e+03 8.542254e+03 4.543711e+03 4.537471e+03 4.552602e+03 4.545185e+03 nan nan nan nan nan nan nan
1.052183e+04 8.504225e+03 8.517476e+03 0.000000e+00 1.023200e+04 4.543822e+03 4.537582e+03 4.552715e+03 4.545296e+03 nan nan nan nan nan nan nan
1.052172e+04 8.496221e+03 8.514240e+03 1.024287e+04 0.000000e+00 4.543801e+03 4.537561e+03 4.552693e+03 4.545275e+03 nan nan nan nan nan nan nan
7.434276e+03 4.355589e+03 4.355546e+03 4.355527e+03 4.355503e+03 0.000000e+00 3.848326e+03 3.859204e+03 3.853873e+03 nan nan nan nan nan nan nan
7.232140e+03 4.285414e+03 4.285373e+03 4.285355e+03 4.285331e+03 3.797802e+03 0.000000e+00 3.804012e+03 3.798832e+03 nan nan nan nan nan nan nan
7.300126e+03 4.309194e+03 4.309152e+03 4.309134e+03 4.309110e+03 3.816466e+03 3.812063e+03 0.000000e+00 3.817506e+03 nan nan nan nan nan nan nan
7.333166e+03 4.320685e+03 4.320643e+03 4.320625e+03 4.320601e+03 3.825477e+03 3.821053e+03 3.831778e+03 0.000000e+00 nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
# Current configuration
24 # Number of CPUs
4 # Number of CUDA devices
4 # Number of OpenCL devices
0 # Number of MIC devices
# to 0 to 1 to 2 to 3 to 4 to 5 to 6 to 7 to 8 to 9 to 10 to 11 to 12 to 13 to 14 to 15
0.000000e+00 1.029027e+01 1.031898e+01 9.529422e+00 1.039846e+01 9.643953e+00 1.113670e+01 1.055939e+01 1.004796e+01 nan nan nan nan nan nan nan
1.085040e+01 0.000000e+00 1.152573e+01 2.350899e+01 2.337711e+01 2.049435e+01 2.198709e+01 2.140979e+01 2.089836e+01 nan nan nan nan nan nan nan
9.920578e+00 1.167180e+01 0.000000e+00 2.304539e+01 2.330630e+01 1.956453e+01 2.105727e+01 2.047997e+01 1.996854e+01 nan nan nan nan nan nan nan
1.093016e+01 2.380006e+01 2.358666e+01 0.000000e+00 1.101548e+01 2.057412e+01 2.206686e+01 2.148955e+01 2.097812e+01 nan nan nan nan nan nan nan
1.097311e+01 2.126338e+01 2.129209e+01 2.050253e+01 0.000000e+00 2.061706e+01 2.210980e+01 2.153250e+01 2.102107e+01 nan nan nan nan nan nan nan
1.162996e+01 2.192023e+01 2.194894e+01 2.115938e+01 2.202842e+01 0.000000e+00 2.276666e+01 2.218935e+01 2.167792e+01 nan nan nan nan nan nan nan
1.359506e+01 2.388534e+01 2.391404e+01 2.312448e+01 2.399352e+01 2.323902e+01 0.000000e+00 2.415445e+01 2.364302e+01 nan nan nan nan nan nan nan
1.245815e+01 2.274842e+01 2.277712e+01 2.198757e+01 2.285661e+01 2.210210e+01 2.359484e+01 0.000000e+00 2.250611e+01 nan nan nan nan nan nan nan
1.236026e+01 2.265053e+01 2.267923e+01 2.188968e+01 2.275872e+01 2.200421e+01 2.349695e+01 2.291965e+01 0.000000e+00 nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan
<?xml version='1.0'?>
<!DOCTYPE platform SYSTEM 'http://simgrid.gforge.inria.fr/simgrid.dtd'>
<platform version='3'>
<config id='General'>
<prop id='network/TCP_gamma' value='-1'></prop>
<prop id='network/latency_factor' value='1'></prop>
<prop id='network/bandwidth_factor' value='1'></prop>
</config>
<AS id='AS0' routing='Full'>
<host id='MAIN' power='1'/>
<host id='CPU0' power='2000000000'/>
<host id='CPU1' power='2000000000'/>
<host id='CPU2' power='2000000000'/>
<host id='CPU3' power='2000000000'/>
<host id='CPU4' power='2000000000'/>
<host id='CPU5' power='2000000000'/>
<host id='CPU6' power='2000000000'/>
<host id='CPU7' power='2000000000'/>
<host id='CPU8' power='2000000000'/>
<host id='CPU9' power='2000000000'/>
<host id='CPU10' power='2000000000'/>
<host id='CPU11' power='2000000000'/>
<host id='CPU12' power='2000000000'/>
<host id='CPU13' power='2000000000'/>
<host id='CPU14' power='2000000000'/>
<host id='CPU15' power='2000000000'/>
<host id='CPU16' power='2000000000'/>
<host id='CPU17' power='2000000000'/>
<host id='CPU18' power='2000000000'/>
<host id='CPU19' power='2000000000'/>
<host id='CPU20' power='2000000000'/>
<host id='CPU21' power='2000000000'/>
<host id='CPU22' power='2000000000'/>
<host id='CPU23' power='2000000000'/>
<host id='CUDA0' power='2000000000'>
<prop id='memsize' value='12079136768'/>
<prop id='memcpy_peer' value='1'/>
</host>
<host id='CUDA1' power='2000000000'>
<prop id='memsize' value='12079136768'/>
<prop id='memcpy_peer' value='1'/>
</host>
<host id='CUDA2' power='2000000000'>
<prop id='memsize' value='12079136768'/>
<prop id='memcpy_peer' value='1'/>
</host>
<host id='CUDA3' power='2000000000'>
<prop id='memsize' value='12079136768'/>
<prop id='memcpy_peer' value='1'/>
</host>
<host id='OpenCL0' power='2000000000'>
<prop id='memsize' value='12079136768'/>
</host>
<host id='OpenCL1' power='2000000000'>
<prop id='memsize' value='12079136768'/>
</host>
<host id='OpenCL2' power='2000000000'>
<prop id='memsize' value='12079136768'/>
</host>
<host id='OpenCL3' power='2000000000'>
<prop id='memsize' value='12079136768'/>
</host>
<host id='RAM' power='1'/>
<link id='Host' bandwidth='10521832623.517040' latency='0.000000'/>
<link id='RAM-OpenCL0' bandwidth='7997534022.141151' latency='0.000010'/>
<link id='OpenCL0-RAM' bandwidth='7434276438.572320' latency='0.000012'/>
<link id='RAM-OpenCL1' bandwidth='7978223026.445667' latency='0.000011'/>
<link id='OpenCL1-RAM' bandwidth='7232140009.638909' latency='0.000014'/>
<link id='RAM-OpenCL2' bandwidth='8025122400.678086' latency='0.000011'/>
<link id='OpenCL2-RAM' bandwidth='7300126055.185305' latency='0.000012'/>
<link id='RAM-OpenCL3' bandwidth='8002101228.048121' latency='0.000010'/>
<link id='OpenCL3-RAM' bandwidth='7333165510.983491' latency='0.000012'/>
<link id='RAM-CUDA0' bandwidth='10517678844.278971' latency='0.000010'/>
<link id='CUDA0-RAM' bandwidth='10521701010.666672' latency='0.000011'/>
<link id='RAM-CUDA1' bandwidth='10517427805.652538' latency='0.000010'/>
<link id='CUDA1-RAM' bandwidth='10521233123.485935' latency='0.000010'/>
<link id='RAM-CUDA2' bandwidth='10517320202.942270' latency='0.000010'/>
<link id='CUDA2-RAM' bandwidth='10521832623.517040' latency='0.000011'/>
<link id='RAM-CUDA3' bandwidth='10517178916.561483' latency='0.000010'/>
<link id='CUDA3-RAM' bandwidth='10521716373.062309' latency='0.000011'/>
<link id='CUDA0-CUDA1' bandwidth='10244090134.034805' latency='0.000012'/>
<link id='CUDA0-CUDA2' bandwidth='7662719221.740685' latency='0.000024'/>
<link id='CUDA0-CUDA3' bandwidth='8527735591.087247' latency='0.000023'/>
<link id='CUDA1-CUDA0' bandwidth='10240684078.899693' latency='0.000012'/>
<link id='CUDA1-CUDA2' bandwidth='7630369996.384952' latency='0.000023'/>
<link id='CUDA1-CUDA3' bandwidth='8542253951.429195' latency='0.000023'/>
<link id='CUDA2-CUDA0' bandwidth='8504224628.018895' latency='0.000024'/>
<link id='CUDA2-CUDA1' bandwidth='8517475744.443908' latency='0.000024'/>
<link id='CUDA2-CUDA3' bandwidth='10232000931.164429' latency='0.000011'/>
<link id='CUDA3-CUDA0' bandwidth='8496220968.849647' latency='0.000023'/>
<link id='CUDA3-CUDA1' bandwidth='8514239613.171523' latency='0.000023'/>
<link id='CUDA3-CUDA2' bandwidth='10242870726.441437' latency='0.000011'/>
<route src='RAM' dst='CUDA0' symmetrical='NO'><link_ctn id='RAM-CUDA0'/><link_ctn id='Host'/></route>
<route src='CUDA0' dst='RAM' symmetrical='NO'><link_ctn id='CUDA0-RAM'/><link_ctn id='Host'/></route>
<route src='RAM' dst='CUDA1' symmetrical='NO'><link_ctn id='RAM-CUDA1'/><link_ctn id='Host'/></route>
<route src='CUDA1' dst='RAM' symmetrical='NO'><link_ctn id='CUDA1-RAM'/><link_ctn id='Host'/></route>
<route src='RAM' dst='CUDA2' symmetrical='NO'><link_ctn id='RAM-CUDA2'/><link_ctn id='Host'/></route>
<route src='CUDA2' dst='RAM' symmetrical='NO'><link_ctn id='CUDA2-RAM'/><link_ctn id='Host'/></route>
<route src='RAM' dst='CUDA3' symmetrical='NO'><link_ctn id='RAM-CUDA3'/><link_ctn id='Host'/></route>
<route src='CUDA3' dst='RAM' symmetrical='NO'><link_ctn id='CUDA3-RAM'/><link_ctn id='Host'/></route>
<route src='CUDA0' dst='CUDA1' symmetrical='NO'><link_ctn id='CUDA0-CUDA1'/><link_ctn id='Host'/></route>
<route src='CUDA0' dst='CUDA2' symmetrical='NO'><link_ctn id='CUDA0-CUDA2'/><link_ctn id='Host'/></route>
<route src='CUDA0' dst='CUDA3' symmetrical='NO'><link_ctn id='CUDA0-CUDA3'/><link_ctn id='Host'/></route>
<route src='CUDA1' dst='CUDA0' symmetrical='NO'><link_ctn id='CUDA1-CUDA0'/><link_ctn id='Host'/></route>
<route src='CUDA1' dst='CUDA2' symmetrical='NO'><link_ctn id='CUDA1-CUDA2'/><link_ctn id='Host'/></route>
<route src='CUDA1' dst='CUDA3' symmetrical='NO'><link_ctn id='CUDA1-CUDA3'/><link_ctn id='Host'/></route>
<route src='CUDA2' dst='CUDA0' symmetrical='NO'><link_ctn id='CUDA2-CUDA0'/><link_ctn id='Host'/></route>
<route src='CUDA2' dst='CUDA1' symmetrical='NO'><link_ctn id='CUDA2-CUDA1'/><link_ctn id='Host'/></route>
<route src='CUDA2' dst='CUDA3' symmetrical='NO'><link_ctn id='CUDA2-CUDA3'/><link_ctn id='Host'/></route>
<route src='CUDA3' dst='CUDA0' symmetrical='NO'><link_ctn id='CUDA3-CUDA0'/><link_ctn id='Host'/></route>
<route src='CUDA3' dst='CUDA1' symmetrical='NO'><link_ctn id='CUDA3-CUDA1'/><link_ctn id='Host'/></route>
<route src='CUDA3' dst='CUDA2' symmetrical='NO'><link_ctn id='CUDA3-CUDA2'/><link_ctn id='Host'/></route>
<route src='RAM' dst='OpenCL0' symmetrical='NO'><link_ctn id='RAM-OpenCL0'/><link_ctn id='Host'/></route>
<route src='OpenCL0' dst='RAM' symmetrical='NO'><link_ctn id='OpenCL0-RAM'/><link_ctn id='Host'/></route>
<route src='RAM' dst='OpenCL1' symmetrical='NO'><link_ctn id='RAM-OpenCL1'/><link_ctn id='Host'/></route>
<route src='OpenCL1' dst='RAM' symmetrical='NO'><link_ctn id='OpenCL1-RAM'/><link_ctn id='Host'/></route>
<route src='RAM' dst='OpenCL2' symmetrical='NO'><link_ctn id='RAM-OpenCL2'/><link_ctn id='Host'/></route>
<route src='OpenCL2' dst='RAM' symmetrical='NO'><link_ctn id='OpenCL2-RAM'/><link_ctn id='Host'/></route>
<route src='RAM' dst='OpenCL3' symmetrical='NO'><link_ctn id='RAM-OpenCL3'/><link_ctn id='Host'/></route>
<route src='OpenCL3' dst='RAM' symmetrical='NO'><link_ctn id='OpenCL3-RAM'/><link_ctn id='Host'/></route>
</AS>
</platform>
##################
# Performance Model Version
44
####################
# COMBs
# number of combinations
5
####################
# COMB_4
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
0
####################
# DEV_0
# device id
0
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cpu0_impl0 (Comb4)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
24c84a50 22118400 0.000000e+00 7.614739e+04 1.570335e+04 4.926736e+07 3.911128e+12 647
e6b94418 153600 0.000000e+00 5.080183e+01 9.743801e+00 2.861616e+06 1.507233e+08 56329
c4a08f5f 4646400 0.000000e+00 8.137654e+03 1.863872e+03 1.657640e+07 1.419696e+11 2037
8cfc3ba0 49766400 0.000000e+00 2.267816e+05 3.915016e+04 1.598810e+08 3.733864e+13 705
a7cdf15b 88473600 0.000000e+00 4.662963e+05 5.310256e+04 3.273400e+08 1.546170e+14 702
####################
# COMB_1
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
1
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cuda1_impl0 (Comb1)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
24c84a50 22118400 0.000000e+00 1.715310e+03 9.993558e+01 9.566285e+06 1.646484e+10 5577
e6b94418 153600 0.000000e+00 5.113274e+01 1.134809e+01 1.518642e+04 8.147708e+05 297
c4a08f5f 4646400 0.000000e+00 2.017727e+02 2.861061e+01 1.652922e+06 3.402201e+08 8192
8cfc3ba0 49766400 0.000000e+00 6.191028e+03 2.666186e+02 2.317302e+07 1.437309e+11 3743
a7cdf15b 88473600 0.000000e+00 1.292684e+04 4.908603e+02 4.657542e+07 6.029413e+11 3603
####################
# COMB_2
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
0
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cuda0_impl0 (Comb2)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
24c84a50 22118400 0.000000e+00 1.694044e+03 9.446026e+01 9.451069e+06 1.606030e+10 5579
e6b94418 153600 0.000000e+00 6.271543e+01 1.282513e+01 1.994351e+04 1.303072e+06 318
c4a08f5f 4646400 0.000000e+00 2.001219e+02 2.795923e+01 1.640199e+06 3.346467e+08 8196
8cfc3ba0 49766400 0.000000e+00 6.117615e+03 2.941760e+02 2.339376e+07 1.434449e+11 3824
a7cdf15b 88473600 0.000000e+00 1.279991e+04 4.666369e+02 4.609249e+07 5.907639e+11 3601
####################
# COMB_0
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
2
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cuda2_impl0 (Comb0)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
24c84a50 22118400 0.000000e+00 1.713334e+03 9.294880e+01 9.365083e+06 1.609274e+10 5466
e6b94418 153600 0.000000e+00 4.994209e+01 9.498420e+00 1.588158e+04 8.218495e+05 318
c4a08f5f 4646400 0.000000e+00 2.026661e+02 2.758349e+01 1.561340e+06 3.222922e+08 7704
8cfc3ba0 49766400 0.000000e+00 6.177427e+03 2.260170e+02 2.327037e+07 1.439434e+11 3767
a7cdf15b 88473600 0.000000e+00 1.286952e+04 4.739314e+02 4.932886e+07 6.356995e+11 3833
####################
# COMB_3
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
3
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cuda3_impl0 (Comb3)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
24c84a50 22118400 0.000000e+00 1.680328e+03 1.055142e+02 9.028404e+06 1.523050e+10 5373
e6b94418 153600 0.000000e+00 5.000193e+01 1.025088e+01 7.350283e+03 3.829751e+05 147
c4a08f5f 4646400 0.000000e+00 1.988673e+02 2.685130e+01 1.504233e+06 3.045963e+08 7564
8cfc3ba0 49766400 0.000000e+00 6.051978e+03 2.759693e+02 2.305804e+07 1.398369e+11 3810
a7cdf15b 88473600 0.000000e+00 1.258002e+04 4.620060e+02 4.874757e+07 6.140725e+11 3875
##################
# Performance Model Version
44
####################
# COMBs
# number of combinations
1
####################
# COMB_4
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
0
####################
# DEV_0
# device id
0
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cpu0_impl0 (Comb4)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
617e5fe6 7372800 0.000000e+00 9.359014e+03 4.860060e+02 2.358472e+06 2.213249e+10 252
ad30af9b 51200 0.000000e+00 9.876737e+01 1.343538e+01 1.590451e+06 1.599914e+08 16103
982013a8 1548800 0.000000e+00 2.134161e+03 1.815312e+02 4.673812e+06 1.004683e+10 2190
25ebb669 16588800 0.000000e+00 2.092160e+04 1.229935e+03 3.661280e+06 7.686456e+10 175
5104f3b7 29491200 0.000000e+00 3.676615e+04 1.578675e+03 5.110494e+06 1.882396e+11 139
##################
# Performance Model Version
44
####################
# COMBs
# number of combinations
1
####################
# COMB_4
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
0
####################
# DEV_0
# device id
0
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cpu0_impl0 (Comb4)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
617e5fe6 7372800 0.000000e+00 1.199994e+04 1.417119e+03 2.051989e+06 2.496714e+10 171
ad30af9b 51200 0.000000e+00 4.029498e+01 7.344934e+00 1.938188e+04 8.069416e+05 481
982013a8 1548800 0.000000e+00 1.778398e+03 2.306933e+02 5.015082e+05 9.068890e+08 282
25ebb669 16588800 0.000000e+00 3.651073e+04 5.293321e+03 4.308266e+06 1.606042e+11 118
5104f3b7 29491200 0.000000e+00 8.248482e+04 9.428391e+03 9.403269e+06 7.857610e+11 114
##################
# Performance Model Version
44
####################
# COMBs
# number of combinations
5
####################
# COMB_4
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
0
####################
# DEV_0
# device id
0
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cpu0_impl0 (Comb4)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
ff82dda0 14745600 0.000000e+00 3.671926e+04 6.264954e+03 4.868973e+07 1.839896e+12 1326
5831f4e0 102400 0.000000e+00 3.685897e+01 6.246340e+00 2.291522e+05 8.688881e+06 6217
6a2f38af 3097600 0.000000e+00 3.808134e+03 7.661841e+02 8.320772e+06 3.296929e+10 2185
0e8bce2b 33177600 0.000000e+00 1.197936e+05 2.202875e+04 9.260042e+07 1.146804e+13 773
f001bd15 58982400 0.000000e+00 2.500810e+05 3.400228e+04 1.668040e+08 4.248568e+13 667
####################
# COMB_2
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
0
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cuda0_impl0 (Comb2)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
ff82dda0 14745600 0.000000e+00 1.225366e+03 1.055960e+02 2.940879e+05 3.630415e+08 240
5831f4e0 102400 0.000000e+00 6.983900e+01 1.260925e+01 8.380680e+02 6.043775e+04 12
6a2f38af 3097600 0.000000e+00 2.036579e+02 2.324388e+01 5.885713e+04 1.214286e+07 289
0e8bce2b 33177600 0.000000e+00 3.666675e+03 2.800845e+02 7.150015e+05 2.636975e+09 195
f001bd15 58982400 0.000000e+00 7.329175e+03 4.915258e+02 1.693039e+06 1.246439e+10 231
####################
# COMB_1
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
1
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cuda1_impl0 (Comb1)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
ff82dda0 14745600 0.000000e+00 1.251704e+03 9.523925e+01 2.928988e+05 3.687452e+08 234
5831f4e0 102400 0.000000e+00 7.712755e+01 1.662959e+01 8.484030e+02 6.847722e+04 11
6a2f38af 3097600 0.000000e+00 2.078053e+02 2.202377e+01 5.402939e+04 1.135371e+07 260
0e8bce2b 33177600 0.000000e+00 3.720059e+03 2.853133e+02 8.295732e+05 3.104214e+09 223
f001bd15 58982400 0.000000e+00 7.383529e+03 3.772204e+02 1.580075e+06 1.169698e+10 214
####################
# COMB_0
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
2
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cuda2_impl0 (Comb0)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
ff82dda0 14745600 0.000000e+00 1.252296e+03 1.169465e+02 2.955417e+05 3.733333e+08 236
5831f4e0 102400 0.000000e+00 7.692512e+01 1.259036e+01 1.230802e+03 9.721587e+04 16
6a2f38af 3097600 0.000000e+00 2.079242e+02 2.471557e+01 6.029802e+04 1.271457e+07 290
0e8bce2b 33177600 0.000000e+00 3.744678e+03 3.676926e+02 7.938716e+05 3.001455e+09 212
f001bd15 58982400 0.000000e+00 7.454402e+03 4.686588e+02 1.669786e+06 1.249646e+10 224
####################
# COMB_3
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
3
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cuda3_impl0 (Comb3)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
ff82dda0 14745600 0.000000e+00 1.227027e+03 1.116503e+02 2.908055e+05 3.597807e+08 237
5831f4e0 102400 0.000000e+00 7.100592e+01 1.678181e+01 8.520710e+02 6.388163e+04 12
6a2f38af 3097600 0.000000e+00 2.027211e+02 2.465123e+01 5.331564e+04 1.096802e+07 263
0e8bce2b 33177600 0.000000e+00 3.582949e+03 2.599939e+02 6.341819e+05 2.284206e+09 177
f001bd15 58982400 0.000000e+00 7.239223e+03 4.831241e+02 1.360974e+06 9.896276e+09 188
##################
# Performance Model Version
44
####################
# COMBs
# number of combinations
5
####################
# COMB_4
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
0
####################
# DEV_0
# device id
0
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cpu0_impl0 (Comb4)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
ff82dda0 14745600 0.000000e+00 3.428845e+04 6.014106e+03 4.670087e+07 1.650564e+12 1362
5831f4e0 102400 0.000000e+00 4.315566e+01 9.048618e+00 2.734774e+05 1.232096e+07 6337
6a2f38af 3097600 0.000000e+00 3.493952e+03 6.537880e+02 8.623074e+06 3.118353e+10 2468
0e8bce2b 33177600 0.000000e+00 1.022247e+05 1.393583e+04 9.251336e+07 9.632909e+12 905
f001bd15 58982400 0.000000e+00 2.235792e+05 2.485110e+04 1.562819e+08 3.537307e+13 699
####################
# COMB_0
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
2
####################
# DEV_0
# number of cores
1
##########
# number of implementations
1
#####
# Model for cuda2_impl0 (Comb0)
# number of entries
5
# sumlnx sumlnx2 sumlny sumlnxlny alpha beta n minx maxx
0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 nan nan 0 0 0
# a b c
nan nan nan
# hash size flops mean (us) dev (us) sum sum2 n
ff82dda0 14745600 0.000000e+00 3.276119e+03 3.115623e+02 8.157537e+05 2.696677e+09 249
5831f4e0 102400 0.000000e+00 5.400294e+01 1.227261e+01 9.720530e+02 5.520483e+04 18
6a2f38af 3097600 0.000000e+00 1.059018e+03 1.208041e+02 2.509872e+05 2.692586e+08 237
0e8bce2b 33177600 0.000000e+00 7.073186e+03 6.003818e+02 1.082197e+06 7.709734e+09 153
f001bd15 58982400 0.000000e+00 1.275670e+04 1.000532e+03 2.462043e+06 3.160076e+10 193
####################
# COMB_1
# number of types devices
1
####################
# DEV_0
# device type (CPU - 0, CUDA - 1, OPENCL - 2, MIC - 3, SCC - 4)
1
####################
# DEV_0
# device id
1