Benchmarks
CPU Benchmark Result
================================================================================ HPLinpack 2.1 -- High-Performance Linpack benchmark -- October 26, 2012 Written by A. Petitet and R. Clint Whaley, Innovative Computing Laboratory, UTK Modified by Piotr Luszczek, Innovative Computing Laboratory, UTK Modified by Julien Langou, University of Colorado Denver ================================================================================ An explanation of the input/output parameters follows: T/V : Wall time / encoded variant. N : The order of the coefficient matrix A. NB : The partitioning blocking factor. P : The number of process rows. Q : The number of process columns. Time : Time in seconds to solve the linear system. Gflops : Rate of execution for solving the linear system. The following parameter values will be used: N : 1024000 NB : 160 PMAP : Row-major process mapping P : 38 Q : 48 PFACT : Right NBMIN : 4 NDIV : 2 RFACT : Crout BCAST : 1ringM DEPTH : 0 SWAP : Mix (threshold = 64) L1 : transposed form U : transposed form EQUIL : yes ALIGN : 8 double precision words -------------------------------------------------------------------------------- - The matrix A is randomly generated for each test. - The following scaled residual check will be computed: ||Ax-b||_oo / ( eps * ( || x ||_oo * || A ||_oo + || b ||_oo ) * N ) - The relative machine precision (eps) is taken to be 1.110223e-16 - Computational tests pass if scaled residuals are less than 16.0 Column=005280 Fraction=0.005 Mflops=56349816.25 Column=010400 Fraction=0.010 Mflops=56376008.60 Column=015520 Fraction=0.015 Mflops=56561106.32 Column=020640 Fraction=0.020 Mflops=56543603.06 Column=025760 Fraction=0.025 Mflops=56509580.84 Column=030880 Fraction=0.030 Mflops=56573651.34 Column=036000 Fraction=0.035 Mflops=56562106.81 Column=041120 Fraction=0.040 Mflops=56529951.15 Column=046240 Fraction=0.045 Mflops=56550143.05 Column=051200 Fraction=0.050 Mflops=56538108.48 Column=056320 Fraction=0.055 Mflops=56516490.44 Column=061440 Fraction=0.060 Mflops=56550341.86 Column=066560 Fraction=0.065 Mflops=56539041.02 Column=071680 Fraction=0.070 Mflops=56514832.06 Column=076960 Fraction=0.075 Mflops=56528308.46 Column=082080 Fraction=0.080 Mflops=56520679.66 Column=087200 Fraction=0.085 Mflops=56501892.91 Column=092320 Fraction=0.090 Mflops=56519118.84 Column=097440 Fraction=0.095 Mflops=56513008.77 Column=102560 Fraction=0.100 Mflops=56499030.29 Column=107680 Fraction=0.105 Mflops=56507297.49 Column=112800 Fraction=0.110 Mflops=56497591.62 Column=117920 Fraction=0.115 Mflops=56479754.39 Column=123040 Fraction=0.120 Mflops=56488861.55 Column=128160 Fraction=0.125 Mflops=56482512.89 Column=133280 Fraction=0.130 Mflops=56467722.84 Column=138400 Fraction=0.135 Mflops=56473124.17 Column=143520 Fraction=0.140 Mflops=56465633.44 Column=148640 Fraction=0.145 Mflops=56451525.63 Column=153760 Fraction=0.150 Mflops=56455942.33 Column=158880 Fraction=0.155 Mflops=56448380.96 Column=164000 Fraction=0.160 Mflops=56435263.13 Column=169120 Fraction=0.165 Mflops=56435563.90 Column=174240 Fraction=0.170 Mflops=56425868.68 Column=179360 Fraction=0.175 Mflops=56411859.46 Column=184480 Fraction=0.180 Mflops=56413021.44 Column=189600 Fraction=0.185 Mflops=56406753.80 Column=194720 Fraction=0.190 Mflops=56395459.58 Column=199840 Fraction=0.195 Mflops=56397119.24 Column=204960 Fraction=0.200 Mflops=56388068.36 Column=210080 Fraction=0.205 Mflops=56374825.49 Column=215200 Fraction=0.210 Mflops=56373525.49 Column=220320 Fraction=0.215 Mflops=56365397.25 Column=225440 Fraction=0.220 Mflops=56354138.15 Column=230560 Fraction=0.225 Mflops=56351775.71 Column=235680 Fraction=0.230 Mflops=56343336.74 Column=240800 Fraction=0.235 Mflops=56332514.92 Column=245920 Fraction=0.240 Mflops=56333188.22 Column=251040 Fraction=0.245 Mflops=56324323.15 Column=256160 Fraction=0.250 Mflops=56312251.68 Column=261280 Fraction=0.255 Mflops=56310652.57 Column=266400 Fraction=0.260 Mflops=56303236.43 Column=271520 Fraction=0.265 Mflops=56293034.56 Column=276640 Fraction=0.270 Mflops=56292653.84 Column=281760 Fraction=0.275 Mflops=56284950.06 Column=286880 Fraction=0.280 Mflops=56275560.46 Column=292000 Fraction=0.285 Mflops=56274401.59 Column=297120 Fraction=0.290 Mflops=56266280.26 Column=302240 Fraction=0.295 Mflops=56255589.37 Column=307360 Fraction=0.300 Mflops=56253197.55 Column=312480 Fraction=0.305 Mflops=56244281.99 Column=317600 Fraction=0.310 Mflops=56235067.81 Column=322720 Fraction=0.315 Mflops=56233896.05 Column=327840 Fraction=0.320 Mflops=56226479.17 Column=332960 Fraction=0.325 Mflops=56216382.85 Column=338080 Fraction=0.330 Mflops=56213896.01 Column=343200 Fraction=0.335 Mflops=56205838.43 Column=348320 Fraction=0.340 Mflops=56196478.01 Column=353440 Fraction=0.345 Mflops=56192444.47 Column=358560 Fraction=0.350 Mflops=56184215.00 Column=363680 Fraction=0.355 Mflops=56174540.11 Column=368800 Fraction=0.360 Mflops=56171583.15 Column=373920 Fraction=0.365 Mflops=56163383.88 Column=379040 Fraction=0.370 Mflops=56154030.62 Column=384160 Fraction=0.375 Mflops=56151453.45 Column=389280 Fraction=0.380 Mflops=56142705.94 Column=394400 Fraction=0.385 Mflops=56132908.05 Column=399520 Fraction=0.390 Mflops=56129013.21 Column=404640 Fraction=0.395 Mflops=56120702.05 Column=409760 Fraction=0.400 Mflops=56111209.14 Column=414880 Fraction=0.405 Mflops=56106950.12 Column=420000 Fraction=0.410 Mflops=56098454.97 Column=425120 Fraction=0.415 Mflops=56088972.59 Column=430240 Fraction=0.420 Mflops=56085861.31 Column=435360 Fraction=0.425 Mflops=56078303.93 Column=440480 Fraction=0.430 Mflops=56069356.80 Column=445600 Fraction=0.435 Mflops=56065087.34 Column=450720 Fraction=0.440 Mflops=56057247.56 Column=455840 Fraction=0.445 Mflops=56047588.49 Column=460960 Fraction=0.450 Mflops=56043920.07 Column=466080 Fraction=0.455 Mflops=56036469.04 Column=471200 Fraction=0.460 Mflops=56027472.10 Column=476320 Fraction=0.465 Mflops=56023343.18 Column=481440 Fraction=0.470 Mflops=56020114.97 Column=486560 Fraction=0.475 Mflops=56014914.70 Column=491680 Fraction=0.480 Mflops=56014060.82 Column=496800 Fraction=0.485 Mflops=56010317.12 Column=501920 Fraction=0.490 Mflops=56005409.50 Column=507040 Fraction=0.495 Mflops=56003878.79 Column=527520 Fraction=0.515 Mflops=55989636.26 Column=548000 Fraction=0.535 Mflops=55971477.56 Column=568480 Fraction=0.555 Mflops=55956507.12 Column=588960 Fraction=0.575 Mflops=55938188.82 Column=609440 Fraction=0.595 Mflops=55918376.57 Column=629920 Fraction=0.615 Mflops=55901358.43 Column=650400 Fraction=0.635 Mflops=55881397.42 Column=670880 Fraction=0.655 Mflops=55861009.41 Column=691360 Fraction=0.675 Mflops=55843268.81 Column=711840 Fraction=0.695 Mflops=55823273.65 Column=814240 Fraction=0.795 Mflops=55723631.14 Column=916640 Fraction=0.895 Mflops=55649093.18 Column=1019040 Fraction=0.995 Mflops=55608308.64 ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR01C2R4 1024000 160 38 48 12874.95 5.55986e+04 HPL_pdgesv() start time Thu May 14 18:32:43 2015 HPL_pdgesv() end time Thu May 14 22:07:18 2015 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 0.0006277 ...... PASSED ================================================================================ Finished 1 tests with the following results: 1 tests completed and passed residual checks, 0 tests completed and failed residual checks, 0 tests skipped because of illegal input values. -------------------------------------------------------------------------------- End of Tests. ================================================================================
55.5986 TF
GPU Benchmark Result
================================================================================ HPLinpack 2.1 -- High-Performance Linpack benchmark -- October 26, 2012 Written by A. Petitet and R. Clint Whaley, Innovative Computing Laboratory, UTK Modified by Piotr Luszczek, Innovative Computing Laboratory, UTK Modified by Julien Langou, University of Colorado Denver ================================================================================ An explanation of the input/output parameters follows: T/V : Wall time / encoded variant. N : The order of the coefficient matrix A. NB : The partitioning blocking factor. P : The number of process rows. Q : The number of process columns. Time : Time in seconds to solve the linear system. Gflops : Rate of execution for solving the linear system. The following parameter values will be used: N : 558080 NB : 1024 PMAP : Row-major process mapping P : 8 Q : 5 PFACT : Left NBMIN : 2 NDIV : 2 RFACT : Right BCAST : 2ringM DEPTH : 0 SWAP : Spread-roll (long) L1 : no-transposed form U : transposed form EQUIL : yes ALIGN : 8 double precision words -------------------------------------------------------------------------------- - The matrix A is randomly generated for each test. - The following scaled residual check will be computed: ||Ax-b||_oo / ( eps * ( || x ||_oo * || A ||_oo + || b ||_oo ) * N ) - The relative machine precision (eps) is taken to be 1.110223e-16 - Computational tests pass if scaled residuals are less than 16.0 displaying Prog:%complete, N:columns, Time:seconds iGF:instantaneous GF, GF:avg GF, GF_per: process GF trsm_cutoff from environment variable 16000 gpu_dgemm_split from environment variable 0.900 monitor_gpu from environment variable 1 gpu_temp_warning from environment variable 88 gpu_clock_warning from environment variable 745 gpu_power_warning from environment variable 225 [compute078:11323] 39 more processes have sent help message help-mpi-btl-openib.txt / no device params found [compute078:11323] Set MCA parameter "orte_base_help_aggregate" to 0 to see all help / error messages 2015-05-02 20:35:51.823 Prog= 1.64% N_left= 555008 Time= 46.05 iGF= 41327.48 GF= 41327.48 iGF_per= 1033.19 GF_per= 1033.19 Prog= 3.27% N_left= 551936 Time= 80.96 iGF= 53914.96 GF= 46755.22 iGF_per= 1347.87 GF_per= 1168.88 Prog= 4.87% N_left= 548864 Time= 116.16 iGF= 52866.85 GF= 48607.52 iGF_per= 1321.67 GF_per= 1215.19 Prog= 5.93% N_left= 546816 Time= 139.30 iGF= 49359.03 GF= 49359.03 iGF_per= 1233.98 GF_per= 1233.98 Prog= 7.51% N_left= 543744 Time= 173.69 iGF= 53127.19 GF= 50105.03 iGF_per= 1328.18 GF_per= 1252.63 Prog= 9.07% N_left= 540672 Time= 207.60 iGF= 53263.86 GF= 50621.03 iGF_per= 1331.60 GF_per= 1265.53 Prog= 10.61% N_left= 537600 Time= 241.25 iGF= 53065.22 GF= 50961.99 iGF_per= 1326.63 GF_per= 1274.05 Prog= 11.63% N_left= 535552 Time= 263.15 iGF= 53275.54 GF= 51202.32 iGF_per= 1331.89 GF_per= 1280.06 Prog= 13.14% N_left= 532480 Time= 296.09 iGF= 53186.56 GF= 51423.08 iGF_per= 1329.66 GF_per= 1285.58 Prog= 14.63% N_left= 529408 Time= 328.34 iGF= 53719.91 GF= 51648.62 iGF_per= 1343.00 GF_per= 1291.22 Prog= 15.62% N_left= 527360 Time= 350.69 iGF= 53104.49 GF= 51616.74 iGF_per= 1327.61 GF_per= 1290.42 Prog= 17.09% N_left= 524288 Time= 382.68 iGF= 53112.66 GF= 51741.77 iGF_per= 1327.82 GF_per= 1293.54 Prog= 18.54% N_left= 521216 Time= 415.00 iGF= 51940.97 GF= 51757.28 iGF_per= 1298.52 GF_per= 1293.93 Prog= 19.97% N_left= 518144 Time= 446.30 iGF= 53019.69 GF= 51845.81 iGF_per= 1325.49 GF_per= 1296.15 Prog= 20.91% N_left= 516096 Time= 466.80 iGF= 52815.08 GF= 51914.81 iGF_per= 1320.38 GF_per= 1297.87 Prog= 22.32% N_left= 513024 Time= 498.01 iGF= 52130.25 GF= 51928.31 iGF_per= 1303.26 GF_per= 1298.21 Prog= 23.70% N_left= 509952 Time= 528.66 iGF= 52443.09 GF= 51958.15 iGF_per= 1311.08 GF_per= 1298.95 Prog= 25.08% N_left= 506880 Time= 559.16 iGF= 52064.64 GF= 51963.96 iGF_per= 1301.62 GF_per= 1299.10 Prog= 25.98% N_left= 504832 Time= 578.59 iGF= 52515.92 GF= 52030.94 iGF_per= 1312.90 GF_per= 1300.77 Prog= 27.32% N_left= 501760 Time= 608.56 iGF= 51926.81 GF= 52025.81 iGF_per= 1298.17 GF_per= 1300.65 Prog= 28.65% N_left= 498688 Time= 637.04 iGF= 53976.45 GF= 52113.03 iGF_per= 1349.41 GF_per= 1302.83 Prog= 29.52% N_left= 496640 Time= 656.63 iGF= 52566.76 GF= 52103.28 iGF_per= 1314.17 GF_per= 1302.58 Prog= 30.82% N_left= 493568 Time= 685.00 iGF= 53090.66 GF= 52144.17 iGF_per= 1327.27 GF_per= 1303.60 Prog= 32.11% N_left= 490496 Time= 713.71 iGF= 51808.52 GF= 52130.67 iGF_per= 1295.21 GF_per= 1303.27 Prog= 33.38% N_left= 487424 Time= 741.42 iGF= 53012.65 GF= 52163.63 iGF_per= 1325.32 GF_per= 1304.09 Prog= 34.21% N_left= 485376 Time= 759.93 iGF= 52581.93 GF= 52168.34 iGF_per= 1314.55 GF_per= 1304.21 Prog= 35.45% N_left= 482304 Time= 786.92 iGF= 53290.17 GF= 52206.82 iGF_per= 1332.25 GF_per= 1305.17 Prog= 36.68% N_left= 479232 Time= 813.73 iGF= 52957.26 GF= 52231.55 iGF_per= 1323.93 GF_per= 1305.79 Prog= 37.89% N_left= 476160 Time= 840.44 iGF= 52505.22 GF= 52240.25 iGF_per= 1312.63 GF_per= 1306.01 Prog= 38.69% N_left= 474112 Time= 857.99 iGF= 52876.94 GF= 52249.33 iGF_per= 1321.92 GF_per= 1306.23 Prog= 39.87% N_left= 471040 Time= 884.55 iGF= 51655.09 GF= 52231.48 iGF_per= 1291.38 GF_per= 1305.79 Prog= 41.04% N_left= 467968 Time= 909.88 iGF= 53462.65 GF= 52265.76 iGF_per= 1336.57 GF_per= 1306.64 Prog= 41.81% N_left= 465920 Time= 926.96 iGF= 52711.68 GF= 52266.25 iGF_per= 1317.79 GF_per= 1306.66 Prog= 42.95% N_left= 462848 Time= 951.95 iGF= 53014.89 GF= 52285.91 iGF_per= 1325.37 GF_per= 1307.15 Prog= 44.08% N_left= 459776 Time= 977.04 iGF= 52127.01 GF= 52281.83 iGF_per= 1303.18 GF_per= 1307.05 Prog= 45.20% N_left= 456704 Time= 1001.57 iGF= 52594.05 GF= 52289.47 iGF_per= 1314.85 GF_per= 1307.24 Prog= 45.93% N_left= 454656 Time= 1017.79 iGF= 52554.29 GF= 52291.95 iGF_per= 1313.86 GF_per= 1307.30 Prog= 47.02% N_left= 451584 Time= 1041.38 iGF= 53453.35 GF= 52318.27 iGF_per= 1336.33 GF_per= 1307.96 Prog= 48.09% N_left= 448512 Time= 1064.80 iGF= 53142.47 GF= 52336.40 iGF_per= 1328.56 GF_per= 1308.41 Prog= 49.15% N_left= 445440 Time= 1088.59 iGF= 51595.65 GF= 52320.21 iGF_per= 1289.89 GF_per= 1308.01 Prog= 49.85% N_left= 443392 Time= 1103.61 iGF= 52924.62 GF= 52341.16 iGF_per= 1323.12 GF_per= 1308.53 Prog= 50.88% N_left= 440320 Time= 1126.96 iGF= 51376.07 GF= 52321.16 iGF_per= 1284.40 GF_per= 1308.03 Prog= 51.91% N_left= 437248 Time= 1149.14 iGF= 53331.81 GF= 52340.67 iGF_per= 1333.30 GF_per= 1308.52 Prog= 52.58% N_left= 435200 Time= 1164.04 iGF= 52676.38 GF= 52340.26 iGF_per= 1316.91 GF_per= 1308.51 Prog= 53.58% N_left= 432128 Time= 1185.84 iGF= 53020.19 GF= 52352.75 iGF_per= 1325.50 GF_per= 1308.82 Prog= 54.56% N_left= 429056 Time= 1207.37 iGF= 52897.94 GF= 52362.48 iGF_per= 1322.45 GF_per= 1309.06 Prog= 55.53% N_left= 425984 Time= 1228.88 iGF= 52203.77 GF= 52359.70 iGF_per= 1305.09 GF_per= 1308.99 Prog= 56.17% N_left= 423936 Time= 1243.00 iGF= 52651.43 GF= 52360.02 iGF_per= 1316.29 GF_per= 1309.00 Prog= 57.11% N_left= 420864 Time= 1263.52 iGF= 53425.02 GF= 52377.32 iGF_per= 1335.63 GF_per= 1309.43 Prog= 58.04% N_left= 417792 Time= 1284.00 iGF= 52747.79 GF= 52383.23 iGF_per= 1318.69 GF_per= 1309.58 Prog= 58.66% N_left= 415744 Time= 1297.70 iGF= 52713.38 GF= 52378.69 iGF_per= 1317.83 GF_per= 1309.47 Prog= 59.57% N_left= 412672 Time= 1317.84 iGF= 52333.05 GF= 52377.99 iGF_per= 1308.33 GF_per= 1309.45 Prog= 60.46% N_left= 409600 Time= 1337.82 iGF= 51982.76 GF= 52372.09 iGF_per= 1299.57 GF_per= 1309.30 Prog= 61.35% N_left= 406528 Time= 1357.07 iGF= 53131.17 GF= 52382.86 iGF_per= 1328.28 GF_per= 1309.57 Prog= 61.93% N_left= 404480 Time= 1369.96 iGF= 52435.59 GF= 52381.69 iGF_per= 1310.89 GF_per= 1309.54 Prog= 62.79% N_left= 401408 Time= 1388.61 iGF= 53488.48 GF= 52396.55 iGF_per= 1337.21 GF_per= 1309.91 Prog= 63.64% N_left= 398336 Time= 1407.30 iGF= 52579.30 GF= 52398.98 iGF_per= 1314.48 GF_per= 1309.9 Prog= 64.47% N_left= 395264 Time= 1425.77 iGF= 52361.13 GF= 52398.49 iGF_per= 1309.03 GF_per= 1309.96 Prog= 65.02% N_left= 393216 Time= 1437.88 iGF= 52765.64 GF= 52399.82 iGF_per= 1319.14 GF_per= 1310.00 Prog= 65.83% N_left= 390144 Time= 1455.91 iGF= 52276.04 GF= 52398.29 iGF_per= 1306.90 GF_per= 1309.96 Prog= 66.64% N_left= 387072 Time= 1473.39 iGF= 53102.79 GF= 52406.65 iGF_per= 1327.57 GF_per= 1310.17 Prog= 67.16% N_left= 385024 Time= 1484.94 iGF= 52748.17 GF= 52410.06 iGF_per= 1318.70 GF_per= 1310.25 Prog= 67.94% N_left= 381952 Time= 1501.87 iGF= 53352.04 GF= 52420.69 iGF_per= 1333.80 GF_per= 1310.52 Prog= 68.71% N_left= 378880 Time= 1519.08 iGF= 51670.00 GF= 52412.18 iGF_per= 1291.75 GF_per= 1310.30 Prog= 69.46% N_left= 375808 Time= 1535.55 iGF= 53134.59 GF= 52419.93 iGF_per= 1328.36 GF_per= 1310.50 Prog= 69.96% N_left= 373760 Time= 1546.90 iGF= 52339.31 GF= 52407.23 iGF_per= 1308.48 GF_per= 1310.18 Prog= 70.70% N_left= 370688 Time= 1563.00 iGF= 52848.22 GF= 52411.77 iGF_per= 1321.21 GF_per= 1310.29 Prog= 71.42% N_left= 367616 Time= 1578.66 iGF= 53467.28 GF= 52422.24 iGF_per= 1336.68 GF_per= 1310.56 Prog= 72.13% N_left= 364544 Time= 1594.50 iGF= 51991.94 GF= 52417.97 iGF_per= 1299.80 GF_per= 1310.45 Prog= 72.60% N_left= 362496 Time= 1605.00 iGF= 52549.45 GF= 52412.38 iGF_per= 1313.74 GF_per= 1310.31 Prog= 73.29% N_left= 359424 Time= 1619.93 iGF= 53601.52 GF= 52423.34 iGF_per= 1340.04 GF_per= 1310.58 Prog= 73.97% N_left= 356352 Time= 1634.66 iGF= 53422.02 GF= 52432.34 iGF_per= 1335.55 GF_per= 1310.81 Prog= 74.41% N_left= 354304 Time= 1644.87 iGF= 52642.74 GF= 52421.26 iGF_per= 1316.07 GF_per= 1310.53 Prog= 75.07% N_left= 351232 Time= 1659.21 iGF= 53350.98 GF= 52429.29 iGF_per= 1333.77 GF_per= 1310.73 Prog= 75.72% N_left= 348160 Time= 1673.93 iGF= 51025.49 GF= 52416.94 iGF_per= 1275.64 GF_per= 1310.42 Prog= 76.36% N_left= 345088 Time= 1687.93 iGF= 52741.29 GF= 52419.63 iGF_per= 1318.53 GF_per= 1310.49 Prog= 76.78% N_left= 343040 Time= 1697.11 iGF= 52439.47 GF= 52421.82 iGF_per= 1310.99 GF_per= 1310.55 Prog= 77.39% N_left= 339968 Time= 1710.75 iGF= 52526.60 GF= 52422.65 iGF_per= 1313.17 GF_per= 1310.57 Prog= 78.00% N_left= 336896 Time= 1724.10 iGF= 52712.99 GF= 52424.90 iGF_per= 1317.82 GF_per= 1310.62 Prog= 78.60% N_left= 333824 Time= 1737.34 iGF= 52188.72 GF= 52423.10 iGF_per= 1304.72 GF_per= 1310.58 Prog= 78.99% N_left= 331776 Time= 1745.87 iGF= 52603.32 GF= 52426.89 iGF_per= 1315.08 GF_per= 1310.67 Prog= 79.57% N_left= 328704 Time= 1758.88 iGF= 51474.94 GF= 52419.84 iGF_per= 1286.87 GF_per= 1310.50 Prog= 80.13% N_left= 325632 Time= 1771.28 iGF= 53036.33 GF= 52424.16 iGF_per= 1325.91 GF_per= 1310.60 Prog= 80.51% N_left= 323584 Time= 1779.48 iGF= 52498.46 GF= 52425.37 iGF_per= 1312.46 GF_per= 1310.63 Prog= 81.06% N_left= 320512 Time= 1791.56 iGF= 52736.28 GF= 52427.46 iGF_per= 1318.41 GF_per= 1310.69 Prog= 81.60% N_left= 317440 Time= 1803.60 iGF= 51897.86 GF= 52423.93 iGF_per= 1297.45 GF_per= 1310.60 Prog= 82.13% N_left= 314368 Time= 1815.15 iGF= 53115.07 GF= 52428.32 iGF_per= 1327.88 GF_per= 1310.71 Prog= 82.47% N_left= 312320 Time= 1823.08 iGF= 52238.81 GF= 52420.90 iGF_per= 1305.97 GF_per= 1310.52 Prog= 82.99% N_left= 309248 Time= 1834.24 iGF= 53157.33 GF= 52425.39 iGF_per= 1328.93 GF_per= 1310.63 Prog= 83.49% N_left= 306176 Time= 1845.14 iGF= 53357.53 GF= 52430.89 iGF_per= 1333.94 GF_per= 1310.77 Prog= 83.82% N_left= 304128 Time= 1852.46 iGF= 52538.57 GF= 52429.83 iGF_per= 1313.46 GF_per= 1310.75 Prog= 84.30% N_left= 301056 Time= 1863.26 iGF= 52053.96 GF= 52427.65 iGF_per= 1301.35 GF_per= 1310.69 Prog= 84.78% N_left= 297984 Time= 1873.99 iGF= 51374.60 GF= 52421.62 iGF_per= 1284.36 GF_per= 1310.54 Prog= 85.24% N_left= 294912 Time= 1884.35 iGF= 52150.23 GF= 52420.13 iGF_per= 1303.76 GF_per= 1310.50 Prog= 85.55% N_left= 292864 Time= 1891.24 iGF= 51754.81 GF= 52415.98 iGF_per= 1293.87 GF_per= 1310.40 Prog= 86.00% N_left= 289792 Time= 1901.33 iGF= 51707.59 GF= 52412.22 iGF_per= 1292.69 GF_per= 1310.31 Prog= 86.44% N_left= 286720 Time= 1911.05 iGF= 52504.16 GF= 52412.69 iGF_per= 1312.60 GF_per= 1310.32 Prog= 86.87% N_left= 283648 Time= 1920.42 iGF= 53364.44 GF= 52417.33 iGF_per= 1334.11 GF_per= 1310.43 Prog= 87.15% N_left= 281600 Time= 1926.64 iGF= 52513.84 GF= 52417.78 iGF_per= 1312.85 GF_per= 1310.4 Prog= 88.63% N_left= 270336 Time= 1959.51 iGF= 52204.43 GF= 52414.20 iGF_per= 1305.11 GF_per= 1310.36 Prog= 90.00% N_left= 259072 Time= 1990.06 iGF= 51683.93 GF= 52402.99 iGF_per= 1292.10 GF_per= 1310.07 Prog= 91.24% N_left= 247808 Time= 2017.93 iGF= 51929.59 GF= 52396.45 iGF_per= 1298.24 GF_per= 1309.91 Prog= 92.39% N_left= 236544 Time= 2043.63 iGF= 51411.77 GF= 52384.07 iGF_per= 1285.29 GF_per= 1309.60 Prog= 93.42% N_left= 225280 Time= 2067.14 iGF= 51099.27 GF= 52369.45 iGF_per= 1277.48 GF_per= 1309.24 Prog= 94.36% N_left= 214016 Time= 2088.71 iGF= 50400.90 GF= 52349.13 iGF_per= 1260.02 GF_per= 1308.73 Prog= 95.20% N_left= 202752 Time= 2108.36 iGF= 49794.47 GF= 52325.32 iGF_per= 1244.86 GF_per= 1308.13 Prog= 95.90% N_left= 192512 Time= 2124.61 iGF= 50226.61 GF= 52301.84 iGF_per= 1255.67 GF_per= 1307.55 Prog= 96.57% N_left= 181248 Time= 2140.85 iGF= 48459.36 GF= 52272.69 iGF_per= 1211.48 GF_per= 1306.82 Prog= 97.17% N_left= 169984 Time= 2155.56 iGF= 47243.92 GF= 52238.37 iGF_per= 1181.10 GF_per= 1305.96 Prog= 99.16% N_left= 113664 Time= 2210.05 iGF= 42122.90 GF= 51988.95 iGF_per= 1053.07 GF_per= 1299.72 Prog= 99.89% N_left= 58368 Time= 2235.27 iGF= 41783.18 GF= 51781.08 iGF_per= 1044.58 GF_per= 1294.53 Prog= 100.00% N_left= 2048 Time= 2244.51 iGF= 14348.21 GF= 51627.00 iGF_per= 358.71 GF_per= 1290.68 ================================================================================ T/V N NB P Q Time Gflops -------------------------------------------------------------------------------- WR03R2L2 558080 1024 8 5 2245.36 5.161e+04 -------------------------------------------------------------------------------- ||Ax-b||_oo/(eps*(||A||_oo*||x||_oo+||b||_oo)*N)= 0.0000136 ...... PASSED ================================================================================ Finished 1 tests with the following results: 1 tests completed and passed residual checks, 0 tests completed and failed residual checks, 0 tests skipped because of illegal input values. -------------------------------------------------------------------------------- End of Tests. ================================================================================
51.61 TF
Vikram-100 Performance
Total Computational Capability of VIkram-100: 55.5986 TF + 51.61 TF = 107.2086 TF
Performance of Vikram-100 over previous 2.2 TF PRL HPC
Varun Sheel / Jagat Bisht | WRF-Chem v3.4, run with a grid resolution of 10km, grid size of 1500km and run for 4 calendar days | ||||
Sanjay Kumar and Ramit | EULAG-MHD, executed with a resolution of 128X128X256 in a periodic cell for 7000 time loops. | ||||
D. Angom | RCCPAC: Coupled cluster code developed at PRL | ||||
V. K. B. Kota / Sudip Kumar Haldar | Generates an ensemble of 20 random matrices of block diagonal form, with dimension 1764, 2352 and 720 respectively. Then it diagonalizes the matrices to find eigenvalues and eigen vectors and calculate ensemble average of different quantities (as a function of time) using these eigenvalues and eigenvectors. |