| System Information | ||||
| Affiliation: | Tohoku University, Information Synergy Center | URL: | http://www.isc.tohoku.ac.jp/index-e.html | |
| Location: | Japan, Sendai | System Use: | Academic | |
| System Manufacturer: | NEC | System Name: | NEC SX-7C | |
| Interconnect Manufacturer: | NEC | Interconnect Type: | IXS | |
| Operating System: | SUPER-UX 16.1 | MPI: | MPI/SX 7.1.3 | |
| MPI Wtick: | 0.000000001 | BLAS: | Mathkeisan 1.6.0 | |
| Language: | C | Compiler: | C++/SX Rev.071 | |
| Compiler Flags: | -Caopt -Orestrict=arg -pi,auto -Popenmp(STREAM) -Caopt -pvctl,vwork=stack -Orestrict=arg -DGM -Pauto(PTRANS,b_eff)-Caopt -pvctl,nodep,vwork=stack -Orestrict=arg -pi,auto -DMPI2 -Pauto -DRA_METHOD='"SS"'(RA) | Processor Type: | NEC SX-8 | |
| Processor Speed: | 2 GHz | Total Processors: | 40 | |
| Processors Entered: | 40 | Processors determined: | 40 | |
| Cores per chip: | 1 | HPL Processes: | 5 | |
| MPI Processes: | 5 | Threads Entered: | 8 | |
| Threads determined: | 8 | FLOPs per cycle: | 8 | |
| Theoretical peak: | 0.64 TFlop/s | Total memory: | GiB | |
| FFT library: | ||||
| Explain Optimizations: | ||||
| Use Gmem (PTRANS,b_eff) Use FFTE 4.0 vector algorithm (G-FFT) Use unreleased ASL library (SN/EP FFT) Use hypercube algorithm (G-RA) Change loop length to 256 (SN/EP RA) | ||||
| HPL | ||||
| HPL: | 0.302208 Tflop/s | HPL time: | 1905.29 | |
| HPL eps: | 1.11022e-16 | HPL Rnorm1: | 0.00000000224411 | |
| HPL Anorm1: | 24002.4 | HPL AnormI: | 24552.8 | |
| HPL Xnorm1: | 48588.7 | HPL XnormI: | 2.72622 | |
| HPL N: | 95232 | HPL NB: | 64 | |
| HPL NProw: | 1 | HPL NPcol: | 5 | |
| HPL depth: | 1 | HPL NBdiv: | 3 | |
| HPL NBmin: | 44 | HPL CPfact: | R | |
| HPL CRfact: | R | HPL CPtop: | 0 | |
| HPL order: | C | |||
| HPL dMach EPS: | 1.110223e-16 | HPL sMach EPS: | 0.00000005960464 | |
| HPL dMach sfMin: | 0 | HPL sMach sfMin: | 1.175494e-38 | |
| HPL dMach Base: | 2 | HPL sMach Base: | 2 | |
| HPL dMach Prec: | 2.220446e-16 | HPL sMach Prec: | 0.0000001192093 | |
| HPL dMach mLen: | 53 | HPL sMach mLen: | 24 | |
| HPL dMach Rnd: | 1 | HPL sMach Rnd: | 1 | |
| HPL dMach eMin: | -1021 | HPL sMach eMin: | -125 | |
| HPL dMach rMin: | 0 | HPL sMach rMin: | 1.175494e-38 | |
| HPL dMach eMax: | 1024 | HPL sMach eMax: | 128 | |
| HPL dMach rMax: | 1.797693e308 | HPL sMach rMax: | 0 | |
| dweps: | 1.110223e-16 | sweps: | 0.00000005960464 | |
| PTRANS | ||||
| PTRANS: | 20.1298 GB/s | PTRANS time: | 0.901063 seconds | |
| PTRANS residual: | 0 | PTRANS N: | 47616 | |
| PTRANS NB: | 1059 | PTRANS NProw: | 1 | |
| PTRANS NPcol: | 5 | |||
| STREAM | ||||
| S-STREAM Copy: | 337.79 GB/s | S-STREAM Scale: | 296.777 GB/s | |
| S-STREAM Add: | 271.459 GB/s | S-STREAM Triad: | 298.638 GB/s | |
| EP-STREAM Copy: | 319.8 GB/s | EP-STREAM Scale: | 283.92 GB/s | |
| EP-STREAM Add: | 266.471 GB/s | EP-STREAM Triad: | 288.597 GB/s | |
| STREAM Vector Size: | 604608921 | STREAM Threads: | 8 | |
| RandomAccess | ||||
| S-RandomAccess: | 0.5943 Gup/s | EP-RandomAccess: | 0.594693 Gup/s | |
| G-RandomAccess: | 0.00214303 Gup/s | G-RandomAccess N: | 8589934592 | |
| G-RandomAccess time: | 16033.3 seconds | G-RandomAccess Check Time: | 4483.55 seconds | |
| G-RandomAccess Errors: | 75995 | G-RandomAccess Errors Fraction: | 0.00000884698 | |
| G-RandomAccess TimeBound: | 0 | G-RandomAccess ExeUpdates: | 34359738368 | |
| RandomAccess N: | 1073741824 | |||
| FFT | ||||
| S-FFT: | 11.435 GFlop/s | EP-FFT: | 11.43 GFlop/s | |
| MPIFFT: | 29.6227 GFlop/s | MPIFFT N: | 536870912 | |
| MPIFFT Max Error: | 0.00000000000000266973 | MPIFFT time0: | 0.00000435198 seconds | |
| MPIFFT time1: | 0.275197 seconds | MPIFFT time2: | 0.894856 seconds | |
| MPIFFT time3: | 0.224332 seconds | MPIFFT time4: | 0.85041 seconds | |
| MPIFFT time5: | 0.315316 seconds | MPIFFT time6: | 0.000000191998 seconds | |
| FFTEnblk: | 16 | FFTEnp: | 8 | |
| FFTEl2size: | 1048576 | |||
| DGEMM | ||||
| S-DGEMM: | 127.593 GFlop/s | EP-DGEMM: | 114.673 GFlop/s | |
| DGEMM N: | 21294 | |||
| RandomRing Latency/Bandwidth | ||||
| RandomRing Latency: | 6.66671 usec | RandomRing Bandwidth: | 12.3982 GB/s | |
| NaturalRing Latency/Bandwidth | ||||
| NaturalRing Latency: | 6.4736 usec | NaturalRing Bandwidth: | 12.3867 GB/s | |
| PingPong Latency/Bandwidth | ||||
| Maximum PingPong Latency: | 5 usec | Maximum PingPong Bandwidth: | 13.055 GB/s | |
| Minimum PingPong Latency: | 4.96475 usec | Minimum PingPong Bandwidth: | 12.9816 GB/s | |
| Average PingPong Latency: | 4.98575 usec | Average PingPong Bandwidth: | 13.0324 GB/s | |
| Size of Data Types | ||||
| char: | 1 byte | short: | 2 bytes | |
| int: | 4 bytes | long: | 8 bytes | |
| void ptr: | 8 bytes | float: | 4 bytes | |
| double: | 8 bytes | size t: | 8 bytes | |
| s64Int: | 8 bytes | u64Int: | 8 bytes | |
| OpenMP | ||||
| M OpenMP: | 200505 | OpenMP Num Threads: | 8 | |
| OpenMP Num Procs: | 8 | OpenMP Max Threads: | 8 | |
| Memory | ||||
| MemProc: | -1 | MemSpec: | -1 | |
| MemVal: | -1 | |||
| CPS | ||||
| CPS_HPCC_FFT_235: | CPS_HPCC_FFTW_ESTIMATE: | |||
| CPS_HPCC_MEMALLCTR: | CPS_HPL_USE_GETPROCESSTIMES: | |||
| CPS_RA_SANDIA_NOPT: | CPS_RA_SANDIA_OPT2: | |||