| System Information | ||||
| Affiliation: | NNSA/Sandia National Laboratories | URL: | http://www.sandia.gov | |
| Location: | USA, New Mexico, Albuquerque | System Use: | Government | |
| System Manufacturer: | Cray Inc. | System Name: | Red Storm/XT3 | |
| Interconnect Manufacturer: | Cray | Interconnect Type: | Cray custom | |
| Operating System: | UNICOS/lc 1.4.35 | MPI: | MPICH 2 v1.0.2 | |
| MPI Wtick: | 0.000001 | BLAS: | ACML 3.0 | |
| Language: | C | Compiler: | PGI 6.1.4 & gcc 3.3.3 | |
| Compiler Flags: | -tp=k8-64 -Mcache_align -O3 -fastsse -mcmodel=medium -Msafeptr -Mipa=fast | Processor Type: | AMD Opteron | |
| Processor Speed: | 2.4 GHz | Total Processors: | 12960 | |
| Processors Entered: | 12960 | Processors determined: | 25920 | |
| Cores per chip: | 2 | HPL Processes: | 25920 | |
| MPI Processes: | 25920 | Threads Entered: | 1 | |
| Threads determined: | 1 | FLOPs per cycle: | 2 | |
| Theoretical peak: | 124.4 TFlop/s | Total memory: | GiB | |
| FFT library: | ||||
| Explain Optimizations: | ||||
| Optimized Random Access test. We implemented an alternative algorithm which treats the collection of P processors as a hypercube, aggregating data so that larger messages are sent, and routing individual datums through dimensions of the hypercube to their destination processor. | ||||
| HPL | ||||
| HPL: | 90.9902 Tflop/s | HPL time: | 7326.82 | |
| HPL eps: | 1.11022e-16 | HPL Rnorm1: | 0.000000243376 | |
| HPL Anorm1: | 250584 | HPL AnormI: | 250563 | |
| HPL Xnorm1: | 2263160 | HPL XnormI: | 14.4748 | |
| HPL N: | 1000000 | HPL NB: | 64 | |
| HPL NProw: | 180 | HPL NPcol: | 144 | |
| HPL depth: | 0 | HPL NBdiv: | 2 | |
| HPL NBmin: | 8 | HPL CPfact: | C | |
| HPL CRfact: | C | HPL CPtop: | 5 | |
| HPL order: | R | |||
| 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: | 3.402823e38 | |
| dweps: | 1.110223e-16 | sweps: | 0.00000005960464 | |
| PTRANS | ||||
| PTRANS: | 2351.5 GB/s | PTRANS time: | 0.85052 seconds | |
| PTRANS residual: | 0 | PTRANS N: | 500000 | |
| PTRANS NB: | 32 | PTRANS NProw: | 180 | |
| PTRANS NPcol: | 144 | |||
| STREAM | ||||
| S-STREAM Copy: | 4.34015 GB/s | S-STREAM Scale: | 4.83892 GB/s | |
| S-STREAM Add: | 4.48295 GB/s | S-STREAM Triad: | 4.46647 GB/s | |
| EP-STREAM Copy: | 2.07182 GB/s | EP-STREAM Scale: | 2.10343 GB/s | |
| EP-STREAM Add: | 2.04224 GB/s | EP-STREAM Triad: | 2.07916 GB/s | |
| STREAM Vector Size: | 12860082 | STREAM Threads: | 1 | |
| RandomAccess | ||||
| S-RandomAccess: | 0.0181845 Gup/s | EP-RandomAccess: | 0.00911352 Gup/s | |
| G-RandomAccess: | 29.818 Gup/s | G-RandomAccess N: | 549755813888 | |
| G-RandomAccess time: | 73.7482 seconds | G-RandomAccess Check Time: | 302.683 seconds | |
| G-RandomAccess Errors: | 14614144 | G-RandomAccess Errors Fraction: | 0.000026583 | |
| G-RandomAccess TimeBound: | 0 | G-RandomAccess ExeUpdates: | 2199023255552 | |
| RandomAccess N: | 33554432 | |||
| FFT | ||||
| S-FFT: | 0.710797 GFlop/s | EP-FFT: | 0.624079 GFlop/s | |
| MPIFFT: | 1529.14 GFlop/s | MPIFFT N: | 68719476736 | |
| MPIFFT Max Error: | 0.00000000000000242365 | MPIFFT time0: | 0.000000953674 seconds | |
| MPIFFT time1: | 1.75321 seconds | MPIFFT time2: | 0.937044 seconds | |
| MPIFFT time3: | 1.4436 seconds | MPIFFT time4: | 1.73086 seconds | |
| MPIFFT time5: | 2.12931 seconds | MPIFFT time6: | 0.00000214577 seconds | |
| FFTEnblk: | 16 | FFTEnp: | 8 | |
| FFTEl2size: | 1048576 | |||
| DGEMM | ||||
| S-DGEMM: | 4.40783 GFlop/s | EP-DGEMM: | 4.39936 GFlop/s | |
| DGEMM N: | 3105 | |||
| RandomRing Latency/Bandwidth | ||||
| RandomRing Latency: | 15.7621 usec | RandomRing Bandwidth: | 0.0591 GB/s | |
| NaturalRing Latency/Bandwidth | ||||
| NaturalRing Latency: | 14.5776 usec | NaturalRing Bandwidth: | 0.154455 GB/s | |
| PingPong Latency/Bandwidth | ||||
| Maximum PingPong Latency: | 9.31323 usec | Maximum PingPong Bandwidth: | 2.09532 GB/s | |
| Minimum PingPong Latency: | 5.67734 usec | Minimum PingPong Bandwidth: | 1.97821 GB/s | |
| Average PingPong Latency: | 7.1714 usec | Average PingPong Bandwidth: | 2.02385 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: | -1 | OpenMP Num Threads: | 0 | |
| OpenMP Num Procs: | 0 | OpenMP Max Threads: | 0 | |
| 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: | |||