| System Information | ||||
| Affiliation: | Oak Ridge National Laboratory | URL: | http://www.nccs.gov | |
| Location: | USA, Tennessee, Oak Ridge | System Use: | Research | |
| System Manufacturer: | Cray | System Name: | XT5 | |
| Interconnect Manufacturer: | Cray | Interconnect Type: | Seastar | |
| Operating System: | CLE | MPI: | MPT 3.4.2 | |
| MPI Wtick: | 0.000001 | BLAS: | ACML 4.3.0 | |
| Language: | C | Compiler: | PGI 9.0.2 | |
| Compiler Flags: | -mp -fast; -mp -Mnontemporal -Mprefetch=distance:8,nta -Msafeptr -fastsse (STREAM) | Processor Type: | AMD Opteron | |
| Processor Speed: | 2.6 GHz | Total Processors: | 224256 | |
| Processors Entered: | 223112 | Processors determined: | 223112 | |
| Cores per chip: | 6 | HPL Processes: | 111556 | |
| MPI Processes: | 111556 | Threads Entered: | 2 | |
| Threads determined: | 2 | FLOPs per cycle: | 2 | |
| Theoretical peak: | 2320.4 TFlop/s | Total memory: | 299008 GiB | |
| FFT library: | none | |||
| Explain Optimizations: | ||||
hpcc-1.0.0 using Sandia's MPIRandomAccess_opt.c Modified HPL broadcast algorithms Modified communication phase of Sandia's AnyNodesMPIRandomAccessUpdate to coordinate updates between ranks on-node, using MPI. No changes were made to lookahead, nor to the generation or application of updates. | ||||
| HPL | ||||
| HPL: | 1467.66 Tflop/s | HPL time: | 33517.5 | |
| HPL eps: | 1.11022e-16 | HPL Rnorm1: | 0.00000282053 | |
| HPL Anorm1: | 1049690 | HPL AnormI: | 1049400 | |
| HPL Xnorm1: | 7168380 | HPL XnormI: | 11.2157 | |
| HPL N: | 4194328 | HPL NB: | 232 | |
| HPL NProw: | 334 | HPL NPcol: | 334 | |
| HPL depth: | 1 | HPL NBdiv: | 2 | |
| HPL NBmin: | 4 | HPL CPfact: | C | |
| HPL CRfact: | R | HPL CPtop: | 1 | |
| HPL order: | R | |||
| HPL dMach EPS: | 1.110223e-16 | HPL sMach EPS: | 0.00000005960464 | |
| HPL dMach sfMin: | 2.225074e-308 | HPL sMach sfMin: | 1.1754939999999999e-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: | 2.225074e-308 | HPL sMach rMin: | 1.1754939999999999e-38 | |
| HPL dMach eMax: | 1024 | HPL sMach eMax: | 128 | |
| HPL dMach rMax: | 1.797693e308 | HPL sMach rMax: | 3.4028230000000003e38 | |
| dweps: | 1.110223e-16 | sweps: | 0.00000005960464 | |
| PTRANS | ||||
| PTRANS: | 13723.2 GB/s | PTRANS time: | 2.5639 seconds | |
| PTRANS residual: | 0 | PTRANS N: | 2097164 | |
| PTRANS NB: | 120 | PTRANS NProw: | 334 | |
| PTRANS NPcol: | 334 | |||
| STREAM | ||||
| S-STREAM Copy: | 10.4798 GB/s | S-STREAM Scale: | 10.5678 GB/s | |
| S-STREAM Add: | 10.3435 GB/s | S-STREAM Triad: | 10.4644 GB/s | |
| EP-STREAM Copy: | 3.5314 GB/s | EP-STREAM Scale: | 3.52742 GB/s | |
| EP-STREAM Add: | 3.49768 GB/s | EP-STREAM Triad: | 3.57011 GB/s | |
| STREAM Vector Size: | 52566685 | STREAM Threads: | 2 | |
| RandomAccess | ||||
| S-RandomAccess: | 0.0332369 Gup/s | EP-RandomAccess: | 0.017055 Gup/s | |
| G-RandomAccess: | 37.6896 Gup/s | G-RandomAccess N: | 17592186044416 | |
| G-RandomAccess time: | 1867.06 seconds | G-RandomAccess Check Time: | 3627.45 seconds | |
| G-RandomAccess Errors: | 23826421 | G-RandomAccess Errors Fraction: | 0.00000135438 | |
| G-RandomAccess TimeBound: | 6.4758e-319 | G-RandomAccess ExeUpdates: | 70368744177664 | |
| RandomAccess N: | 134217728 | |||
| FFT | ||||
| S-FFT: | 1.1955 GFlop/s | EP-FFT: | 0.792142 GFlop/s | |
| MPIFFT: | 3879.21 GFlop/s | MPIFFT N: | 1099511627776 | |
| MPIFFT Max Error: | 0.00000000000000227799 | MPIFFT time0: | 0.00000214577 seconds | |
| MPIFFT time1: | 16.8123 seconds | MPIFFT time2: | 3.27396 seconds | |
| MPIFFT time3: | 17.3095 seconds | MPIFFT time4: | 5.07976 seconds | |
| MPIFFT time5: | 13.9836 seconds | MPIFFT time6: | 0.00000214577 seconds | |
| FFTEnblk: | 16 | FFTEnp: | 4 | |
| FFTEl2size: | 1048576 | |||
| DGEMM | ||||
| S-DGEMM: | 19.4899 GFlop/s | EP-DGEMM: | 19.2461 GFlop/s | |
| DGEMM N: | 6278 | |||
| RandomRing Latency/Bandwidth | ||||
| RandomRing Latency: | 31.0895 usec | RandomRing Bandwidth: | 0.0264497 GB/s | |
| NaturalRing Latency/Bandwidth | ||||
| NaturalRing Latency: | 11.301 usec | NaturalRing Bandwidth: | 0.34982 GB/s | |
| PingPong Latency/Bandwidth | ||||
| Maximum PingPong Latency: | 10.55 usec | Maximum PingPong Bandwidth: | 1.65211 GB/s | |
| Minimum PingPong Latency: | 6.86944 usec | Minimum PingPong Bandwidth: | 1.51926 GB/s | |
| Average PingPong Latency: | 8.87961 usec | Average PingPong Bandwidth: | 1.5907 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: | 200805 | OpenMP Num Threads: | 2 | |
| OpenMP Num Procs: | 12 | OpenMP Max Threads: | 2 | |
| 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: | |||