HPC Challenge Benchmark Record

System Information
Affiliation:   RIKEN Advanced Institute for Computational Scinece   URL:   http://www.aics.riken.jp/index_e.html
Location:   Japan, Kobe, Hyogo   System Use:   Research
System Manufacturer:   Fujitsu   System Name:   K computer
Interconnect Manufacturer:   Fujitsu   Interconnect Type:   Tofu Interconnect
Operating System:   Linux   MPI:   Parallelnavi Technical Computing Language V1.0L20
MPI Wtick:   0.0000001   BLAS:   Parallelnavi Technical Computing Language V1.0L20
Language:   C   Compiler:   Parallelnavi Technical Computing Language V1.0L20
Compiler Flags:   -Kfast,parallel,openmp,ocl,preex (and "-mlcmain=main -SSL2BLAMP" for LINKFLAGS, "-Xg" for C files, "-Fwide" for Fortran files)   Processor Type:   Fujitsu SPARC64 VIIIfx
Processor Speed:   2 GHz   Total Processors:   82944
Processors Entered:   82944   Processors determined:   663552
Cores per chip:   8   HPL Processes:   82944
MPI Processes:   82944   Threads Entered:   8
Threads determined:   8   FLOPs per cycle:  
Theoretical peak:   10616.832 TFlop/s   Total memory:   1327104 GiB
FFT library:   FFTE-6.1 alpha  
Explain Optimizations:
G-HPL: adopted pipelined broadcast communication and promoted fine-grain overlapped data transfer G-RandomAccess: replaced MPI function calls with RDMA function calls, introduced 3-way data sorting and transfer to improve load imbalance, overlapped data transfer with data sorting, transformed data-sorting loop to use conditional move CPU instructions and applied loop distribution to table-updating loop S&EP-RandomAccess: applied loop distribution to table-updating loop and increased iterations of inner loops G-FFT: used the latest version of FFTE library EP-STREAM: inserted compiler directives to use a CPU feature of fast cache line allocation

HPL
HPL:   9515.09 Tflop/s   HPL time:   69122.7
HPL eps:   1.11022e-16   HPL Rnorm1:   0.000000902259
HPL Anorm1:   2491160   HPL AnormI:   2491020
HPL Xnorm1:   2565590   HPL XnormI:   1.85442
HPL N:   9955008   HPL NB:   448
HPL NProw:   144   HPL NPcol:   576
HPL depth:   1   HPL NBdiv:   2
HPL NBmin:   8   HPL CPfact:   L
HPL CRfact:   L   HPL CPtop:   0
HPL order:   C
HPL dMach EPS:   1.110223e-16   HPL sMach EPS:   0.00000005960464
HPL dMach sfMin:   2.225074e-308   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:   2.225074e-308   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:   15911 GB/s   PTRANS time:   12.4571 seconds
PTRANS residual:   0   PTRANS N:   4977504
PTRANS NB:   193   PTRANS NProw:   144
PTRANS NPcol:   576

STREAM
S-STREAM Copy:   45.1736 GB/s   S-STREAM Scale:   45.1617 GB/s
S-STREAM Add:   43.7171 GB/s   S-STREAM Triad:   46.5061 GB/s
EP-STREAM Copy:   44.6386 GB/s   EP-STREAM Scale:   44.553 GB/s
EP-STREAM Add:   43.7105 GB/s   EP-STREAM Triad:   46.5047 GB/s
STREAM Vector Size:   398269452   STREAM Threads:   8

RandomAccess
S-RandomAccess:   0.113488 Gup/s   EP-RandomAccess:   0.113494 Gup/s
G-RandomAccess:   460.495 Gup/s   G-RandomAccess N:   70368744177664
G-RandomAccess time:   611.244 seconds   G-RandomAccess Check Time:   917.054 seconds
G-RandomAccess Errors:   2097152   G-RandomAccess Errors Fraction:   0.0000000298023
G-RandomAccess TimeBound:   -1   G-RandomAccess ExeUpdates:   281474976710656
RandomAccess N:   1073741824

FFT
S-FFT:   6.30607 GFlop/s   EP-FFT:   6.35504 GFlop/s
MPIFFT:   252100 GFlop/s   MPIFFT N:   12383472844800
MPIFFT Max Error:   0.00000000000000346651   MPIFFT time0:   0.00000360096 seconds
MPIFFT time1:   3.06023 seconds   MPIFFT time2:   0.712761 seconds
MPIFFT time3:   3.15126 seconds   MPIFFT time4:   0.618561 seconds
MPIFFT time5:   2.9872 seconds   MPIFFT time6:   0.00000510179 seconds
FFTEnblk:   32   FFTEnp:   8
FFTEl2size:   6291456

DGEMM
S-DGEMM:   120.307 GFlop/s   EP-DGEMM:   120.302 GFlop/s
DGEMM N:   19956

RandomRing Latency/Bandwidth
RandomRing Latency:   6.37917 usec   RandomRing Bandwidth:   0.186382 GB/s

NaturalRing Latency/Bandwidth
NaturalRing Latency:   5.11208 usec   NaturalRing Bandwidth:   3.1187 GB/s

PingPong Latency/Bandwidth
Maximum PingPong Latency:   7.18512 usec   Maximum PingPong Bandwidth:   4.57103 GB/s
Minimum PingPong Latency:   2.75768 usec   Minimum PingPong Bandwidth:   4.36834 GB/s
Average PingPong Latency:   4.67483 usec   Average PingPong Bandwidth:   4.47042 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:   201107   OpenMP Num Threads:   8
OpenMP Num Procs:   8   OpenMP Max Threads:   8

Memory
MemProc:   -1   MemSpec:   -1
MemVal:   -1

CPS
CPS_HPCC_FFT_235:   1   CPS_HPCC_FFTW_ESTIMATE:   0
CPS_HPCC_MEMALLCTR:   0   CPS_HPL_USE_GETPROCESSTIMES:   0
CPS_RA_SANDIA_NOPT:   1   CPS_RA_SANDIA_OPT2:   0


Version: 1.4.2.f - Run Type: opt - Parent ID: 456
Created: 2016-11-13 - Exported: Sat May 27 02:02:44 2017
HPC Challenge Benchmark Record