HPCG Use of the Memory Bandwidth

Home Previous page Next page

Maximum Measured Memory
Processor Computer Efficiency Efficiency Bandwidth
Bound [%] [%] Use [%]
Nvidia Tesla-100 Summit 2.69 1.5 56
Intel Xeon Phi "KNL" Cori 4.67 1.5 32
Fujitsu SPARC VIIIfx K 11.71 5.3 45
Fujitsu SX/ACE SX/ACE 23.44 11.4 49

The page presents once more the table suggesting that the recent supercomputers do not use the memory bandwidth optimally, but to about 50 % only. The table refers to the HPCG computations, but it could be speculated that the use of the memory bandwidth by other simulation programs is not much better.