Benchmarking and systems performance - hosted by Elisabeth Stahl

Elisabeth Stahl

Blog Authors:  ELISABETH STAHL   is Chief Technical Strategist and Executive IT Specialist, IBM Systems and Technology Group, and has been working in systems performance for over 25 years.

  • Add a Comment
  • Edit
  • More Actions v
  • Quarantine this Entry

Comments (3)

1 smw commented Permalink

If I understand the architecture, then the LINPACK result of 874.1 GF on 32 cores, 3.55 GHz is 96.2% of peak. That sounds outrageous, in the sense of being too good to be true. Am I calculating this wrong? Were the cores overclocked? Do you have the output from the run? <div>&nbsp;</div> What % of peak can Power7 produce on serial square DGEMMs? <div>&nbsp;</div> Thanks!

2 clarisse commented Permalink

The LINPACK HPC run was indeed run with Intelligent Energy Optimization enabled achieving an Rmax of 874.1 Gflops with a correspinding o Rpeak of 988.2 Gflops. <div>&nbsp;</div> Clarisse Taaffe-Hedglin

3 YONGLEIG commented Permalink

Any reason of no or delayed TPC-C benchmark?

Add a Comment Add a Comment