CSE Distinguished Lecture Series: Satoshi Matsuoka, "FLOPS to BYTES: Accelerating Beyond Moore’s Law"

*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************

Event Details
  • Date/Time:
    • Tuesday August 30, 2016 - Wednesday August 31, 2016
      11:00 am - 11:59 am
  • Location: Klaus Advanced Computing Building, Room 1116E, 266 Ferst Drive, Atlanta 30332
  • Phone:
  • URL:
  • Email:
  • Fee(s):
    Free
  • Extras:
Contact

Anna Stroup

Assistant to CSE Chair


Summaries

Summary Sentence: CSE Distinguished Lecture from Dr. Satoshi Matsuoka, professor, Tokyo Institute of Technology

Full Summary: No summary paragraph submitted.

Media
  • Satoshi Matsuoka Satoshi Matsuoka
    (image/jpeg)

Abstract:

The so-called “Moore’s Law”, by which the performance of the processors will increase exponentially by factors of four every three years or so, is slated to be ending in 10 to 15 years due to the lithography of VLSIs reaching its limits around that time, and combined with other physical factors. This is largely due to the transistor power needs becoming constant and as a result, means to sustain continuous performance must be sought otherwise than increasing the clock rate or the number of floating point units in the chips, i.e., an increase in the FLOPS.

The promising new parameter in place of the transistor count is the perceived increase in the capacity and bandwidth of storage, driven by device, architecture, as well as packaging innovations: 

DRAM-alternative Non-Volatile Memory (NVM) devices, 3-D memory and logic stacking evolving from VIAs to direct silicone stacking, as well as next-generation terabit optics and networks. The overall effect of this is that the trend to increase the computational intensity as advocated today will no longer result in performance increase, but rather, exploiting the memory and bandwidth capacities will instead be the right methodology. However, such shift in compute-vs-data tradeoffs would not exactly be a return to the old vector days, since other physical factors such as latency will not change when spatial communication is involved in X-Y directions. Such conversion of performance metrics from FLOPS to BYTES could lead to disruptive alterations on how the computing system, both hardware and software, would be evolving towards the future.

 

Bio:

Satoshi Matsuoka is a professor at Tokyo Institute of Technology (TITech) and a leader of the TSUBAME series of supercomputers. Matsuoka built TITech into an HPC leader, adopting GPGPUs and other energy efficient techniques early on and helping put Japan on a course for productive exascale science. He is a fellow of the ACM and European ISC, and has won many awards, including the JSPS Prize from the Japan Society for Promotion of Science in 2006, the ACM Gordon Bell Prize for 2011, and the Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology in 2012.

Additional Information

In Campus Calendar
No
Groups

College of Computing, School of Computational Science and Engineering

Invited Audience
Undergraduate students, Faculty/Staff, Public, Graduate students
Categories
Seminar/Lecture/Colloquium
Keywords
cse, CSE Distinguished Lecture Series, lecture, School of Computational Science and Engineering
Status
  • Created By: Devin Young
  • Workflow Status: Published
  • Created On: Aug 25, 2016 - 12:38pm
  • Last Updated: Apr 13, 2017 - 5:14pm