The Ultimate DataFlow for Ultimate SuperComputers-on-a-Chip, for Scientific Computing, Geo Physics, Complex Mathematics, and Information Processing

20 Sep 2020 · Veljko Milutinovic, Erfan Sadeqi Azer, Kristy Yoshimoto, Gerhard Klimeck, Miljan Djordjevic, Milos Kotlar, Miroslav Bojovic, Bozidar Miladinovic, Nenad Korolija, Stevan Stankovic, Nenad Filipović, Zoran Babovic, Miroslav Kosanic, Akira Tsuda, Mateo Valero, Massimo De Santo, Erich Neuhold, Jelena Skoručak, Laura Dipietro, Ivan Ratkovic ·

This article starts from the assumption that near future 100BTransistor SuperComputers-on-a-Chip will include N big multi-core processors, 1000N small many-core processors, a TPU-like fixed-structure systolic array accelerator for the most frequently used Machine Learning algorithms needed in bandwidth-bound applications and a flexible-structure reprogrammable accelerator for less frequently used Machine Learning algorithms needed in latency-critical applications.

PDF Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Datasets

Add Datasets introduced or used in this paper

Edit Social Preview

The Ultimate DataFlow for Ultimate SuperComputers-on-a-Chip, for Scientific Computing, Geo Physics, Complex Mathematics, and Information Processing

Code Edit Add Remove Mark official

Categories

Datasets Edit

Code

Add Remove Mark official

Datasets