Re:David Patterson Says It’s Time for New Computer Architect...
by crb002 on Monday September 17, 2018 @05:37PM
(#18010328)
Massive parallel prefix and reduction operations in RAM. Start with just the MPI standard reduction ops. 1000x faster than Von Neuman bottleneck.
[ Parent
| on HN ]
Re:David Patterson Says It’s Time for New Computer Architect...
by crb002 on Monday September 17, 2018 @05:42PM
(#18010371)
Then an ASIC for sparse matrix multiply. Valiant's reduction of CFG parsing. Massive speedup to parsing workflows, and boon to security by getting rid of hand rolled parsers.