Re:Emergent Chip Vastly Accelerates Deep Neural Networks
by johnzabroski on Monday January 11, 2016 @02:01PM
(#10882387)
Also, that this is another example of more specialized chip sets eating away at general purpose CPU/GPU market share.
Re:Emergent Chip Vastly Accelerates Deep Neural Networks
by sawwit on Monday January 11, 2016 @02:31PM
(#10882665)
> Static random-access memory (static RAM or SRAM) is a type of semiconductor memory that uses bistable latching circuitry (flip-flop) to store each bit. SRAM exhibits data remanence,[1] but it is still volatile in the conventional sense that data is eventually lost when the memory is not powered.
The term static differentiates SRAM from DRAM (dynamic random-access memory) which must be periodically refreshed. SRAM is faster and more expensive than DRAM; it is typically used for CPU cache while DRAM is used for a computer's main memory.
WP
Re:Emergent Chip Vastly Accelerates Deep Neural Networks
by 6502nerdface on Monday January 11, 2016 @12:52PM
(#10881909)
Also, the on-board RAM is SRAM rather than DRAM.
Re:Emergent Chip Vastly Accelerates Deep Neural Networks
by fpgaminer on Monday January 11, 2016 @05:56PM
(#10884264)
Where does it say that? On-board SRAM would be very strange, as it's incredibly expensive and not at all performant compared to DRAM.
Re:Emergent Chip Vastly Accelerates Deep Neural Networks
by nl on Monday January 11, 2016 @07:50PM
(#10884812)
From the paper's abstract: This allows fitting the model
into on-chip SRAM cache rather than off-chip DRAM memory
The chip is able to fit much more into SRAM because the chip uses network compression, pruning, quantization, Huffman encoding, etc.