A scalable custom simulation machine for the Bayesian Confidence Propagation Neural Network model of the brain

Farahini, NasimKTH,Elektroniksystem,Kungl. Tekniska högskolan, KTH, Sweden (author)

QC 20140522
A multi-chip custom digital super-computer called eBrain for simulating Bayesian Confidence Propagation Neural Network (BCPNN) model of the human brain has been proposed. It uses Hybrid Memory Cube (HMC), the 3D stacked DRAM memories for storing synaptic weights that are integrated with a custom designed logic chip that implements the BCPNN model. In 22nm node, eBrain executes BCPNN in real time with 740 TFlops/s while accessing 30 TBs synaptic weights with a bandwidth of 112 TBs/s while consuming less than 6 kWs power for the typical case. This efficiency is three orders better than general purpose supercomputers in the same technology node.

TEKNIK OCH TEKNOLOGIER Elektroteknik och elektronik hsv//swe
ENGINEERING AND TECHNOLOGY Electrical Engineering, Electronic Engineering, Information Engineering hsv//eng
3d-stacked drams
Human brain
Hybrid memory
Logic chips
Neural network model
Simulation machine
Synaptic weight
Technology nodes

Hemani, AhmedKTH,Elektroniksystem,Kungl. Tekniska högskolan, KTH, Sweden(Swepub:kth)u131a9ju (author)
Lansner, AndersKTH,Beräkningsbiologi, CB,Kungl. Tekniska högskolan, KTH, Sweden(Swepub:kth)u12s8cr8 (author)
Clermidy, F.Kungl. Tekniska högskolan, KTH, Sweden (author)
Svensson, ChristerLinköpings universitet,Elektroniska komponenter,Tekniska högskolan(Swepub:liu)chrsv76 (author)
KTHElektroniksystem (creator_code:org_t)

In:2014 19th Asia and South Pacific Design Automation Conference (ASP-DAC): IEEE, s. 578-5859781479928163

By the author/editor: Farahini, Nasim; Hemani, Ahmed; Lansner, Anders; Clermidy, F.; Svensson, Christ ...

About the subject

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.