Fabric vectors for deep learning acceleration
AssigneeCerebras Systems Inc.
InventorsSean Lie, Michael Morrison, Michael Edwin James, Srikanth Arekapudi, Gary R. Lauterbach
Life of this patent
Estimating the term…
Loading patent…
AssigneeCerebras Systems Inc.
InventorsSean Lie, Michael Morrison, Michael Edwin James, Srikanth Arekapudi, Gary R. Lauterbach
Estimating the term…
Techniques in advanced deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements performs flow-based computations on wavelets of data. Each processing element has a respective compute element and a respective routing element. Instructions executed by the compute element include operand specifiers, some specifying a data structure register storing a data structure descriptor describing an operand as a fabric vector or a memory vector. The data structure descriptor further describes various attributes of the fabric vector: length, microthreading eligibility, number of data elements to receive, transmit, and/or process in parallel, virtual channel and task identification information, whether to terminate upon receiving a control wavelet, and whether to mark an outgoing wavelet a control wavelet.
A method comprising:
A method comprising:
A system comprising:
A system comprising:
Dependencies are inferred from the claim text.