US Patent:
20190325296, Oct 24, 2019
Inventors:
- Redmond WA, US
Kalin Ovtcharov - Issaquah WA, US
Eric S. Chung - Woodinville WA, US
Todd Michael Massengill - Woodinville WA, US
Ming Gang Liu - Kirkland WA, US
Gabriel Leonard Weisz - Bethesda MD, US
International Classification:
G06N 3/063
G06F 15/80
Abstract:
Neural network processors that have been customized based on application specific synthesis specialization parameters and related methods are described. Certain example neural network processors and methods described in the present disclosure expose several major synthesis specialization parameters that can be used for specializing a microarchitecture instance of a neural network processor to specific neural network models including: (1) aligning the native vector dimension to the parameters of the model to minimize padding and waste during model evaluation, (2) increasing lane widths to drive up intra-row-level parallelism, or (3) increasing matrix multiply tiles to exploit sub-matrix parallelism for large neural network models.