Patent · US Active

FP16-S7E8 mixed precision for deep learning and other algorithms

US11093579B2 · kind B2 · utility

2Cited by
21References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 5, 2018
Grant dateAug 17, 2021
Priority date
Expiry dateNov 12, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F2207/382
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Disclosed embodiments relate to mixed-precision vector multiply-accumulate (MPVMAC) In one example, a processor includes fetch circuitry to fetch a compress instruction having fields to specify locations of a source vector having N single-precision formatted elements, and a compressed vector having N neural half-precision (NHP) formatted elements, decode circuitry to decode the fetched compress instruction, execution circuitry to respond to the decoded compress instruction by: converting each element of the source vector into the NHP format and writing each converted element to a corresponding compressed vector element, wherein the processor is further to fetch, decode, and execute a MPVMAC instruction to multiply corresponding NHP-formatted elements using a 16-bit multiplier, and accumulate each of the products with previous contents of a corresponding destination using a 32-bit accumulator.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.