公开(公告)号：US12039421B2

公开(公告)日：2024-07-16

申请号：US17122384

申请日：2020-12-15

Applicant: Intel Corporation

Inventor： Yingyu Miao ,  Ning Xue

IPC: G06F17/16 ,  G06N20/00 ,  H03M7/30 ,  G06F11/14

CPC classification number: G06N20/00 ,  G06F17/16 ,  H03M7/3088 ,  H03M7/702 ,  G06F11/14

Abstract: An apparatus to facilitate deep learning numeric data and sparse matrix compression is disclosed. The apparatus includes a processor comprising a compression engine to: receive a data packet comprising a plurality of cycles of data samples, and for each cycle of the data samples: pass the data samples of the cycle to a compressor dictionary; identify, from the compressor dictionary, tags for each of the data samples, wherein the compressor dictionary comprises at least a first tag for data having a value of zero and a second tag for data having a value of one; and compress the data samples into compressed cycle data by storing the tags as compressed data, wherein the data samples identified with the first tag are compressed using the first tag and the data samples identified with the second tag are compressed using the second tag at the same time as values of the data samples identified with the first tag or the second tag are excluded from the compressed cycle data.

公开(公告)号：US20210174259A1

公开(公告)日：2021-06-10

申请号：US17122384

申请日：2020-12-15

Applicant: Intel Corporation

Inventor： Yingyu Miao ,  Ning Xue

IPC: G06N20/00 ,  H03M7/30 ,  G06F17/16

Abstract: An apparatus to facilitate deep learning numeric data and sparse matrix compression is disclosed. The apparatus includes a processor comprising a compression engine to: receive a data packet comprising a plurality of cycles of data samples, and for each cycle of the data samples: pass the data samples of the cycle to a compressor dictionary; identify, from the compressor dictionary, tags for each of the data samples, wherein the compressor dictionary comprises at least a first tag for data having a value of zero and a second tag for data having a value of one; and compress the data samples into compressed cycle data by storing the tags as compressed data, wherein the data samples identified with the first tag are compressed using the first tag and the data samples identified with the second tag are compressed using the second tag at the same time as values of the data samples identified with the first tag or the second tag are excluded from the compressed cycle data.