WO2023015560 - SYSTEMS AND METHODS FOR SPARSITY-AWARE VECTOR PROCESSING IN GENERAL PURPOSE CPUS

National phase entry is expected:
Publication Number WO/2023/015560
Publication Date 16.02.2023
International Application No. PCT/CN2021/112508
International Filing Date 13.08.2021
Title **
[English] SYSTEMS AND METHODS FOR SPARSITY-AWARE VECTOR PROCESSING IN GENERAL PURPOSE CPUS
[French] SYSTÈMES ET PROCÉDÉS DE TRAITEMENT VECTORIEL SENSIBLE À LA PARCIMONIE DANS DES CPU À USAGE GÉNÉRAL
Applicants **
HUAWEI TECHNOLOGIES CO.,LTD. Huawei Administration Building, Bantian Longgang District Shenzhen, Guangdong 518129, CN
Inventors
MAHMOUD, Mostafa Suite 400, 303 Terry Fox Drive, Kanata. Ottawa, Ontario 231, CA
AZIMI, Reza 19 Allstate Parkway Markham. Toronto, Ontario 3W07, CA
LI, Dawei Huawei Administration Building, Bantian Longgang District Shenzhen, Guangdong 518129, CN
SUN, Wenbo Huawei Administration Building, Bantian Longgang District Shenzhen, Guangdong 518129, CN
front page image
Application details
Total Number of Claims/PCT *
Number of Independent Claims *
Number of Priorities *
Number of Multi-Dependent Claims *
Number of Drawings *
Pages for Publication *
Number of Pages with Drawings *
Pages of Specification *
*
*
International Searching Authority
*
Applicant's Legal Status
*
*
*
*
*
Entry into National Phase under
*
Translation

Recalculate

* The data is based on automatic recognition. Please verify and amend if necessary.

** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.

Quotation for National Phase entry

Country StagesTotal
China Filing1351
EPO Filing, Examination8767
Japan Filing595
South Korea Filing482
USA Filing, Examination2910
MasterCard Visa

Total: 14105

The term for entry into the National Phase has expired. This quotation is for informational purposes only

Abstract[English] Systems and methods for sparsity-aware vector processing in general purpose CPUs are described. An aspect of the disclosure provides for a method including receiving a stream of vector instructions for processing. The method further includes determining an ineffectual computation corresponding to a first lane of a first vector instruction of the stream of vector instructions and determining an effectual computation corresponding to a second lane of a second vector instruction of the stream of vector instructions, where the second vector instruction is subsequent to the first vector instruction according to a processing order of the stream of vector instructions, and the second lane of the second vector instruction and the first lane of the first vector instruction correspond to a same lane. The method further includes coalescing the second lane with the first lane and processing said stream of vector instructions.[French] L'invention concerne des systèmes et des procédés de traitement vectoriel sensible à la parcimonie dans des CPU à usage général. Un aspect de l'invention concerne un procédé comprenant la réception d'un flux d'instructions vectorielles pour le traitement. Le procédé comprend en outre la détermination d'un calcul sans effet correspondant à une première voie d'une première instruction vectorielle du flux d'instructions vectorielles et la détermination d'un calcul avec effet correspondant à une seconde voie d'une seconde instruction vectorielle du flux d'instructions vectorielles, la seconde instruction vectorielle étant postérieure à la première instruction vectorielle selon un ordre de traitement du flux d'instructions vectorielles, et la seconde voie de la seconde instruction vectorielle et la première voie de la première instruction vectorielle correspondant à une même voie. Le procédé comprend en outre la fusion de la seconde voie avec la première voie et le traitement dudit flux d'instructions vectorielles.
An unhandled error has occurred. Reload 🗙