- 专利标题: INSTRUCTIONS AND LOGIC TO PERFORM FLOATING-POINT AND INTEGER OPERATIONS FOR MACHINE LEARNING
-
申请号: EP21195277.5申请日: 2018-03-26
-
公开(公告)号: EP3937004A1公开(公告)日: 2022-01-12
- 发明人: Kaul, Himanshu , Anders, Mark A. , Mathew, Sanu K. , Yao, Anbang , Ray, Joydeep , Tang, Ping T. , Strickland, Michael S. , Chen, Xiaoming , Appu, Abhishek R. , Koker, Altug , Sinha, Kamal , Vembu, Balaji , Galoppo von Borries, Nicolas C. , Nurvitadhi, Eriko , Barik, Rajkishore , Lin, Tsung-Han , Ranganathan, Vasanth , Jahagirdar, Sanjeev , Shpeisman, Tatiana
- 申请人: INTEL Corporation
- 申请人地址: US Santa Clara, CA 95054 2200 Mission College Blvd.
- 代理机构: Samson & Partner Patentanwälte mbB
- 优先权: US201715787129 20171018
- 主分类号: G06F7/483
- IPC分类号: G06F7/483 ; G06F7/544 ; G06F9/30 ; G06N3/04 ; G06N3/063 ; G06N3/08
摘要:
The present disclosure provides a graphics processing unit, GPU, comprising: a plurality of memory controllers, a cache memory coupled with the plurality of memory controllers, a a graphics multiprocessor coupled with the cache memory and the plurality of memory controllers. The graphics multiprocessor having a single instruction, multiple thread, SIMT, architecture. The graphics multiprocessor includes a register file and a plurality of compute units coupled with the register file. The plurality of compute units including a first compute unit to perform a mixed precision matrix operation and a second compute unit to perform, in response to a single instruction, multiple compute operations, wherein the multiple compute operations include a fused multiply-add operation and a rectified linear unit operation applied to an output of the fused multiply-add operation.
公开/授权文献
信息查询