公开(公告)号：US11176493B2

公开(公告)日：2021-11-16

申请号：US16397481

申请日：2019-04-29

Applicant: Google LLC

Inventor： Lawrence J. Madar, III ,  Temitayo Fadelu ,  Harshit Khaitan ,  Ravi Narayanaswami

IPC: G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for virtualizing external memory as local to a machine learning accelerator. One ambient computing system comprises: an ambient machine learning engine; a low-power CPU; and an SRAM that is shared among at least the ambient machine learning engine and the low-power CPU; wherein the ambient machine learning engine comprises virtual address logic to translate from virtual addresses generated by the ambient machine learning engine to physical addresses within the SRAM.

公开(公告)号：US20230418677A1

公开(公告)日：2023-12-28

申请号：US18036506

申请日：2020-12-21

Applicant: Google LLC

Inventor： Temitayo Fadelu ,  Ravi Narayanaswami ,  JiHong Min ,  Dongdong Li ,  Suyog Gupta ,  Jason Jong Kyu Park

IPC: G06F9/50 ,  G06F9/48

CPC classification number: G06F9/5055 ,  G06F9/4881

Abstract: The present disclosure describes a system and method for preempting a long-running process with a higher priority process in a machine learning system, such as a hardware accelerator. The machine learning hardware accelerator can be a multi-chip system including semiconductor chips that can be application-specific integrated circuits (ASIC) designed to perform machine learning operations. An ASIC is an integrated circuit (IC) that is customized for a particular use.

公开(公告)号：US12197959B2

公开(公告)日：2025-01-14

申请号：US18036506

申请日：2020-12-21

Applicant: Google LLC

Inventor： Temitayo Fadelu ,  Ravi Narayanaswami ,  JiHong Min ,  Dongdong Li ,  Suyog Gupta ,  Jason Jong Kyu Park

IPC: G06F9/48 ,  G06F9/50

Abstract: The present disclosure describes a system and method for preempting a long-running process with a higher priority process in a machine learning system, such as a hardware accelerator. The machine learning hardware accelerator can be a multi-chip system including semiconductor chips that can be application-specific integrated circuits (ASIC) designed to perform machine learning operations. An ASIC is an integrated circuit (IC) that is customized for a particular use.

公开(公告)号：US20200342350A1

公开(公告)日：2020-10-29

申请号：US16397481

申请日：2019-04-29

Applicant: Google LLC

Inventor： Lawrence J. Madar, III ,  Temitayo Fadelu ,  Harshit Khaitan ,  Ravi Narayanaswami

IPC: G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for virtualizing external memory as local to a machine learning accelerator. One ambient computing system comprises: an ambient machine learning engine; a low-power CPU; and an SRAM that is shared among at least the ambient machine learning engine and the low-power CPU; wherein the ambient machine learning engine comprises virtual address logic to translate from virtual addresses generated by the ambient machine learning engine to physical addresses within the SRAM.