Inventor

CHENG LIQUN

US29 patents

⚠️ This page may combine multiple inventors who share the name “CHENG LIQUN”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

CHENG LIQUN

GOOGLE LLC

Machine level resource distribution

Data caching

Asymmetric data communication for host-device interface

Asymmetric data communication for host-device interface

Managing processing system efficiency

Managing processing system efficiency

Generating recommendations based on performance metrics for scheduling jobs on distributed computing devices

Recommendations for scheduling jobs on distributed computing devices

Autonomous warehouse-scale computers

Autonomous warehouse-scale computers

Hardware-optimized neural architecture search

Controlled cache injection of incoming data

Controlled cache injection of incoming data

Data caching

OneShot neural architecture and hardware architecture search

Hybrid and hierarchical multi-trial and OneShot neural architecture search on datacenter machine learning accelerators

Heterogeneous ML accelerator cluster with flexible system resource balance

Asynchronous copying of data within memory

Asynchronous copying of data within memory

GOOGLE INC

Dynamic service level objective power control in distributed process

Data caching

Virtualization-aware prefetching

INTEL CORP

Exclusive ownership snoop filter

Preselecting E/M line replacement technique for a snoop filter

CHENG LIQUN

Searching a shared cache by using search hints and masked ways

FANG ZHEN

Using criticality information to route cache coherency communications

UNIV UTAH TECHNOLOGY COMMERCIA

Microarchitectural wire management for performance and power in partitioned architectures

VARMA ANKUSH

Multi-processor computing system having fast processor response to cache agent request capacity limit warning

SILICON GRAPHICS INC

Apparatus and method of controlling data sharing on a shared memory computer system