Google Inc.

David Lo

Liqun Cheng

Parthasarathy Ranganathan

Rama Krishna Govindaraju

Nishant P Patil

Haishan Zhu

Sundar Jayakumar Dev

The subject matter described herein provides systems and techniques to address the challenges of growing hardware and workload heterogeneity using a Warehouse-Scale Computer (WSC) design that improves the efficiency and utilization of WSCs. The WSC design may include an abstraction layer and an efficiency layer in the software stack of the WSC. The abstraction layer and the efficiency layer may be designed to improve job scheduling, simplify resource management, and drive hardware-software co-optimization using machine learning techniques and automation in order to customize the WSC for applications at scale. The abstraction layer may embrace platform/hardware and workload diversity through greater coordination between hardware and higher layers of the WSC software stack in the WSC design. The efficiency layer may employ machine learning techniques at scale to realize hardware/software co-optimizations as a part of the autonomous WSC design.

Autonomous warehouse-scale computers

Methods, systems, and computer storage media storing instructions for managing processing system efficiency. One of the methods includes obtaining data splitting a plurality of general-purpose processing units in a processing system into a high-priority domain and a low-priority domain, wherein the general-purpose processing units in the high-priority domain are assigned to perform one or more tasks comprising one or more high-priority tasks, and the general-purpose processing units in the low-priority domain are assigned to perform one or more low-priority tasks; and during runtime of the processing system, obtaining memory usage measurements that characterize usage of system memory by the high-priority domain and the low-priority domain; and adjusting, based on the memory usage measurements, a configuration of (i) the high-priority domain, (ii) the low-priority domain, or (iii) both to adjust utilization of the system memory by the general-purpose processing units.

Managing processing system efficiency

Methods, systems, and apparatus for dynamic service level objective power control in a datacenter. In one aspect, a method includes determining a current service level value that measures a current performance of the service by a set of processing devices performing the service, the service having an associated service level objective value; and for each processing device: when the current service level value does not meet the service level objective value of the service, generating a first control signal that causes a processing device performing the service to operate at a first power consumption level; and when the current service level value does meet the service level objective value of the service, generating a control signal that cause the processing device to operate at a reduced power consumption level that is less than the first power consumption level.

Growing community of inventors

Palo Alto, CA, United States of America

David Lo