发明名称 Apparatus and method for heterogeneous chip multiprocessors via resource allocation and restriction
摘要 A method and apparatus for heterogeneous chip multiprocessors (CMP) via resource restriction. In one embodiment, the method includes the accessing of a resource utilization register to identify a resource utilization policy. Once accessed, a processor controller ensures that the processor core utilizes a shared resource in a manner specified by the resource utilization policy. In one embodiment, each processor core within a CMP includes an instruction issue throttle resource utilization register, an instruction fetch throttle resource utilization register and other like ways of restricting its utilization of shared resources within a minimum and maximum utilization level. In one embodiment, resource restriction provides a flexible manner for allocating current and power resources to processor cores of a CMP that can be controlled by hardware or software. Other embodiments are described and claimed.
申请公布号 US8924690(B2) 申请公布日期 2014.12.30
申请号 US201213482713 申请日期 2012.05.29
申请人 Intel Corporation 发明人 Fossum Tryggve;Chrysos George;Dutton Todd A.
分类号 G06F9/30;G06F9/38;G06F9/50;G06F1/32 主分类号 G06F9/30
代理机构 Blakely, Sokoloff, Taylor & Zafman LLP 代理人 Blakely, Sokoloff, Taylor & Zafman LLP
主权项 1. A semiconductor die, comprising: a first processing core and a second processing core both coupled to a processor controller; said first processing core having a first register, a bit position of said first register to indicate whether said first processing core is permitted to issue an instruction in a given cycle, said first register's contents being writable to define a first percentage of cycles in which said first processing core is permitted to process a next instruction over the course of said first processing core's operation until such time that said first register's contents are changed; said second processing core having a second register, a bit position of said second register to indicate whether said second processing core is permitted to issue an instruction in a given cycle, said second register's contents being writable to define a second percentage of cycles in which said second processing core is permitted to process a next instruction over the course of said second processing core's operation until such time that said second register's contents are changed; and wherein said processor controller is to prioritize an issuance of an instruction by said first processing core over an issuance of an instruction by said second processing core when said first percentage is greater than said second percentage.
地址 Santa Clara CA US