Paired ROBs: A Cost-Effective Reorder Buffer Sharing Strategy for SMT Processors
نویسندگان
چکیده
An important design issue of SMT processors is to find proper sharing strategies of resources among threads. This paper proposes a ROB sharing strategy, called paired ROB, that considers the fact that task parallelism is not always available to fully utilize resources of multithreaded processors. To this aim, an evaluation methodology is proposed and used for the experiments, which analyzes performance under different degrees of parallelism. Results show that paired ROBs are a cost-effective strategy that provides better performance than private ROBs for low task parallelism, whereas it incurs slight performance losses for high task parallelism.
منابع مشابه
A Reorder Buffer Design for High Performance Processors
Modern reorder buffers (ROBs) were conceived to improve processor performance by allowing instruction execution out of the original program order and run ahead of sequential instruction code exploiting existing instruction level parallelism (ILP). The ROB is a functional structure of a processor execution engine that supports speculative execution, physical register recycling, and precise excep...
متن کاملThe Impact of Resource Sharing Control on the Design of Multicore Processors
One major obstacle faced by designers when entering the multicore era is how to harness the massive computing power which these cores provide. Since Instructional-Level Parallelism (ILP) is inherently limited, one single thread is not capable of efficiently utilizing the resource of a single core. Hence, Simultaneous MultiThreading (SMT) microarchitecture can be introduced in an effort to achie...
متن کاملUsing Rewriting Rules and Positive Equality to Formally Verify Wide-Issue Out-Of-Order Microprocessors with a Reorder Buffer1
Rewriting rules and Positive Equality [4] are combined in an automatic way in order to formally verify out-of-order processors that have a Reorder Buffer, and can issue/retire multiple instructions per clock cycle. Only register-register instructions are implemented, and can be executed out-of-order, as soon as their data operands can be either read from the Register File, or forwarded as resul...
متن کاملAn Intelligent Resource Sharing Protocol on Write Buffers in Simultaneous Multi-Threading Processors
Simultaneous Multi-Threading (SMT) has been widely studied to lend modern-day CPUs a mechanism to improve resource utilization so as to lead to a higher instruction throughput by allowing concurrent execution of multiple independent threads with sharing of key datapath components. The key to a high-performance SMT is to optimize the distribution of shared resources among temporally competing th...
متن کاملStatic Partitioning vs Dynamic Sharing of Resources in Simultaneous MultiThreading Microarchitectures
Simultaneous MultiThreading (SMT) achieves better system resource utilization and higher performance because it exploits Thread-Level Parallelism (TLP) in addition to Instruction-Level Parallelism (ILP). Theoretically, system resources in every pipeline stage of an SMT microarchitecture can be dynamically shared. However, in commercial application, all the major queues are statically partitione...
متن کامل