Harnessing ISA diversity
Authors:
Open Access
- 14 June 2014
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM SIGARCH Computer Architecture News
- Vol. 42 (3) , 121-132
Abstract
Heterogeneous multicore architectures have the potential for high performance and energy efficiency. These architectures may be composed of small power-efficient cores, large high-performance cores, and/or specialized cores that accelerate the performance of a particular class of computation. Architects have explored multiple dimensions of heterogeneity, both in terms of micro-architecture and specialization. While early work constrained the cores to share a single ISA, this work shows that allowing heterogeneous ISAs further extends the effectiveness of such architectures This work exploits the diversity offered by three modern ISAs: Thumb, x86-64, and Alpha. This architecture has the potential to outperform the best single-ISA heterogeneous architecture by as much as 21%, with 23% energy savings and a reduction of 32% in Energy Delay Product.Keywords
Funding Information
- Division of Computing and Communication Foundations (CCF-1219059, CCF-1302682)
This publication has 18 references indexed in Scilit:
- Power struggles: Revisiting the RISC vs. CISC debate on contemporary ARM and x86 architectures2013
- Execution migration in a heterogeneous-ISA chip multiprocessor2012
- QuickIA: Exploring heterogeneous architectures on real prototypes2012
- Energy- and area-efficient architectures through application clustering and architectural heterogeneityACM Transactions on Architecture and Code Optimization, 2009
- A Tale of Two Processors: Revisiting the RISC-CISC DebateLecture Notes in Computer Science, 2009
- Core architecture optimization for heterogeneous chip multiprocessors2006
- Using SimPoint for accurate and efficient simulationACM SIGMETRICS Performance Evaluation Review, 2003
- Automatically characterizing large scale program behavior2002
- The Alpha 21264 microprocessorIEEE Micro, 1999
- A unified model of pointwise equivalence of procedural computationsACM Transactions on Programming Languages and Systems, 1994