Within-Die Variation-Aware Scheduling in Superscalar Processors for Improved Throughput
- 28 May 2008
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 57 (7) , 940-951
Abstract
Within-die parameter variations can cause wide delay distribution among similar functional units in superscalar processors. Conventionally, the frequency of operation is reduced to accommodate the slowest unit, which in turn degrades throughput. We present a low-overhead design technique that sets the operating frequency in a superscalar processor based on the faster units and allows more cycles for the slower units. We propose an associated priority scheduling strategy to schedule instructions in the functional units to maximize throughput. Simulation results on a set of benchmarks show that, by assigning a higher scheduling priority to faster units, we can achieve 18 percent improvement in performance on average with negligible design overhead.Keywords
This publication has 19 references indexed in Scilit:
- Power efficient resource scaling in partitioned architectures through dynamic heterogeneity2006
- Speed binning aware design methodology to improve profit under parameter variations2006
- Testing Logic Cores using a BIST P1500 Compliant Approach: A Case of Study2005
- Cascaded carry-select adder (C2SA)2005
- Speed binning with path delay test in 150-nm technologyIEEE Design & Test of Computers, 2003
- Achieving at-speed structural testIEEE Design & Test of Computers, 2003
- Parameter variations and impact on circuits and microarchitecture2003
- Razor: a low-power pipeline based on circuit-level timing speculation2003
- Performance and hardware complexity tradeoffs in designing multithreaded architectures2002
- Embedded software-based self-test for programmable core-based designsIEEE Design & Test of Computers, 2002