Within-Die Variation-Aware Scheduling in Superscalar Processors for Improved Throughput

Authors:
Patrick Ndai;Swarup Bhunia;Amit Agarwal;Kaushik Roy
Affiliations:
Purdue University, West Lafayette;Case Western Reserve University, Cleveland;Intel Corporation, Hillsboro;Purdue University, West Lafayette
Venue:
IEEE Transactions on Computers
Year:
2008

Citing 0
Cited 5

Process variation characterization of chip-level multiprocessors

Proceedings of the 46th Annual Design Automation Conference
Low-overhead Fmax calibration at multiple operating points using delay-sensitivity-based path selection

ACM Transactions on Design Automation of Electronic Systems (TODAES)
VAIL: variation-aware issue logic and performance binning for processor yield and profit improvement

Proceedings of the 16th ACM/IEEE international symposium on Low power electronics and design
Performance-asymmetry-aware scheduling for Chip Multiprocessors with static core coupling

Journal of Systems Architecture: the EUROMICRO Journal
Low-power resource binding by postsilicon customization

ACM Transactions on Design Automation of Electronic Systems (TODAES)

Quantified Score

Hi-index	14.98

Visualization

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% improvement in performance on average with negligible design overhead.