MLP-Aware instruction queue resizing: the key to power-efficient performance

Authors:
Pavlos Petoumenos;Georgia Psychou;Stefanos Kaxiras;Juan Manuel Cebrian Gonzalez;Juan Luis Aragon
Affiliations:
Department of Electrical and Computer Engineering, University of Patras, Greece;Department of Electrical and Computer Engineering, University of Patras, Greece;Department of Electrical and Computer Engineering, University of Patras, Greece;Computer Engineering Department, University of Murcia, Spain;Computer Engineering Department, University of Murcia, Spain
Venue:
ARCS'10 Proceedings of the 23rd international conference on Architecture of Computing Systems
Year:
2010

Citing 14
Cited 3

Instruction issue logic for high-performance, interruptable pipelined processors

ISCA '87 Proceedings of the 14th annual international symposium on Computer architecture
Trace cache: a low latency approach to high bandwidth instruction fetching

Proceedings of the 29th annual ACM/IEEE international symposium on Microarchitecture
Reducing power in superscalar processor caches using subbanking, multiple line buffers and bit-line segmentation

ISLPED '99 Proceedings of the 1999 international symposium on Low power electronics and design
Wattch: a framework for architectural-level power analysis and optimizations

Proceedings of the 27th annual international symposium on Computer architecture
Power aware microarchitecture resource scaling

Proceedings of the conference on Design, automation and test in Europe
A circuit level implementation of an adaptive issue queue for power-aware microprocessors

GLSVLSI '01 Proceedings of the 11th Great Lakes symposium on VLSI
Energy-effective issue logic

ISCA '01 Proceedings of the 28th annual international symposium on Computer architecture
Energy: efficient instruction dispatch buffer design for superscalar processors

ISLPED '01 Proceedings of the 2001 international symposium on Low power electronics and design
Microarchitecture Optimizations for Exploiting Memory-Level Parallelism

Proceedings of the 31st annual international symposium on Computer architecture
A First-Order Superscalar Processor Model

Proceedings of the 31st annual international symposium on Computer architecture
Dynamic Resizing of Superscalar Datapath Components for Energy Efficiency

IEEE Transactions on Computers
A Case for MLP-Aware Cache Replacement

Proceedings of the 33rd annual international symposium on Computer Architecture
A Memory-Level Parallelism Aware Fetch Policy for SMT Processors

HPCA '07 Proceedings of the 2007 IEEE 13th International Symposium on High Performance Computer Architecture
Integrated analysis of power and performance for pipelined microprocessors

IEEE Transactions on Computers

Where replacement algorithms fail: a thorough analysis

Proceedings of the 7th ACM international conference on Computing frontiers
Token3D: reducing temperature in 3d die-stacked CMPs through cycle-level power control mechanisms

Euro-Par'11 Proceedings of the 17th international conference on Parallel processing - Volume Part I
MLP-aware dynamic instruction window resizing for adaptively exploiting both ILP and MLP

Proceedings of the 46th Annual IEEE/ACM International Symposium on Microarchitecture

Quantified Score

Hi-index	0.00

Visualization

Abstract

Several techniques aiming to improve power-efficiency (measured as EDP) in out-of-order cores trade energy with performance. Prime exam ples are the techniques to resize the instruction queue (IQ). While most of them produce good results, they fail to take into account that changing the timing of memory accesses can have significant consequences on the memo ry-level parallelism (MLP) of the application and thus incur disproportional performance degradation. We propose a novel mechanism that deals with this realization by collecting fine-grain information about the maximum IQ resiz ing that does not affect the MLP of the program. This information is used to override the resizing enforced by feedback mechanisms when this resizing might reduce MLP. We compare our technique to a previously proposed non-MLP-aware management technique and our results show a significant in crease in EDP savings for most benchmarks of the SPEC2000 suite.