Achieving reliable system performance by fast recovery of branch miss prediction

Authors:
Min Choi;Jong Hyuk Park;Seungho Lim;Young-Sik Jeong
Affiliations:
School of Information and Communication Engineering, Chungbuk National University, Cheongju 361-763, South Korea;Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul 139-742, South Korea;Department of Digital Information Engineering, Hankuk University of Foreign Studies, Yongin 449-791, South Korea;Department of Computer Engineering, Wonkwang University, Iksan 305-701, South Korea
Venue:
Journal of Network and Computer Applications
Year:
2012

Citing 14
Cited 1

Using speculative retirement and larger instruction windows to narrow the performance gap between memory consistency models

Proceedings of the ninth annual ACM symposium on Parallel algorithms and architectures
Implementation of precise interrupts in pipelined processors

ISCA '85 Proceedings of the 12th annual international symposium on Computer architecture
The MIPS R10000 Superscalar Microprocessor

IEEE Micro
The Alpha 21264 Microprocessor

IEEE Micro
The Design Space of Register Renaming Techniques

IEEE Micro
Cherry: checkpointed early resource recycling in out-of-order microprocessors

Proceedings of the 35th annual ACM/IEEE international symposium on Microarchitecture
Checkpointing alternatives for high performance, power-aware processors

Proceedings of the 2003 international symposium on Low power electronics and design
Checkpoint Processing and Recovery: Towards Scalable Large Instruction Window Processors

Proceedings of the 36th annual IEEE/ACM International Symposium on Microarchitecture
Checkpointed Early Load Retirement

HPCA '05 Proceedings of the 11th International Symposium on High-Performance Computer Architecture
An analysis of a resource efficient checkpoint architecture

ACM Transactions on Architecture and Code Optimization (TACO)
Reducing Branch Misprediction Penalty via Selective Branch Recovery

HPCA '04 Proceedings of the 10th International Symposium on High Performance Computer Architecture
Kilo-Instruction Processors: Overcoming the Memory Wall

IEEE Micro
Fast branch misprediction recovery in out-of-order superscalar processors

Proceedings of the 19th annual international conference on Supercomputing
Measuring Benchmark Similarity Using Inherent Program Characteristics

IEEE Transactions on Computers

Editorial: Special issue on trusted computing and communications

Journal of Network and Computer Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Today's technology evolution provides users inexpensive and powerful computer systems. However, there are argues that system reliability and fault tolerance is necessary in the systems as well. A proper design for the reliable and fault-tolerant computer system requires a trade-off among cost, reliability, and availability. In this paper, we propose a low-cost recovery scheme for reliable system performance. With this approach, it completely eliminates the roll-back overhead on branch misprediction. Thus, the instruction fetcher does not stop and it fetches instructions from the correct path immediately after the misprediction detected. So, this approach prevents a processor from flushing the pipeline, even under branch misprediction by allowing the instruction fetcher to work continuously. Our approach reduces the branch misprediction penalty for achieving reliable system performance. It instantly reconstructs the map table to any mispredicted branch and it outperforms the conventional RMT by an average of 10.93%.