A New Recovery Mechanism in Superscalar Microprocessors by Recovering Critical Misprediction

Jiongyao YE; Yu WAN; Takahiro WATANABE

doi:10.1587/transfun.E94.A.2639

A New Recovery Mechanism in Superscalar Microprocessors by Recovering Critical Misprediction

Jiongyao YE, Yu WAN, Takahiro WATANABE

Full Text Views

0

Share
Cite this

Summary :

Current trends in modern out-of-order processors involve implementing deeper pipelines and a large instruction window to achieve high performance, which lead to the penalty of the branch misprediction recovery being a critical factor in overall processor performance. Multi path execution is proposed to reduce this penalty by executing both paths following a branch, simultaneously. However, there are some drawbacks in this mechanism, such as design complexity caused by processing both paths after a branch and performance degradation due to hardware resource competition between two paths. In this paper, we propose a new recovery mechanism, called Recovery Critical Misprediction (RCM), to reduce the penalty of branch misprediction recovery. The mechanism uses a small trace cache to save the decoded instructions from the alternative path following a branch. Then, during the subsequent predictions, the trace cache is accessed. If there is a hit, the processor forks the second path of this branch at the renamed stage so that the design complexity in the fetch stage and decode stage is alleviated. The most contribution of this paper is that our proposed mechanism employs critical path prediction to identify the branches that will be most harmful if mispredicted. Only the critical branch can save its alternative path into the trace cache, which not only increases the usefulness of a limited size of trace cache but also avoids the performance degradation caused by the forked non-critical branch. Experimental results employing SPECint 2000 benchmark show that a processor with our proposed RCM improves IPC value by 10.05% compared with a conventional processor.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E94-A No.12 pp.2639-2648

Publication Date: 2011/12/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E94.A.2639

Type of Manuscript: Special Section PAPER (Special Section on VLSI Design and CAD Algorithms)

Category: High-Level Synthesis and System-Level Design

Cite this

Copy

Jiongyao YE, Yu WAN, Takahiro WATANABE, "A New Recovery Mechanism in Superscalar Microprocessors by Recovering Critical Misprediction" in IEICE TRANSACTIONS on Fundamentals, vol. E94-A, no. 12, pp. 2639-2648, December 2011, doi: 10.1587/transfun.E94.A.2639.
Abstract: Current trends in modern out-of-order processors involve implementing deeper pipelines and a large instruction window to achieve high performance, which lead to the penalty of the branch misprediction recovery being a critical factor in overall processor performance. Multi path execution is proposed to reduce this penalty by executing both paths following a branch, simultaneously. However, there are some drawbacks in this mechanism, such as design complexity caused by processing both paths after a branch and performance degradation due to hardware resource competition between two paths. In this paper, we propose a new recovery mechanism, called Recovery Critical Misprediction (RCM), to reduce the penalty of branch misprediction recovery. The mechanism uses a small trace cache to save the decoded instructions from the alternative path following a branch. Then, during the subsequent predictions, the trace cache is accessed. If there is a hit, the processor forks the second path of this branch at the renamed stage so that the design complexity in the fetch stage and decode stage is alleviated. The most contribution of this paper is that our proposed mechanism employs critical path prediction to identify the branches that will be most harmful if mispredicted. Only the critical branch can save its alternative path into the trace cache, which not only increases the usefulness of a limited size of trace cache but also avoids the performance degradation caused by the forked non-critical branch. Experimental results employing SPECint 2000 benchmark show that a processor with our proposed RCM improves IPC value by 10.05% compared with a conventional processor.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E94.A.2639/_p

Copy

@ARTICLE{e94-a_12_2639,
author={Jiongyao YE, Yu WAN, Takahiro WATANABE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A New Recovery Mechanism in Superscalar Microprocessors by Recovering Critical Misprediction},
year={2011},
volume={E94-A},
number={12},
pages={2639-2648},
abstract={Current trends in modern out-of-order processors involve implementing deeper pipelines and a large instruction window to achieve high performance, which lead to the penalty of the branch misprediction recovery being a critical factor in overall processor performance. Multi path execution is proposed to reduce this penalty by executing both paths following a branch, simultaneously. However, there are some drawbacks in this mechanism, such as design complexity caused by processing both paths after a branch and performance degradation due to hardware resource competition between two paths. In this paper, we propose a new recovery mechanism, called Recovery Critical Misprediction (RCM), to reduce the penalty of branch misprediction recovery. The mechanism uses a small trace cache to save the decoded instructions from the alternative path following a branch. Then, during the subsequent predictions, the trace cache is accessed. If there is a hit, the processor forks the second path of this branch at the renamed stage so that the design complexity in the fetch stage and decode stage is alleviated. The most contribution of this paper is that our proposed mechanism employs critical path prediction to identify the branches that will be most harmful if mispredicted. Only the critical branch can save its alternative path into the trace cache, which not only increases the usefulness of a limited size of trace cache but also avoids the performance degradation caused by the forked non-critical branch. Experimental results employing SPECint 2000 benchmark show that a processor with our proposed RCM improves IPC value by 10.05% compared with a conventional processor.},
keywords={},
doi={10.1587/transfun.E94.A.2639},
ISSN={1745-1337},
month={December},}

Copy

TY - JOUR
TI - A New Recovery Mechanism in Superscalar Microprocessors by Recovering Critical Misprediction
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2639
EP - 2648
AU - Jiongyao YE
AU - Yu WAN
AU - Takahiro WATANABE
PY - 2011
DO - 10.1587/transfun.E94.A.2639
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E94-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2011
AB - Current trends in modern out-of-order processors involve implementing deeper pipelines and a large instruction window to achieve high performance, which lead to the penalty of the branch misprediction recovery being a critical factor in overall processor performance. Multi path execution is proposed to reduce this penalty by executing both paths following a branch, simultaneously. However, there are some drawbacks in this mechanism, such as design complexity caused by processing both paths after a branch and performance degradation due to hardware resource competition between two paths. In this paper, we propose a new recovery mechanism, called Recovery Critical Misprediction (RCM), to reduce the penalty of branch misprediction recovery. The mechanism uses a small trace cache to save the decoded instructions from the alternative path following a branch. Then, during the subsequent predictions, the trace cache is accessed. If there is a hit, the processor forks the second path of this branch at the renamed stage so that the design complexity in the fetch stage and decode stage is alleviated. The most contribution of this paper is that our proposed mechanism employs critical path prediction to identify the branches that will be most harmful if mispredicted. Only the critical branch can save its alternative path into the trace cache, which not only increases the usefulness of a limited size of trace cache but also avoids the performance degradation caused by the forked non-critical branch. Experimental results employing SPECint 2000 benchmark show that a processor with our proposed RCM improves IPC value by 10.05% compared with a conventional processor.
ER -