Hongjin Liu

Hongjin Liu


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 December 2022 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
JNjiawei Nian
jiawei Nian
ZLZongnan Liang
Zongnan Liang
HLHongjin Liu
Hongjin Liu
MYMengfei Yang
Mengfei Yang
Branch prediction structures are increasingly used in space processors due to their crucial role in improving processor performance. Due to radiation effects such as Single Event Upset (SEU) causing system failures, it is necessary to provide protection techniques for branch prediction modules against complex spatial environments. In this paper, we proposed a simple, efficient, low-power, and fault-tolerant design scheme for L0 BTB consisting of a master-slave and a check-decision module. The strategy sets up the L0 BTB structure as a master-slave structure and adds an error check to detect single-bit errors. Experimental results show that we achieve 100% fault tolerance without a loss hit rate. The increase in resource usage is 1.1x, and the path delay increases by 8.1%, superior to other methods. The L0 BTB is a fully-associative structure and multiple entries are accessed simultaneously, which introduces significant power consumption. We added a low-power design for the master-slave module to reduce the query power consumption by 65.9%. In addition, we also applied the scheme to the RAS module. The experimental results demonstrate that our approach is an efficient, generic, fault-tolerant design scheme that can be deployed to different register files.

23 March 2024 in Electronics
Verified
Journal Article
Open access
PDF file
JNjiawei Nian
jiawei Nian
HLHongjin Liu
Hongjin Liu
XGXin Gao
Xin Gao
SZShaolin Zhang
Shaolin Zhang
YMYang Mengfei
Yang Mengfei
Modern processors often face challenges when handling instructions that overwhelm the branch target buffer (BTB), leading to front-end bottlenecks. As the BTB’s capacity increases, its prediction module can become slower and power-hungry. In this paper, we introduce a straightforward yet highly effective two-level prediction mechanism to mitigate the escalating power consumption in the BTB structure, achieved by reducing the number of accesses. Our approach incorporates two main elements: M-BTB and V-BTB. M-BTB encompasses the first-level prediction mechanism and a fully associative BTB, while V-BTB houses the second-level prediction mechanism and a set-associative BTB. To implement our prediction mechanism, we optimize the traditional two-level BTB structure. The first level employs the skew mechanism, and the second level dissects the tag bits to create the Partial tag. These two levels of prediction mechanism correspond to the bank/way prediction for the two-level BTB structure. Our experimental results show that the first-stage prediction mechanism reduces M-BTB accesses by 75%, while the second-stage prediction mechanism ensures that over 98% of addresses require just zero or one way of the V-BTB to achieve a hit result. Our proposed approach achieves a remarkable 86–97% reduction in power consumption, with a minimal impact on performance and an increase in overall area efficiency.