.png){kind=icon}
返回
A sampling-based acceleration method for heterogeneous chiplet NoC simulations
.png){kind=icon}
PRE
AI
DOI：10.1016/j.future.2024.107643.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
To tackle the challenges posed by Moore's Law, Chiplet technology emerges as a promising solution. Chiplets comprising CPUs and accelerators are connected by Networks-on-Chip (NoC) for large-scale integration and efficient communications. However, the slow simulation speed of NoCs has become a bottleneck, limiting the overall performance of chiplet simulations. Existing solutions only focus on accelerating NoC simulation in homogeneous architecture. In this paper, we introduce a novel TOPSIS-based Heterogeneous Trace Score- sampling method (THTS) for faster NoC simulation in heterogeneous architecture. THTS enables quick and accurate sampling of representative NoC traces. Additionally, we propose a weight exploration model to further enhance sampling accuracy. Compared with the traditional NoC sampling method (NoCLabs), THTS reduces the error of the average packet latency by 22.17% and the total simulation time by 1.6 folds. THTS estimates the NoC performance with an average loss less than 5%, while speeding up the NoC simulation by up to 3 times. In addition, under different weight space sizes, the time required for the weight exploration model to solve the optimal weight vector is within seconds, remarkably speeding up the solution process. Notably, the predicted NoC simulation error under the optimal weight is only 1.42%.
Keyword:
Chiplet
Heterogeneous architecture
Network on chip
Sampling method
Simulation acceleration
期刊
F
IF:
6.1
论文数:
6.9K
被引数:
2.3W
机构
引用论文
OPTIC NEURITIS AND MULTIPLE SCLEROSIS: DO FACTOR B ALLELES INFLUENCE PROGRESSION OF DISEASE?.png)
The Lancet
The LancetIF0
PREAI
分享收藏Pulse radiolytic measurement of redox potentials: the tyrosine and tryptophan radicalsBiochemistry
BiochemistryIF0
PREAI
分享收藏Aggregation of Electric Vehicles for Emergency Frequency Control of Two-Area Interconnected Grid
PREAI
分享收藏
查看更多内容