Follow
Seyyed Hasan Mozafari
Seyyed Hasan Mozafari
Verified email at mail.mcgill.ca - Homepage
Title
Cited by
Cited by
Year
Cell design methodology based on transmission gate for low-power high-speed balanced XOR-XNOR circuits in hybrid-CMOS logic style
T Nikoubin, M Grailoo, SH Mozafari
Journal of Low Power Electronics 6 (4), 503-512, 2010
342010
PipeBERT: high-throughput BERT inference for arm big. Little multi-core processors
HY Chang, SH Mozafari, C Chen, JJ Clark, BH Meyer, WJ Gross
Journal of Signal Processing Systems 95 (7), 877-894, 2023
102023
A Low Cost circuit level fault detection technique to Full Adder design
SH Mozafari, M Fazeli, S Hessabi, SG Miremadi
2011 18th IEEE International Conference on Electronics, Circuits, and …, 2011
72011
Hot spare components for performance-cost improvement in multi-core SIMT
SH Mozafari, BH Meyer
2015 IEEE International Symposium on Defect and Fault Tolerance in VLSI and …, 2015
62015
Yield-aware performance-cost characterization for multi-core SIMT
SH Mozafari, BH Meyer, K Skadron
Proceedings of the 25th edition on great lakes symposium on VLSI, 237-240, 2015
62015
Implementing convolutional neural networks using hartley stochastic computing with adaptive rate feature map compression
SH Mozafari, JJ Clark, WJ Gross, BH Meyer
IEEE Open Journal of Circuits and Systems 2, 805-819, 2021
42021
Efficient performance evaluation of multi-core simt processors with hot redundancy
SH Mozafari, BH Meyer
IEEE Transactions on Emerging Topics in Computing 6 (4), 498-510, 2016
42016
Hartley stochastic computing for convolutional neural networks
SH Mozafari, JJ Clark, WJ Gross, BH Meyer
2021 IEEE Workshop on Signal Processing Systems (SiPS), 1-6, 2021
32021
Hot sparing for lifetime-chip-performance and cost improvement in application specific SIMT processors
SH Mozafari, BH Meyer
Design Automation for Embedded Systems 24, 249-266, 2020
32020
Characterizing the effectiveness of hot sparing on cost and performance-per-watt in application specific SIMT
SH Mozafari, BH Meyer
Integration 69, 198-209, 2019
32019
Fast heterogeneous task mapping for reducing edge dnn latency
ML Kornelsen, SH Mozafari, JJ Clark, BH Meyer, WJ Gross
2022 IEEE 33rd International Conference on Application-specific Systems …, 2022
22022
Constructing new matrices and investigating their determinants
N Mirashe, AR Moghaddamfar, SH Mozafari, SMH Pooya, S Navid Salehy, ...
Asian-European Journal of Mathematics 1 (04), 575-588, 2008
22008
BERTPerf: Inference Latency Predictor for BERT on ARM big. LITTLE Multi-Core Processors
M Abdelgawad, SH Mozafari, JJ Clark, BH Meyer, WJ Gross
2022 IEEE Workshop on Signal Processing Systems (SiPS), 1-6, 2022
12022
Work-in-progress: Utilizing latency and accuracy predictors for efficient hardware-aware NAS
N Firouzian, SH Mozafari, JJ Clark, WJ Gross, BH Meyer
2022 International Conference on Hardware/Software Codesign and System …, 2022
12022
Area, throughput, and power trade-offs for FPGA-and ASIC-based execution stream compression
MI Mera, J Caplan, SH Mozafari, BH Meyer, P Milder
ACM Transactions on Embedded Computing Systems (TECS) 16 (4), 1-20, 2017
12017
The determinants of matrices constructed by subdiagonal, main diagonal and superdiagonal
N Mirashe, AR Moghaddamfar, SH Mozafari
Lobachevskii Journal of Mathematics 31 (3), 295-306, 2010
12010
Automatic Pruning of Fine-tuning Datasets for Transformer-based Language Models
M Tayaranian, SH Mozafari, BH Meyer, JJ Clark, WJ Gross
arXiv preprint arXiv:2407.08887, 2024
2024
Faster Inference of Integer SWIN Transformer by Removing the GELU Activation
M Tayaranian, SH Mozafari, JJ Clark, B Meyer, W Gross
arXiv preprint arXiv:2402.01169, 2024
2024
Efficient 1D Grouped Convolution for PyTorch a Case Study: Fast On-Device Fine-Tuning for SqueezeBERT
SH Mozafari, JJ Clark, WJ Gross, BH Meyer
2023 IEEE 34th International Conference on Application-specific Systems …, 2023
2023
High-Throughput Edge Inference for BERT Models via Neural Architecture Search and Pipeline
HY Chang, SH Mozafari, JJ Clark, BH Meyer, WJ Gross
Proceedings of the Great Lakes Symposium on VLSI 2023, 455-459, 2023
2023
The system can't perform the operation now. Try again later.
Articles 1–20