关注
Abhimanyu Bambhaniya
Abhimanyu Bambhaniya
School of Electrical and Computer Engineering, Georgia Institute of Technology
在 gatech.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Vegeta: Vertically-integrated extensions for sparse/dense gemm tile acceleration on cpus
G Jeong, S Damani, AR Bambhaniya, E Qin, CJ Hughes, S Subramoney, ...
2023 IEEE International Symposium on High-Performance Computer Architecture …, 2023
142023
Enabling flexibility for sparse tensor acceleration via heterogeneity
E Qin, R Garg, A Bambhaniya, M Pellauer, A Parashar, S Rajamanickam, ...
arXiv preprint arXiv:2201.08916, 2022
72022
Hardware-Software co-design for real-time latency-accuracy navigation in tinyML applications
P Behnam, J Tong, A Khare, Y Chen, Y Pan, P Gadikar, A Bambhaniya, ...
IEEE Micro, 2023
52023
COMET: A comprehensive cluster design methodology for distributed deep learning training
DK Kadiyala, S Rashidi, T Heo, AR Bambhaniya, T Krishna, A Daglis
arXiv preprint arXiv:2211.16648, 2022
52022
Subgraph stationary hardware-software inference co-design
P Behnam, A Tumanov, T Krishna, P Gadikar, Y Chen, J Tong, Y Pan, ...
Proceedings of Machine Learning and Systems 5, 563-577, 2023
32023
Accelerating Attention Based Models via HW-SW Co-Design using Fine-Grained Sparsification
AR Bambhaniya, A Yazdanbakhsh, S Subramanian, T Krishna
Architecture and System Support for Transformer Models (ASSYST@ ISCA 2023), 2023
22023
Demystifying Platform Requirements for Diverse LLM Inference Use Cases
A Bambhaniya, R Raj, G Jeong, S Kundu, S Srinivasan, M Elavazhagan, ...
arXiv preprint arXiv:2406.01698, 2024
12024
Progressive Gradient Flow for Robust N: M Sparsity Training in Transformers
AR Bambhaniya, A Yazdanbakhsh, S Subramanian, SC Kao, S Agrawal, ...
arXiv preprint arXiv:2402.04744, 2024
12024
Enabling Real-time DNN Switching via Weight-Sharing
J Tong, Y Chen, Y Pan, A Bambhaniya, A Khare, T Heo, A Tumanov, ...
Conference proceedings International Symposium on Computer Architecture, 2022
12022
Leveraging Memory Expansion to Accelerate Large-Scale DL Training
D Kadiyala, S Rashidi, T Heo, A Bambhaniya, T Krishna, A Daglis
2024 IEEE International Symposium on Performance Analysis of Systems and …, 2024
2024
Abstracting Sparse DNN Acceleration via Structured Sparse Tensor Decomposition
G Jeong, PA Tsai, AR Bambhaniya, SW Keckler, T Krishna
arXiv preprint arXiv:2403.07953, 2024
2024
Progressive Gradient Flow for Robust N: M Sparsity Training in Transformers
A Rajeshkumar Bambhaniya, A Yazdanbakhsh, S Subramanian, SC Kao, ...
arXiv e-prints, arXiv: 2402.04744, 2024
2024
Proteus: HLS-based NoC Generator and Simulator
AR Bambhaniya, Y Chen, R Banerjee, T Krishna
2023 Design, Automation & Test in Europe Conference & Exhibition (DATE), 1-6, 2023
2023
COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training
D Kiran Kadiyala, S Rashidi, T Heo, A Rajeshkumar Bambhaniya, ...
arXiv e-prints, arXiv: 2211.16648, 2022
2022
MoE-ERAS: Expert Residency Aware Selection
AR Bambhaniya, SC Kumar, T Krishna
Machine Learning for Computer Architecture and Systems 2024, 0
Sparsify the Weights but Let the Gradients Flow!
A Yazdanbakhsh, AR Bambhaniya, S Subramanian, SC Kao, S Agrawal, ...
系统目前无法执行此操作,请稍后再试。
文章 1–16