Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDTushar Krishna
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c102]Zishen Wan, Che-Kai Liu, Mohamed Ibrahim, Hanchen Yang, Samuel Spetalnick, Tushar Krishna, Arijit Raychowdhury:
H3DFact: Heterogeneous 3D Integrated CIM for Factorization with Holographic Perceptual Representations. DATE 2024: 1-6- [c101]Jianming Tong, Anirudh Itagi, Prasanth Chatarasi, Tushar Krishna:
FEATHER: A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching. ISCA 2024: 198-214 - [c100]William Won, Saeed Rashidi, Sudarshan Srinivasan, Tushar Krishna:
LIBRA: Enabling Workload-Aware Multi-Dimensional Network Topology Optimization for Distributed Training of Large AI Models. ISPASS 2024: 205-216 - [c99]Zishen Wan, Che-Kai Liu, Hanchen Yang, Ritik Raj, Chaojian Li, Haoran You, Yonggan Fu, Cheng Wan, Ananda Samajdar, Yingyan Celine Lin, Tushar Krishna, Arijit Raychowdhury:
Towards Cognitive AI Systems: Workload and Characterization of Neuro-Symbolic AI. ISPASS 2024: 268-279 - [c98]Divya Kiran Kadiyala, Saeed Rashidi, Taekyung Heo, Abhimanyu Bambhaniya, Tushar Krishna, Alexandros Daglis:
Leveraging Memory Expansion to Accelerate Large-Scale DL Training. ISPASS 2024: 292-294 - [c97]Jingtian Dang, Jianming Tong, Anupam Golder, Cong Hao, Arijit Raychowdhury, Tushar Krishna:
Accurate Low-Degree Polynomial Approximation of Non-Polynomial Operators for Fast Private Inference in Homomorphic Encryption. MLSys 2024 - [i63]Zishen Wan, Che-Kai Liu, Hanchen Yang, Chaojian Li, Haoran You, Yonggan Fu, Cheng Wan, Tushar Krishna, Yingyan Lin, Arijit Raychowdhury:
Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI. CoRR abs/2401.01040 (2024) - [i62]Abhimanyu Rajeshkumar Bambhaniya, Amir Yazdanbakhsh, Suvinay Subramanian, Sheng-Chun Kao, Shivani Agrawal, Utku Evci, Tushar Krishna:
Progressive Gradient Flow for Robust N: M Sparsity Training in Transformers. CoRR abs/2402.04744 (2024) - [i61]Akshat Ramachandran, Zishen Wan, Geonhwa Jeong, John Gustafson, Tushar Krishna:
Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference. CoRR abs/2403.05465 (2024) - [i60]Hao Kang, Qingru Zhang, Souvik Kundu, Geonhwa Jeong, Zaoxing Liu, Tushar Krishna, Tuo Zhao:
GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM. CoRR abs/2403.05527 (2024) - [i59]Geonhwa Jeong, Po-An Tsai, Abhimanyu Rajeshkumar Bambhaniya, Stephen W. Keckler, Tushar Krishna:
Abstracting Sparse DNN Acceleration via Structured Sparse Tensor Decomposition. CoRR abs/2403.07953 (2024) - [i58]Jianming Tong, Jingtian Dang, Anupam Golder, Callie Hao, Arijit Raychowdhury, Tushar Krishna:
Accurate Low-Degree Polynomial Approximation of Non-polynomial Operators for Fast Private Inference in Homomorphic Encryption. CoRR abs/2404.03216 (2024) - [i57]Zishen Wan, Che-Kai Liu, Mohamed Ibrahim, Hanchen Yang, Samuel Spetalnick, Tushar Krishna, Arijit Raychowdhury:
H3DFact: Heterogeneous 3D Integrated CIM for Factorization with Holographic Perceptual Representations. CoRR abs/2404.04173 (2024) - [i56]Raveesh Garg, Hyoukjun Kwon, Eric Qin, Yu-Hsin Chen, Tushar Krishna, Liangzhen Lai:
PipeOrgan: Efficient Inter-operation Pipelining with Flexible Spatial Organization and Interconnects. CoRR abs/2405.01736 (2024) - [i55]Jianming Tong, Anirudh Itagi, Prasanth Chatarasi, Tushar Krishna:
FEATHER: A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching. CoRR abs/2405.13170 (2024) - [i54]Abhimanyu Bambhaniya, Ritik Raj, Geonhwa Jeong, Souvik Kundu, Sudarshan Srinivasan, Midhilesh Elavazhagan, Madhu Kumar, Tushar Krishna:
Demystifying Platform Requirements for Diverse LLM Inference Use Cases. CoRR abs/2406.01698 (2024) - [i53]Geonhwa Jeong, Po-An Tsai, Stephen W. Keckler, Tushar Krishna:
SDQ: Sparse Decomposed Quantization for LLM Inference. CoRR abs/2406.13868 (2024) - [i52]Saeed Rashidi, William Won, Sudarshan Srinivasan, Puneet Gupta, Tushar Krishna:
FRED: Flexible REduction-Distribution Interconnect and Communication Implementation for Wafer-Scale Distributed Training of DNN Models. CoRR abs/2406.19580 (2024) - [i51]Akshat Ramachandran, Souvik Kundu, Tushar Krishna:
CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs. CoRR abs/2407.05266 (2024) - 2023
- [j27]Anurag Kar
, Xueyang Liu, Yonghae Kim, Gururaj Saileshwar, Hyesoon Kim, Tushar Krishna:
Mitigating Timing-Based NoC Side-Channel Attacks With LLC Remapping. IEEE Comput. Archit. Lett. 22(1): 53-56 (2023) - [j26]Zeyu Chen, Ankur Bindal, Vaidehi Garg, Tushar Krishna:
SPOCK: Reverse Packet Traversal for Deadlock Recovery. IEEE Des. Test 40(6): 86-99 (2023) - [j25]John Kim, Tushar Krishna:
Introduction to the Special Issue on Next-Generation On-Chip and Off-Chip Communication Architectures for Edge, Cloud and HPC. ACM J. Emerg. Technol. Comput. Syst. 19(4): 31:1 (2023) - [j24]Francisco Muñoz-Martínez, José L. Abellán, Manuel E. Acacio, Tushar Krishna:
STIFT: A Spatio-Temporal Integrated Folding Tree for Efficient Reductions in Flexible DNN Accelerators. ACM J. Emerg. Technol. Comput. Syst. 19(4): 32:1-32:20 (2023) - [j23]Payman Behnam, Jianming Tong, Alind Khare, Yangyu Chen, Yue Pan, Pranav Gadikar, Abhimanyu Bambhaniya, Tushar Krishna, Alexey Tumanov:
Hardware-Software Co-Design for Real-Time Latency-Accuracy Navigation in Tiny Machine Learning Applications. IEEE Micro 43(6): 93-101 (2023) - [j22]Gokul Subramanian Ravi, Tushar Krishna, Mikko H. Lipasti:
TNT: A Modular Approach to Traversing Physically Heterogeneous NOCs at Bare-wire Latency. ACM Trans. Archit. Code Optim. 20(3): 35:1-35:25 (2023) - [j21]Gauthaman Murali, Aditya Iyer, Lingjun Zhu, Jianming Tong, Francisco Muñoz-Martínez, Srivatsa Rangachar Srinivasa, Tanay Karnik, Tushar Krishna, Sung Kyu Lim:
On Continuing DNN Accelerator Architecture Scaling Using Tightly Coupled Compute-on-Memory 3-D ICs. IEEE Trans. Very Large Scale Integr. Syst. 31(10): 1603-1613 (2023) - [c96]Afshin Abdi, Saeed Rashidi, Faramarz Fekri, Tushar Krishna:
Efficient Distributed Inference of Deep Neural Networks via Restructuring and Pruning. AAAI 2023: 6640-6648 - [c95]Francisco Muñoz-Martínez, Raveesh Garg, Michael Pellauer, José L. Abellán, Manuel E. Acacio, Tushar Krishna:
Flexagon: A Multi-dataflow Sparse-Sparse Matrix Multiplication Accelerator for Efficient DNN Processing. ASPLOS (3) 2023: 252-265 - [c94]Sheng-Chun Kao, Suvinay Subramanian, Gaurav Agrawal, Amir Yazdanbakhsh, Tushar Krishna:
FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks. ASPLOS (2) 2023: 295-310 - [c93]Abhimanyu Rajeshkumar Bambhaniya, Yangyu Chen, Anshuman, Rohan Banerjee, Tushar Krishna:
Proteus : HLS-based NoC Generator and Simulator. DATE 2023: 1-6 - [c92]Ananda Samajdar, Jan Moritz Joseph, Tushar Krishna:
AIrchitect: Automating Hardware Architecture and Mapping Optimization. DATE 2023: 1-6 - [c91]Geonhwa Jeong, Sana Damani, Abhimanyu Rajeshkumar Bambhaniya, Eric Qin, Christopher J. Hughes, Sreenivas Subramoney, Hyesoon Kim, Tushar Krishna:
VEGETA: Vertically-Integrated Extensions for Sparse/Dense GEMM Tile Acceleration on CPUs. HPCA 2023: 259-272 - [c90]Sudarshan Sharma, Uday Kamal, Jianming Tong, Tushar Krishna, Saibal Mukhopadhyay:
SNATCH: Stealing Neural Network Architecture from ML Accelerator in Intelligent Sensors. SENSORS 2023: 1-4 - [c89]Geonhwa Jeong, Bikash Sharma, Nick Terrell, Abhishek Dhanotia, Zhiwei Zhao, Niket Agarwal, Arun Kejariwal, Tushar Krishna:
Characterization of Data Compression in Datacenters. ISPASS 2023: 1-12 - [c88]William Won, Taekyung Heo, Saeed Rashidi, Srinivas Sridharan, Sudarshan Srinivasan, Tushar Krishna:
ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale. ISPASS 2023: 283-294 - [c87]Payman Behnam, Alexey Tumanov, Tushar Krishna, Pranav Gadikar, Yangyu Chen, Jianming Tong, Yue Pan, Abhimanyu Rajeshkumar Bambhaniya, Alind Khare:
Subgraph Stationary Hardware-Software Inference Co-Design. MLSys 2023 - [c86]Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo, Jason Yik, Debabrata Mohapatra, Dongyuan Zhan, Jinook Song, Peter Capak, Peizhao Zhang, Peter Vajda, Colby R. Banbury, Mark Mazumder, Liangzhen Lai, Ashish Sirasao, Tushar Krishna, Harshit Khaitan, Vikas Chandra, Vijay Janapa Reddi:
XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse. MLSys 2023 - [i50]Francisco Muñoz-Martínez, Raveesh Garg, José L. Abellán, Michael Pellauer, Manuel E. Acacio, Tushar Krishna:
Flexagon: A Multi-Dataflow Sparse-Sparse Matrix Multiplication Accelerator for Efficient DNN Processing. CoRR abs/2301.10852 (2023) - [i49]Geonhwa Jeong, Sana Damani, Abhimanyu Rajeshkumar Bambhaniya, Eric Qin, Christopher J. Hughes, Sreenivas Subramoney, Hyesoon Kim, Tushar Krishna:
VEGETA: Vertically-Integrated Extensions for Sparse/Dense GEMM Tile Acceleration on CPUs. CoRR abs/2302.08687 (2023) - [i48]Raveesh Garg, Michael Pellauer, Sivasankaran Rajamanickam, Tushar Krishna:
Exploiting Inter-Operation Data Reuse in Scientific Applications using GOGETA. CoRR abs/2303.11499 (2023) - [i47]William Won, Taekyung Heo, Saeed Rashidi, Srinivas Sridharan, Sudarshan Srinivasan, Tushar Krishna:
ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale. CoRR abs/2303.14006 (2023) - [i46]Maruti K. Mudunuru, James A. Ang, Mahantesh Halappanavar, Simon D. Hammond, Maya B. Gokhale, James C. Hoe, Tushar Krishna, Sarat Sreepathi, Matthew R. Norman, Ivy Bo Peng, Philip W. Jones:
Perspectives on AI Architectures and Co-design for Earth System Predictability. CoRR abs/2304.03748 (2023) - [i45]William Won, Midhilesh Elavazhagan, Sudarshan Srinivasan, Ajaya Durg, Swati Gupta, Tushar Krishna:
TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Training. CoRR abs/2304.05301 (2023) - [i44]Srinivas Sridharan, Taekyung Heo, Louis Feng, Zhaodong Wang, Matt Bergeron, Wenyin Fu, Shengbao Zheng, Brian Coutinho, Saeed Rashidi, Changhai Man, Tushar Krishna:
Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces. CoRR abs/2305.14516 (2023) - [i43]Payman Behnam, Jianming Tong, Alind Khare, Yangyu Chen, Yue Pan, Pranav Gadikar, Abhimanyu Rajeshkumar Bambhaniya, Tushar Krishna, Alexey Tumanov:
Subgraph Stationary Hardware-Software Inference Co-Design. CoRR abs/2306.17266 (2023) - 2022
- [j20]Sheng-Chun Kao, Hyoukjun Kwon, Michael Pellauer, Angshuman Parashar, Tushar Krishna:
A Formalism of DNN Accelerator Flexibility. Proc. ACM Meas. Anal. Comput. Syst. 6(2): 41:1-41:23 (2022) - [j19]Prasanth Chatarasi, Hyoukjun Kwon, Angshuman Parashar, Michael Pellauer, Tushar Krishna, Vivek Sarkar:
Marvel: A Data-Centric Approach for Mapping Deep Learning Operators on Spatial Accelerators. ACM Trans. Archit. Code Optim. 19(1): 6:1-6:26 (2022) - [j18]Michael Ferdman, Jorge Albericio, Tushar Krishna, Peter A. Milder:
Guest Editorial: IEEE TC Special Issue: Hardware Acceleration of Machine Learning. IEEE Trans. Computers 71(12): 3072-3073 (2022) - [j17]Gordon Euhyun Moon, Hyoukjun Kwon, Geonhwa Jeong, Prasanth Chatarasi, Sivasankaran Rajamanickam, Tushar Krishna:
Evaluating Spatial Accelerator Architectures with Tiled Matrix-Matrix Multiplication. IEEE Trans. Parallel Distributed Syst. 33(4): 1002-1014 (2022) - [c85]Ananda Samajdar, Eric Qin, Michael Pellauer, Tushar Krishna:
Self adaptive reconfigurable arrays (SARA): learning flexible GEMM accelerator configuration and mapping-space using ML. DAC 2022: 583-588 - [c84]Sheng-Chun Kao, Michael Pellauer, Angshuman Parashar, Tushar Krishna:
DiGamma: Domain-aware Genetic Algorithm for HW-Mapping Co-optimization for DNN Accelerators. DATE 2022: 232-237 - [c83]Tarannum Khan, Saeed Rashidi, Srinivas Sridharan, Pallavi Shurpali, Aditya Akella, Tushar Krishna:
Impact of RoCE Congestion Control Policies on Distributed Training of DNNs. HOTI 2022: 39-48 - [c82]Sheng-Chun Kao, Tushar Krishna:
MAGMA: An Optimization Framework for Mapping Multiple DNNs on Multiple Accelerator Cores. HPCA 2022: 814-830 - [c81]Hossein Farrokhbakht, Paul V. Gratz, Tushar Krishna, Joshua San Miguel, Natalie D. Enright Jerger:
Stay in your Lane: A NoC with Low-overhead Multi-packet Bypassing. HPCA 2022: 957-970 - [c80]Sheng-Chun Kao, Angshuman Parashar, Po-An Tsai, Tushar Krishna:
Demystifying Map Space Exploration for NPUs. IISWC 2022: 269-281 - [c79]Raveesh Garg, Eric Qin, Francisco Muñoz-Martínez, Robert Guirado, Akshay Jain, Sergi Abadal, José L. Abellán, Manuel E. Acacio, Eduard Alarcón, Sivasankaran Rajamanickam, Tushar Krishna:
Understanding the Design-Space of Sparse/Dense Multiphase GNN dataflows on Spatial Accelerators. IPDPS 2022: 571-582 - [c78]Saeed Rashidi, William Won, Sudarshan Srinivasan, Srinivas Sridharan, Tushar Krishna:
Themis: a network bandwidth-aware collective scheduling policy for distributed training of DL models. ISCA 2022: 581-596 - [c77]Geonhwa Jeong, Bikash Sharma, Nick Terrell, Abhishek Dhanotia, Zhiwei Zhao, Niket Agarwal, Arun Kejariwal, Tushar Krishna:
Understanding Data Compression in Warehouse-Scale Datacenter Services. ISPASS 2022: 221-223 - [c76]Difei Cao, Jinsun Yoo, Zhuangdi Xu, Enrique Saurez, Harshit Gupta, Tushar Krishna, Umakishore Ramachandran:
MicroEdge: a multi-tenant edge cluster system architecture for scalable camera processing. Middleware 2022: 322-334 - [c75]Sheng-Chun Kao, Hyoukjun Kwon, Michael Pellauer, Angshuman Parashar, Tushar Krishna:
A Formalism of DNN Accelerator Flexibility. SIGMETRICS (Abstracts) 2022: 53-54 - [i42]Eric Qin, Raveesh Garg, Abhimanyu Bambhaniya, Michael Pellauer, Angshuman Parashar, Sivasankaran Rajamanickam, Cong Hao, Tushar Krishna:
Enabling Flexibility for Sparse Tensor Acceleration via Heterogeneity. CoRR abs/2201.08916 (2022) - [i41]Sheng-Chun Kao, Xiaoyu Huang, Tushar Krishna:
DNNFuser: Generative Pre-Trained Transformer as a Generalized Mapper for Layer Fusion in DNN Accelerators. CoRR abs/2201.11218 (2022) - [i40]Sheng-Chun Kao, Michael Pellauer, Angshuman Parashar, Tushar Krishna:
DiGamma: Domain-aware Genetic Algorithm for HW-Mapping Co-optimization for DNN Accelerators. CoRR abs/2201.11220 (2022) - [i39]Sheng-Chun Kao, Hyoukjun Kwon, Michael Pellauer, Angshuman Parashar, Tushar Krishna:
A Formalism of DNN Accelerator Flexibility. CoRR abs/2206.02987 (2022) - [i38]Tarannum Khan, Saeed Rashidi, Srinivas Sridharan, Pallavi Shurpali, Aditya Akella, Tushar Krishna:
Impact of RoCE Congestion Control Policies on Distributed Training of DNNs. CoRR abs/2207.10898 (2022) - [i37]Sheng-Chun Kao, Amir Yazdanbakhsh, Suvinay Subramanian, Shivani Agrawal, Utku Evci, Tushar Krishna:
Training Recipe for N: M Structured Sparsity with Decaying Pruning Mask. CoRR abs/2209.07617 (2022) - [i36]Sheng-Chun Kao, Angshuman Parashar, Po-An Tsai, Tushar Krishna:
Demystifying Map Space Exploration for NPUs. CoRR abs/2210.03731 (2022) - [i35]Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo, Jason Yik, Debabrata Mohapatra, Dongyuan Zhan, Jinook Song, Peter Capak, Peizhao Zhang, Peter Vajda, Colby R. Banbury, Mark Mazumder, Liangzhen Lai, Ashish Sirasao, Tushar Krishna, Harshit Khaitan, Vikas Chandra, Vijay Janapa Reddi:
XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse. CoRR abs/2211.08675 (2022) - [i34]Divya Kiran Kadiyala, Saeed Rashidi, Taekyung Heo, Abhimanyu Rajeshkumar Bambhaniya, Tushar Krishna, Alexandros Daglis:
COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training. CoRR abs/2211.16648 (2022) - 2021
- [j16]Hyoukjun Kwon, Michael Pellauer, Angshuman Parashar, Tushar Krishna:
Flexion: A Quantitative Metric for Flexibility in DNN Accelerators. IEEE Comput. Archit. Lett. 20(1): 1-4 (2021) - [j15]Francisco Muñoz-Martínez, José L. Abellán, Manuel E. Acacio, Tushar Krishna:
STONNE: Enabling Cycle-Level Microarchitectural Simulation for DNN Inference Accelerators. IEEE Comput. Archit. Lett. 20(2): 122-125 (2021) - [j14]Bahar Asgari, Ramyad Hadidi, Tushar Krishna, Hyesoon Kim, Sudhakar Yalamanchili:
Efficiently Solving Partial Differential Equations in a Partially Reconfigurable Specialized Hardware. IEEE Trans. Computers 70(4): 524-538 (2021) - [j13]Gauthaman Murali, Heechun Park, Eric Qin, Hakki Mert Torun, Majid Ahadi Dolatsara, Madhavan Swaminathan, Tushar Krishna, Sung Kyu Lim:
Clock Delivery Network Design and Analysis for Interposer-Based 2.5-D Heterogeneous Systems. IEEE Trans. Very Large Scale Integr. Syst. 29(4): 605-616 (2021) - [c74]Geonhwa Jeong, Gokcen Kestor, Prasanth Chatarasi, Angshuman Parashar, Po-An Tsai, Sivasankaran Rajamanickam, Roberto Gioiosa, Tushar Krishna:
Union: A Unified HW-SW Co-Design Ecosystem in MLIR for Evaluating Tensor Operations on Spatial Accelerators. PACT 2021: 30-44 - [c73]Jan Moritz Joseph, Lennart Bamberg, Geonhwa Jeong, Ruei-Ting Chien, Rainer Leupers, Alberto García-Ortiz, Tushar Krishna, Thilo Pionteck:
Bridging the Frequency Gap in Heterogeneous 3D SoCs through Technology-Specific NoC Router Architectures. ASP-DAC 2021: 197-203 - [c72]Robert Guirado, Hyoukjun Kwon, Sergi Abadal, Eduard Alarcón, Tushar Krishna:
Dataflow-Architecture Co-Design for 2.5D DNN Accelerators using Wireless Network-on-Package. ASP-DAC 2021: 806-812 - [c71]Geonhwa Jeong, Eric Qin, Ananda Samajdar, Christopher J. Hughes, Sreenivas Subramoney, Hyesoon Kim, Tushar Krishna:
RASA: Efficient Register-Aware Systolic Array Matrix Engine for CPU. DAC 2021: 253-258 - [c70]Hyoukjun Kwon, Liangzhen Lai, Michael Pellauer, Tushar Krishna, Yu-Hsin Chen, Vikas Chandra:
Heterogeneous Dataflow Accelerators for Multi-DNN Workloads. HPCA 2021: 71-83 - [c69]Hossein Farrokhbakht, Henry Kao, Kamran Hasan, Paul V. Gratz, Tushar Krishna, Joshua San Miguel, Natalie D. Enright Jerger:
Pitstop: Enabling a Virtual Network Free Network-on-Chip. HPCA 2021: 682-695 - [c68]Francisco Muñoz-Martínez, José L. Abellán, Manuel E. Acacio, Tushar Krishna:
STONNE: Enabling Cycle-Level Microarchitectural Simulation for DNN Inference Accelerators. IISWC 2021: 201-213 - [c67]Eric Qin, Geonhwa Jeong, William Won, Sheng-Chun Kao, Hyoukjun Kwon, Sudarshan Srinivasan, Dipankar Das, Gordon Euhyun Moon, Sivasankaran Rajamanickam, Tushar Krishna:
Extending Sparse Tensor Accelerators to Support Multiple Compression Formats. IPDPS 2021: 1014-1024 - [c66]Saeed Rashidi, Matthew Denton, Srinivas Sridharan, Sudarshan Srinivasan, Amoghavarsha Suresh, Jade Nie, Tushar Krishna:
Enabling Compute-Communication Overlap in Distributed Deep Learning Training Platforms. ISCA 2021: 540-553 - [c65]Sheng-Chun Kao, Tushar Krishna:
E3: A HW/SW Co-design Neuroevolution Platform for Autonomous Learning in Edge Device. ISPASS 2021: 288-298 - [c64]Jan Moritz Joseph, Ananda Samajdar, Lingjun Zhu, Rainer Leupers, Sung Kyu Lim, Thilo Pionteck, Tushar Krishna:
Architecture, Dataflow and Physical Design Implications of 3D-ICs for DNN-Accelerators. ISQED 2021: 60-66 - [c63]Lennart Bamberg, Tushar Krishna, Jan Moritz Joseph:
Technology-aware Router Architectures for On-Chip-Networks in Heterogeneous Technologies. NANOCOM 2021: 17:1-17:7 - [c62]Francisco Muñoz-Martínez, José L. Abellán, Manuel E. Acacio, Tushar Krishna:
A novel network fabric for efficient spatio-temporal reduction in flexible DNN accelerators. NOCS 2021: 1-8 - [c61]Srikant Bharadwaj, Shomit Das, Yasuko Eckert, Mark Oskin, Tushar Krishna:
DUB: dynamic underclocking and bypassing in nocs for heterogeneous GPU workloads. NOCS 2021: 49-54 - [c60]Mayank Parasar, Natalie D. Enright Jerger, Paul V. Gratz, Joshua San Miguel, Tushar Krishna:
SEEC: stochastic escape express channel. SC 2021: 34 - [e1]Tushar Krishna, John Kim, Sergi Abadal, Joshua San Miguel:
NOCS '21: International Symposium on Networks-on-Chip, Virtual Event, October 14-15, 2021. ACM 2021, ISBN 978-1-4503-9083-5 [contents] - [i33]Ananda Samajdar, Michael Pellauer, Tushar Krishna:
Self-Adaptive Reconfigurable Arrays (SARA): Using ML to Assist Scaling GEMM Acceleration. CoRR abs/2101.04799 (2021) - [i32]Raveesh Garg, Eric Qin, Francisco Muñoz-Martínez, Robert Guirado, Akshay Jain, Sergi Abadal, José L. Abellán, Manuel E. Acacio, Eduard Alarcón, Sivasankaran Rajamanickam, Tushar Krishna:
A Taxonomy for Classification and Comparison of Dataflows for GNN Accelerators. CoRR abs/2103.07977 (2021) - [i31]Eric Qin, Geonhwa Jeong, William Won, Sheng-Chun Kao, Hyoukjun Kwon, Sudarshan Srinivasan, Dipankar Das, Gordon Euhyun Moon, Sivasankaran Rajamanickam, Tushar Krishna:
Extending Sparse Tensor Accelerators to Support Multiple Compression Formats. CoRR abs/2103.10452 (2021) - [i30]Sheng-Chun Kao, Tushar Krishna:
Domain-specific Genetic Algorithm for Multi-tenant DNNAccelerator Scheduling. CoRR abs/2104.13997 (2021) - [i29]Gordon Euhyun Moon, Hyoukjun Kwon, Geonhwa Jeong, Prasanth Chatarasi, Sivasankaran Rajamanickam, Tushar Krishna:
Evaluating Spatial Accelerator Architectures with Tiled Matrix-Matrix Multiplication. CoRR abs/2106.10499 (2021) - [i28]Sheng-Chun Kao, Suvinay Subramanian, Gaurav Agrawal, Tushar Krishna:
ATTACC the Quadratic Bottleneck of Attention Layers. CoRR abs/2107.06419 (2021) - [i27]Ananda Samajdar, Jan Moritz Joseph, Matthew Denton, Tushar Krishna:
AIRCHITECT: Learning Custom Architecture Design and Mapping Space. CoRR abs/2108.08295 (2021) - [i26]Geonhwa Jeong, Gokcen Kestor, Prasanth Chatarasi, Angshuman Parashar, Po-An Tsai, Sivasankaran Rajamanickam, Roberto Gioiosa, Tushar Krishna:
Union: A Unified HW-SW Co-Design Ecosystem in MLIR for Evaluating Tensor Operations on Spatial Accelerators. CoRR abs/2109.07419 (2021) - [i25]William Won, Saeed Rashidi, Sudarshan Srinivasan, Tushar Krishna:
Exploring Multi-dimensional Hierarchical Network Topologies for Efficient Distributed Training of Trillion Parameter DL Models. CoRR abs/2109.11762 (2021) - [i24]Geonhwa Jeong, Eric Qin, Ananda Samajdar, Christopher J. Hughes, Sreenivas Subramoney, Hyesoon Kim, Tushar Krishna:
RASA: Efficient Register-Aware Systolic Array Matrix Engine for CPU. CoRR abs/2110.01752 (2021) - [i23]Saeed Rashidi, William Won, Sudarshan Srinivasan, Srinivas Sridharan, Tushar Krishna:
Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models. CoRR abs/2110.04478 (2021) - 2020
- [b3]Tushar Krishna, Hyoukjun Kwon, Angshuman Parashar, Michael Pellauer, Ananda Samajdar:
Data Orchestration in Deep Learning Accelerators. Synthesis Lectures on Computer Architecture, Morgan & Claypool Publishers 2020, ISBN 978-3-031-00639-5 - [j12]Hyoukjun Kwon, Prasanth Chatarasi, Vivek Sarkar, Tushar Krishna, Michael Pellauer, Angshuman Parashar:
MAESTRO: A Data-Centric Approach to Understand Reuse, Performance, and Hardware Cost of DNN Mappings. IEEE Micro 40(3): 20-29 (2020) - [j11]Steffen Maass, Mohan Kumar Kumar, Taesoo Kim, Tushar Krishna, Abhishek Bhattacharjee:
ECOTLB: Eventually Consistent TLBs. ACM Trans. Archit. Code Optim. 17(4): 27:1-27:24 (2020) - [j10]Jinwoo Kim, Gauthaman Murali, Heechun Park, Eric Qin, Hyoukjun Kwon, Venkata Chaitanya Krishna Chekuri, Nael Mizanur Rahman, Nihar Dasari, Arvind Singh, Minah Lee, Hakki Mert Torun, Kallol Roy, Madhavan Swaminathan, Saibal Mukhopadhyay, Tushar Krishna, Sung Kyu Lim:
Architecture, Chip, and Package Codesign Flow for Interposer-Based 2.5-D Chiplet Integration Enabling Heterogeneous IP Reuse. IEEE Trans. Very Large Scale Integr. Syst. 28(11): 2424-2437 (2020) - [c59]Srikant Bharadwaj, Jieming Yin, Bradford M. Beckmann, Tushar Krishna:
Kite: A Family of Heterogeneous Interposer Topologies Enabled via Accurate Interconnect Modeling. DAC 2020: 1-6 - [c58]Lei Yang, Zheyu Yan, Meng Li, Hyoukjun Kwon, Liangzhen Lai, Tushar Krishna, Vikas Chandra, Weiwen Jiang, Yiyu Shi:
Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks. DAC 2020: 1-6 - [c57]Saeed Rashidi, Pallavi Shurpali, Srinivas Sridharan, Naader Hassani, Dheevatsa Mudigere, Krishnakumar Nair, Misha Smelyanski, Tushar Krishna:
Scalable Distributed Training of Recommendation Models: An ASTRA-SIM + NS3 case-study with TCP/IP transport. Hot Interconnects 2020: 33-42 - [c56]Eric Qin, Ananda Samajdar, Hyoukjun Kwon, Vineet Nadella, Sudarshan Srinivasan, Dipankar Das, Bharat Kaul, Tushar Krishna:
SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training. HPCA 2020: 58-70 - [c55]