T
Tushar Krishna
Researcher at Georgia Institute of Technology
Publications - 114
Citations - 2647
Tushar Krishna is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Dataflow & Computer science. The author has an hindex of 18, co-authored 114 publications receiving 1299 citations.
Papers
More filters
Proceedings ArticleDOI
MAERI: Enabling Flexible Dataflow Mapping over DNN Accelerators via Reconfigurable Interconnects
TL;DR: MAERI is a DNN accelerator built with a set of modular and configurable building blocks that can easily support myriad DNN partitions and mappings by appropriately configuring tiny switches and provides 8-459% better utilization across multiple dataflow mappings over baselines with rigid NoC fabrics.
Proceedings ArticleDOI
SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training
Eric Qin,Ananda Samajdar,Hyoukjun Kwon,Vineet Nadella,Sudarshan Srinivasan,Dipankar Das,Bharat Kaul,Tushar Krishna +7 more
TL;DR: SIGMA is proposed, a flexible and scalable architecture that offers high utilization of all its processing elements (PEs) regardless of kernel shape and sparsity, and includes a novel reduction tree microarchitecture named Forwarding Adder Network (FAN).
Proceedings ArticleDOI
Understanding Reuse, Performance, and Hardware Cost of DNN Dataflow: A Data-Centric Approach
Hyoukjun Kwon,Prasanth Chatarasi,Michael Pellauer,Angshuman Parashar,Vivek Sarkar,Tushar Krishna +5 more
TL;DR: This work introduces a set of data-centric directives to concisely specify the DNN dataflow space in a compiler-friendly form and codifies this analysis into an analytical cost model, MAESTRO (Modeling Accelerator Efficiency via Patio-Temporal Reuse and Occupancy), that estimates various cost-benefit tradeoffs of a dataflow including execution time and energy efficiency for a DNN model and hardware configuration.
Posted Content
SCALE-Sim: Systolic CNN Accelerator Simulator
TL;DR: This work introduces Systolic CNN Accelerator Simulator (SCALE-Sim), which is a configurable systolic array based cycle accurate DNN accelerator simulator that exposes various micro-architectural features as well as system integration parameters to the designer to enable comprehensive design space exploration.
Proceedings ArticleDOI
A Systematic Methodology for Characterizing Scalability of DNN Accelerators using SCALE-Sim
Ananda Samajdar,Jan Moritz Joseph,Yuhao Zhu,Paul N. Whatmough,Matthew Mattina,Tushar Krishna +5 more
TL;DR: This work demonstrates and analyzes the trade-off space for performance, DRAM bandwidth, and energy, and identifies sweet spots for various workloads and hardware configurations, and observes that a judicious choice of scaling can lead to performance improvements as high as 50 per layer, within the availableDRAM bandwidth.