Tushar Krishna
Google (United States) · 318 works · 15,616 citations · h-index 41
Top works
- The gem5 simulator
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks
- 14.5 Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks
- GARNET: A detailed on-chip network model inside a full-system simulator
- SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training
- MAERI
- Understanding Reuse, Performance, and Hardware Cost of DNN Dataflow
- SCALE-Sim: Systolic CNN Accelerator Simulator
- MAESTRO: A Data-Centric Approach to Understand Reuse, Performance, and Hardware Cost of DNN Mappings
- SCORPIO
- A Systematic Methodology for Characterizing Scalability of DNN Accelerators using SCALE-Sim
- MAERI
- SCORPIO: A 36-core research chip demonstrating snoopy coherence on a scalable mesh NoC with in-network ordering
- Breaking the on-chip latency barrier using SMART
- Heterogeneous Dataflow Accelerators for Multi-DNN Workloads
- Architecture, Chip, and Package Codesign Flow for Interposer-Based 2.5-D Chiplet Integration Enabling Heterogeneous IP Reuse
- Characterizing the Deployment of Deep Neural Networks on Commercial Edge Devices
- GAMMA
- ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale
- Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks