Visvesh Sathe
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Visvesh Sathe has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Luis Ceze
University of Washington, Paul G. Allen School of Computer Science and Engineering, Seattle, USA
2 shared publications - Thierry Moreau
University of Washington
2 shared publications - Amrita Mazumdar
School of Computer Science & Engineering School of Computer Science & Engineering School of Computer Science & Engineering School of Computer Science & Engineering School of Computer Science & Engineering Department of Electrical Engineering and Computer Sciences University of Washington University of Washington University of Washington University of Washington University of Washington University of California Berkeley
1 shared publication Armin Alaghi
School of Computer Science & Engineering Department of Electrical Engineering University of Washington University of Washington
1 shared publication- Armin Alaghi
University of Washington
1 shared publication - Mark Oskin
University of Washington
1 shared publication
Latest Publications
- 7 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 65 (12) , 4285-4298
Energy-Efficient Neural Network Acceleration in the Presence of Bit-Level Memory Errors
As a result of the increasing demand for deep neural network (DNN)-based services, efforts to develop hardware accelerators for DNNs are growing rapidly. However, while highly efficient accelerators on convolutional DNNs (ConvDNNs) have been developed, less progress has been made with regards to fully-connected DNNs. Based on analysis of bit-level SRAM errors, we propose memory adaptive training with in-situ canaries (MATIC), a methodology that enables aggressive voltage scaling of accelerator weight memories to improve the energyefficiency of DNN accelerators. To enable accurate operation with voltage overscaling, MATIC combines characteristics of SRAM bit failures with the error resilience of neural networks in a memory-adaptive training (MAT) process. Furthermore, PVT-related voltage margins are eliminated using bit-cells from synaptic weights as in-situ canaries to track runtime environmental variation. Demonstrated on a low-power DNN accelerator fabricated in 65 nm CMOS, MATIC enables up to 3.3× energy reduction versus the nominal voltage, or 18.6× application error reduction. We also perform a simulation study that extends MAT to Conv-DNNs, and characterize the accuracy impact of bit failure statistics. Finally, we develop a weight refinement algorithm to improve the performance of MAT, and show that it improves absolute accuracy by 0.8-1.3% or reduces training time by 5-10×.
- 7 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 65 (12) , 4285-4298
Energy-Efficient Neural Network Acceleration in the Presence of Bit-Level Memory Errors
As a result of the increasing demand for deep neural network (DNN)-based services, efforts to develop hardware accelerators for DNNs are growing rapidly. However, while highly efficient accelerators on convolutional DNNs (ConvDNNs) have been developed, less progress has been made with regards to fully-connected DNNs. Based on analysis of bit-level SRAM errors, we propose memory adaptive training with in-situ canaries (MATIC), a methodology that enables aggressive voltage scaling of accelerator weight memories to improve the energyefficiency of DNN accelerators. To enable accurate operation with voltage overscaling, MATIC combines characteristics of SRAM bit failures with the error resilience of neural networks in a memory-adaptive training (MAT) process. Furthermore, PVT-related voltage margins are eliminated using bit-cells from synaptic weights as in-situ canaries to track runtime environmental variation. Demonstrated on a low-power DNN accelerator fabricated in 65 nm CMOS, MATIC enables up to 3.3× energy reduction versus the nominal voltage, or 18.6× application error reduction. We also perform a simulation study that extends MAT to Conv-DNNs, and characterize the accuracy impact of bit failure statistics. Finally, we develop a weight refinement algorithm to improve the performance of MAT, and show that it improves absolute accuracy by 0.8-1.3% or reduces training time by 5-10×.
- Open Access
Exploring Computation-Communication Tradeoffs in Camera Systems
Cameras are the defacto sensor. The growing demand for real-time and low-power computer vision, coupled with trends towards high-efficiency heterogeneous systems, has given rise to a wide range of image processing acceleration techniques at the camera node and in the cloud. In this paper, we characterize two novel camera systems that use acceleration techniques to push the extremes of energy and performance scaling, and explore the computation-communication tradeoffs in their design. The first case study targets a camera system designed to detect and authenticate individual faces, running solely on energy harvested from RFID readers. We design a multi-accelerator SoC design operating in the sub-mW range, and evaluate it with real-world workloads to show performance and energy efficiency improvements over a general purpose microprocessor. The second camera system supports a 16-camera rig processing over 32 Gb/s of data to produce real-time 3D-360 degree virtual reality video. We design a multi-FPGA processing pipeline that outperforms CPU and GPU configurations by up to 10x in computation time, producing panoramic stereo video directly from the camera rig at 30 frames per second. We find that an early data reduction step, either before complex processing or offloading, is the most critical optimization for in-camera systems.
Open AccessExploring Computation-Communication Tradeoffs in Camera Systems
Cameras are the defacto sensor. The growing demand for real-time and low-power computer vision, coupled with trends towards high-efficiency heterogeneous systems, has given rise to a wide range of image processing acceleration techniques at the camera node and in the cloud. In this paper, we characterize two novel camera systems that use acceleration techniques to push the extremes of energy and performance scaling, and explore the computation-communication tradeoffs in their design. The first case study targets a camera system designed to detect and authenticate individual faces, running solely on energy harvested from RFID readers. We design a multi-accelerator SoC design operating in the sub-mW range, and evaluate it with real-world workloads to show performance and energy efficiency improvements over a general purpose microprocessor. The second camera system supports a 16-camera rig processing over 32 Gb/s of data to produce real-time 3D-360 degree virtual reality video. We design a multi-FPGA processing pipeline that outperforms CPU and GPU configurations by up to 10x in computation time, producing panoramic stereo video directly from the camera rig at 30 frames per second. We find that an early data reduction step, either before complex processing or offloading, is the most critical optimization for in-camera systems.