Výsledky vyhledávání - "Nirmal Saxena"

Characterizing and Mitigating Soft Errors in GPU DRAM

Autor: Michael J. Sullivan, Nirmal Saxena, Stephen W. Keckler, Mike O'Connor, Siva Kumar Sastry Hari, Saurabh Hukerikar, Paul Racunas, Timothy Tsai, Donghyuk Lee

Publikováno v: MICRO

GPUs are used in high-reliability systems, including high-performance computers and autonomous vehicles. Because GPUs employ a high-bandwidth, wide-interface to DRAM and fetch each memory access from a single DRAM device, implementing full-device cor

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::11720616142d3d84858253ba6b9d3f31
https://doi.org/10.1145/3466752.3480111

Zobrazit plný text záznamu

On the Measurement of Safe Fault Failure Rates in High-Performance Compute Processors

Autor: Nirmal Saxena, Guangshan Duan, Yanxiang Huang, Richard Bramley, Paul Racunas

Publikováno v: ITC

Accurate determination of the safe-fault failure rate of complex digital designs is an exascale problem. We present a novel measurement methodology and results which could have a profound impact on the performance and availability for GPUs in safety

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::889c8d964f2f9ca39df4d9f8f20d7829
https://doi.org/10.1109/itc44778.2020.9325239

Zobrazit plný text záznamu

Resiliency of automotive object detection networks on GPU architectures

Autor: Paul Racunas, Saurabh Hukerikar, Yanxiang Huang, Richard Bramley, Atieh Lotfi, Keshav Balasubramanian, Nirmal Saxena

Publikováno v: ITC

Safety is the most important aspect of an autonomous driving platform. Deep neural networks (DNNs) play an increasingly critical role in localization, perception, and control in these systems. The object detection and classification inference are of

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::65739e795b8f03286f5f0c5026512faf
https://doi.org/10.1109/itc44170.2019.9000150

Zobrazit plný text záznamu

Low Overhead Tag Error Mitigation for GPU Architectures

Autor: Nirmal Saxena, Richard Bramley, Philip Payman Shirvani, Paul Racunas, Atieh Lotfi

Publikováno v: DSN

Cache structures on modern GPUs or CPUs occupy a large area and are frequently accessed. This increases their vulnerability to transient errors. With some area and energy overhead, these structures are often protected by ECC or parity checking. Howev

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::7daad84337074115e9c8b1f2c5182c50
https://doi.org/10.1109/dsn.2018.00041

Zobrazit plný text záznamu

Keynote 1: The road to resilient computing in autonomous driving is paved with redundancy

Autor: Krishna C. Saraswat, Sanu Mathew, Nirmal Saxena

Publikováno v: IRPS

Deep neural networks use the computational power of massively parallel processors in applications such as autonomous driving. Autonomous driving demands resiliency (as in safety and reliability) and trillions of operations per second of computing per

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::835dff6fb5ca808f8125c7d3dc339a37
https://doi.org/10.1109/irps.2018.8353536

Zobrazit plný text záznamu