Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Patel, Pratyush"'
Autor:
Anthony-Petersen, Robin, Chang, Clarence L., Chang, Yen-Yung, Chaplinsky, Luke, Fink, Caleb W., Garcia-Sciveres, Maurice, Guo, Wei, Hertel, Scott A., Li, Xinran, Lin, Junsong, Lisovenko, Marharyta, Mahapatra, Rupak, Matava, William, McKinsey, Daniel N., Osterman, David Z., Patel, Pratyush K., Penning, Bjoern, Platt, Mark, Pyle, Matt, Qi, Yinghe, Reed, Maggie, Rydstrom, Ivar, Romani, Roger K., Sadoulet, Bernard, Serfass, Bruno, Sorensen, Peter, Suerfu, Burkhant, Velan, Vetri, Wang, Gensheng, Wang, Yue, Watkins, Samuel L., Williams, Michael R.
We describe observations of low energy excess (LEE) events (background events observed in all light dark matter direct detection calorimeters) and noise in a two-channel silicon athermal phonon detector with 375 meV baseline energy resolution. We mea
Externí odkaz:
http://arxiv.org/abs/2410.16510
GPUs are known to be power-hungry, and due to the boom in artificial intelligence, they are currently the major contributors to the high power demands of upcoming datacenters. Most GPU usage in these popular workloads consist of large general matrix-
Externí odkaz:
http://arxiv.org/abs/2409.18324
Autor:
Patel, Pratyush, Choukse, Esha, Zhang, Chaojie, Shah, Aashaka, Goiri, Íñigo, Maleki, Saeed, Bianchini, Ricardo
Recent innovations in generative large language models (LLMs) have made their applications and use-cases ubiquitous. This has led to large-scale deployments of these models, using complex, expensive, and power-hungry AI accelerators, most commonly GP
Externí odkaz:
http://arxiv.org/abs/2311.18677
Autor:
Patel, Pratyush, Choukse, Esha, Zhang, Chaojie, Goiri, Íñigo, Warrier, Brijesh, Mahalingam, Nithish, Bianchini, Ricardo
Recent innovation in large language models (LLMs), and their myriad use-cases have rapidly driven up the compute capacity demand for datacenter GPUs. Several cloud providers and other enterprises have made substantial plans of growth in their datacen
Externí odkaz:
http://arxiv.org/abs/2308.12908
Autor:
Patel, Pratyush, Lim, Katie, Jhunjhunwalla, Kushal, Martinez, Ashlie, Demoulin, Max, Nelson, Jacob, Zhang, Irene, Anderson, Thomas
Field-Programmable Gate Arrays (FPGAs) are more energy efficient and cost effective than CPUs for a wide variety of datacenter applications. Yet, for latency-sensitive and bursty workloads, this advantage can be difficult to harness due to high FPGA
Externí odkaz:
http://arxiv.org/abs/2304.04488
Autor:
Anthony-Petersen, Robin, Biekert, Andreas, Bunker, Raymond, Chang, Clarence L., Chang, Yen-Yung, Chaplinsky, Luke, Fascione, Eleanor, Fink, Caleb W., Garcia-Sciveres, Maurice, Germond, Richard, Guo, Wei, Hertel, Scott A., Hong, Ziqing, Kurinsky, Noah, Li, Xinran, Lin, Junsong, Lisovenko, Marharyta, Mahapatra, Rupak, Mayer, Adam, McKinsey, Daniel N., Mehrotra, Siddhant, Mirabolfathi, Nader, Neblosky, Brian, Page, William A., Patel, Pratyush K., Penning, Bjoern, Pinckney, H. Douglas, Platt, Mark, Pyle, Matt, Reed, Maggie, Romani, Roger K., Queiroz, Hadley Santana, Sadoulet, Bernard, Serfass, Bruno, Smith, Ryan, Sorensen, Peter F., Suerfu, Burkhant, Suzuki, Aritoki, Underwood, Ryan, Velan, Vetri, Wang, Gensheng, Wang, Yue, Watkins, Samuel L., Williams, Michael R., Yefremenko, Volodymyr, Zhang, Jianjie
Publikováno v:
Nat. Commun. 15, 6444 (2024)
The performance of superconducting qubits is degraded by a poorly characterized set of energy sources breaking the Cooper pairs responsible for superconductivity, creating a condition often called ``quasiparticle poisoning". Both superconducting qubi
Externí odkaz:
http://arxiv.org/abs/2208.02790
Autor:
Hajinazar, Nastaran, Patel, Pratyush, Patel, Minesh, Kanellopoulos, Konstantinos, Ghose, Saugata, Ausavarungnirun, Rachata, Oliveira Jr., Geraldo Francisco de, Appavoo, Jonathan, Seshadri, Vivek, Mutlu, Onur
Computers continue to diversify with respect to system designs, emerging memory technologies, and application memory demands. Unfortunately, continually adapting the conventional virtual memory framework to each possible system configuration is chall
Externí odkaz:
http://arxiv.org/abs/2005.09748
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We propose a server-based approach to manage a general-purpose graphics processing unit (GPU) in a predictable and efficient manner. Our proposed approach introduces a GPU server that is a dedicated task to handle GPU requests from other tasks on the
Externí odkaz:
http://arxiv.org/abs/1709.06613
Publikováno v:
In Journal of Systems Architecture August 2018 88:97-109
