Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Muzahid, Abdullah"'
Neural network training is inherently sequential where the layers finish the forward propagation in succession, followed by the calculation and back-propagation of gradients (based on a loss function) starting from the last layer. The sequential comp
Externí odkaz:
http://arxiv.org/abs/2305.13236
Autor:
Mandal, Shantanu, Chethan, Adhrik, Janfaza, Vahid, Mahmud, S M Farabi, Anderson, Todd A, Turek, Javier, Tithi, Jesmin Jahan, Muzahid, Abdullah
Software configurations play a crucial role in determining the behavior of software systems. In order to ensure safe and error-free operation, it is necessary to identify the correct configuration, along with their valid bounds and rules, which are c
Externí odkaz:
http://arxiv.org/abs/2304.09181
Automatic software generation based on some specification is known as program synthesis. Most existing approaches formulate program synthesis as a search problem with discrete parameters. In this paper, we present a novel formulation of program synth
Externí odkaz:
http://arxiv.org/abs/2211.00828
Autor:
Mahmud, Farabi, Kim, Sungkeun, Chawla, Harpreet Singh, Tsai, Chia-Che, Kim, Eun Jung, Muzahid, Abdullah
Publikováno v:
Annual Computer Security Applications Conference ACSAC 2023
For a distributed last-level cache (LLC) in a large multicore chip, the access time to one LLC bank can significantly differ from that to another due to the difference in physical distance. In this paper, we successfully demonstrated a new distance-b
Externí odkaz:
http://arxiv.org/abs/2112.10028
Autor:
Janfaza, Vahid, Weston, Kevin, Razavi, Moein, Mandal, Shantanu, Mahmud, Farabi, Hilty, Alex, Muzahid, Abdullah
Deep Neural Networks (DNN) are computationally intensive to train. It consists of a large number of multidimensional dot products between many weights and input vectors. However, there can be significant similarity among input vectors. If one input v
Externí odkaz:
http://arxiv.org/abs/2110.14904
Autor:
Majumder, Pritam, Huang, Jiayi, Kim, Sungkeun, Muzahid, Abdullah, Siegers, Dylan, Tsai, Chia-Che, Kim, Eun Jung
The resurgence of near-memory processing (NMP) with the advent of big data has shifted the computation paradigm from processor-centric to memory-centric computing. To meet the bandwidth and capacity demands of memory-centric computing, 3D memory has
Externí odkaz:
http://arxiv.org/abs/2104.13671
Autor:
Weston, Kevin, Jafanza, Vahid, Kansal, Arnav, Taur, Abhishek, Zahran, Mohamed, Muzahid, Abdullah
Computer applications are continuously evolving. However, significant knowledge can be harvested from a set of applications and applied in the context of unknown applications. In this paper, we propose to use the harvested knowledge to tune hardware
Externí odkaz:
http://arxiv.org/abs/2004.13074
Autor:
Mandal, Shantanu, Anderson, Todd A., Turek, Javier S., Gottschlich, Justin, Zhou, Shengtian, Muzahid, Abdullah
Publikováno v:
Proceedings of Machine Learning and Systems (MLSys), 3 (2021), 139-155
The problem of automatic software generation is known as Machine Programming. In this work, we propose a framework based on genetic algorithms to solve this problem. Although genetic algorithms have been used successfully for many problems, one criti
Externí odkaz:
http://arxiv.org/abs/1908.08783
Autor:
Alam, Mejbah, Gottschlich, Justin, Tatbul, Nesime, Turek, Javier, Mattson, Timothy, Muzahid, Abdullah
The field of machine programming (MP), the automation of the development of software, is making notable research advances. This is, in part, due to the emergence of a wide range of novel techniques in machine learning. In this paper, we apply MP to t
Externí odkaz:
http://arxiv.org/abs/1709.07536
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.