T�tulo: Data Orchestration in Deep Learning Accelerators (Synthesis Lectures on Computer Architecture)
Editor: Springer
Fecha de publicaci�n: 2020
Idioma: Ingl�s
ISBN 10: 3031006399
ISBN 13: 9783031006395
Encuadernaci�n: Encuadernaci�n de tapa blanda
Estado: New

Acerca de

Sinopsis

This Synthesis Lecture focuses on techniques for efficient data orchestration within DNN accelerators. The End of Moore's Law, coupled with the increasing growth in deep learning and other AI applications has led to the emergence of custom Deep Neural Network (DNN) accelerators for energy-efficient inference on edge devices. Modern DNNs have millions of hyper parameters and involve billions of computations; this necessitates extensive data movement from memory to on-chip processing engines. It is well known that the cost of data movement today surpasses the cost of the actual computation; therefore, DNN accelerators require careful orchestration of data across on-chip compute, network, and memory elements to minimize the number of accesses to external DRAM. The book covers DNN dataflows, data reuse, buffer hierarchies, networks-on-chip, and automated design-space exploration. It concludes with data orchestration challenges with compressed and sparse DNNs and future trends. The target audience is students, engineers, and researchers interested in designing high-performance and low-energy accelerators for DNN inference.

Acerca del autor

Tushar Krishna is an Assistant Professor in the School of Electrical and Computer Engineering at the Georgia Institute of Technology. He received a Ph.D. in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology in 2014. Prior to that, he received an M.S.E in Electrical Engineering from Princeton University in 2009 and a B.Tech in Electrical Engineering from the Indian Institute of Technology (IIT), Delhi in 2007. Before joining Georgia Tech in 2015, he worked as a researcher in the VSSAD Group at Intel in Massachusetts. Dr. Krishna’s research spans computer architecture, interconnection networks, networks-on-chip (NoC), and deep learning accelerators, with a focus on optimizing data movement in modern computing systems. Three of his papers have been selected for IEEE Micro’s Top Picks from Computer Architecture, one more received an honorable mention, and three have won best paper awards. He received the National Science Foundation (NSF) CRII awardin 2018 and both a Google Faculty Award and a Facebook Faculty Award in 2019.Hyoukjun Kwon is a research scientist at Facebook AR/VR. He received his Ph.D. in Computer Science from Georgia Institute of Technology in 2020, advised by Dr. Tushar Krishna. He received B.S. degrees in Environmental Materials Science and in Computer Science and Engineering from Seoul National University in 2015. His research interests include communication-centric DNN accelerator designs, modeling of DNN accelerator architecture and mapping, NoC for accelerators, and co-optimization of DNN model, mapping, and accelerator architecture. He is actively leading the development of multiple open-source tools and RTLs in the DNN accelerator domain, including MAESTRO, MAERI, Microswitch NoC, and OpenSMART. One of his papers was selected for IEEE Micro’s Top Picks from computer architecture in 2019, one received honorable mention in 2018, and another won the best paper award at HPCA 2020.Angshuman Parashar is a Senior Research Scientist at NVIDIA. His research interests are in building, evaluating, and programming spatial and data-parallel architectures, with a present focus on automated mapping of machine learning algorithms onto architectures based on explicit decoupled data orchestration. Prior to NVIDIA, he was a member of the VSSAD group at Intel, where he worked with a small team of experts in architecture, languages, workloads, and implementation to design and evaluate a new spatial architecture. Dr. Parashar received his Ph.D. in Computer Science and Engineering from the Pennsylvania State University in 2007, and his B.Tech. in Computer Science and Engineering from the Indian Institute of Technology, Delhi in 2002.Michael Pellauer is a Senior Research Scientist at NVIDIA. His research interest is building domain specific accelerators, with a special emphasis on deep learning and sparse tensor algebra. Prior to NVIDIA, he was a member of the VSSAD group at Intel,where he performed research and advanced development on customized spatial accelerators. Dr. Pellauer holds a Ph.D. from the Massachusetts Institute of Technology in Cambridge, Massachusetts (2010), a Master’s from Chalmers University of Technology in Gothenburg, Sweden (2003), and a Bachelor’s from Brown University in Providence, Rhode Island (1999).Ananda Samajdar is a Ph.D. student at the school of Electrical and Computer Engineering (ECE) at the Georgia Institute of Technology. He completed his B.Tech. (Hons.) in Electronics and Communication Engineering (ECE) from the Indian Institute of Information Technology, Allahabad India (IIIT-A) in 2013. Before joining Georgia Tech, Anand worked as a VLSI design engineer at Qualcomm Bangalore for three years. Anand’s research interest includes designing custom architecture for efficient and deep learning systems. He has authored a number of papers in top-tier computer architecture conferences. Two of his papers received honorablementions in the IEEE MICRO Top Picks 2019, and one was awarded the best paper award at HPCA 2020. He is also the recipient of the silver medal for the ACM student research competition at ASPLOS 2019.

"Sobre este t�tulo" puede pertenecer a otra edici�n de este libro.

Descripci�n de la librer�a

We carry a wide selection of books from South Asia, United States, UK.

Ver la p�gina web de la librer�a

Informaci�n empresarial del vendedor

Readingos GmbH
Kaiserstra�e 47, Frankfurt am Main, 60329, Germany

Condiciones de venta y env�o

Condiciones de venta

Derecho a cancelaci�n

Si eres un consumidor puedes cancelar el presente contrato de acuerdo con lo indicado a continuaci�n. Son consumidores las personas f�sicas que act�en con un prop�sito ajeno a su actividad comercial, empresarial, oficio o profesi�n.

Documento de informaci�n al consumidor y usuario sobre el desistimiento

Derecho de desistimiento:

Tiene derecho a cancelar este contrato en un plazo de 14 d�as por cualquier motivo.

El plazo de desistimiento expirar� a los 14 d�as naturales del d�a en que t� o un tercero que hayas indicado, distinto del transportista, adquiera la posesi�n material del �ltimo bien, componente o pieza.

Para ejercer el derecho de desistimiento, deber�s notificarnos a Biblios, 47 Kaisetstrasse, 60329, frankfurt am main, hessen, Germany, de tu decisi�n de desistir del contrato a trav�s de una declaraci�n inequ�voca (por ejemplo, una carta enviada por correo postal, fax o correo electr�nico). Podr�s utilizar el modelo de formulario de desistimiento que figura a continuaci�n, aunque su uso no es obligatorio. Tienes asimismo la opci�n de cumplimentar y enviar electr�nicamente el modelo de formulario de desistimiento o cualquier otra declaraci�n inequ�voca a trav�s de nuestro sitio web a "Mis pedidos" en "Mi cuenta". Si recurres a esta opci�n, te comunicaremos sin demora en un soporte duradero (por ejemplo, por correo electr�nico) la recepci�n de dicho desistimiento.

Para cumplir el plazo de desistimiento, basta con que la comunicaci�n relativa al ejercicio por tu parte de este derecho sea enviada antes de que venza el plazo correspondiente.

Consecuencias del desistimiento:

En caso de desistimiento por tu parte, te devolveremos todos los pagos recibidos de ti, incluidos los gastos de entrega (con la excepci�n de los gastos adicionales resultantes de la elecci�n por tu parte de una modalidad de entrega diferente a la modalidad menos costosa de entrega ordinaria que ofrezcamos) sin ninguna demora indebida y, en todo caso, a m�s tardar 14 d�as naturales a partir de la fecha en la que se nos informes de tu decisi�n de desistir del presente contrato. Procederemos a efectuar dicho reembolso utilizando el mismo medio de pago empleado por ti para la transacci�n inicial, a no ser que hayas dispuesto expresamente lo contrario; en todo caso, no incurrir�s en ning�n gasto como consecuencia del reembolso.

Podremos retenerte el reembolso hasta haber recibido los bienes, o hasta que hayas presentado una prueba de la devoluci�n de los mismos, seg�n qu� condici�n se cumpla primero. Deber�s devolvernos o entregarnos directamente los bienes a Biblios, 47 Kaisetstrasse, 60329, frankfurt am main, Germany, sin ninguna demora indebida y, en cualquier caso, a m�s tardar en el plazo de 14 d�as naturales a partir de la fecha en que nos comuniques tu decisi�n de desistimiento del contrato. Se considerar� cumplido el plazo si efect�as la devoluci�n de los bienes antes de que haya concluido dicho plazo. Deber�s asumir el coste directo de devoluci�n de los bienes. Solo ser�s responsable de la disminuci�n de valor de los bienes resultante de una manipulaci�n distinta a la necesaria para establecer la naturaleza, las caracter�sticas y el funcionamiento de los bienes.

Excepciones al derecho de desistimiento:

La entrega de peri�dicos, publicaciones especializadas o revistas con la excepci�n de contratos de suscripci�n; y
La entrega de contenido digital (incluyendo apps, MP3, etc.) que no hubiera sido entregado en un medio tangible (por ejemplo: CD o DVD), si al realizar tu pedido has aceptado que podemos proceder al env�o del producto y que no resulta posible su cancelaci�n una vez comienza la entrega.

Modelo de formulario de desistimiento

(S�lo debe cumplimentar y enviar el presente formulario si desea desistir del contrato)

A la atenci�n de: (Biblios, 47 Kaisetstrasse, 60329, frankfurt am main, hessen, Germany)

Por la presente le comunico/comunicamos* que desisto de mi/desistimos de nuestro* contrato de venta del siguiente bien/prestaci�n del siguiente servicio*

Pedido el/recibido el*:

Nombre del consumidor y usuario o de los consumidores y usuarios:

Domicilio del consumidor y usuario o de los consumidores y usuarios:

Firma del consumidor y usuario o de los consumidores y usuarios (solo si el presente formulario se presenta en papel):

Fecha:

* Eliminar en su caso

Condiciones de env�o

Tarifas de env�o de Alemania a Estados Unidos de America

Tarifas de env�o de Alemania a Estados Unidos de America
Cantidad del pedido	De 25 a 45 d�as h�biles	De 8 a 14 d�as h�biles
Primer art�culo	EUR 9.95	EUR 18.70

Los plazos de entrega los establecen los vendedores y var�an seg�n el transportista y la ubicaci�n. Los pedidos que pasan por la aduana pueden sufrir retrasos y los compradores son responsables de los aranceles o tarifas asociadas. Los vendedores pueden ponerse en contacto con usted en relaci�n con cargos adicionales para cubrir cualquier aumento en los costes de env�o de los art�culos.

Informaci�n detallada sobre el vendedor