Results 11 to 20 of about 1,840,164 (310)

Validating direct memory access interfaces with conformance checking [PDF]

open access: yes2014 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2014
Li Lei, Kai Cong, Zhenkun Yang, Fei Xie
openaire   +2 more sources

A Remote Direct Memory Access Protocol Specification [PDF]

open access: yesRequest for Comments, 2007
R. Recio   +4 more
openaire   +2 more sources

Remote Direct Memory Access (RDMA) Protocol Extensions [PDF]

open access: yesRequest for Comments, 2014
H. Shah   +4 more
openaire   +2 more sources

Optimization Method of Streaming Storage Based on GCC Compiler [PDF]

open access: yesJisuanji kexue, 2022
To solve the problem of cache pollution and mandatory loss caused by streaming memory access,some high-perfor-mance general-purpose processor platforms provide a dedicated path and supporting instructions for accessing memory directly without accessing ...
GAO Xiu-wu, HUANG Liang-ming, JIANG Jun
doaj   +1 more source

vsocket:an RDMA-based Acceleration Method Compatible with Standard Socket [PDF]

open access: yesJisuanji kexue, 2023
In order to be compatible with Linux standard sockets and utilize RDMA to improve the performance of programs using sockets,this paper proposes to construct a middleware Viscore Socket adaptor,referred to as vsocket between the upper-la-yer application ...
CHEN Yunfang, MAO Haotian, ZHANG Wei
doaj   +1 more source

CNN-DMA: A Predictable and Scalable Direct Memory Access Engine for Convolutional Neural Network with Sliding-window Filtering

open access: yesACM Great Lakes Symposium on VLSI, 2021
Memory bandwidth utilization has become the key performance bottleneck for state-of-the-art variants of neural network kernels. Current structures such as depth-wise, point-wise and atrous convolutions have already introduced diverse and discontinuous ...
Zheng Wang   +12 more
semanticscholar   +1 more source

System-Level Communication Performance Estimation for DMA-Controlled Accelerators

open access: yesIEEE Access, 2021
The performance of a hardware accelerator is often limited by the communication bandwidth between local on-chip memories and DRAM across on-chip bus.
Sunwoo Kim   +2 more
doaj   +1 more source

A Delay-Based Machine Learning Model for DMA Attack Mitigation

open access: yesCryptography, 2021
Direct Memory Access (DMA) is a state-of-the-art technique to optimize the speed of memory access and to efficiently use processing power during data transfers between the main system and a peripheral device. However, this advanced feature opens security
Yutian Gui   +3 more
doaj   +1 more source

Optimization of Communication Schemes for DMA-Controlled Accelerators

open access: yesIEEE Access, 2021
The hardware accelerator controlled by direct memory access (DMA) is greatly influenced by the communication bandwidth from/to DRAM through on-chip buses. This paper proposes a novel performance estimation algorithm to optimize the communication schemes (
Jooho Wang   +2 more
doaj   +1 more source

Home - About - Disclaimer - Privacy