Filters








43,072 Hits in 1.4 sec

High-throughput coherence control and hardware messaging in Everest

A. K. Nanda, A.-T. Nguyen, M. M. Michael, D. J. Joseph
2001 IBM Journal of Research and Development  
Everest is an architecture for high-performance cache coherence and message passing in partitionable distributed shared-memory systems that use commodity shared multiprocessors (SMPs) as building blocks  ...  Everest provides high-throughput protocol handling in three dimensions: multiple protocol engines, split request-response handling, and pipelined design.  ...  He is currently involved in several research projects at IBM, including MemorIES (Memory Instrumentation and Emulation System), High Throughput Coherence Controllers, and the Watson Commercial Server Performance  ... 
doi:10.1147/rd.452.0299 fatcat:smlewcsijzg6li5ezb5ydrbvye

High-throughput coherence controllers

A.K. Nanda, A.-T. Nguyen, M.M. Michael, D.J. Joseph
Proceedings Sixth International Symposium on High-Performance Computer Architecture. HPCA-6 (Cat. No.PR00550)  
Recent research shows that the occupancy of the coherence controllers is a major performance bottleneck for distributed cache coherent shared memory multiprocessors.  ...  Our results show that applying any of the parallel mechanisms in the coherence controllers allows integrating four times as many processors per coherence controller, thus reducing system cost, while maintaining  ...  For future high-throughput coherence controller designs, we recommend that high throughput features be added in the following order: separate LPE and RPE controllers, split request/response streams, pipelining  ... 
doi:10.1109/hpca.2000.824346 dblp:conf/hpca/NandaNMJ00 fatcat:wb2honxwi5emzmtnz3cfjtzgeu

Design trade-offs in high-throughput coherence controllers

A.-T. Nguyen, J. Torrellas
Oceans 2002 Conference and Exhibition. Conference Proceedings (Cat. No.02CH37362)  
Recent research shows that the high occupancy of Coherence Controllers (CCs) is a major performance bottleneck in scalable shared-memory multiprocessors.  ...  These supports all serve to increase the overall throughput of CCs and improve overall system performance.  ...  A high CC occupancy hinders performance by inducing contention and reducing CC throughput.  ... 
doi:10.1109/pact.2003.1238015 dblp:conf/IEEEpact/NguyenT03 fatcat:2k62jfqlfff5hmtyx2anqlp37q

Optical performance of laser light source for ArF immersion double patterning lithography tool

Katsuhiko Wakana, Hiroaki Tsushima, Shinichi Matsumoto, Masaya Yoshino, Takahito Kumazaki, Hidenori Watanabe, Takeshi Ohta, Satoshi Tanaka, Toru Suzuki, Hiroaki Nakarai, Yasufumi Kawasuji, Akihiko Kurosu (+5 others)
2009 Optical Microlithography XXII  
In addition, we verified by simulation that the spectrum bandwidth control in the GT62A contributes to Depth of Focus (DOF) enhancement.  ...  Light source requirements for double patterning lithography tool are high power and high uptime to enhance economic efficiency, as well as extremely stable optical performances for high resolution capabilities  ...  Therefore, high-throughput and high-resolution exposure tools for the 193nm lithography require ArF light sources with high output power and stable narrow spectrum bandwidth.  ... 
doi:10.1117/12.813476 fatcat:qyrhwnnrcrbgnhey7ywfc5bxai

Data acquisition with the SCINET, a scalable-coherent-interface network

Harald Richter, Matthias Ohlenroth
1999 Fusion engineering and design  
SCI is a standardized, high-speed interconnect for peripheral devices, processors, memories, PCs and workstations that provides for a distributed shared memory with optional cache coherence between computing  ...  Test stands were established as a sample SCI-based data-acquisition system that showed up to 45 MB s − 1 of throughput and B5 ms latency for end-to-end data transfers.  ...  To control the plasma confinement and to get information about the physical behaviour, a high-speed and high-volume data-acquisition system is needed for the online and offline monitoring and evaluation  ... 
doi:10.1016/s0920-3796(98)00409-8 fatcat:klkcrda3dvdyppx5yciti35a4m

Maestro-link: A high performance interconnect for PC cluster [chapter]

Shinichi Yamagiwa, Masaaki Ono, Takeshi Yamazaki, Pusit Kulkasem, Masayuki Hirota, Koichi Wada
1998 Lecture Notes in Computer Science  
Maestro consists of multiple PC(Personal Computer)s and dedicated network hardware for high performance message passing and maintaining cache coherency.  ...  In this paper, an architecture of the high performance network interface of Maestro is presented.  ...  The obtained throughput was 63MBytes/sec. The throughput is determined mainly by the bandwidth of DRAM.  ... 
doi:10.1007/bfb0055273 fatcat:fcpmnhp72vdl7ah7lpu3xlcvje

Adaptive Power Control Using Large Scale Antenna of the Massive MIMO System in the Mobile Communication

2015 KSII Transactions on Internet and Information Systems  
Also, because the massive MIMO system with high SINR can use high order modulation scheme, it can support higher throughput.  ...  Although the MU-MIMO system doesn't enhance throughput of each user, it supports high throughput for network by unit of cell.  ...  As a result of simulation, the proposed adaptive power control achieves high throughput of system in a mobile communication.  ... 
doi:10.3837/tiis.2015.08.018 fatcat:xbtj3qmv7nagznisjxamgzqrze

Massive MIMO for Connectivity with Drones: Case Studies and Future Directions

Prabhu Chandhar, Erik G. Larsson
2019 IEEE Access  
Applications, such as surveillance, disaster management, and drone racing, place high requirements on the communication with the drones in terms of throughput, reliability, and latency.  ...  high sum throughput (in the order of 10 Gbps).  ...  Compelling features of Massive MIMO for this application include: high throughput, spatial multiplexing, coverage extension and high-mobility support.  ... 
doi:10.1109/access.2019.2928764 fatcat:fe6i3fi765bnvaou6qwdf2i2jq

New multichannel Ethernet protocol for passive optical star local area networks using coherent transmission

Daniel Rodellar, Cristian Bungarzeanu, H. Garcia, Caroline Brisson, Alain Kueng, Philippe A. Robert, Stephan Fischer, Ralf Steinmetz, Heinrich J. Stuettgen, Harmen R. van As, Roberto Vercelli
1998 Broadband European Networks and Multimedia Services  
Some suggestions are made for congestion control in high-capacity networks and different channel-jumping strategies are proposed.  ...  A new optical local area network that combines dense Wavelength Division Multiplexing (WDM) techniques and coherent transmission 4,5 benefits is presented.  ...  We also consider some suggestions for congestion control in high-capacity networks and therefore we show that a multichannel protocol shows better performance than a single channel one.  ... 
doi:10.1117/12.321902 dblp:conf/syben/RodellarBGBKR98 fatcat:kjndgoi3lfcxboou24qiaqcfme

Modulation rate adaptation in urban and vehicular environments

Joseph Camp, Edward Knightly
2008 Proceedings of the 14th ACM international conference on Mobile computing and networking - MobiCom '08  
cross-layer framework that enables (i) implementation of multiple and previously unimplemented rate adaptation mechanisms, (ii) experimental evaluation and comparison of rate adaptation protocols on controlled  ...  Our evaluation reveals that SNR-triggered protocols are susceptible to overselection from the ideal rate when the coherence time is low (a scenario that we show occurs in practice even in a nonmobile topology  ...  Figure 3 : 3 Throughput versus coherence time for a high-quality Rayleigh channel. Fig the coherence time for each of the four mechanisms.  ... 
doi:10.1145/1409944.1409981 dblp:conf/mobicom/CampK08 fatcat:notb5goc45ep5moombmyowbss4

Modulation Rate Adaptation in Urban and Vehicular Environments: Cross-Layer Implementation and Experimental Evaluation

Joseph Camp, Edward Knightly
2010 IEEE/ACM Transactions on Networking  
cross-layer framework that enables (i) implementation of multiple and previously unimplemented rate adaptation mechanisms, (ii) experimental evaluation and comparison of rate adaptation protocols on controlled  ...  Our evaluation reveals that SNR-triggered protocols are susceptible to overselection from the ideal rate when the coherence time is low (a scenario that we show occurs in practice even in a nonmobile topology  ...  Figure 3 : 3 Throughput versus coherence time for a high-quality Rayleigh channel. Fig the coherence time for each of the four mechanisms.  ... 
doi:10.1109/tnet.2010.2051454 fatcat:hhac2djsjrdbpffqfcv2kh6nxi

High Performance Memory Accesses on FPGA-SoCs: A Quantitative Analysis

Matthias Gobel, Chi Ching Chi, Mauricio Alvarez-Mesa, Ben Juurlink
2015 2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines  
Surprisingly, the coherent ACP achieves a relatively low maximum throughput of 159 MiB/s.  ...  By using all four High Performance ports of the Zynq-7000 in parallel, a throughput of 3440 MiB/s@214 MHz can be achieved when using the XC7Z045 chip, with a theoretical maximum of the used DDR3-1066 chip  ... 
doi:10.1109/fccm.2015.23 dblp:conf/fccm/GobelCAJ15 fatcat:hgi3cwdkyrcjbcqnr5r3n6yvgy

Massive MIMO for Drone Communications: Case Studies and Future Directions [article]

Prabhu Chandhar, Erik G. Larsson
2019 arXiv   pre-print
Applications, such as surveillance, disaster management, and drone racing, place high requirements on the communication with the drones in terms of throughput, reliability, and latency.  ...  can be utilized for achieving high sum throughput (in the order of 10 Gbps).  ...  Compelling features of Massive MIMO for this application include: high throughput, spatial multiplexing, coverage extension and high-mobility support.  ... 
arXiv:1711.07668v2 fatcat:oihepjtl7nh5hlg3pkynzjwtx4

On Characterizing Performance of the Cell Broadband Engine Element Interconnect Bus

Thomas William Ainsworth, Timothy Mark Pinkston
2007 First International Symposium on Networks-on-Chip (NOCS'07)  
understanding the design and performance of onchip networks implemented within the context of a commercial multicore chip, this paper analytically evaluates the EIB network using conventional latency and throughput  ...  The Cell Broadband Engine's Element Interconnect Bus (EIB), with its four data rings and shared command bus for end-to-end control, supports twelve nodes-more than most mainstream on-chip networks, which  ...  Fig. 4 shows the traffic pattern used for the high-efficiency test that resulted in a throughput of 197 GB/sec.  ... 
doi:10.1109/nocs.2007.34 dblp:conf/nocs/AinsworthP07 fatcat:yczpqryk7nbrfn6cqv4fkben4q

Experimental and theoretical study of OTA throughput of 4G LTE wireless terminals for different system bandwidths and coherence bandwidths in Rich Isotropic Multipath

A. Hussain, P.-S. Kildal
2012 2012 IEEE International Conference on Wireless Information Technology and Systems (ICWITS)  
Index Terms-OTA; LTE; OFDM; throughput; coherence bandwidth;delay spread I.  ...  The paper shows experimental and theoretical study of over-the-air (OTA) throughput of LTE wireless devices for different system bandwidths and coherence bandwidths in rich isotropic multipath (RIMP) environment  ...  In this study we investigate the effects of system bandwidths (B s ) and coherence bandwidths (B c ) on threshold, throughput, and diversity gain of a given DUT.  ... 
doi:10.1109/icwits.2012.6417811 fatcat:h63asulzuvbb5dztozlroum2kq
« Previous Showing results 1 — 15 out of 43,072 results