Filters








1,676 Hits in 3.5 sec

Dataflow architectures and multithreading

B. Lee, A.R. Hurson
1994 Computer  
Due to its simplicity and elegance in describing parallelism and data dependencies, the dataflow execution model has been the subject of many research efforts.  ...  Since the early 197Os, a number of hardware prototypes have been built and evaluated,' and dif-6. R. S .  ...  Multithreading Architectures based on the dataflow model offer the advantage of instructionlevel context switching.  ... 
doi:10.1109/2.303620 fatcat:d2ow7yxkbvh2xdbtaq4ztr6hdi

Programming Abstractions and Toolchain for Dataflow Multithreading Architectures

Kyriakos Stavrou, Demos Pavlou, Marios Nikolaides, Panayiotis Petrides, Paraskevas Evripidou, Pedro Trancoso, Zdravko Popovic, Roberto Giorgi
2009 2009 Eighth International Symposium on Parallel and Distributed Computing  
In this work we propose an abstraction layer that enables compiling and running a program written for an abstract Dataflow Multithreading architecture on different implementations.  ...  In particular, the Dataflow Multithreading architectures have proven to be good candidates for these systems.  ...  Acknowledgments This project was partially funded by HiPEAC (EU FP6 IST 004408, FP7 IST 217068), SARC (EU FP6 FET 27648) and the Cyprus Research Promotion Foundation under the grant ΔΠE/0505/25.  ... 
doi:10.1109/ispdc.2009.35 dblp:conf/ispdc/StavrouPNPETPG09 fatcat:hj24bpcpxfag7a5ikk6uh2oygu

Scheduled dataflow: execution paradigm, architecture, and performance evaluation

K.M. Kavi, R. Giorgi, J. Arul
2001 IEEE transactions on computers  
AbstractÐIn this paper, the Scheduled Dataflow (SDF) architectureÐa decoupled memory/execution, multithreaded architecture using nonblocking threadsÐis presented in detail and evaluated against Superscalar  ...  Our research deviates from this trend by exploring a simpler, yet powerful execution paradigm that is based on dataflow and multithreading.  ...  ACKNOWLEDGMENTS This research is supported in part by the following grants from the US National Science Foundation: CCR-9796310, EIA-9805216, and EIA-9820147 and Italian grant from CNR 203.15.9/97. the  ... 
doi:10.1109/tc.2001.947011 fatcat:e7cco3kjqvcopmukezqkuzyahq

Scheduled dataflow: execution paradigm, architecture, and performance evaluation

K.M. Kavi, R. Giorgi, J. Arul
2001 IEEE transactions on computers  
AbstractÐIn this paper, the Scheduled Dataflow (SDF) architectureÐa decoupled memory/execution, multithreaded architecture using nonblocking threadsÐis presented in detail and evaluated against Superscalar  ...  Our research deviates from this trend by exploring a simpler, yet powerful execution paradigm that is based on dataflow and multithreading.  ...  ACKNOWLEDGMENTS This research is supported in part by the following grants from the US National Science Foundation: CCR-9796310, EIA-9805216, and EIA-9820147 and Italian grant from CNR 203.15.9/97. the  ... 
doi:10.1109/12.947003 fatcat:inhwbcvzrnhplobil2togefjg4

Execution and Cache Performance of the Scheduled Dataflow Architecture

Joseph Arul, Krishna Kavi, Roberto Giorgi
2000 Journal of universal computer science (Online)  
The analytical analysis of our architecture showed that we could achieve a better performance than other classical dataflow architectures (i.e., ETS), hybrid models (e.g., EARTH) and decoupled multithreaded  ...  IA-64), superscalar and superspeculative architectures.  ...  Conclusions In this paper we presented a dataflow multithreaded architecture that utilizes controlflow like scheduling of instructions.  ... 
doi:10.3217/jucs-006-10-0948 dblp:journals/jucs/KaviAG00 fatcat:ayzfhn4jyra4jbhra6jpulqz6m

Beyond Dataflow

Borut Robi�, Jurij �ilc, Theo Ungerer
2000 Journal of Computing and Information Technology  
In particular, there has been active research and development in multithreaded architectures that evolved from the dataflow model.  ...  This paper presents some recent advanced dataflow architectures.  ...  MTA and EARTH The Efficient Architecture of Running Threads (EARTH) (Hum et al., 1994 and Maquelin, 1995) is based on the MTA (Multithreaded Architecture) and dates back to the Argument Fetch Dataflow  ... 
doi:10.2498/cit.2000.02.01 fatcat:3bonvcsg6jbnzj3uouzwkc5tcm

A Survey on Hardware and Software Support for Thread Level Parallelism [article]

Somnath Mazumdar, Roberto Giorgi
2016 arXiv   pre-print
Hence, hardware and software support for threads is more and more needed to improve peak-performance capacity, overall system throughput, and has therefore been the subject of much research.  ...  To support growing massive parallelism, functional components and also the capabilities of current processors are changing and continue to do so.  ...  Dataflow architecture had initially been introduced for ILP [Den80] and also was initially implemented in a form of "restricted dataflow" in a superscalar processor [HP86] .  ... 
arXiv:1603.09274v3 fatcat:75isdvgp5zbhplocook6273sq4

Article summaries

A.R. Hurson, K.M. Kavi, B. Shirazi, B. Lee
1996 IEEE Parallel & Distributed Technology Systems & Applications  
processing, which offers new alternatives in computer architecture design, and analyze cache memo y 's application to the dataflow environment. urrent microelectronics technology has enabled chip capacity  ...  Research efforts have long focused on the dataflow computation model, simple and elegant in describing parallelism and data dependencies.  ...  ACKNOWLEDGMENTS This work has been supported in part by the National Science Foundation under Grants MIP-9622836 and MIP-9622593.  ... 
doi:10.1109/88.544436 fatcat:gghokp44izf65ocixorvsnjix4

Inter-thread Communication in Multithreaded, Reconfigurable Coarse-grain Arrays [article]

Dani Voitsechov, Yoav Etsion
2018 arXiv   pre-print
In this paper we introduce direct inter-thread communications for massively multithreaded CGRAs, where intermediate values are communicated directly through the compute fabric on a point-to-point basis  ...  This method avoids the need to write values to memory, eliminates the need for a dedicated scratchpad, and avoids workgroup-global barriers.  ...  As part of this push, Voitsechov and Etsion introduced the massively multithreaded CGRA (MT-CGRA) architecture [6, 7] , which maps the compute graph of CUDA kernels to a CGRA and uses the dynamic dataflow  ... 
arXiv:1801.05178v1 fatcat:r3kop6qsvzgmdn4oe252d32ynq

Speculative multithreaded processors

G.S. Sohi, A. Roth
2001 Computer  
With this trend comes a renewed and increasing interest in multithreaded architectures.  ...  Speculative Multithreaded Processors S emiconductor technologies-along with innovative computer architectures-have provided the bricks and mortar for building phenomenal improvements in processing speed  ...  School, and by an Intel Foundation Graduate Fellowship.  ... 
doi:10.1109/2.917542 fatcat:fsdtjvtfsnheljrwckngvqg73m

VHDL Implementation of Scheduled Dataflow Architecture and the Impact of Efficient Way of Passing of Data

Joseph M. Arul, Han-Yao Ko, Hwa-Yuan Chung
2014 2014 World Congress on Computing and Communication Technologies  
Besides, this architecture comes as a new paradigm to closely link the ILP and TLP by combining the sequential and dataflow paradigm. This is named as Scheduled Dataflow Architecture (SDF).  ...  Besides, designing this new architecture using VHDL, the main focus of this architecture was a new way of passing of data in a multithreaded architecture.  ...  Such architecture is known as decoupled architecture. This particular architecture research combines dataflow, decoupled and non-blocking multithreaded concepts.  ... 
doi:10.1109/wccct.2014.62 fatcat:lvfkwguapbhybppc4casl3mjiq

An Approach for Direct Dataflow Execution on Contemporary Multicore Systems

Dumitrel Loghin, Bogdan Marius Tudor, Yong Meng Teo
2013 2013 Data-Flow Execution Models for Extreme Scale Computing  
• Traditional imperative programming models -Explicit and coarse-grain parallelism • Dataflow programming model -Implicit and fine-grain parallelism • Dataflow machines are not widely - Manchester Dataflow  ...  Machine (1985) -MIT Tagged-token Dataflow Architecture (1990) -Manchester Multi-ring Dataflow Simulation (1985) - MM(n) -matrix multiplication on square matrices of size n -PR(n) -prime number counting  ...  Conclusions • An approach for direct execution of dataflow programs on multicore systems -EDFG with node fusion optimizations with different task granularities -RDE for multithreaded direct EDFG execution  ... 
doi:10.1109/dfm.2013.9 fatcat:f6epppvymvd43iigo6pocuyore

Automatic run-time extraction of communication graphs from multithreaded applications

Ai-Hsin Liu, Robert P. Dick
2006 Proceedings of the 4th international conference on Hardware/software codesign and system synthesis - CODES+ISSS '06  
In a more ideal world, it would be possible to quickly and easily determine the run-time communication properties of large commercial and academic multithreaded applications.  ...  It presently supports the analysis of arbitrary multithreaded applications running on the Linux operating system. This software is called CETA. It is freely available for academic and non-profit use.  ...  The current release supports extraction of communication graphs from multithreaded Linux applications running on the Intel x86 architecture.  ... 
doi:10.1145/1176254.1176268 dblp:conf/codes/LiuD06 fatcat:n6ipslof7jh3fnpbbknd3zdili

Multithreaded Processors

T. Ungerer
2002 Computer journal  
This survey paper explains and classifies the various multithreading techniques in research and in commercial microprocessors and compares multithreaded processors with chip multiprocessors.  ...  The main approaches are the (single) chip multiprocessor and the multithreaded processor which optimize the throughput of multiprogramming workloads rather than single-thread performance.  ...  Another root of multithreading comes from dataflow architectures.  ... 
doi:10.1093/comjnl/45.3.320 fatcat:hlkkabuhrzhkrmuyqomzfmc6zm

The WaveScalar architecture

Steven Swanson, Andrew Schwerin, Martha Mercaldi, Andrew Petersen, Andrew Putnam, Ken Michelson, Mark Oskin, Susan J. Eggers
2007 ACM Transactions on Computer Systems  
To allow programmers to easily express parallelism, WaveScalar supports pthread-style, coarse-grain multithreading and dataflow-style, fine-grain threading.  ...  WaveScalar is a dataflow instruction set and execution model designed for scalable, low-complexity/high-performance processors.  ...  WaveScalar is a dynamic dataflow architecture. Dynamic dataflow architectures differ in how they manage and assign tags to values.  ... 
doi:10.1145/1233307.1233308 fatcat:va44t6ut4jbytjpzwl2zc5runa
« Previous Showing results 1 — 15 out of 1,676 results