| 1. |
- Arslan, Mehmet Ali, et al.
(författare)
-
Partitioning and Mapping Dynamic Dataflow Programs
- 2012
-
Ingår i: [Host publication title missing]. - 1058-6393. ; , s. 1452-1456
-
Konferensbidrag (refereegranskat)abstract
- Partitioning and mapping are important design decisions in exploiting the parallelism of programs that are to be run on systems with multiple processing elements. In this paper we introduce a fast, incremental approach for mapping dynamic dataflow programs to multiprocessor systems. We use causation traces and architecture descriptions as input for the mapping process that devises several heuristics for reaching a short makespan for the given trace. We evaluate our approach by comparing our results to two different lower bounds and another algorithm used often in solving mapping problems: simulated annealing.
|
|
| 2. |
|
|
| 3. |
- Cedersjö, Gustav, et al.
(författare)
-
Toward Efficient Execution of Dataflow Actors
- 2012
-
Ingår i: [Host publication title missing]. - 1058-6393. ; , s. 1465-1469
-
Konferensbidrag (refereegranskat)abstract
- Dataflow descriptions are a natural match to application areas such as signal processing, cryptography, networking, image processing, and media coding. This paper addresses the problem of efficiently executing the basic elements of a dataflow program, its actors, written in a language such as MPEG's RVC-CAL. Using actor machines as an execution model for dataflow actors, we devise a metric for measuring the quality of a translation in terms of program size and execution efficiency, and then build, evaluate and compare a number of translators with each other and prior art, using MPEG reference code as a benchmark.
|
|
| 4. |
- Christopoulos, Dimitrios, et al.
(författare)
-
Capacity Analysis of Multibeam Joint Decoding over Composite Satellite Channels
- 2011
-
Ingår i: Proc. of the 45th Asilomar Conference on Signals, Systems and Computer. - : IEEE Signal Processing Society. - 1058-6393. - 9781467303231
-
Konferensbidrag (refereegranskat)abstract
- The throughput of current multibeam satellite systemsis limited by self interference. Interference mitigationtechniques have the potential to significantly increase the spectralefficiency of these satellite communication systems. The presentcontribution investigates the ergodic capacity of the return linkof a multibeam satellite system, where full frequency reuse is employedand user signals are jointly processed at the gateway. Theproposed model incorporates correlated satellite antennas overRician channels which represent some inherent characteristics ofsatellite communications. Additionally, the effects of shadowingcaused by user mobility, are modeled via the lognormal distribution.Hence, a composite Rician/lognormal fading channel withfully correlated receive antennas is considered. For this channel, anew lower bound on the ergodic capacity is analytically deducedand verified through simulations.
|
|
| 5. |
- Di Taranto, Rocco, 1977, et al.
(författare)
-
Simultaneous Routing and Power Allocation using Location Information
- 2013
-
Ingår i: Conference Record - Asilomar Conference on Signals, Systems and Computers. - 1058-6393. - 9781479923908 ; , s. 1700-1704
-
Konferensbidrag (refereegranskat)abstract
- To guarantee optimal performance of wireless networks,simultaneous optimization of routing and resource allocationis needed. Optimal routing of data depends on the linkcapacities which, in turn, are determined by the allocation of communication resources to the links. Simultaneous routing and resource allocation (SRRA) problems have been studied under the assumption that (global) channel state information (CSI) is collected at a central node. This is a drawback as SRRA depends on channels between all pairs of nodes in the network, thus leading to poor scalability of the CSI-based approach. In this paper, we first investigate to what extent it is possible to rely solely on location information (i.e., position of nodes) when solving the SRRA problem. We also propose a distributed heuristic based onwhich nodes can locally adjust their rate based on the local CSI. Our numerical results show that the proposed heuristic achieves near-optimal flow in the network under different shadowing conditions.
|
|
| 6. |
- Etzlinger, B., et al.
(författare)
-
Cooperative Simultaneous Localization and Synchronization: A Distributed Hybrid Message Passing Algorithm
- 2013
-
Ingår i: Conference Record - Asilomar Conference on Signals, Systems and Computers. - 1058-6393. - 9781479923908 ; , s. 1978-1982
-
Konferensbidrag (refereegranskat)abstract
- Cooperative sensor self-localization (CSL) in wireless networks usually requires the nodes to be equipped with specific ranging hardware including ultra-wideband or ultrasonic distance sensors. Such designs are not suitable for application in low-cost, low-power sensor networks. Here, we demonstrate how low-cost, low-power, asynchronous sensor nodes can be used to perform CSL (and, simultaneously, distributed synchronization) by means of time-stamped communication without additional ranging hardware. Our method combines a belief propagation message passing algorithm for cooperative simultaneous localization and synchronization (CoSLAS) with a MAC-layer time stamping scheme.We validate the models underlying the CoSLAS algorithm by means of measurements, and we demonstrate that the localization accuracy achieved by our hardware implementation is far better than that corresponding to the time resolution and measurement errors of the hardware.
|
|
| 7. |
- Gao, Xiang, et al.
(författare)
-
Massive MIMO channels - measurements and models
- 2013
-
Ingår i: 2013 Asilomar Conference on Signals, Systems and Computers. - 1058-6393. - 9781479923908 ; , s. 280-284
-
Konferensbidrag (refereegranskat)abstract
- Spatial multiplexing using Massive MIMO has been shown to have very promising properties, including large gains in spectral efficiency and several orders of magnitude lower transmit power, as compared to today's access schemes. The properties of massive MIMO have been studied mostly for theoretical channels with independent and identically distributed (i.i.d.) complex Gaussian coefficients. To efficiently evaluate massive MIMO in more realistic scenarios, we need channel models that capture important massive MIMO channel characteristics. We pursue this by analyzing measurement data from a measurement campaign in the 2.6 GHz frequency range, using a physically large array with 128 elements. Key propagation characteristics are identified from the measurements. We use the cluster-based COST 2100 MIMO channel model as a basis, and propose an extension to include those important propagation properties for massive MIMO. Statistical models of the total number of clusters, their visibility regions and visibility gains at the base station side are found based on the measurement data.
|
|
| 8. |
|
|
| 9. |
- Gruian, Flavius
(författare)
-
Runtime Voltage/Frequency Scaling for Energy-Aware Streaming Applications
- 2012
-
Ingår i: Proceedings of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR). - 1058-6393. - 9781467350501 - 9781467350518 ; , s. 1439-1443
-
Konferensbidrag (refereegranskat)abstract
- Power and energy consumption, today essential in all types of systems, can be reduced by scaling the voltage/frequency at runtime and/or powering down idle components. Efficient management requires not only pertinent decisions, but also early access to workload information, as well as domain specific solutions. This paper focuses on runtime energy management for streaming applications running on multiprocessor platforms with dynamic voltage/frequency (speed) scaling capabilities. Our energy management occurs at processor level, and employs a number of orthogonal techniques based on hints gathered from load history, buffer pressure and future workload estimates. The manager operates both through speed adjustments and priorities. A preliminary evaluation based on a high-level simulation of an MPEG-4 SP decoder, shows that a combination of specific and generic techniques is the closest to an ideal energy lower bound.
|
|
| 10. |
- Janneck, Jörn
(författare)
-
A machine model for dataflow actors and its applications
- 2011
-
Ingår i: Proceedings of the 45th Annual Asilomar Conference on Signals, Systems, and Computers. - 1058-6393. ; , s. 756-760
-
Konferensbidrag (refereegranskat)abstract
- In application areas that process stream-like data such as multimedia, networking and DSP, the pipelined concurrent processing is frequently represented as a dataflow network of communicating computational kernels connected by FIFO queues. However, while dataflow is a natural medium for conceptualizing and modeling stream-processing systems, its adoption as a programming methodology has been hindered by an unappealing choice between expres- siveness and efficient implementability—efficient implemen- tation techniques being primarily limited to restricted sub- classes of dataflow programs. The paper presents a simple machine model for a very general class of dataflow programs and shows how it can be used as a foundation for their efficient implementation.
|
|
