| 1. |
- Sander, Ingo, et al.
(author)
-
High-Level Estimation and Trade-Off Analysis for Adaptive Real-Time Systems
- 2009
-
In: 2009 IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL & DISTRIBUTED PROCESSING. - 9781424437511 ; , s. 2985-2988
-
Conference paper (peer-reviewed)abstract
- We propose a novel design estimation method for adaptive streaming applications to be implemented on a partially reconfigurable FPGA. Based on experimental results we enable accurate design cost estimates at an early design stage. Given the size and computation time of a set of configurations, which can be derived through logic synthesis, our method gives estimates for configuration parameters, such as bitstream sizes, computation mid reconfiguration times. To fulfil the system's throughput requirements, the required FIFO buffer sizes are then calculated using a hybrid analysis approach based on integer linear programming and simulation. Finally, we are able to calculate the total design cost as the sum of the costs for the FPGA area, the required configuration memory and the FIFO buffers. We demonstrate our method by analysing non-obvious trade-offs for a static and dynamic implementation of adaptivity.
|
|
| 2. |
- Zhu, Jun, et al.
(author)
-
Buffer Minimization of Real-Time Streaming Applications Scheduling on Hybrid CPU/FPGA Architectures
- 2009
-
In: DATE. - 9781424437818 ; , s. 1506-1511
-
Conference paper (peer-reviewed)abstract
- We address the problem of real-time streaming applications scheduling on hybrid CPU/FPGA architectures. The main contribution is a two-step approach to minimize the buffer requirement for streaming applications with throughput guarantees. A novel declarative way of constraint based scheduling for real-time hybrid SW/HW systems is proposed, while the application throughput is guaranteed by periodic phases in execution. We use a voice-band modem application to exemplify the scheduling capabilities of our method. The experimental results show the advantages of our techniques in both less buffer requirement and higher throughput guarantees compared to the traditional PAPS method.
|
|
| 3. |
- Zhu, Jun, et al.
(author)
-
Constrained Global Scheduling of Streaming Applications on MPSoCs
- 2010
-
In: 2010 15TH ASIA AND SOUTH PACIFIC DESIGN AUTOMATION CONFERENCE (ASP-DAC 2010). - 9781424457656 ; , s. 223-228
-
Conference paper (peer-reviewed)abstract
- We present a global scheduling framework for synchronous data flow (SDF) streaming applications on MPSoCs, based on optimized computation and contention-free routing. The global scheduling of processors computing and communication transactions are formulated as constraint based problem, to avoid the scheduling overhead in TDMA-like heuristic schemes. A public domain constraint solver is exploited to solve the NP-complete scheduling efficiently, together with problem specific constraint modeling techniques. Experimental results show that the proposed framework can achieve a high predictable application throughput with minimized buffer cost. For instance, for applications in communication domain, higher throughput (up to 87%) has been observed with less buffer cost, compared to scenarios considering the heuristic scheduling overhead.
|
|
| 4. |
- Zhu, Jun, et al.
(author)
-
Energy efficient streaming applications with guaranteed throughput on MPSoCs
- 2008
-
In: Proceedings of the 7th ACM International Conference on Embedded Software, EMSOFT 2008. - New York, NY, USA : ACM. - 9781605584683 ; , s. 119-128
-
Conference paper (peer-reviewed)abstract
- In this paper we present a design space exploration flow to achieve energy efficiency for streaming applications on MPSoCs while meeting the specified throughput constraints. The public domain simulators Sim-Panalyzer and Cacti are used to estimate the energy dissipations of the parameterized architectural components. As the main contributions, we schedule the streaming applications on a multi-clock synchronous modeling framework, guarantee the application timing properties by throughput analysis, and customize both processor voltage-frequency levels and memory sizes in the design space to optimize the application pipeline parallelism for energy efficiency. Two widely used heuristic algorithms (i.e., greedy and taboo search) are used during the design optimization process. Our experiments show an energy reduction of 21% without any loss in application throughput compared with an ad-hoc approach.
|
|
| 5. |
- Zhu, Jun, et al.
(author)
-
HetMoC : Heterogeneous Modeling in SystemC
- 2010
-
In: Proceedings of the Forum on Design Langauges (FDL). - : IET. - 9782953050431 ; , s. 117-122
-
Conference paper (peer-reviewed)abstract
- We propose a novel heterogeneous model-of-computation (HetMoC) framework in SystemC for embedded computing systems. As the main contribution, we formally define the computation and communication in multiple domains (continuous-time, discrete-event, synchronous/reactive, and untimed) as polymorphic processes and signals, and present domain interfaces to integrate different domains together for heterogeneous process networks. Especially, the continuous-time signals are defined with time continuum, which are distinguished from existing approaches. For implementation, a functional modeling style has been adopted to construct HetMoC. A solver with error estimation has been exploited in numerical approximation, and the time-varying functionalities in adaptive systems have been captured in HetMoC as well. In experiments, based on an adaptive transceiver system case study, HetMoC shows promising capabilities compared with a reference model in SystemC-AMS.
|
|
| 6. |
- Zhu, Jun, et al.
(author)
-
Pareto Efficient Design for Reconfigurable Streaming Applications on CPU/FPGAs
- 2010
-
In: Proceedings of Design Automation and Test in Europe (DATE ’10). - 9783981080162 ; , s. 1035-1040
-
Conference paper (peer-reviewed)abstract
- We present a Pareto efficient design method for multi-dimensional optimization of run-time reconfigurable streaming applications on CPU/FPGA platforms, which automatically allocates applications with optimized buffer requirement and software/hardware implementation cost. At the same time, application performance is guaranteed with sustainable throughput during run-time reconfigurations. As the main contribution, we formulate the constraint based application allocation, scheduling, and reconfiguration analysis, and propose a design Pareto-point calculation flow. A public domain solver - Gecode is used in solutions finding. The capability of our method has been exemplified by two cases studies on applications from media and communication domains.
|
|
| 7. |
- Zhu, Jun, et al.
(author)
-
Performance Analysis of Reconfiguration in Adaptive Real-Time Streaming Applications
- 2008
-
In: PROCEEDINGS OF THE 2008 IEEE/ACM/IFIP WORKSHOP ON EMBEDDED SYSTEMS FOR REAL-TIME MULTIMEDIA. - 9781424426126 ; , s. 53-58
-
Conference paper (peer-reviewed)abstract
- We propose a design optimization framework for adaptive real-time streaming applications. The main contribution is a hybrid approach for performance analysis combining formal analysis and simulation using a two-phase framework. We formulate the scheduling problem of adaptive streaming applications with ILP analysis, and use the simulation based on the synchronous model of computation to ensure throughput guarantees. We finally illustrate the capabilities of our methodology by experiments.
|
|
| 8. |
- Zhu, Jun, et al.
(author)
-
Performance Analysis of Reconfigurations in Adaptive Real-Time Streaming Applications
- 2012
-
In: ACM Transactions on Embedded Computing Systems. - : Association for Computing Machinery (ACM). - 1539-9087 .- 1558-3465. ; 11:1
-
Journal article (peer-reviewed)abstract
- We propose a performance analysis framework for adaptive real-time synchronous data flow streaming applications on runtime reconfigurable FPGAs. As the main contribution, we present a constraint based approach to capture both streaming application execution semantics and the varying design concerns during reconfigurations. With our event models constructed as cumulative functions on data streams, we exploit a novel compile-time analysis framework based on iterative timing phases. Finally, we implement our framework on a public domain constraint solver, and illustrate its capabilities in the analysis of design trade-offs due to reconfigurations with experiments.
|
|
| 9. |
- Zhu, Jun, et al.
(author)
-
SDF to Synchronous Cross Domain Analysis in ForSyDe Stream Processing Framework
- 2006
-
Conference paper (peer-reviewed)abstract
- Stream processing has been a very active field in parallel programming for its suitability to expressthe concurrent architecture in embedded systems. Caused by its concurrent reasoning features,stream programming frameworks are built on some abstract models of computation (MoCs) tohandle the complexity and unpredictability. To allow us focus on the essential issues of time,communication and synchronisation of the parallel tasks, the support from a sound heterogeneousMoCs framework to stream application system is still in need. ForSyDe is our high levelexecutable design framework to express multi-computational-models, based on stream processingconcept. It is a heterogeneous diagram to describe intricate application behaviors, and offers crossdomain analysis features to support multi-domains integration and optimization. A case study inForSyDe framework shows that the communication structure of a stream application in SDFdomain could be migrated to the synchronous domain without any extra work on its computationfunctions. To integrate it with our work on a communication based NoC simulator, we believesome more interesting design exploration work could be done on the analysis of communicationand computation efforts, besides power issues.
|
|
