KMLM List

[Torsten Mähne <Torsten.Maehne@xxxxxx>]

Hello Martin,

due to the discrete event model of computation implemented in the SystemC 
kernel, it is difficult to parallelize the execution of a SystemC simulation, 
as a central scheduler is required. However, by applying TLM techniques and 
some other coding guidelines, it is possible to profit of multi-core machines 
during simulation using a parallel simulation engine, called SystemC-SMP. 
Details can be found in the following paper, which has been published in DATE 
2010 conference in Dresden, Germany:


Parallel Simulation of SystemC TLM 2.0 Compliant MPSoC on SMP Workstations [p. 
606]
A. Mello, I. Maia, A. Greiner and F. Pecheux

The simulation speed is a key issue in virtual prototyping of Multi-Processors 
System on Chip (MPSoCs). The SystemC TLM2.0 (Transaction Level Modeling) 
approach accelerates the simulation by using Interface Method Calls (IMC) to 
implement the communications between hardware components. Another source of 
speedup can be exploited by parallel simulation. Multi-core workstations are 
becoming the mainstream, and SMP workstations will soon contain several tens of 
cores. The standard SystemC simulation engine uses a centralized scheduler, 
that is clearly the bottleneck for a parallel simulation. This paper has two 
main contributions. The first is a general modeling strategy for shared memory 
MPSoCs, called TLM-DT (Transaction Level Modeling with Distributed Time). The 
second is a truly parallel simulation engine, called SystemC-SMP. First 
experimental results on a 40 processor MPSoC virtual prototype running on a 
dual-core workstation demonstrate a 1.8 speedup, versus a sequential simulation.

Keywords MPSoC, Parallel Simulation, SystemC, SMP workstations

<http://www.date-conference.com/proceedings/PAPERS/2010/DATE10/HTMFILES/FRAMES/DATEABS.HTM#IP2_03>


Best regards,

Torsten

Am 19.10.2010 um 01:18 schrieb martin:

> Sir,
>  
> I am looking parallel systemc kernel to speed up the simulation since
> we encounter very long simulation time although we have multiple-core 
> machines.
> Do you know where I can find any commercial tools or open source tools for
> parallel systemc kernels?
>  
>  
> Sincerely,
> Martin Chang
> Huawei Technolgies
> 2330 Central Expressway,
> Santa Clara, CA 95050
> Phone: (408)330-4785
> Fax:     (408)330-5088
>