Real-time Parallel Software Design Case Study: Implementation of the Rt-2dfft Benchmark on the Maspar Mp-x Architecture

نویسندگان

  • David P. Koester
  • Joseph J. Rushanan
چکیده

We extended and tested the MITRE real-time embedded scalable high performance computing benchmarking concept by implementing the RT_2DFFT benchmark on the MasPar MP-X series of massively parallel processors (MPPs). The RT_2DFFT benchmark specifies a symmetric two-dimensional fast Fourier transform (FFT) within a real-time software test bench. The test bench provides the realistic stimulus for the RT_2DFFT benchmark, including input/output (I/O) from/to onboard buffers. We developed a single RT_2DFFT implementation, heavily dependent on available library functions from MasPar, that can examine both benchmark latency specifications: latency equal to the period and latency greater than the period. Through the use of the MasPar RT_2DFFT benchmark implementation, we show that the MasPar MPPs can read a two-dimensional data set or input array from an I/O buffer, perform the two-dimensional FFT, and write the processed array out to an I/O buffer—all within the one second input array inter-arrival period specified in the benchmark. If latency is permitted to extend beyond one second, we show that it may be possible to reduce the machine size by processing sufficient multiple FFTs simultaneously, so that an entire row of a two-dimensional input array is assigned to a single processor. In this instance, the RT_2DFFT benchmark runs more efficiently, because communications overhead is minimized during both I/O and FFT processing.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Performance of Piston on the Ap1000

PISTON is a machine independent software framework for developing scientiic applications on parallel computers. It presents a consistent data-parallel distributed memory model across a wide range of architectures. It has been implemented on the Fujitsu AP1000 as well as on SIMD and SMP machines. This paper brieey describes the implementation of PISTON on the AP1000 and presents timing results a...

متن کامل

Integer-Encoded Massively Parallel Processing of Fast-Learning Fuzzy ARTMAP Neural Networks

In this paper we develop techniques that are suitable for the parallel implementation of Fuzzy ARTMAP networks. Speedup and learning performance results are provided for execution on a DECmpp/Sx-1208 parallel processor consisting of a DEC RISC Workstation Front-End (FE) and MasPar MP-1 Back-End (BE) with 8,192 processors. Experiments of the parallel implementation were conducted on the Letters ...

متن کامل

Proceedings of the Working Conference on Programming Models for Massively Parallel

This paper presents a portable parallel programming environment for Modula-2*, an explicitly parallel machine-independent extension of Modula-2. Modula-2* ooers synchronous and asynchronous par-allelism, a global single address space, and automatic data and process distribution. The Modula-2* system consists of a compiler, a debugger, a cross-architecture make, graphical X Windows control panel...

متن کامل

A Fast Parallel Implementation of the Wavelet Packet Best Basis Algorithm on the MP-2 for Real-Time MRI

Adaptive signal representations such as those determined by best-basis type algorithms have found extensive application in image processing, although their use in real-time applications may be limited by the complexity of the algorithm. In contrast to the wavelet transform which can be computed in O(n) time, the full wavelet packet expansion required for the standard best basis search takes O(n...

متن کامل

Strategies for the Implementation of Interconnection Network Simulators on Parallel Computers

Methods for simulating multistage interconnection networks using massively parallel SIMD computers are presented. Aspects of parallel simulation of interconnection networks are discussed and different strategies of mapping the architecture of the network to be simulated onto the parallel machine are studied and compared. To apply these methods to a wide variety of network topologies, the discus...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998