Project Triton: towards Improved Programmability of Parallel Computers Compilation Techniques. Triton/1 Parallel Architecture
نویسندگان
چکیده
This paper appeard in: The main objective of Project Triton is adequate programmability of massively parallel computers. This goal can be achieved by tightly coupling the design of programming languages and parallel hardware. The approach taken in the Project Triton is to let high-level, machine independent parallel programming languages drive the design of parallel hardware. This approach permits machine-independent parallel programs to be compiled into eecient machine code. The main results are as follows: Modula-2*. This language extends Modula-2 with constructs for expressing a wide range of parallel algorithms in a portable, problem-oriented, and readable way. We present techniques for the eecient translation of Modula-2* and similar imperative languages for several modern parallel machines and derive recommendations for future parallel architectures. Triton/1 is a scalable mixed-mode SIMD/MIMD parallel computer with a highly eecient communications network. It overcomes several deeciencies of current parallel hardware and adequately supports high-level parallel languages.
منابع مشابه
Triton / 1 : A Massively - Parallel Mixed - Mode ComputerDesigned to Support High Level
We present the architecture of Triton/1, a scalable, mixed-mode (SIMD/MIMD) parallel computer. The novel features of Triton/1 are: Support for high-level, machine-independent programming languages; Fast SIMD/MIMD mode switching; Special hardware for barrier synchronization of multiple process groups; A self-routing, deadlock free perfect shuue interconnect with latency hiding. The architecture ...
متن کاملTriton A Massively Parallel Mixed Mode Computer Designed to Support High Level Languages
We present the architecture of Triton a scalable mixed mode SIMD MIMD parallel computer The novel features of Triton are Support for high level machine independent pro gramming languages Fast SIMD MIMD mode switching Special hardware for barrier synchronization of multiple process groups A self routing dead lock free perfect shu e inter connect with latency hiding The architecture is the outcom...
متن کاملForward Position Kinematics of a Parallel Manipulator with New Architecture
The forward position kinematics (FPK) of a parallel manipulator with new architecture supposed to be used as a moving mechanism in a flight simulator project is discussed in this paper. The closed form solution for the FPK problem of the manipulator is first determined. It has, then, been shown that there are at most 24 solutions for FPK problem. This result has been verified by using other tec...
متن کاملA Comparative Study of the Programmability of a Signal Processing Application in an MIMD and an SIMD Multiprocessor
In this report, we address the issues of compilation and execution of a functional program, SISAL (Streams and Iterations in a Single Assignment Language), on the MP-1TM SIMD (Single Instructionstream Multiple Data-stream) parallel machine. SISAL has been successful on many shared memory multiprocessors (SMM) as well as sequential machines. However, the compiler has not been available for distr...
متن کاملذخیره 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 1994