Single-Path Programming on a Chip-Multiprocessor System

نویسندگان

  • Martin Schoeberl
  • Peter Puschner
  • Raimund Kirner
چکیده

In this paper we explore a time-predictable chip-multiprocessor (CMP) system based on single-path programming. To keep the timing constant, even in the case of shared memory access for the CMP cores, the tasks on the cores are synchronized with the time-sliced memory arbitration unit. 1 The Single-Path CMP System The main goal of our approach is to build an architecture that provides a combination of good performance and high temporal predictability. We rely on chip-multiprocessing to achieve the performance goal and on an offline-planning approach to make our system predictable. The idea of the latter is to take as many control decisions as possible before the system is actually run. This reduces the number of branching decisions that need to be taken during system operation, which, in turn, causes a reduction of the number of possible action sequences with possibly different timings that need to be considered when planning respectively evaluating the system’s timely operation.

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

A Single-Path Chip-Multiprocessor System

In this paper we explore the combination of a time-predictable chipmultiprocessor system with the single-path programming paradigm. Time-sliced arbitration of the main memory access provides time-predictable memory load and store instructions. Single-path programming avoids control flow dependent timing variations. To keep the execution time of tasks constant, even in the case of shared memory ...

متن کامل

Real-time Processor Interconnection Network for FPGA-based Multiprocessor System-on-Chip (MPSoC)

This paper introduces a new approach for a network on chip (NOC) design which is based on a NlogN interconnect topology. The intended application area for the NOC is the real-time communication of multiprocessors that are hosted by a single Field Programmable Gate Array (FPGA). The proposed NOC is an on-chip multistage interconnection network for which an upper limit can be guaranteed that is a...

متن کامل

Low Latency on Chip Permutation Network for Multiprocessor System on Chip

This On-Chip Permutation Network for Multiprocessor System-On-Chip presents the silicon-proven design of a novel on-chip network to support guaranteed traffic permutation in multiprocessor system-on-chip applications the routing algorithm, the deflection routing is not energy-efficient due to the extra hops needed for deflected data transfer, compared to a minimal routing. Moreover, the deflect...

متن کامل

On Chip Permutation Network for Multiprocessor System on Chip

This On-Chip Permutation Network for Multiprocessor System-On-Chip presents the silicon-proven design of a novel on-chip network to support guaranteed traffic permutation in multiprocessor system-on-chip applications the routing algorithm, the deflection routing is not energy-efficient due to the extra hops needed for deflected data transfer, compared to a minimal routing. Moreover, the deflect...

متن کامل

An On-Chip Traffic Permutation Network for Multiprocessor System-On-Chip

The Networks on Chip (NoC), due to their flexibility, scalability and high bandwidth features they are considered as on-chip communication fabrics for future multiprocessor systemon-chips(MPSOCs).In this paper the design of a network on chip to support a guaranteed throughput is explained. The close nework topology is used with the three stages of switches and each stage having three switches o...

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 2009