Hardware Parameters of Vliw Cores and Code Quality Factors Affecting Alias

نویسندگان

  • Roberto Costa
  • Marco Garatti
  • Erven Rohou
  • Stefano Crespi
چکیده

Recent studies have shown that the ability of disambiguating memory addresses (often referred to as alias analysis) gives concrete performance benefits to the compilation of C code for VLIW machines. This experimental research studies which factors, though external to alias analysis, strongly determine its impact on the performance of compiled code. These factors belong to two categories: architectural parameters of the target machine and optimizations performed by the compiler. Sensitivity analysis of the benefit coming from alias analysis as a function of these parameters was performed with an industrial compiler for a commercially available VLIW family and the main results are presented. Such results can help hardware designers to evaluate the need for memory disambiguation in order to fully exploit their architecture. On the other hand, once the target machine has been defined, the results can also help compiler writers to decide how much effort to invest in memory disambiguation.

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

Image Optimization in Single Photon Emission Computed Tomography by Hardware Modifications with Monte Carlo Simulation

Introduction: In Single Photon Emission Computed Tomography (SPECT), the projection data used for image reconstruction are distorted by several factors, including attenuation and scattering of gamma rays, collimator structure, data acquisition method, organ motion, and washout of radiopharmaceuticals. All these make reconstruction of a quantitative SPECT image very difficult. Simulation of a SP...

متن کامل

Code optimizations for a VLIW-style network processing unit

The explosive growth in network bandwidth and Internet services such as QoS (quality of service) and SLA (service level agreement) monitoring have created the need for new networking hardware called a Network Processing Unit (NPU). In order to rapidly reconfigure the NPU for frequently varying Internet services and technologies, a high-performance C compiler is urgently needed. Several code gen...

متن کامل

Implementing Hardware Multithreading in a VLIW Architecture

Hardware multithreading is a well-known technique to increase the utilization of processor resources. However, most studies have focused on superscalar processor organizations. This paper analyzes which type of hardware multithreading is most suitable for a VLIW architecture and proposes two buffers to increase the efficiency of hardware multithreading. An important goal of our work is that no ...

متن کامل

Automatic Design of VLIW and EPIC Instruction Formats

instruction format design, template design, instruction-set architecture, abstract ISA, concrete ISA, VLIW processors, EPIC processors, HPL-PD architecture, instruction encoding, bit allocation, affinity allocation, applicationspecific processors, design space exploration Very long instruction word (VLIW), and in its generalization, explicitly parallel instruction computing (EPIC) architectures...

متن کامل

Simultaneous MultiStreaming for Complexity-Effective VLIW Architectures

Very Long Instruction Word (VLIW) architectures exploit instruction level parallelism (ILP) with the help of the compiler to achieve higher instruction throughput with minimal hardware. However, control and data dependencies between operations limit the available ILP, which not only hinders the scalability of VLIW architectures, but also result in code size expansion. Although speculation and p...

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 2004