The Plan-Du Style Compilation Technique for Eager Data Transfer in Thread-Based Execution

نویسندگان

  • Masahiro Yasugi
  • Satoshi Matsuoka
  • Akinori Yonezawa
چکیده

Plan-do compilation technique is a new, advanced compilation framework for eager data transfer on distributed-memory parallel architectures. The technique is especially eective for a recent breed of low-latency architectures by realizing a high-throughput low-latency communication scheme, pipelined sends. The compilation of high-level, plan-do style code into low-level, eager data transfer code is achieved via straightforward application of a set of translation rules. Preliminary low-level benchmark results on a real parallel architecture, EM-4, exhibit good speedups.

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

The Plan - Do Style Compilation Technique for Eager Data Transfer in Thread - Based Execution

Plan-do compilation technique is a new, advanced compilation framework for eager data transfer on distributed-memory parallel architectures. The technique is especially eective for a recent breed of low-latency architectures by realizing a high-throughput low-latency communication scheme, pipelined sends. The compilation of high-level, plan-do style code into low-level, eager data transfer code...

متن کامل

Reducing the overhead of dynamic compilation

The execution model for mobile, dynamically-linked, object–oriented programs has evolved from fast interpretation to a mix of interpreted and dynamically compiled execution. The primary motivation for dynamic compilation is that compiled code executes significantly faster than interpreted code. However, dynamic compilation, which is performed while the application is running, introduces executi...

متن کامل

Thread Integration for Error Detection and Performance

This paper presents a technique for integrating multiple threads of computation for simultaneous execution and which is well suited for fault-tolerant application programs. A post-pass compiler has been developed that is capable of taking the application program as the host thread and automatically integrating the additional code as a guest thread to produce a composite thread, the execution of...

متن کامل

Exploiting Thread-Level Speculative Parallelism with Software Value Prediction

Software value prediction (SVP) is an effective and powerful compilation technique helping to expose thread-level speculative parallelism. With the help of value analysis and profiling, the compiler identifies critical and predictable variable values and generates speculatively parallelized programs with appropriate value prediction and misprediction recovery code. In this paper, we examine thi...

متن کامل

Pipelined Query Processing in Coprocessor Environments

Query processing on GPU-style coprocessors is severely limited by the movement of data. With teraflops of compute throughput in one device, even high-bandwidth memory cannot provision enough data for a reasonable utilization. Query compilation is a proven technique to improve memory efficiency. However, its inherent tuple-at-a-time processing style does not suit the massively parallel execution...

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 1994