Integrating Data Caching into the SUDS Runtime System

نویسندگان

  • Kevin W. Wilson
  • Anant Agarwal
چکیده

In this thesis, I describe the design and implementation of a software data cache for speculative loads in the SUDS (Software Undo System) runtime system. The basic functionality of this cache exploits short-term temporal locality and some spatial locality in the memory accesses of speculative processing elements. The cache implementation is also extended to exploit temporal locality of accesses on a longer time scale. Using four sample applications, I compare the performance of the caching version of the SUDS runtime system to the performance of the original SUDS runtime system and to the performance of optimized sequential versions of the applications. With software data caching, the sample applications demonstrate speedups of 20% to 300% compared to SUDS without caching. In addition, software caching allows SUDS to demonstrate parallel speedups on three of the four applications. Thesis Supervisor: Anant Agarwal Title: Professor

برای دانلود 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

SUDS: automatic parallelization for raw processors

A computer can never be too fast or too cheap. Computer systems pervade nearly every aspect of science, engineering, communications and commerce because they perform certain tasks at rates unachievable by any other kind of system built by humans. A computer system’s throughput, however, is constrained by that system’s ability to find concurrency. Given a particular target work load the computer...

متن کامل

Offline Language-free Writer Identification based on Speeded-up Robust Features

This article proposes offline language-free writer identification based on speeded-up robust features (SURF), goes through training, enrollment, and identification stages. In all stages, an isotropic Box filter is first used to segment the handwritten text image into word regions (WRs). Then, the SURF descriptors (SUDs) of word region and the corresponding scales and orientations (SOs) are extr...

متن کامل

A Software Framework for Supporting General Purpose Applications on Raw Computation Fabrics

This paper presents SUDS (Software Un-Do System), a data speculation system for Raw processors. SUDS manages speculation in software. The key to managing speculation in software is to use the compiler to minimize the number of data items that need to be managed at runtime. Managing speculation in software enables Raw processors to achieve good performance on integer applications without sacrifi...

متن کامل

Neutrino: Revisiting Memory Caching for Iterative Data Analytics

In-memory analytics frameworks such as Apache Spark are rapidly gaining popularity as they provide order of magnitude performance speedup over disk-based systems for iterative workloads. For example, Spark uses the Resilient Distributed Dataset (RDD) abstraction to cache data in memory and iteratively compute on it in a distributed cluster. In this paper, we make the case that existing abtracti...

متن کامل

A Multithreaded Runtime System With Thread Migration for Distributed Memory Parallel Computing

Multithreading is very effective at tolerating the latency of remote memory accesses in distributed memory parallel computers, but does nothing to reduce the number or cost of those memory accesses. Compiler techniques and runtime approaches, such as caching remote memory accesses and prefetching, are often used to reduce the number of remote memory accesses. Another approach to reduce the numb...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014