Cache Coherent Shared Memory under Split - C CS 258 , Spring 1999 Final Report

نویسنده

  • Ronny Krashinsky
چکیده

Split-C is a single program, multiple data (SPMD) programming language. Split-C provides the ability to use a shared address space abstraction on a distributed shared memory (DSM) system, such as a network of workstations (NOW). The existing Split-C compiler translates all references to shared variables owned by another processor into network transactions. We implement SWCC-Split-C, a modified Split-C compiler which automatically caches remote accesses to avoid redundant network transactions. Our cache coherence system is implemented entirely in software. It uses a directory system and a simple MSI coherence protocol to provide cache coherence with blocks of fine granularity. We demonstrate significant improvements for programs with redundant remote memory accesses, and programs with spatial locality in remote accesses. Our SWCC-Split-C compiler is ideally suited to irregular applications with access patterns which are difficult to predict.

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

Type Data tra c Replacement tra c Coherence tra cUMA

Shared-bus multiprocessors represent a mainstream of accepted and commercially viable computer systems. However, as microprocessors become faster and demand more bandwidth, the already limited scalability of shared-bus decreases even further. As an eeort, not a mutually exclusive but rather a complementary to developing better backplane bus, this paper considers adapting distributed shared-memo...

متن کامل

Design and Performance of SMPs With Asynchronous Caches

Asynchronous, cache coherence, shared-memory multiprocessor, SMP We propose and evaluate a cache-coherent symmetric multiprocessor system (SMP) based on asynchronous caches. In a system with asynchronous caches, processors and memory controllers may observe the same coherence request at different points in time. All protocol transactions are unidirectional and processors do not report snoop res...

متن کامل

CCHIME: A Cache Coherent Hybrid Interconnected Memory Extension

This paper presents a hybrid shared memory architecture which combines the scalability of a multistage interconnection network with the contention reduction benefits of coherent caches. We achieve this by replacing the memory modules and final stages of a multistage interconnection network with clusters of coherent caches. The performance of Cache Coherent Hybrid Interconnected Memory Extension...

متن کامل

Fault-Tolerance Using Cache-Coherent Distributed Shared Memory Systems

In this paper, we describe new protocols augmenting traditional cache coherency mechanisms to implement fault-tolerance based on Recovery Blocks and checkpointing. Concurrent processes compound rollback recovery since the rollback can potentially lead to a "domino-effect" whereby the process is rolled back to the beginning. Several approaches have been proposed to limit the domino effect. One s...

متن کامل

Design of a Simulator for Large-Scale Distributed Shared-Memory Cache-Coherent Architectures

As the scale and the complexity of parallel computer systems grow rapidly, the study of interactions between application algorithms and parallel architectures becomes more important. Execution-driven simulation under realistic workloads proves to be an accurate and eecient technique for studying the performance of computer systems. However, direct-execution simulation of shared-memory cache-coh...

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 1999