Cymric: A Framework for Prototyping Near-Memory Architectures

نویسندگان

  • Chad D. Kersey
  • Sudhakar Yalamanchili
  • Hyesoon Kim
چکیده

Over the past two years, a prototyping infrastructure has grown up around CHDL; a C++ library for designing and simulating hardware, and HARP; a family of instruction set architectures for data parallel computing. Among the fruits of this effort are several processor cores, including a singleinstruction-multiple-thread implementation of HARP called Harmonica and a variety of FPGA and simulation oriented memory system components. Collectively, these pieces form Cymric, an infrastructure for prototyping near-memory processor architectures. Here, we report on the current status of our efforts, enumerating the software and hardware components produced and discussing the tools we have found indispensable in their production.

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

Rapid Prototyping of Dataflow Programs on Hardware/Software Architectures

In this paper, the problem of automatically mapping large-grain data ow programs onto heterogeneous hardware/software architectures is treated. Starting with a given hardware/software partition, interfaces are inserted into the speci cation to account for communication, in particular across hardware/software boundaries. Depending on the target architecture, the interfaces are re ned according t...

متن کامل

Rapid Prototyping of Data ow Programs on Hardware/Software Architectures

In this paper the problem of automatically mapping large grain data ow programs onto heterogeneous hard ware software architectures is treated Starting with a given hardware software partition interfaces are in serted into the speci cation to account for communi cation in particular across hardware software bounda ries Depending on the target architecture the inter faces are re ned according to...

متن کامل

RPM: A Rapid Prototyping Engine for Multiprocessor Systems

In multiprocessor systems, processing nodes contain a processor, some cache and a share of the system memory, and are connected through a scalable interconnect. The system memory partitions may be shared (shared-memory systems) or disjoint (messagepassing systems). Within each class of systems many architectural variations are possible. Fair comparisons among systems are difficult because of th...

متن کامل

Rpm: a Rapid Prototyping Engine for Multiprocessor Systems1

In multiprocessor systems, processing nodes contain a processor, some cache and a share of the system memory, and are connected through a scalable interconnect. The system memory partitions may be shared (shared-memory systems) or disjoint (messagepassing systems). Within each class of systems many architectural variations are possible. Fair comparisons among systems are difficult because of th...

متن کامل

Maya: A Simulation Platform for Parallel Architectures and Distributed Shared Memories

Maya is a simulation platform for evaluating the performance of parallel programs on parallel architectures with di erent memory coherence protocols. It uses the communication library PVM to ensure portability. Rapid prototyping of di erent memory protocols of varying degrees of coherence is possible and the impact of these protocols on the performance of application programs can be studied. We...

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 2015