Accelerator Centric Computing

Introduction

Below is a set of notes that describe the main design choices for the ACC architecture, as discussed so far. There are more parameters and options which are not addressed here, and those which are, are not necessarily the result of consensus. Please contribute to this document, but maintain the structure.

Scratchpad Memory

  • Physically, in close proximity to the accelerators.
  • Shared among the accelerators of a tile - not unique (physically) to every accelerator
  • Limited in size, but can be relatively large (1MB?).
  • The implementation

A unified address space across scratchpad memories and main system memory. The library writer who wants to use an accelerator, would have to do something like this in their C code:

scratchpad<double> A[1024];

to the system programmer, it will appear as if the lowest parts of their address space are

Scratchpad memory appears to be mapped at a range of addresses of the physical main memory. The idea is similar to the address mapping between

Edit | Attach | Watch | Print version | History: r9 | r4 < r3 < r2 < r1 | Backlinks | Raw View | Raw edit | More topic actions...
Topic revision: r2 - 2010-03-02 - KonstantinosMenychtas
 
  • Edit
  • Attach
This site is powered by the TWiki collaboration platform Powered by PerlCopyright © 2008-2019 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding URCS? Send feedback