Follow us Follow us Signalogic on LinkedIn
Home > HPC > CIM Accelerators

Server Accelerator Cards


 

Signalogic vs. Nvidia comparison. Shown above
are the SigC641x and Tesla C870 PCIe cards
  

On this page...

Related pages...

Overview

Server accelerator cards are intended to improve server performance, typically while offering some additional benefit such as saving space (same number of servers, no increase in rack space), limiting energy usage, increased privacy or security by avoiding external information transfer, etc. Without a server accelerator, the standard approach is to "throw more servers" at the problem -- which, while it may work -- incurs penalties in cost, space, energy, lack of security, etc.

There are generally four (4) categories of server accelerators:

Performance Accelerators

The most effective -- but most difficult to achieve -- type of accelerator is one that applies to a broad range of programs and applications. Signalogic's objectives are threefold:

The last objective is the most crucial. Linux developers are known by a somewhat fanatic devotion to open source software. Anything that requires Linux developers to detour from standard C/C++ programming under Linux -- for example learning the API of an application specific accelerator -- is typically not well-received. To do so would imply that specialized programmers are needed, code is difficult to maintain over time, and code may not be compatible with a wide range of servers. To avoid these issues, CIM arrays leverage OpenMP syntax, using that as a basis and extending it to take further advantage of CIM capabilities.

Heterogeneous CPU Solution

Performance accelerators rely on a "heterogeneous CPU solution", which refers to use of fundamentally different types of CPU in the same server. In the case of Nvidia, a GPU is combined with the host x86 (or ARM) CPU. CIM arrays use TI multicore CPUs. The goal is to combine CPU properties in a way that the end result is optimal, achieving a result greater than the sum. The situation is somewhat analogous to using heterogeneous metals (alloys) in super conductivity -- super conductivity itself was discovered in 1911, but optimal usage (getting it to work at room temperature) remains a sought-after breakthrough.

The technology of combining heterogeneous CPUs in one server and achieving an effective, easy-to-use solution is inherently difficult. Signalogic has several patents pending in this area.