High Performance Computing (HPC) application examples include data center and cloud processing such as video content delivery (to PCs, smart phones, and TV), optimizing telecom carrier network bandwidth, security applications (such as automated search of surveillance and UAV/drone video data), computer vision, bioscience research, and tasks such as climate modeling, particle physics simulations, and oil and gas exploration. Available as drop-in servers pre-configured with accelerators, accelerator(s) and/or software run-time license.
|Name or Standard/Profile||HPC Server Acceleration with CIM Software|
|Supported Tools/Features||-Supports ARM and other servers -Accelerates servers up to 500x -Half-length, single-slot PCI or PCIe card. Self-contained cooling. Power consumption 40-50W typical -Linux programmers use modified OpenMP syntax to annotate C/C++ source code and designate code sections for acceleration -Up to eight (8) concurrent acceleration threads, up to 256 data structures (e.g. channels, instances, etc) per thread -Transparent build process. Under Linux, TI CGT 7.2 or higher required. -Superset of OpenMP, CIM library includes offloading, application specific APIs, and more|
|eXpress DSP Compliant||No|
|Free Evaluation||Not Available|
Another advantage of CIM technology is as a means to protect your IP. Since the build process operates at the source code level, the CIM stream is not built with Gcc tools, is not linked with Linux libraries or drivers, and is not subject to GPL or other open source/free software licenses. When CIM code runs in executable form on the CIM array, it's running on hardware completely separate from the motherboard or ARM host. Whether third-party licenses apply depends solely on your source code content.
A list and links to documentation relevant to the solution, including schematics, board layout suggestions.
TI Product Family Experience
- C64x DSP
- DaVinci DM64x DSP
- C66x DSP
- Communications Equipment