keyboard_arrow_up

High Performance Application-Optimised Microcontrollers

In order to get a competitive edge, product developers continue to look for new and ingenious ways to solve the various engineering problems that they face – so that they can improve system performance and simultaneously simplify the deployment process. Semiconductor manufacturers need, more than ever before, to present the industry with something that has unique value and distinguishes itself from the on-going convergence upon a very limited number of platforms. 

Conventional DMA architectures or a memory-move instructions used in most data intensive applications (such as video processing), require a large overhead to manage the transfer process. An innovative new architecture is now being implemented, however, where each peripheral within a system contains a limited memory to expedite faster data transport when instructions being are executed. This enables a marked reduction in the associated overhead and means that the processor core performs at very high rates with minimal interrupts. Thanks to an architecture of this kind, the inclusion of DMA to processor blocks can be avoided, so that computational results are streamed directly to the designated end point – with the upshot that zero wait state operation is possible and higher data throughput in less clock cycles are thereby witnessed.

  With the release of the FT900 high performance microcontroller, FTDI Chip has been able to demonstrate the benefits of this sort of architecture. The device has a 32-bit RISC core, which is extremely well suited to video and audio processing tasks. Because these tasks generally rely on recurring operations, the architecture employed has been optimised specifically to provide developers with a highly efficient data transport mechanism that is far more effective and less cumbersome than conventional memory-move instructions or DMA architecture implementations. This streaming mechanism is composed of a single 32-bit instruction set that enables rapid data movement to be carried out to/from the memory to the connected peripherals. It contains source, destination and size information within the instruction set.

The new FT900 application-optimised microcontroller from FTDI Chip, thanks to its proprietary streaming architecture and targeted instruction set, is able to achieve Drhystone MIPS (DMIPS) benchmarks that outstrip those of rival processor cores, including the latest ARM Cortex products.

More information : http://www.ftdichip.com/MCU.html