Texas Instruments TMS320

From Wikipedia, the free encyclopedia

Texas Instruments TMS320 is a blanket name for a series of digital signal processors (DSPs) from Texas Instruments. It was introduced on April 8, 1983 through the TMS32010 processor, which was then the fastest DSP on the market.

The processor is available in many different variants, some with fixed-point arithmetic and some with floating point arithmetic. The floating point DSP TMS320C3x, which exploits delayed branch logic, has as many as three delay slots.

The flexibility of this line of processors has led to it being used not merely as a co-processor for digital signal processing but also as a main CPU. They all support standard IEEE JTAG control for development.

The original TMS32010 and its subsequent variants is an example of a CPU with a so-called "modified" Harvard architecture, which features separate address and data memory. The TMS32010 featured a fast multiply-and-accumulate useful in both DSP applications as well as transformations used in computer graphics. The graphics controller card for the Apollo Computer DN570 Workstation, released in 1985, was based on the TMS32010 and could transform 20,000 2D vectors/second.

Contents

[edit] Variants

The TMS320 architecture has been around for a while so a number of product variants have developed. The product codes used by Texas Instruments after the first TMS32010 processor have involved a very popular series of processor named TMS320Cabcd where a is the main series, b the generation and cd is some custom number for a minor sub-variant.

For this reason people working with DSPs often abbreviate a processor as "C5x" when the actual name is something like TMS320C5510, since all products obviously have the name "TMS320" and all processors with "C5" in the name are code compatible and share the same basic features. Sometimes you will even hear people talking about "C55x" and similar subgroupings, since processors in the same series and same generation are even more similar.

  • Outside the main series:
    • TMS320C1x, the first generation 16-bit fixed point DSPs. All processors in these series are code compatible with the TMS32010
      • TMS32010, the very first processor in the first series introduced in 1983, using external memory
      • TMS320M10, the same processor but with an internal ROM of 3KB
      • TMS320C10, TMS320C15 etc.
    • TMS320C3x, floating point
      • TMS320C33
    • TMS320C4x, floating point
    • TMS320C8x, multiprocessor chip
      • TMS320C80 MVP (multimedia video processor) has a 32 bit floating point "master processor" and four 32-bit fixed-point "parallel processors", similar in many ways to the Cell microprocessor.
  • TMS320 C2000 series, or TMS320C2x, fixed point
  • TMS320 C5000 series, or TMS320C5x: , fixed point
    • TMS320C55x generation - fixed point used in some OMAP chips
  • TMS320 C6000 series, or TMS320C6x:
    • TMS320C62x fixed point
    • TMS320C64x fixed point - code compatible with TMS320C62x
    • TMS320C67x floating point - code compatible with TMS320C62x
  • OMAP variants, these also have an ARM processor in the same chip, see main article on Texas Instruments OMAP. (There are also OMAP processors with other secondary processors, so these are not necessarily DSPs.)
  • DA variants (target "Internet audio")
  • DM variants:
    • DM270 has an ARM7TDMI core and a TMS320 C5409 DSP
    • DM320 has an ARM926 core and a TMS320 C5409 DSP
    • DSC25 has an ARM7TDMI core and a TMS320 DSP

[edit] Toolchain

The TMS320 series can be programmed using C, C++, and/or assembly language. Most work on the TMS320 processors is done using Texas Instruments proprietary toolchain and their integrated development environment Code Composer Studio, which includes a mini operating system called DSP/BIOS. Additionally, a department at the Chemnitz University of Technology has developed preliminary support for the TMS320C6x series in the GNU Compiler Collection.[1]

[edit] References

  1. ^ Jan Parthey and Robert Baumgartl, Porting GCC to the TMS320-C6000 DSP Architecture, Appeared in the Proceedings of GSPx’04, Santa Clara, September 2004, [1]

[edit] External links