Need info on systolic arrays in actual use

I need some references of where systolic arrays have actually been used in equipment or instruments.

Thanks in advance,

Marco ________________________ Marc Reinig UCO/Lick Observatory Laboratory for Adaptive Optics

Reply to
Marc Reinig
Loading thread data ...

- smith waterman algorithm for DNA matching

- fully parallel filters, mainly FIR filters

- all algorithms without feedback if implemented using pielining (pipelined array multipliers, benes sorters, ...)

Kolja Sulimma

Reply to
Kolja Sulimma

Thanks,

I know the applications.

I'm actually looking for specific equipment in which they have been used. i.e. XY corp. uses them in their ..., Univ. of X uses them in the XXX instrument, etc.

Marco ________________________ Marc Reinig UCO/Lick Observatory Laboratory for Adaptive Optics

Reply to
Marc Reinig

The problem is, that in many cases the publications do not clearly state whether a systolic algorithm is used. You can only assume that any problem that can be solved by systolic algorithms will be solved by systolic algortithms if done in hardware.

A recent one:

formatting link

Kolja

Reply to
Kolja Sulimma

Thanks Kolja,

Marco ________________________ Marc Reinig UCO/Lick Observatory Laboratory for Adaptive Optics

Reply to
Marc Reinig

I previously gave the best references I could find to the Paracel machines.

The FDF (Fast Data Finder) originated with TRW for text searching and development was continued by Paracel. A patent search for FDF should find that. The FDF2 used an 8 processor element/chip ASIC.

GeneMatcher is/was a Paracel product for DNA and protein sequence comparison, also an ASIC based systolic array. The processor unit is much more complicated than the FDF, especially with the included result processors. Within the array between every eight data processors is logic for collecting results and saving them for later analysis.

For FPGA based systolic arrays, there is Time Logic.

formatting link

-- glen

Reply to
glen herrmannsfeldt

There was also Princeton's PNAC by Lopresti in this area. And all the work by Kung in the 1980s (iWARP). Also see the Application Specific Array Processors (ASAP) conference for ongoing work (

formatting link
).

-- Steve

-- 3/11/08

Reply to
Steven Guccione

I remember from my student time Systola 1024 boards. Afaik there were some papers done with real applications (e.g. DNA Sequencing). I am too lazy to dig that old stuff out, but google "Systola 1024" should reveal some stuff.

Florian

Reply to
Florian Stock

ElectronDepot website is not affiliated with any of the manufacturers or service providers discussed here. All logos and trade names are the property of their respective owners.