DSP/Veclib
by Sinectonalysis, Inc.

Software Overview

DSP/Veclib is high-performance run-time function library which provides over 300 hand-coded and 
ultra-optimized DSP and vector math functions, for tasks in image processing, radar, sonar signal 
processing, or graphics and scientific data analysis. After thorough verification and testing, the 
algorithms were implemented in `C30 and `C40 assembler to provide the absolutely fastest execution 
speed. Sinectonalysis' libraries are based on proprietary programming technology which uses 
software pipelining, minimizes register and memory access conflicts to give developers the maximum 
performance attainable with the TMS320 architecture. Algorithms are matched to the DSP chip 
internal pipeline architecture to keep the pipeline fully utilized at all times, to maximize 
throughput. The end result is a comprehensive suite of DSP and vector function building  blocks 
which enables software developers to implement DSP applications with maximum performance and 
minimum programming effort.

Features and Benefits

•	Highest TMS320C3x/'C4x performance available for C, C++, ADA, and Assembler
•	Minimizes use of size-limited memory sections, tips for speed in the manual.
•	Hand coded for maximum performance. Easy to use, build DSP programs quickly.
•	Universal—works with all environments and boards. Small modules.
•	Includes over 300 interruptible, relocatable, and re-entrant functions.

Processor and System Specifications

•	Devices supported: TMS320C3x, TMS320C4x, Run-Time DSP/Math Support Libraries
•	Languages supported: C, C++, ADA, Assember
•	Host platforms: PC, Sun, HP, DEC, RS6000, Mac, VAX, PowerPC, others

Algorithm Verification

•	This library and five other commercially-available libraries for the `C40 have been tested by 
systems integrator Hema Electronik GmbH (Aalen, Germany). The Hema test program used the 3L 
Parallel C compiler and a DSP board with a 40-MHz TMS320C40. All Hema tests were configured for a 
large memory model and parameter passing via the stack.
•	Hema concluded that the Sinectonalysis library is the fastest, best documented, and most 
comprehensive library and is based on the "most efficient code." Because of the work performed by 
Hema, the European community-supported ESPRIT project for Neural Network based Vision and Sensor 
Signal System for Industrial Quality Control (NEUROQUACS) has chosen a suite of Sinectonalysis 
libraries including DSP/Veclib for its development purposes. The NEUROQUACS team cited 
Sinectonalysis for its excellent performance, fast technical support, and functions which cover the 
widest task spectrum.
•	Also Spectrum Signal Processing has tested these libraries for ISO 9000 compliance.

Availability

•	Immediate

Company Background and Contact Information

Sinectonalysis, Inc. develops high-performance software for digital signal processors and 
parallel-processing environments for applications in signal processing, advanced algebra, image 
processing, and other scientific and engineering functions. The company specializes in optimizing 
algorithms and assembly code to take advantage of the TMS320C40 and TMS320C30 architectures. 
Sinectonalysis also offers consulting and code development services.
Contact:	Alexander Orenshteyn
		3702 S. Virginia St.
		Suite G-12 #164
		Reno, Nevada 89502-6034 
		(702) 345-0148
		Fax: (702) 345-0149
		e-mail: sinecto@clark.net