Design with Spartan™-3A DSP today!

Evaluate development tools built just for you:

• Algorithm developers: quickly target floating-point MATLAB algorithms to fixed-point logic on Xilinx devices using the AccelDSP™ & System Generator for DSP .
• System designers: define detailed hardware architectures using Xilinx IP and partition designs between co-processors and programmable devices using System Generator for DSP .
• Hardware engineers: generate optimized FPGA implementations using the ISE™ Foundation™ RTL design environment .

Breakthrough in Price for High Performance DSP

The new Spartan-3A DSP platform is ideal for cost sensitive DSP algorithmic and co-processing applications requiring significant DSP performance. The new Spartan-3A DSP platform consists of two devices, the 3SD3400A and the 3SD1800A. The 3SD3400A delivers over 30 GMAC/s (30 billion multiply accumulate operations per second) and up to 2,200 Mbps memory bandwidth at a volume price starting at under $45* while the 3SD1800A delivers over 20 GMAC/s for under $30* in a small-footprint package.

Now Power Efficient

The new power-efficient Spartan-3A DSP devices deliver 4.06 GMACs per mW of high performance signal processing capability.  Spartan-3A DSP devices deliver 50% static power savings (70% savings in suspend mode), when compared with similar non-low power devices. Dedicated DSP48A slices help keep dynamic power in Spartan-3A DSP devices inherently low.

This unprecedented price/performance and power efficiency breakthrough targets many price and enery sensitive applications.

*25K units/yr in late 2008

Why Use the Spartan-3A DSP?

The Spartan-DSP platform offers the most cost-efficient DSP devices from Xilinx with the new XC3SD3400A and XC3SD1800A devices that deliver over 30 GMAC/s and 2196 Mbps memory bandwidth. At the heart of the Spartan-3 DSP architecture is the XtremeDSP DSP48A slice that enables designers to optimize their complex design challenges.
The XtremeDSP DSP48A slices support many independent functions:

• Multiplier
• Multiplier-accumulator (MACC)
• Multiplier followed by an adder
• Three-input adder
• Barrel shifter
• Wide bus multiplexers
• Magnitude comparator
• Wide counter

You can also connect multiple DSP48A slices to form wide math functions, DSP filters, and complex arithmetic functions without the use of general FPGA fabric to:

• Use silicon efficiently
• Reduce power consumption
• Deliver very high performance