Altera Demonstrates Industry's First Model-Based Floating-Point DSP Capabilities for FPGAs


Altera's New Highly-Efficient Floating-Point DSP Design Flow Validated by BDTI, Industry's Most Trusted Source of Independent DSP Technology Analysis

SAN JOSE, Calif., Sept. 12, 2011 - Altera Corporation (NASDAQ: ALTR) today demonstrated its new floating-point digital signal processing (DSP) design flow using FPGAs, the industry's first model-based floating-point design tool that allows implementation of complex floating-point DSP algorithms on an FPGA. Independent analysis conducted by Berkeley Design Technology, Inc. (BDTI) validates the high performance, efficiency and ease of implementing floating-point DSP designs in Altera's Stratix® and Arria® FPGA families.

The floating-point DSP design flow includes Altera's floating-point DSP compiler, which is integrated into the DSP Builder Advanced Blockset, Quartus® II RTL tool chain, and ModelSim simulator, as well as the MATLAB and Simulink tools from MathWorks to simplify the DSP algorithm-implementation process on FPGAs. The floating-point design flow combines and integrates the algorithm modeling and simulation, RTL generation, synthesis, place and route, and design verification stages. The integration enables quick development and rapid design-space exploration, both at the algorithmic level and at the FPGA level, and ultimately reduces overall design effort.

"Using Altera's high-level DSP model-based flow, designers can implement and verify complex floating-point algorithms more efficiently and quickly than would be possible with traditional HDL-based design," said Vince Hu, vice president of product and corporate marketing at Altera. "Once the algorithm is modeled and debugged at a high level, the design can be easily synthesized and targeted to any Altera FPGA."

Altera's new design flow is ideally suited to the demanding linear algebra problems typically requiring the dynamic range offered by floating-point DSP. BDTI benchmarked a parameterizable floating-point matrix-inversion design. Matrix inversion is representative of the type of processing used in radar systems, multiple-input, multiple output (MIMO) wireless systems, medical imaging and many other DSP applications.

In the evaluation of Altera's floating-point design flow, independent technology analysis firm BDTI stated, "Rather than building a datapath consisting of elementary floating-point operators..., the floating-point compiler generates a fused datapath that combines elementary operators into a single function or datapath. In doing so, it eliminates the redundancies present in traditional floating-point FPGA designs." BDTI concluded, "With the fused datapath methodology, complex floating-point datapaths are implemented with higher performance and efficiency than previously possible."

Read BDTI's complete FPGA floating-point DSP design flow analysis at www.altera.com/floatingpoint.

About Altera

Altera® programmable solutions enable system and semiconductor companies to rapidly and cost-effectively innovate, differentiate and win in their markets. Find out more about Altera's FPGA, CPLD and ASIC devices at www.altera.com. Follow Altera via Facebook, RSS and Twitter.

All Topics