Scribd
Upload
20 views2 pages

Fpga

The CORDIC algorithm efficiently computes various mathematical functions and has applications in DSP operations like DCTs and FFTs. FPGA architectures have evolved to support memory options that enhance DSP applications, transitioning from flip-flops to larger embedded SRAM memories. These advancements allow for better concurrency and flexibility in memory usage, benefiting high-speed applications such as image processing.

Uploaded by

pooja
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
20 views2 pages

Fpga

The CORDIC algorithm efficiently computes various mathematical functions and has applications in DSP operations like DCTs and FFTs. FPGA architectures have evolved to support memory options that enhance DSP applications, transitioning from flip-flops to larger embedded SRAM memories. These advancements allow for better concurrency and flexibility in memory usage, benefiting high-speed applications such as image processing.

Uploaded by

pooja
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd

CORDIC(Coordinate Rotation Digital Computer) algorithm is an area-

efficient technique for computing trigonometric, hyperbolic, and linear


functions.
First developed by Volder for circular coordinate systems and later unified
by Walther include linear and hyperbolic coordinate systems.
Functions as sinθ, cosθ,polar-to-rectangular and rectangular-to- polar
coordinate conversions, sinhθ, coshθ, and several other functions in its
unified form.
Formed basis for DSP operations as Discrete Co-sine Transforms (DCTs),
Fast Fourier Transforms (FFTs), sine-wave synthesis, computing
eigenvalue decompositions, and solving singular value problems.
• FPGA architectures have evolved, so options for memory also evolved
to favor DSP applications.
• On first FPGAs,only memory available was in form of flip-flops.Flip-
flops are abundant in most reconfigurable architectures, many
applications (especially image processing applications).
• Also FPGA have larger embedded SRAM memories flexibility in trading
depth for width and vice versa.
• Deep memories provide two memory ports for better concurrency.
Each of two ports can be driven by a different clock source & operate
with different memory aspect ratio.Larger memories are useful for
larger buffers & for high-speed, flexible FIFOs across clock domains.

You might also like