Sep 5, 2019 · Artificial Intelligence

Implementing Bilinear Interpolation on FPGA for Neural Network Acceleration

The article explains the principles of bilinear interpolation, why it is needed for smooth image scaling in neural‑network layers such as Interp and Resize, and details FPGA‑specific optimizations—including lookup‑table based coefficient pre‑computation, two‑line BRAM caching, and index‑driven data swapping—to reduce DSP usage and improve throughput.

BRAMBilinear InterpolationDSP

0 likes · 14 min read

Implementing Bilinear Interpolation on FPGA for Neural Network Acceleration

Java High-Performance Architecture

Feb 1, 2016 · Frontend Development

Is Switch Faster Than a Lookup Table in JavaScript? A 50,000-Iteration Test

After reading 'High-Performance JavaScript', I tested the speed of a switch statement versus a lookup table over 50,000 iterations, finding the switch slightly faster contrary to the book’s claim, and reflecting on the practical benefits of lookup tables such as clearer code and easier maintenance.

Code OptimizationJavaScriptLookup Table

0 likes · 3 min read

Is Switch Faster Than a Lookup Table in JavaScript? A 50,000-Iteration Test