HPC from Python to Nim
summary
A speaker compares Python (NumPy) and Nim for a genetics preprocessing workload, showing how a Nim implementation on a Raspberry Pi can outperform NumPy on an Intel i7-7700K. The talk introduces Nim as a statically compiled language, steps through Nim-specific performance techniques (inlining, type usage, disabling bounds checks, OpenMP threading, compiler flags and algorithmic improvements), and concludes with benchmarks and practical tips for Python users moving to Nim for HPC.
AI-written summary · about
related talks
01h 33mPower up your work with compiling and profiling
55mAccelerated Python: The Community and Ecosystem
01h 06mBodo: Automatic HPC Performance and Scaling for Data Processing in Python
44mPython's Bright Future in Science
35mPython at the Speed of Light: A Complete Tour of the CUDA Ecosystem
30mNumba, a JIT compiler for fast numerical code
20mNumS: Scalable Array Programming for the Cloud
31m"Optimizing Scientific Python with C++, CUDA, and Serverless Compute"