Jiqun Tu

Jiqun Tu received a PhD in physics on lattice QCD from Columbia University before joining NVIDIA as a senior compute developer technology engineer. At NVIDIA, he works on using the latest hardware and software features on the latest NVIDIA GPUs to accelerate a broad range of HPC applications.
Avatar photo

Posts by Jiqun Tu

Simulation / Modeling / Design

Constructing CUDA Graphs with Dynamic Parameters

Ever since its introduction in CUDA 10, CUDA Graphs has been used in a variety of applications. A graph groups a set of CUDA kernels and other CUDA operations... 7 MIN READ
Data Science

Running Python UDFs in Native NVIDIA CUDA Kernels with the RAPIDS cuDF

In this post, I introduce a design and implementation of a framework within RAPIDS cuDF that enables compiling Python user-defined functions (UDF) and inlining... 12 MIN READ