Differences between rocRand and cuRand when using HIP

In cuRand, the state of an RNG is a plain struct e.g. for XORWOW: struct curandStateXORWOW { unsigned int d, v[5]; int boxmuller_flag; int boxmuller_flag_double; float boxmuller_extra; double boxmuller_extra_double; }; whereas, in rocRand, the implementation is a lot more C++: class xorwow_engine { public: struct xorwow_state { unsigned int d; #ifndef ROCRAND_DETAIL_BM_NOT_IN_STATE …



GSoC_summary

This project will convert Macaque auditory thalamocortical circuits model based on NetPyNE implementation into NeuroML standard formats and testing it across multiple simulation engines to ensure that it produce the same results. First, I converted the morphology and ion channels for almost all neurons in the Macaque_auditory_thalamocortical_model. The conversions for …



Learning_HPC

This article is used to record the resources and projects for my HPC learning. Parallel_Computing CUDA CUDA_Chinese HIP ISPC MPI OpenMP NEURON GeNN EDEN Arbor



Hello World!

I am Hengye Zhu, a contributor of Google Summer of Code Program. It is a great honor to be selected for the 2025 GSoC_INCF Project 12: Developing Standardised Biophysically Detailed Neuronal Circuit Models Using NeuroML. As I dive into this project, I'll be documenting my experiences, challenges, and learnings here …