ROCm-Simulation 25.10 Release notes#
2 min read time
This is the initial release of the AMD ROCm Simulation Domain toolkit (ROCm-Simulation), a comprehensive open-source software collection designed to accelerate physics-based and numerical simulations on AMD GPUs. This release introduces two components; Taichi Lang and GSplat.
Release highlights#
This release introduces the following ROCm-enabled components:
Taichi Lang is an open-source, imperative, parallel programming language for high-performance numerical computation. It is embedded in Python and uses just-in-time (JIT) compiler frameworks (such as LLVM) to offload the compute-intensive Python code to the native GPU or CPU instructions.
GSplat (Gaussian splatting) is a highly efficient technique for real-time rendering of 3D scenes trained from a collection of multiview 2D images of the scene. It has emerged as an alternative to neural radiance fields (NeRFs), offering significant advantages in rendering speed while maintaining visual quality.
System requirements#
Note
For the 25.10 release, the ROCm-Simulation components must be installed separately and have unique hardware requirements. See installation instructions to proceed for each component. See support and versioning information in the compatibility matrix.
ROCm-Simulation components#
The following table lists the ROCm-Simulation component version for the 25.10 release. Click to go to the component’s source code on GitHub.
| Name | Version | |
|---|---|---|
| Taichi Lang | 1.8.0b1 | |
| GSplat | 1.5.3b1 |