rocThrust
rocPRIM
rocThrust | rocPRIM | |
---|---|---|
2 | 1 | |
91 | 145 | |
- | 4.8% | |
8.3 | 8.5 | |
8 days ago | 6 days ago | |
C++ | C++ | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
rocThrust
- Nvidia in the Valley
-
Would out-of-box support for GPU/OpenCL/CUDA execution policy for parallel operations be useful?
Of course NVIDIA isn't going to advertise or add ROCm support to their library, but AMD made the (genius economically speaking, albeit this made NVIDIA folks understandably angry) decision to just fork Thrust into rocThrust, since it is open source.
rocPRIM
-
Nvidia in the Valley
> AMD doesn't have a library of warp-level/kernel-level/global "software primitives" like Cuda Unbound or Thrust either.
The ROCm software primatives library is rocPRIM and the ROCm equivalent to Thrust is rocThrust.
https://github.com/ROCmSoftwarePlatform/rocPRIM
What are some alternatives?
hipCUB - Reusable software components for ROCm developers
core - Decentralized Fog Computing Platform
ssgl - single source shaders for opengl
AdaptiveCpp - Implementation of SYCL and C++ standard parallelism for CPUs and GPUs from all vendors: The independent, community-driven compiler for C++-based heterogeneous programming models. Lets applications adapt themselves to all the hardware in the system - even at runtime!
Bolt - Bolt is a C++ template library optimized for GPUs. Bolt provides high-performance library implementations for common algorithms such as scan, reduce, transform, and sort.
alpaka - Abstraction Library for Parallel Kernel Acceleration :llama:
stdgpu - stdgpu: Efficient STL-like Data Structures on the GPU