hipBLAS
alpaka
hipBLAS | alpaka | |
---|---|---|
3 | 1 | |
102 | 333 | |
4.9% | 1.8% | |
9.2 | 9.1 | |
3 days ago | about 4 hours ago | |
C++ | C++ | |
GNU General Public License v3.0 or later | Mozilla Public License 2.0 |
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.
hipBLAS
- A 100x speedup with unsafe Python
-
How do you build Apps with hipblas using CMake?
For example: the simple SGEMM example can be manually compiled in either platform simply as:
-
How do you build hipblas using CMake?
'm trying to build the SGEMM example in the library using CMake v3.16, but I'm just stuck ...
alpaka
-
Cross Platform GPU-Capable Framework?
Note that Kokkos uses CUDA, OpenMP and also SYCL in order to have a wide range of targets. I'd also suggest taking a look at Alpaka https://github.com/alpaka-group/alpaka which is similar in some ways.
What are some alternatives?
clspv - Clspv is a compiler for OpenCL C to Vulkan compute shaders
GLSL - GLSL Shading Language Issue Tracker
kompute - General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usecases. Backed by the Linux Foundation.
OpenCLOn12 - The OpenCL-on-D3D12 mapping layer
clvk - Implementation of OpenCL 3.0 on Vulkan
ParallelReductionsBenchmark - Thrust, CUB, TBB, AVX2, CUDA, OpenCL, OpenMP, SyCL - all it takes to sum a lot of numbers fast!
ginkgo - Numerical linear algebra software package
arbor - The Arbor multi-compartment neural network simulation library.
monolish - monolish: MONOlithic LInear equation Solvers for Highly-parallel architecture
parallel-kd-tree - Parallel k-d tree with C++17, MPI and OpenMP
Umpire - An application-focused API for memory management on NUMA & GPU architectures
aomp - AOMP is an open source Clang/LLVM based compiler with added support for the OpenMP® API on Radeon™ GPUs. Use this repository for releases, issues, documentation, packaging, and examples.