pnnl / s-blas
This package includes the implementation for four sparse linear algebra kernels: Sparse-Matrix-Vector-Multiplication (SpMV), Sparse-Triangular-Solve (SpTRSV), Sparse-Matrix-Transposition (SpTrans) and Sparse-Matrix-Matrix-Multiplication (SpMM) for Single-node Multi-GPU (scale-up) platforms such as NVIDIA DGX-1 and DGX-2.
☆24Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for s-blas
- This package includes the implementation for Sparse-Matrix-Vector-Multiplication (SpMV) and Sparse-Matrix-Matrix-Multiplication (SpMM) fo…☆10Updated 4 years ago
- A Synchronization-Free Algorithm for Parallel Sparse Triangular Solves (SpTRSV)☆19Updated 4 years ago
- development repository for the open earth compiler☆77Updated 3 years ago
- CSR-based SpGEMM on nVidia and AMD GPUs☆45Updated 8 years ago
- LonestarGPU: Irregular algorithms parallelized for GPUs☆33Updated 5 years ago
- Parallelized and vectorized SpMV on Intel Xeon Phi (Knights Landing, AVX512, KNL)☆24Updated 9 months ago
- ☆37Updated this week
- Data-Centric MLIR dialect☆38Updated last year
- CUDA Flux is a profiler for GPU applications which reports the basic block executions frequencies of compute kernels☆31Updated 3 years ago
- ROC_SHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆41Updated last year
- CSR-based SpMV on Heterogeneous Processors (Intel Broadwell, AMD Kaveri and nVidia Tegra K1)☆26Updated 9 years ago
- A repository where GPU applications are aggregated using a common build flow that supports multiple CUDA versions.☆45Updated 2 months ago
- Performance Prediction Toolkit☆51Updated 3 years ago
- A pattern-based algorithmic autotuner for graph processing on GPUs.☆30Updated last year
- CUDAAdvisor: a GPU profiling tool☆48Updated 6 years ago
- Multiple 1-stencil implementations using nvidia cuda.☆13Updated 6 years ago
- Tartan: Evaluating Modern GPU Interconnect via a Multi-GPU Benchmark Suite☆60Updated 6 years ago
- A sparse BLAS lib supporting multiple backends☆40Updated this week
- ☆47Updated 5 years ago
- HeteroSync is a benchmark suite for performing fine-grained synchronization on tightly coupled GPUs☆27Updated 2 months ago
- Implementation of TSM2L and TSM2R -- High-Performance Tall-and-Skinny Matrix-Matrix Multiplication Algorithms for CUDA☆31Updated 4 years ago
- The Combinatorial BLAS (CombBLAS) is an extensible distributed-memory parallel graph library offering a small but powerful set of linear …☆69Updated last week
- A Benchmark Suite for Heterogeneous System Computation☆52Updated 3 weeks ago
- Multi-GPU dynamic scheduler using PGAS style cross-GPU communication☆27Updated last year
- A Method for efficiently processing SpMV using SIMD and load balancing☆16Updated 2 years ago
- SST Macro Element Library☆34Updated last month
- Official BOLT Repository☆28Updated 3 months ago
- SIMD-X: Programming and Processing of Graph Algorithms on GPUs [USENIX ATC '19]☆18Updated 4 years ago
- ☆41Updated 4 years ago