FastCuda is a handwritten CUDA operator library featuring progressive GEMM and Reduce kernels, cuBLAS benchmarking, and C/C++/Python interfaces for learning, profiling, and performance optimization.
-
Updated
Mar 18, 2026 - Cuda
#
spmm
Here are 11 public repositories matching this topic...
Sort: Most stars
Sort options
Fast SpMM implementation on GPUs for GNN (IPDPS'23)
-
Updated
Dec 31, 2023 - C++
Codes for DTC-SpMM (ASPLOS'24)
-
Updated
Jun 2, 2024 - C++
📚 Coursework for "Introduction to High Performance Computing" (30240192)
hpc homework cuda high-performance-computing coursework tsinghua tsinghua-university thu spmm thu-learn
-
Updated
Jun 21, 2022 - C++
Proof-of-concept implementation of a search engine that uses sparse matrix multiplication to identify the best peptide candidates for a given mass spectrum.
search search-engine gpu engine eigen cuda psm sparse identification proteomics mass-spectrometry spectrometry spmv peptide-identification mass spgemm peptide spmm
-
Updated
Dec 19, 2024 - C#
RA-SpMM: Regime-Aware Sparse Matrix Multiplication for GNN Workloads on GPUs. 8-rule router, 6 preprocessing-free kernels, 3.25x over cuSPARSE (FGCS 2026).
cuda benchmarks gpu-computing graph-neural-networks gnn spmm tensor-cores sparse-matrix-multiplication sparse-linear-algebra
-
Updated
Apr 30, 2026 - Python
Searching for peptide candidates using sparse matrix + matrix/vector multiplication.
search search-engine gpu engine eigen cuda psm sparse identification proteomics mass-spectrometry spectrometry spmv peptide-identification mass spgemm peptide spmm
-
Updated
Dec 19, 2024 - C++
Reproducible Instruction Roofline analysis of cuSPARSE and Ginkgo SpMM on RTX 4090 using Nsight Compute metrics.
-
Updated
May 13, 2026 - Cuda
Improve this page
Add a description, image, and links to the spmm topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the spmm topic, visit your repo's landing page and select "manage topics."