PyTorch-Based Fast and Efficient Processing for Various Machine Learning Applications with Diverse Sparsity

PyTorch Memory Efficient Sparse Sparse Matrix Multiplication

Sparse Matrix Computations in CUDA

Parallel Sparse Matrix Multiplication via CUDA

Code for Sparse Matrix and Vector multiplication. Parallelised using CUDA and MPI

CUDA sparse binary 2-D FFT with compact CSC input, Bluestein transforms, and cuFFT/SpFFT baselines.

CUDA SpMV kernels (scalar, warp-per-row, ELL) on NVIDIA A100 benchmarked against cuSPARSE on SuiteSparse matrices, plus AVX2 + cache-tiled CPU baselines on Intel Xeon Gold. Vector kernel reaches 98-110% of HBM2 peak, beating cuSPARSE by 24-56% on regular matrices.

University project on Sparse Matrix transposition with CUDA.

Reproducible Instruction Roofline analysis of cuSPARSE and Ginkgo SpMM on RTX 4090 using Nsight Compute metrics.

Sparse binary 2D FFT on CUDA/cuFFT with memory-footprint optimization, streaming tiles, Hermitian symmetry, and Nsight analysis.

Machine problems