parallel-reduction

Implementing a small functional language with a combinator graph reduction engine

Six-stage CUDA parallel reduction optimization: from basic global memory to warp shuffles and bank conflict avoidance

Contrast Enhancement on GPU using Parallel Reduction v7

This is a GPU program built with CUDA using parallel reduction

A Unity project to test the ParallelReduce algorithm using jobs.

Parallel sequence alignment program that finds the optimal mutation in one sequence of the other. Parallelizes CPU and GPU using OpenMP and CUDA, and communicates with multiple computers using MPI.

CUDA reduction primitive using warp shuffles, grid-stride loading, and memory-bandwidth profiling with Nsight Compute.

Programs in terminal applying the parallel programming model with the CUDA arquitecture

GPU parallel programming exercises - shared memory, tiling, reduction patterns. PMPP + Oak Ridge National Lab CUDA series.

How much of GEMM performance is memory access order? Five CPU variants of the same matrix product, a shared-memory tiled CUDA kernel and a CUDA sum reduction, all measured on one shape. Loop reordering alone is worth 37.9x. C++17, CMake, no dependencies.

CUDA reduction kernels benchmarked against CUB, with optimization experiments across multiple implementation strategies.