Par4All is an automatic parallelizing and optimizing compiler (workbench) for C and Fortran sequential programs

The C++ reference implementation of the Pipe-and-Filter framework TeeTime

This repository contains the code of a JVMTI agent which automatically analyses the java bytecode during runtime and exploits the implicit loop parallelism in the code and parallelize it on the fly. This research work was published in IC4E 2018, San Diego.

A compiler to generate OpenMP programs for equations involving constructs like Forall, Summation, etc., frequently used in the scientific domain

Boinc wrapper, john the ripper boinc implementation

A minimal cmake based project skeleton for developping a kokkos application

Extensions to xv6 operating system done for course on Operating Systems at IIT Delhi

C library for interfacing with icepool-board on Linux using libftdi.

Parallellization of the Kmeans algorithm with OpenMP

An implementation of different parallelization approaches for the Adaptive Mesh Refinement problem, along with a comparison of their performance on the Ohio Supercomputer.

High Perfomance Computing project for parallelizing recursive fibonacci function with the usage of three API (OMP, MPI and CUDA)

Parallelized versions of popular Machine Learning algorithms, written in C using (mostly) the OpenMP API.

This repository lists 4 problems solved using C. Each problem has its own serial and parallel implementations. For the latter, the OpenMP API was utilized.

A hunter for 4x4 Turkish letter matrix. It finds possible Turkish words performly.

This repository contains multiple projects which involve distributed and parallel programming. We encompass OpenMP, MPI, CUDA and Open ACC. It has been used a private cluster (Pirineus3) to execute the programs. You'll find explanations on the reports.

The repository includes lab exercises for the course Parallel Programming (CS6306)

Program 2: OpenMP Programning

Implementation and analysis of parallel task decomposition techniques for the Mandelbrot set computation, developed as part of the PAR (parallelism) course at the FIB - UPC Barcelona. Using OpenMP, focusing on iterative and recursive task decomposition.

General processing using GPU through compute shaders