COMP 422/534 Parallel Computing Resources

Cilk

Cilk is an algorithmic multithreaded language. Cilk enables programmers to concentrate on structuring programs to expose parallelism and exploit locality. The responsibility of scheduling the computation to run efficiently is left to Cilk's runtime system, which takes care of details such as load balancing and communication. Unlike other multithreaded languages, Cilk is algorithmic in that its runtime system guarantees efficient and predictable performance.

Links

Cilk Home
An Introduction to Cilk
Cilk 5.4.6 Language Reference Manual
Cilk Implementation Description
Scheduling Computations by Work Stealing
Detecting Data Races in Cilk Programs

Cilk Hub

OpenMP

OpenMP (Open specifications for Multi Processing) is an API for explicit multi-threaded, shared memory parallelism. OpenMP consists of compiler directives, runtime library routines, and environment variables.

Links

OpenMP specifications, tutorials, and more
LLNL OpenMP Tutorial
B. Chapman, G. Jost, R. van der Pas. Using OpenMP: Portable Shared Memory Parallel Programming. 2007.

MPI

The Message Passing Interface (MPI) is a standard communication library specification for message passing. MPI is the standard implementation technology for portable, scalable, high performance parallel programs.

Links

MPI Home
MPI 1.1 Standard
MPI Tutorials
Manual Pages for Commands and Library Procedures
MPICH MPI Implementation Home
Book: Using MPI - Portable Parallel Programming with the Message Passing Interface, 3rd Edition

CUDA is NVIDIA's programming model for graphics processing units (GPUs). GPUs are increasing in popularity because they can perform an enormous amount of computation at low power. Below is documentation for NVIDIA's CUDA Toolkit, version 7.0.

Links

CUDA Toolkit Documentation v7.0 [ HTML]


Some particularly useful documents

CUDA Programming Guide [PDF]
CUDA C Best Practices Guide [PDF]
CUDA Compiler Driver nvcc [PDF]
CUDA-GDB CUDA Debugger [PDF]


All of the documents [PDF]