Resources for Parallel Programming

CSE436 and 536: Concurrent and Multicore Programming, Oakland University

Introduction to Parallel and High Performance Computing

• top500
• HPCWire Online Magazine
• Major HPC/Supercomputing(SC) Conference: SC (SC in US), ISC (SC in Europe)
• Moore's Law
• Introduction to Parallel Computing from LLNL

Linux and C Programming

• Linux/Unix Introduction
• VI Command
• C Programming Tutorial
• Compiler, Assembler, Linker and Loader: A Brief Story
• GNU Compiler Collection (gcc) online manual
• Intel Compiler Manual

Performance Application Programming Interface(PAPI) Programming and Hardware Counter

• Short slide introduction and Longer slide for overview for PAPI
• PAPI Official website
• A list of derived metrics that can be calcualted using PAPI events
• PAPI API Reference Manual
• PAPI Getting Started which has an example showing the use of PAPI_flops API.
• One simple PAPI example
• RAPL access to PAPI, Reading RAPL energy measurements from Linux
• Ubuntu has a papi-examples packages that included lots of examples of advanced use PAPI, the files are stored in /usr/share/doc/papi-examples
• papi-tools provides utilities command for use with PAPI: papi_mem_info to list the system memory info. papi_avail to list the events available on the system.

Parallel Algorithm Design

• axpy, matvec, and matmul examples

OpenMP

• OpenMP Official Website, which provides the official standard, Technical Report, example document and tons of other information.
• OpenMP tutorial from LLNL

Parallel Program Measurement and Analysis

• isoefficiency paper
• Strong Scaling vs Weak Scaling, google search the keywords
• Amdahl's Law vs. Gustafson-Barsis' Law

Cilk and Cilkplus

• MIT Cilk
• Intel Cilkplus Runtime
• Cilkplus Tutorial
• Cilkplus Examples from Intel Compiler Manual
• Cilkplus performance tools (cilkview, cilkscreen)

PThread

• POSIX Threads Programming from LLNL
• PThread examples used during the class

Computer Architecture, Memory Hierarchy and Cache Coherence

• Lecture Notes for Computer Architecture from MIT
• A Primer on Memory Consistency and Cache Coherence from the Synthesis Lectures on Computer Architecture
• Computer Organization and Design, Revised Fourth Edition, The latest edition (5th edition) (bible for undergraduate computer architecture course)
• Computer Architecture, 5th Edition A Quantitative Approach (bible book for graduate computer architecture course)
• Ulrich Drepper, What Every Programmer Should Know About Memory

GPU and CUDA Programming

• GPU and CUDA examples used during the class
• Matrix Multiplication Examples (both using global memory and shared memory)
• CUDA C Programming Guide
• CUDA Toolkit documentation, which includes CUDA installation, C programming guide, APIs for cuBlas, cuFFT etc, tools, compiler SDK, and others.
• GPU Accelerated Computing with C and C++, which also has some videos.

MPI Programming

• Examples used during the class
• MPI Official Website that include the standard document.
• MPI Tutorial from LLNL

PGAS and others

• PGAS Introduction
• UPC, Berkeley UPC
• X10 and Chapel

Other Related Topics (not covered in the class)

• MapReduce with Hadoop/Spark
• Performance Profiling and Analysis Tools (TAU, HPCToolkit, Intel VTune, nvprof, etc)
• Algorithm/Dwarfs (Sequential, OpenMP, Cilkplus, C++11 (std::thread and std::async, CUDA and MPI versions)
• Dense matrix (axpy, mv, mm)
• Linear Algebra (LU, QR)
• Reduction (sum)
• Stencil and image processing related (jacobi, FFT)
• Sorting (quicksort)
• Graph (traversal, UTS)
• Sparse matrix
• Smith–Waterman
• Larger application
• Co-Design Prox App
• Mantevo miniapps

Interesting to Read

• HPC is dying, and MPI is killing it by Jonathan Dursi
• Linus: The Whole "Parallel Computing Is The Future" Is A Bunch Of Crock