Differences

This shows you the differences between two versions of the page.

--- high_performance_computing_and_best_practices [2014/09/08 16:32] – [Accessing Resources via SSH] wsi
+++ high_performance_computing_and_best_practices [2022/07/21 06:59] (current) – external edit 127.0.0.1
@@ Line 1: / Line 1: @@
+====== High Performance Computing and Best Practices ======
+===== Background =====
+==== HPC Vs. Single Processors ====
+Serial Computing - Instructions run one at a time:
+{{:images:serialproblem.gif?400|}}
+Parallel Computing - Problem is split into multiple problems, each problem can be run concurrently (at the same time) on multiple processors
+{{:images:parallelproblem.gif?500|}}
+==== Need for HPC ====
+//Time// - Parallel computing can solve problems faster
+//Cost// - Parallel computing can be accomplished with cheap hardware and the time savings can lead to cost savings
+//Larger Problems// - Complex problems like climate change, traffic, website transactions, and plasma physics can be infeasible with serial computing and are better suited to parallel computing
+==== Concepts and Terminology ====
+//HPC// - High Performance Computing, solving big problems with big computing power
+//Cluster// - A group of computers working together
+//Node// - A single computer, many nodes join together to form a cluster
+//Core/CPU// - A processing unit
+//Job// - A problem or program to be run
+//Parallel Overhead// - Extra time needed to setup and coordinate a parallel job: synchronizing, data exchange, start-up/termination, etc
+//Scalability// - Ability of a system to handle more work or its ability to be enlarged to accommodate more work
+==== Limits and Cost ====
+$Speedup = \frac{1}{(P/N)+S}$
+P = parallel fraction, N = number of processors, S = serial fraction
+{{:images:amdahl2.gif|}}
+Development cost of parallel programming is higher.
+==== Memory Architectures ====
+===== Batch Processing =====
+==== Batch Processing and Shared Resources ====
+The need for shared resources
+//Our Cluster//
+  * 16 cores on two nodes
+//NERSC//
+  * National Energy Research Scientific Computing Center
+  * Primary scientific computing facility for the Office of Science in the U.S. Department of Energy
+  * Multiple machines with over 100,000 cores
+{{:images:nersc.jpg?300|}}
+//Sunway TaihuLight//
+  * in China, currently the top HPC center with 10,649,600 cores
+{{::sunway-supercomputer-6.jpg?200|}}
+Check [[https://www.top500.org/|www.top500.org]] for an updated list of the top500 supercomputers
+==== Batch Processing Management ====
+With multiple users wishing to access computing resources, we need a way to manage who gets to use what resources and when they can do so.
+Some Resource Managers:
+  * [[http://www.adaptivecomputing.com/products/open-source/torque/|Torque]]
+  * [[https://computing.llnl.gov/linux/slurm/slurm.html|Slurm]]
+  * [[http://www.adaptivecomputing.com/products/hpc-products/moab-hpc-suite-enterprise-edition/|Moab]]
+===== Using HPC Resources at WSI =====
+==== Accessing Resources via SSH ====
+In the office:
+  $ ssh user@control
+==== Launching and Managing Your Jobs ====
+[[torque_tutorial|Using Torque (NERSC)]]
+[[slurm_tutorial|Using Slurm]]
+==== Version Control ====
+Often multiple programmers will be working on a codebase simultaneously. Alice may want to work on the code but Bob does too. If they both make changes to a file without telling each other, changes might get lost. Using a version control system ensures that Alice and Bob can work on the code together without undoing each-others work or breaking the code.
+=== Commonly used Version Control Systems ===
+Github
+SVN
+===== HPC Best Practices =====
+  * Redundant Data
+  * Seperate Storage from Compute Nodes
+  * Central Source for User Documentation