Contents Print pageExpand/Collapse all1. Overview of Parallel Processing1.1. Specifying Processes, Threads, and Cores in SMP, DMP, and Hybrid Parallel1.1.1. Auto-hybrid1.2. Parallel Processing Terminology1.2.1. Hardware Terminology1.2.2. Software Terminology1.3. HPC Licensing2. Using Shared-Memory Parallel (SMP) Processing2.1. Activating Parallel Processing in a Shared-Memory Architecture2.1.1. System-Specific Considerations 2.2. Troubleshooting3. GPU Accelerator Capability3.1. Activating the GPU Accelerator Capability3.2. Supported GPU Hardware, Analysis Types, and Features3.2.1. GPU Hardware3.2.2. Supported Analysis Types3.2.3. Supported Features3.3. Troubleshooting4. Using Distributed-Memory Parallel (DMP) Processing4.1. Configuration Requirements for DMP Processing4.1.1. Prerequisites for Running a DMP Analysis4.1.2. Setting Up the Cluster Environment for DMP4.2. Starting a DMP Analysis4.2.1. Starting a DMP Analysis via the Launcher4.2.2. Starting a DMP Analysis via Command Line4.2.3. Starting a DMP Analysis via the HPC Job Manager4.2.4. Starting a DMP Solution in the Mechanical Application (via Ansys Workbench)4.2.5. Using MPI Files4.2.6. Directory Structure Across Machines4.3. Supported Analysis Types and Features4.3.1. Supported Analysis Types4.3.2. Supported Features4.4. Understanding the Working Principles and Behavior of Distributed-memory Parallelism4.4.1. Differences in General Behavior 4.4.2. Differences in Solution Processing4.4.3. Differences in Postprocessing4.4.4. Restarts with DMP processing4.5. Example Problem4.5.1. Example: Running a DMP Analysis on Linux4.6. Troubleshooting4.6.1. Setup and Launch Issues4.6.2. Stability Issues4.6.3. Solution and Performance Issues5. Using Hybrid Parallel Processing (SMP + DMP)5.1. Activating Hybrid Parallel Processing5.1.1. Activating Hybrid Parallel by Command or Product Launcher5.1.2. System-Specific Considerations Chapter 1: Overview of Parallel Processing »
