Skip to content

Latest commit

 

History

History
475 lines (316 loc) · 8.78 KB

outline.rst

File metadata and controls

475 lines (316 loc) · 8.78 KB
Raw

1.0 Current Release Notes

2.0 Installation Guide

2.1 Quick Start Guide

2.2 Installation Guide Ubuntu

2.3 Installation Guide Fedora

3.0 Programing Guides

3.1 HC Programing Guide

3.1.1 Programing Model

  1. Kernels
  2. Thread Hierarchy
  3. Memory Hierarchy
  4. Heterogeneous Programing
  5. Compute Capability

3.1.2 Programing Interface

  1. Compilation with HCC
  2. HC C++ Runtime

3.1.3 Performance Guidelines

3.1.4 Language Extensions

3.1.5 Mathematical Functions

3.1.6 Textures

3.1.6 Environment Variables

3.2 HC Best Practices

3.2.1 Assessing Your Application

3.2.2 Heterogeneous Computing

3.2.3 Application Profiling

3.2.4 Parallelizing your Application

3.2.5 Getting Started with your First Application

3.2.6 Driving Application Correctness

3.2.7 Optimizing your Application

3.2.8 Performance Metrics

3.2.9 Memory Optimizations

3.2.10 GPU Device Architecture Software Optimizations

3.2.11 Instruction Level Optimizations

3.2.12 Control Flow

3.2.13 Deploying HCC Application

3.2.14 Recommended Best Practices

3.2.115 HCC compiler switches

3.3 HIP Programing Guide

3.3.1 Programing Model

  1. Kernels
  2. Thread Hierarchy
  3. Memory Hierarchy
  4. Heterogeneous Programing
  5. Compute Capability

3.3.2 Programing Interface

  1. Compilation with HCC
  2. HC C++ Runtime

3.3.3 Performance Guidelines

3.3.4 Language Extensions

3.3.5 Mathematical Functions

3.3.6 Textures

3.3.7 Environment Variables

3.4 HIP Best Practices

3.4.1 Assessing Your Application

3.4.2 Heterogeneous Computing

3.4.3 Application Profiling

3.4.4 Parallelizing your Application

3.4.5 Getting Started with your First application

3.4.6 Driving Application Correctness

3.4.7 Optimizing your Application

3.4.8 Performance Metrics

3.4.9 Memory Optimizations

3.4.10 GPU Device Architecture Software Optimizations

3.4.11 Instruction Level Optimizations

3.4.12 Control Flow

3.4.13 Deploying HIP Application

3.4.14 Recommended Best Practices

3.4.15 HCC compiler switches

3.5 OpenCL Programing Guide

3.5.1 Programing Model

  1. Kernels
  2. Thread Hierarchy
  3. Memory Hierarchy
  4. Heterogeneous Programing
  5. Compute Capability

3.5.2 Programing Interface

  1. Compilation with OpenCL
  2. OpenCL Runtime

3.5.3 Performance Guidelines

3.5.4 Language Extensions

3.5.5 Mathematical Functions

3.5.6 Textures

3.57 Environment Variables

3.6 OpenCL Best Practices

3.6.1 Assessing Your Application

3.6.2 Heterogeneous Computing

3.6.3 Application Profiling

3.6.4 Parallelizing your Application

3.6.5 Getting Started with your First application

3.6.6 Driving Application Correctness

3.6.7 Optimizing your Application

3.6.8 Performance Metrics

3.6.9 Memory Optimizations

3.6.10 GPU Device Architecture Software Optimizations

3.6.11 Instruction Level Optimizations

3.6.12 Control Flow

3.6.13 Deploying OpenCL Application

3.6.14 Recommended Best Practices

3.6.15 OpenCL compiler switches

5.0 GCN ISA Manuals

5.1 GCN 1.1 Hawaii

5.2 GCN 2.0 Fiji and Polaris

5.2 GCN - Vega

5.4 Inline GCN ISA Assembly Guide

6.0 ROCm API References

6.1 ROCr System Runtime API

6.2 HCC Language Runtime API

6.3 HIP Language Runtime API

6.4 HIP Device Runtime API

6.5 HIP Math API

6.6 Math Libarary API's

6.6.1 rocBLAS

6.6.2 rocFFT

6.6.3 hcRAND

6.6.4 hsSPARSE

6.6.5 clBLAS

6.6.6 clFFT

6.6.7 clSPARSE

6.6.8 clRAND

6.7 Deep Learning API's

6.7.1 MIOpen

7.0 ROCm Tools

7.1 HCC

7.2 GCN Assembler and Disassembler

7.3 GCN Assembler Tools

7.4 ROCm-GDB

7.5 ROCm Debugger API

7.6 ROCm-Profiler

7.7 CodeXL

7.8 GPUperfAPI

7.9 ROCm Binary Utilities

8.0 ROCm Compiler SDK

8.1 GCN Native ISA LLVM Code Generator

8.2 ROCm Code Object Format

8.3 ROC Device Library

  1. OCML
  2. OKML

8.4 ROCr Runtime

8.4.1 Introduction

8.4.2 Programing Model

  1. Initialization and agent discovery
  2. Queues and AQL Packets
  3. Signals and packet launch

8.4.3 Programing Guide

  1. Initialization and shut down
  2. Runtime Notifications
  3. System and agent information
  4. Signals
  5. Queues
  6. Architected Queuing Language Packets
  7. Memory
  8. Code Object Loading
  9. Common definitions

8.4.4 Best Practices Mapping Programing Language to ROCr runtime

9.0 ROCM System Managment

9.1 ROCm-SMI

9.2 Programing ROCm-SMI

9.3 SYSFS Interface

10 ROCm Virtualization & Containers

10.1 KVM Passthrough

10.2 ROCm-Docker

11 Remote Device Programing

11.1 ROCnRDMA

11.2 UCX

11.3 MPI

11.4 IPC

12 Other Solutions

12.1 ROCr Error Codes

13 ROCm Glossary