Skip to main content
Ctrl+K
This is not the latest version of ROCm documentation. See ROCm documentation for the latest version.
AMD Logo
ROCm™ Software 6.2.4 Version List
  • GitHub
  • Community
  • Blogs
  • Infinity Hub
  • Support

ROCm Documentation

  • What is ROCm?
  • Release notes

Install

  • ROCm on Linux
  • HIP SDK on Windows
  • Deep learning frameworks
  • Build ROCm from source

How to

  • Use ROCm for AI
    • Installation
    • Train a model
    • Run models from Hugging Face
    • Deploy your model
  • Use ROCm for HPC
  • Fine-tune LLMs and inference optimization
    • Conceptual overview
    • Fine-tuning and inference
      • Using a single accelerator
      • Using multiple accelerators
    • Model quantization techniques
    • Model acceleration libraries
    • LLM inference frameworks
    • Optimize with Composable Kernel
    • Optimize Triton kernels
    • Profile and Debug
  • System optimization
    • AMD Instinct MI300X
    • AMD Instinct MI300A
    • AMD Instinct MI200
    • AMD Instinct MI100
    • AMD RDNA 2
  • AMD MI300X performance validation and tuning
    • Performance validation
    • System tuning
    • Workload tuning
  • GPU cluster networking
  • Use MPI
  • System debugging
  • Use advanced compiler features
    • ROCm compiler infrastructure
    • Use AddressSanitizer
    • OpenMP support
  • Set the number of CUs
  • ROCm examples

Compatibility

  • Compatibility matrix
  • Linux system requirements
  • Windows system requirements
  • Third-party support
  • User and kernel-space support matrix
  • Docker image support matrix
  • Use ROCm on Radeon GPUs

Conceptual

  • GPU architecture overview
    • MI300 microarchitecture
      • AMD Instinct MI300/CDNA3 ISA
      • White paper
      • MI300 and MI200 Performance counter
    • MI250 microarchitecture
      • AMD Instinct MI200/CDNA2 ISA
      • White paper
    • MI100 microarchitecture
      • AMD Instinct MI100/CDNA1 ISA
      • White paper
  • GPU memory
  • File structure (Linux FHS)
  • GPU isolation techniques
  • Using CMake
  • ROCm & PCIe atomics
  • Inception v3 with PyTorch
  • Oversubscription of hardware resources

Reference

  • ROCm libraries
  • ROCm tools, compilers, and runtimes
  • Accelerator and GPU hardware specifications
  • Precision support

Contribute

  • Contributing to the ROCm docmentation
    • ROCm documentation toolchain
    • Building documentation
  • Providing feedback about the ROCm documentation
  • ROCm licenses
  • ROCm libraries

ROCm libraries

ROCm libraries#

Applies to Linux and Windows

2024-08-22

3 min read time

Machine Learning and Computer Vision
  • Composable Kernel

  • MIGraphX

  • MIOpen

  • MIVisionX

  • rocAL

  • rocDecode

  • rocPyDecode

  • ROCm Performance Primitives (RPP)

Primitives
  • hipCUB

  • hipTensor

  • rocPRIM

  • rocThrust

Communication
  • RCCL

Math
  • half

  • hipBLAS / rocBLAS

  • hipBLASLt

  • hipFFT / rocFFT

  • hipfort

  • hipRAND / rocRAND

  • hipSOLVER / rocSOLVER

  • hipSPARSE / rocSPARSE

  • hipSPARSELt

  • rocALUTION

  • rocWMMA

  • Tensile

previous

Oversubscription of hardware resources in AMD Instinct accelerators

next

ROCm tools, compilers, and runtimes

  • Terms and Conditions
  • ROCm Licenses and Disclaimers
  • Privacy
  • Trademarks
  • Statement on Forced Labor
  • Fair and Open Competition
  • UK Tax Strategy
  • Cookie Policy
  • Cookie Settings
© 2024 Advanced Micro Devices, Inc