mirror of
https://github.com/ROCm/ROCm.git
synced 2026-01-09 22:58:17 -05:00
Compare commits
217 Commits
roc-2.10.0
...
roc-3.7.x
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
010d529b5a | ||
|
|
862dcd9d45 | ||
|
|
1d4428ed08 | ||
|
|
f3d2c2e4c5 | ||
|
|
8946653ba4 | ||
|
|
5121abd825 | ||
|
|
b54610ef82 | ||
|
|
e0361edcf8 | ||
|
|
67f7748999 | ||
|
|
3b9619ac45 | ||
|
|
3b421076e0 | ||
|
|
3dfc8c3954 | ||
|
|
1d4cac07ae | ||
|
|
de1efc447a | ||
|
|
f0bcd280f1 | ||
|
|
cf36f54099 | ||
|
|
d304044378 | ||
|
|
4464dc282e | ||
|
|
9f7604f51b | ||
|
|
f213e32845 | ||
|
|
efad9684ee | ||
|
|
6d99ada0ae | ||
|
|
fb77891fae | ||
|
|
b0b858d81c | ||
|
|
7c97c6b102 | ||
|
|
dee1c4a0e7 | ||
|
|
29060c09ec | ||
|
|
d7eb52fced | ||
|
|
13e2fb06b9 | ||
|
|
e3017948a9 | ||
|
|
09643c4a90 | ||
|
|
8c835d14fc | ||
|
|
25dea0df9f | ||
|
|
11968356fc | ||
|
|
c2d8aa3426 | ||
|
|
cc37d13828 | ||
|
|
63ed31781d | ||
|
|
5502ce3c41 | ||
|
|
2adb254db3 | ||
|
|
640b0e0cec | ||
|
|
4b67bbc512 | ||
|
|
4eddbb0f2f | ||
|
|
6dd212c1ff | ||
|
|
1b49b1d598 | ||
|
|
d85d330f17 | ||
|
|
c3efbe0263 | ||
|
|
e72d9d16f2 | ||
|
|
d6ebde1c2b | ||
|
|
c270440e1d | ||
|
|
87212e992e | ||
|
|
b9f3ba6cda | ||
|
|
befa37295e | ||
|
|
6e957870bd | ||
|
|
6906210c51 | ||
|
|
88a2c6a311 | ||
|
|
10366c7bae | ||
|
|
613020c029 | ||
|
|
bbf233a8a0 | ||
|
|
6dfc3154dc | ||
|
|
f38ab28a19 | ||
|
|
5aa6de9001 | ||
|
|
45bc0b6e8f | ||
|
|
46fe870c8d | ||
|
|
2d3d61969f | ||
|
|
6d9651756c | ||
|
|
435eee1860 | ||
|
|
ca7d03f4a6 | ||
|
|
aa48cad227 | ||
|
|
2f3d09e898 | ||
|
|
82ecac74bb | ||
|
|
d693175b09 | ||
|
|
293b24d915 | ||
|
|
950874f674 | ||
|
|
34586f3bd4 | ||
|
|
39790b6ea4 | ||
|
|
b6bf0086d0 | ||
|
|
c81f5e59cf | ||
|
|
353f901378 | ||
|
|
21e76e3fa5 | ||
|
|
488b62219f | ||
|
|
1a5a5efbd3 | ||
|
|
f69a8c19e5 | ||
|
|
6eb53b9931 | ||
|
|
4bfa3780e3 | ||
|
|
c159d23e3c | ||
|
|
fb1709623b | ||
|
|
e853bbe63d | ||
|
|
657ed79dee | ||
|
|
da8a01deb0 | ||
|
|
fbdfeecd14 | ||
|
|
c524da62f0 | ||
|
|
854b2278e9 | ||
|
|
b00a2885ea | ||
|
|
0e53cfa829 | ||
|
|
fef7342549 | ||
|
|
f6565e7f3f | ||
|
|
c56404399b | ||
|
|
664311f4fe | ||
|
|
f45bfbfeed | ||
|
|
f00e4fdf7b | ||
|
|
ae5f7d7be9 | ||
|
|
720760ad63 | ||
|
|
b8a0a90287 | ||
|
|
73ed1122fa | ||
|
|
d50a208edd | ||
|
|
720c7cddc7 | ||
|
|
586a57823a | ||
|
|
c546c5fe3c | ||
|
|
a3ce396048 | ||
|
|
51a22a97f9 | ||
|
|
72ddeef85b | ||
|
|
6cafd3b8fd | ||
|
|
111f8e8409 | ||
|
|
27bc1477f1 | ||
|
|
edc179783c | ||
|
|
8fac5002c4 | ||
|
|
77764b4887 | ||
|
|
b952ebd666 | ||
|
|
db6dbdcc7a | ||
|
|
924f08a6af | ||
|
|
9406a51332 | ||
|
|
c76270cb72 | ||
|
|
5a82caca04 | ||
|
|
6a4ae7c703 | ||
|
|
f49275a805 | ||
|
|
93858f653b | ||
|
|
2a1c123ad8 | ||
|
|
7676103619 | ||
|
|
202562d9fe | ||
|
|
c10e1fcfe2 | ||
|
|
a298b06a72 | ||
|
|
2f9e5b68e7 | ||
|
|
ccfe2f1a34 | ||
|
|
09196ba787 | ||
|
|
606cc11ebe | ||
|
|
caead32d16 | ||
|
|
75d01b3a23 | ||
|
|
6e3be7651a | ||
|
|
a7d27a43dc | ||
|
|
af5b8e1b93 | ||
|
|
b7e9232861 | ||
|
|
dd86238927 | ||
|
|
f452920919 | ||
|
|
150d8a89da | ||
|
|
7af0f9144b | ||
|
|
ca1f7bc166 | ||
|
|
a0773a297a | ||
|
|
b421b06456 | ||
|
|
754ebcec86 | ||
|
|
27daab068e | ||
|
|
6c70298860 | ||
|
|
f5cae8347d | ||
|
|
2759642432 | ||
|
|
8879e01c90 | ||
|
|
5d05e3fdb6 | ||
|
|
5c8047181e | ||
|
|
eba4c1a25c | ||
|
|
01d806e5c1 | ||
|
|
d3ede323b6 | ||
|
|
f5ab073219 | ||
|
|
56e083faac | ||
|
|
fd95c06730 | ||
|
|
0852725b63 | ||
|
|
0bcf42d721 | ||
|
|
789ab1a6db | ||
|
|
65beddddb8 | ||
|
|
917a03430f | ||
|
|
fefcb606fa | ||
|
|
8f3d0331e0 | ||
|
|
9f39dd9458 | ||
|
|
7b52d73349 | ||
|
|
b22c12266a | ||
|
|
c02e11b650 | ||
|
|
9ff3311a58 | ||
|
|
1ca2e8eb87 | ||
|
|
7370793bc7 | ||
|
|
20cd1c8e53 | ||
|
|
a65935a02e | ||
|
|
03270a5bd5 | ||
|
|
1d24ed9f9c | ||
|
|
c0876b7ae5 | ||
|
|
6b5707bfd9 | ||
|
|
e6499f1563 | ||
|
|
8ac3b0dcd9 | ||
|
|
7f986f30d1 | ||
|
|
87aa7362a3 | ||
|
|
dde6ae15db | ||
|
|
63eea0e9e7 | ||
|
|
0ffc79f9b8 | ||
|
|
32d48a74b9 | ||
|
|
f6aa4d149e | ||
|
|
6ef9776d50 | ||
|
|
929f927ada | ||
|
|
e0043fa0a1 | ||
|
|
354d8b5615 | ||
|
|
aa17cc4dd0 | ||
|
|
c73d4777b9 | ||
|
|
cd0a756584 | ||
|
|
3d6de36a21 | ||
|
|
19efdc7d7b | ||
|
|
ea1b9f85f5 | ||
|
|
d948b1c844 | ||
|
|
046a4c35a6 | ||
|
|
916bc37963 | ||
|
|
caf1f2e5aa | ||
|
|
e5bbf892a9 | ||
|
|
36e7bc054b | ||
|
|
d8fb001470 | ||
|
|
c67e8b1e2f | ||
|
|
3ec6301df1 | ||
|
|
dffe4ff850 | ||
|
|
77d20a4b1d | ||
|
|
7c52f68bd4 | ||
|
|
c6bb911570 | ||
|
|
e8c598d156 | ||
|
|
e9490d3a0b | ||
|
|
67a3649dce |
BIN
AMD_ROCm_Release_Notes_v3.7.pdf
Normal file
BIN
AMD_ROCm_Release_Notes_v3.7.pdf
Normal file
Binary file not shown.
Binary file not shown.
733
README.md
733
README.md
@@ -1,506 +1,327 @@
|
||||
# AMD ROCm Release Notes v2.10
|
||||
|
||||
# AMD ROCm Release Notes v3.7.0
|
||||
|
||||
This page describes the features, fixed issues, and information about downloading and installing the ROCm software.
|
||||
It also covers known issues and deprecated features in the ROCm v2.10 release.
|
||||
It also covers known issues and deprecated features in this release.
|
||||
|
||||
- [What Is ROCm?](#What-Is-ROCm)
|
||||
* [ROCm Components](#ROCm-Components)
|
||||
- [Supported Operating Systems and Documentation Updates](#Supported-Operating-Systems-and-Documentation-Updates)
|
||||
* [Supported Operating Systems](#Supported-Operating-Systems)
|
||||
* [Important ROCm Links](#Important-ROCm-Links)
|
||||
|
||||
- [Whats New in This Release](#Whats-New-in-This-Release)
|
||||
* [rocBLAS Support for Complex GEMM](#rocBLAS-Support-for-Complex-GEMM)
|
||||
* [Support for SLES 15 SP1](#Support-for-SLES-15-SP1)
|
||||
* [Code Marker Support for rocProfiler and rocTracer Libraries](#Code-Marker-Support-for-rocProfiler-and-rocTracer-Libraries)
|
||||
|
||||
- [Fixed Issues](#Fixed-Issues)
|
||||
* [Running TensorFlow and PyTorch Frameworks Consecutively Results in the Memory Access Fault error ](#Running-TensorFlow-and-PyTorch-Frameworks-Consecutively-Results-in-the-Memory-Access-Fault-error)
|
||||
* [Issue with the Docker Container Environment Variable Setting](#Issue-with-the-Docker-Container-Environment-Variable-Setting)
|
||||
* [Printf Functionality in ROCm Re-Enabled](#Printf-functionality-in-ROCm-Re-Enabled)
|
||||
|
||||
- [Known Issues](#Known-Issues)
|
||||
* [Memory Access Fault Error While Running RCCL in Docker Container](#Memory-Access-Fault-Error-While-Running-RCCL-in-Docker-Container)
|
||||
* [Workaround for Tracer Library Fails to Load on RHEL](#Workaround-for-Tracer-Library-Fails-to-Load-on-RHEL)
|
||||
* [AMD ROCm Documentation Updates](#AMD-ROCm-Documentation-Updates)
|
||||
|
||||
- [Deprecated Features](#Deprecated-Features)
|
||||
* [ROCm OpenCL Driver](#ROCm-OpenCL-Driver)
|
||||
* [Peer-to-Peer Bridge Driver for PeerDirect](#Peer-to-Peer-Bridge-Driver-for-PeerDirect)
|
||||
|
||||
- [Deploying ROCm](#Deploying-ROCm)
|
||||
* [Ubuntu](#Ubuntu)
|
||||
* [CentOS RHEL](#CentOS-RHEL)
|
||||
- [What\'s New in This Release](#Whats-New-in-This-Release)
|
||||
* [AOMP Enhancements](#AOMP-Enhancements)
|
||||
* [Compatibility with NVIDIA Communications Collective Library v2\.7 API](#Compatibility-with-NVIDIA-Communications-Collective-Library-v27-API)
|
||||
* [Singular Value Decomposition of Bi\-diagonal Matrices](#Singular-Value-Decomposition-of-Bi-diagonal-Matrices)
|
||||
* [rocSPARSE_gemmi\() Operations for Sparse Matrices](#rocSPARSE_gemmi-Operations-for-Sparse-Matrices)
|
||||
|
||||
|
||||
- [Known Issues](#Known-Issues)
|
||||
|
||||
- [ROCm Installation](#ROCm-Installation)
|
||||
- [Getting the ROCm Source Code](#Getting-the-ROCm-Source-Code)
|
||||
- [Deploying ROCm](#Deploying-ROCm)
|
||||
|
||||
- [Hardware and Software Support](#Hardware-and-Software-Support)
|
||||
|
||||
- [Machine Learning and High Performance Computing Software Stack for AMD GPU](#Machine-Learning-and-High-Performance-Computing-Software-Stack-for-AMD-GPU)
|
||||
* [ROCm Binary Package Structure](#ROCm-Binary-Package-Structure)
|
||||
* [ROCm Platform Packages](#ROCm-Platform-Packages)
|
||||
|
||||
|
||||
## What Is ROCm?
|
||||
ROCm is designed to be a universal platform for gpu-accelerated computing. This modular design allows hardware vendors to build drivers that support the ROCm framework. ROCm is also designed to integrate multiple programming languages and makes it easy to add support for other languages.
|
||||
|
||||
Note: You can also clone the source code for individual ROCm components from the GitHub repositories.
|
||||
# Supported Operating Systems
|
||||
|
||||
## Support for Ubuntu 20.04
|
||||
|
||||
### ROCm Components
|
||||
The following components for the ROCm platform are released and available for the v2.10 release:
|
||||
|
||||
• Drivers
|
||||
In this release, AMD ROCm extends support to Ubuntu 20.04, including dual-kernel.
|
||||
|
||||
• Tools
|
||||
## List of Supported Operating Systems
|
||||
|
||||
• Libraries
|
||||
The AMD ROCm v3.7.x platform is designed to support the following operating systems:
|
||||
|
||||
• Source Code
|
||||
* Ubuntu 20.04 and 18.04.4 (Kernel 5.3)
|
||||
* CentOS 7.8 & RHEL 7.8 (Kernel 3.10.0-1127) (Using devtoolset-7 runtime support)
|
||||
* CentOS 8.2 & RHEL 8.2 (Kernel 4.18.0 ) (devtoolset is not required)
|
||||
* SLES 15 SP1
|
||||
|
||||
You can access the latest supported version of drivers, tools, libraries, and source code for the ROCm platform at the following location:
|
||||
https://github.com/RadeonOpenCompute/ROCm
|
||||
## Fresh Installation of AMD ROCm v3.7 Recommended
|
||||
A fresh and clean installation of AMD ROCm v3.7 is recommended. An upgrade from previous releases to AMD ROCm v3.7 is not supported.
|
||||
|
||||
### Supported Operating Systems
|
||||
The ROCm v2.10.x platform is designed to support the following operating systems:
|
||||
For more information, refer to the AMD ROCm Installation Guide at:
|
||||
|
||||
• SLES 15 SP1
|
||||
https://github.com/RadeonOpenCompute/ROCm/blob/roc-3.7.x/ROCm_Installation_Guide_v3.7.md
|
||||
|
||||
• Ubuntu 16.04.6(Kernel 4.15) and 18.04.3(Kernel 5.0)
|
||||
**Note**: AMD ROCm release v3.3 or prior releases are not fully compatible with AMD ROCm v3.5 and higher versions. You must perform a fresh ROCm installation if you want to upgrade from AMD ROCm v3.3 or older to 3.5 or higher versions and vice-versa.
|
||||
|
||||
• CentOS 7.6 (Using devtoolset-7 runtime support)
|
||||
|
||||
• RHEL 7.6 (Using devtoolset-7 runtime support)
|
||||
# AMD ROCm Documentation Updates
|
||||
|
||||
For details about deploying the ROCm v2.10.x on these operating systems, see the Deploying ROCm section later in the document.
|
||||
## AMD ROCm Installation Guide
|
||||
|
||||
### Important ROCm Links
|
||||
Access the following links for more information on:
|
||||
• ROCm documentation, see
|
||||
https://rocm-documentation.readthedocs.io/en/latest/index.html
|
||||
The AMD ROCm Installation Guide in this release includes:
|
||||
|
||||
• ROCm binary structure, see
|
||||
https://github.com/RadeonOpenCompute/ROCm/blob/master/README.md#rocm-binary-package-structure
|
||||
* Updated Supported Environments
|
||||
|
||||
• Common ROCm installation issues, see
|
||||
https://rocm.github.io/install_issues.html
|
||||
https://github.com/RadeonOpenCompute/ROCm/blob/roc-3.7.x/ROCm_Installation_Guide_v3.7.md
|
||||
|
||||
• Instructions to install PyTorch after ROCm is installed – https://rocm-documentation.readthedocs.io/en/latest/Deep_learning/Deep-learning.html#pytorch
|
||||
|
||||
Note: These instructions reference the rocm/pytorch:rocm2.9_ubuntu16.04_py2.7_pytorch image. However, you can substitute the Ubuntu 18.04 image listed at https://hub.docker.com/r/rocm/pytorch/tags
|
||||
## AMD ROCm - HIP Documentation Updates
|
||||
|
||||
### Texture and Surface Functions
|
||||
The documentation for Texture and Surface functions is updated and available at:
|
||||
|
||||
## Whats New in This Release
|
||||
https://rocmdocs.amd.com/en/latest/Programming_Guides/Kernel_language.html
|
||||
|
||||
### rocBLAS Support for Complex GEMM
|
||||
The rocBLAS library is a gpu-accelerated implementation of the standard Basic Linear Algebra Subroutines (BLAS). rocBLAS is designed to enable you to develop algorithms, including high performance computing, image analysis, and machine learning.
|
||||
### Warp Shuffle Functions
|
||||
The documentation for Warp Shuffle functions is updated and available at:
|
||||
|
||||
In the AMD ROCm release v2.10, support is extended to the General Matrix Multiply (GEMM) routine for multiple small matrices processed simultaneously for rocBLAS in AMD Radeon Instinct MI50. Both single and double precision, CGEMM and ZGEMM, are now supported in rocBLAS.
|
||||
https://rocmdocs.amd.com/en/latest/Programming_Guides/Kernel_language.html
|
||||
|
||||
### Support for SLES 15 SP1
|
||||
In the AMD ROCm v2.10 release, support is added for SUSE Linux® Enterprise Server (SLES) 15 SP1. SLES is a modular operating system for both multimodal and traditional IT.
|
||||
### Compiler Defines and Environment Variables
|
||||
The documentation for the updated HIP Porting Guide is available at:
|
||||
|
||||
Note: The SUSE Linux® Enterprise Server is a licensed platform. Ensure you have registered and have a license key prior to installation. Use the following SUSE command line to apply your license:
|
||||
SUSEConnect -r < Key>
|
||||
https://rocmdocs.amd.com/en/latest/Programming_Guides/HIP-porting-guide.html#hip-porting-guide
|
||||
|
||||
#### SLES 15 SP1
|
||||
The following section tells you how to perform an install and uninstall ROCm on SLES 15 SP 1.
|
||||
Run the following commands once for a fresh install on the operating system:
|
||||
|
||||
sudo usermod -a -G video $LOGNAME
|
||||
sudo usermod -a -G sudo $LOGNAME
|
||||
sudo reboot
|
||||
## AMD ROCm Debug Agent
|
||||
|
||||
Installation
|
||||
1. Install the "dkms" package.
|
||||
ROCm Debug Agent Library
|
||||
|
||||
sudo SUSEConnect --product PackageHub/15.1/x86_64
|
||||
sudo zypper install dkms
|
||||
|
||||
2. Add the ROCm repo.
|
||||
https://rocmdocs.amd.com/en/latest/ROCm_Tools/rocm-debug-agent.html
|
||||
|
||||
sudo zypper clean --all
|
||||
sudo zypper addrepo --no-gpgcheck http://repo.radeon.com/rocm/zyp/zypper/ rocm
|
||||
sudo zypper ref
|
||||
zypper install rocm-dkms
|
||||
sudo zypper install rocm-dkms
|
||||
sudo reboot
|
||||
|
||||
#Run the following command once
|
||||
## General AMD ROCm Documentatin Links
|
||||
|
||||
cat <<EOF | sudo tee /etc/modprobe.d/10-unsupported-modules.conf
|
||||
allow_unsupported_modules 1
|
||||
EOF
|
||||
sudo modprobe amdgpu
|
||||
|
||||
3. Verify the ROCm installation.
|
||||
Access the following links for more information:
|
||||
|
||||
Run /opt/rocm/bin/rocminfo and /opt/rocm/opencl/bin/x86_64/clinfo commands to list the GPUs and verify that the ROCm installation is successful.
|
||||
* For AMD ROCm documentation, see
|
||||
|
||||
Uninstallation
|
||||
https://rocmdocs.amd.com/en/latest/
|
||||
|
||||
To uninstall, use the following command:
|
||||
* For installation instructions on supped platforms, see
|
||||
|
||||
sudo zypper remove rocm-dkms rock-dkms
|
||||
|
||||
#Ensure all other installed packages/components are removed
|
||||
https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
|
||||
|
||||
Note: Ensure all the content in the /opt/rocm directory is completely removed.
|
||||
* For AMD ROCm binary structure, see
|
||||
|
||||
https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html#build-amd-rocm
|
||||
|
||||
### Code Marker Support for rocProfiler and rocTracer Libraries
|
||||
Code markers provide the external correlation ID for the calling thread. This function indicates that the calling thread is entering and leaving an external API region.
|
||||
* For AMD ROCm Release History, see
|
||||
|
||||
• The rocProfiler library enables you to profile performance counters and derived metrics. This library supports GFX8/GFX9 and provides a hardware-specific low-level performance analysis interface for profiling of GPU compute applications. The profiling includes hardware performance counters with complex performance metrics.
|
||||
https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html#amd-rocm-version-history
|
||||
|
||||
• The rocTracer library provides a specific runtime profiler to trace API and asynchronous activity. The API provides functionality for registering the runtimes API callbacks and the asynchronous activity records pool support.
|
||||
|
||||
• rocTX provides a C API for code markup for performance profiling and supports annotation of code ranges and ASCII markers.
|
||||
|
||||
# What\'s New in This Release
|
||||
|
||||
## Fixed Issues
|
||||
Fixed Issues in the v2.10 Release
|
||||
### Running TensorFlow and PyTorch Frameworks Consecutively Results in the Memory Access Fault error
|
||||
Issue: Running the TensorFlow and PyTorch frameworks in quick succession results in a Memory Access Fault error.
|
||||
## AOMP ENHANCEMENTS
|
||||
|
||||
Resolution: This issue is resolved, and the error no longer appears.
|
||||
AOMP is a scripted build of LLVM. It supports OpenMP target offload on AMD GPUs. Since AOMP is a Clang/LLVM compiler, it also supports GPU offloading with HIP, CUDA, and OpenCL.
|
||||
|
||||
### Issue with the Docker Container Environment Variable Setting
|
||||
Issue: Applications fail when the docker container is launched on the NUMA system without the ‘security-opt seccomp=unconfined’ setting.
|
||||
The following enhancements are made for AOMP in this release:
|
||||
* OpenMP 5.0 is enabled by default. You can use -fopenmp-version=45 for OpenMP 4.5 compliance
|
||||
* Restructured to include the ROCm compiler
|
||||
* B=Bitcode search path using hip policy HIP_DEVICE_LIB_PATH and hip-devic-lib command line option to enable global_free for kmpc_impl_free
|
||||
|
||||
Resolution: Configure the “–security-opt seccomp=unconfined” variable setting to avoid this issue.
|
||||
Restructured hostrpc, including:
|
||||
* Replaced hostcall register functions with handlePayload(service, payload). Note, handlPayload has a simple switch to call the correct service handler function.
|
||||
* Removed the WITH_HSA macro
|
||||
* Moved the hostrpc stubs and host fallback functions into a single library and the include file. This enables the stubs openmp cpp source instead of hip and reorganizes the directory openmp/libomptarget/hostrpc.
|
||||
* Moved hostrpc_invoke.cl to DeviceRTLs/amdgcn.
|
||||
* Generalized the vargs processing in printf to work for any vargs function to execute on the host, including a vargs function that uses a function pointer.
|
||||
* Reorganized files, added global_allocate and global_free.
|
||||
* Fixed llvm TypeID enum to match the current upstream llvm TypeID.
|
||||
* Moved strlen_max function inside the declare target #ifdef _DEVICE_GPU in hostrpc.cpp to resolve linker failure seen in pfspecifier_str smoke test.
|
||||
* Fixed AOMP_GIT_CHECK_BRANCH in aomp_common_vars to not block builds in Red Hat if the repository is on a specific commit hash.
|
||||
* Simplified and reduced the size of openmp host runtime
|
||||
* Switched to default OpenMP 5.0
|
||||
|
||||
### Printf Functionality in ROCm Re-Enabled
|
||||
Known issues with hc:printf have been addressed in ROCm v2.10. The hc:printf functionality has now been re-enabled on all supported distros.
|
||||
For more information, see https://github.com/ROCm-Developer-Tools/aomp
|
||||
|
||||
|
||||
## Known Issues
|
||||
### Memory Access Fault Error While Running RCCL in Docker Container
|
||||
Issue: The Memory Access Fault error appears while running ROCm Communication Collectives Library (RCCL) tests in the Docker container.
|
||||
## ROCm COMMUNICATIONS COLLECTIVE LIBRARY
|
||||
|
||||
Resolution: While launching the Docker container to run tests related to RCCL, including PyTorch, increase the size limit for the shared memory (SHM) directory to 1 GB. To increase the size limit of the shared memory directory, enter:
|
||||
### Compatibility with NVIDIA Communications Collective Library v2\.7 API
|
||||
|
||||
“--shm-size = 1G”
|
||||
ROCm Communications Collective Library (RCCL) is now compatible with the NVIDIA Communications Collective Library (NCCL) v2.7 API.
|
||||
|
||||
By default, Docker uses only16 MB of shared memory. Running a Docker container for RCCL requires you to resize the limit to 1 GB.
|
||||
RCCL (pronounced "Rickle") is a stand-alone library of standard collective communication routines for GPUs, implementing all-reduce, all-gather, reduce, broadcast, reduce-scatter, gather, scatter, and all-to-all. There is also initial support for direct GPU-to-GPU send and receive operations. It has been optimized to achieve high bandwidth on platforms using PCIe, xGMI as well as networking using InfiniBand Verbs or TCP/IP sockets. RCCL supports an arbitrary number of GPUs installed in a single node or multiple nodes, and can be used in either single- or multi-process (e.g., MPI) applications.
|
||||
|
||||
### Workaround for Tracer Library Fails to Load on RHEL
|
||||
Issue: When running /opt/rocm/bin/rocprof --hip-trace <output filename>, a warning message is printed to console: "Tool lib "/opt/rocm/roctracer/tool/libtracer_tool.so" failed to load", and no output file is generated, on systems with RHEL distro.
|
||||
The collective operations are implemented using ring and tree algorithms and have been optimized for throughput and latency. For best performance, small operations can be either batched into larger operations or aggregated through the API.
|
||||
|
||||
Resolution: You can use either of the following workarounds to fix the issue:
|
||||
For more information about RCCL APIs and compatibility with NCCL v2.7, see
|
||||
https://rccl.readthedocs.io/en/develop/index.html
|
||||
|
||||
• Run Idconfig
|
||||
|
||||
'SUDO LDCONFIG'
|
||||
## Singular Value Decomposition of Bi\-diagonal Matrices
|
||||
|
||||
or
|
||||
|
||||
• Configure LD_LIBRARY_PATH
|
||||
Rocsolver_bdsqr now computes the Singular Value Decomposition (SVD) of bi-diagonal matrices. It is an auxiliary function for the SVD of general matrices (function rocsolver_gesvd).
|
||||
|
||||
'EXPORT LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/OPT/ROCM/ROCTRACER/LIB'
|
||||
BDSQR computes the singular value decomposition (SVD) of a n-by-n bidiagonal matrix B.
|
||||
|
||||
The SVD of B has the following form:
|
||||
|
||||
## Deprecated Features
|
||||
The following features are deprecated in the AMD ROCm v2.10 release.
|
||||
B = Ub * S * Vb'
|
||||
where
|
||||
• S is the n-by-n diagonal matrix of singular values of B
|
||||
• the columns of Ub are the left singular vectors of B
|
||||
• the columns of Vb are its right singular vectors
|
||||
|
||||
### ROCm OpenCL Driver
|
||||
The AMD ROCm-OpenCL-Driver is now deprecated. Users should migrate to ROCm-CompilerSupport, which provides more comprehensive functionality. The compiler support repository provides various lightning compiler-related services. It currently contains a single library, the Code Object Manager (Comgr) at lib/comgr.
|
||||
The computation of the singular vectors is optional; this function accepts input matrices U (of size nu-by-n) and V (of size n-by-nv) that are overwritten with U*Ub and Vb’*V. If nu = 0 no left vectors are computed; if nv = 0 no right vectors are computed.
|
||||
|
||||
ROCm-OpenCL-Driver will no longer be actively maintained after the v2.10 release. If your application was developed with the ROCm-OpenCL-Driver, we would encourage you to switch to the ROCm-CompilerSupport repository.
|
||||
Optionally, this function can also compute Ub’*C for a given n-by-nc input matrix C.
|
||||
|
||||
### Peer-to-Peer Bridge Driver for PeerDirect
|
||||
The Peer-to-Peer bridge driver for the PeerDirect feature still works in the current release, however, it is now included as part of the ROCk kernel driver. ROCmRDMA allows third-party kernel drivers to utilize DMA access to the GPU memory. It allows a direct path for data exchange (peer-to-peer) using the standard features of PCI Express.
|
||||
PARAMETERS
|
||||
|
||||
Currently, ROCmRDMA provides the following benefits:
|
||||
• [in] handle: rocblas_handle.
|
||||
|
||||
• Direct access to ROCm memory for 3rd party PCIe devices
|
||||
• [in] uplo: rocblas_fill.
|
||||
|
||||
• Support for PeerDirect(c) interface to offloads the CPU when dealing with ROCm memory for RDMA network stacks
|
||||
Specifies whether B is upper or lower bidiagonal.
|
||||
|
||||
## Deploying ROCm
|
||||
AMD hosts both Debian and RPM repositories for the ROCm v2.10x packages.
|
||||
• [in] n: rocblas_int. n >= 0.
|
||||
|
||||
The following directions show how to install ROCm on supported Debian-based systems such as Ubuntu 18.04.
|
||||
The number of rows and columns of matrix B.
|
||||
|
||||
Note: These directions may not work as written on unsupported Debian-based distributions. For example, newer versions of Ubuntu may not be compatible with the rock-dkms kernel driver. In this case, you can exclude the rocm-dkms and rock-dkms packages.
|
||||
• [in] nv: rocblas_int. nv >= 0.
|
||||
|
||||
For more information on the ROCm binary structure, see
|
||||
https://github.com/RadeonOpenCompute/ROCm/blob/master/README.md#rocm-binary-package-structure
|
||||
The number of columns of matrix V.
|
||||
|
||||
For information about upstream kernel drivers, see the Using Debian-based ROCm with Upstream Kernel Drivers section.
|
||||
• [in] nu: rocblas_int. nu >= 0.
|
||||
|
||||
## Ubuntu
|
||||
### Installing a ROCm Package from a Debian Repository
|
||||
To install from a Debian Repository:
|
||||
1. Run the following code to ensure that your system is up to date:
|
||||
|
||||
sudo apt update
|
||||
|
||||
sudo apt dist-upgrade
|
||||
|
||||
sudo apt install libnuma-dev
|
||||
|
||||
sudo reboot
|
||||
|
||||
|
||||
2. Add the ROCm apt repository.
|
||||
The number of rows of matrix U.
|
||||
|
||||
For Debian-based systems like Ubuntu, configure the Debian ROCm repository as follows:
|
||||
|
||||
wget -q0 –
|
||||
http://repo.radeon.com/rocm/apt/debian/rocm.gpg.key |
|
||||
• [in] nc: rocblas_int. nu >= 0.
|
||||
|
||||
sudo apt-key add -echo 'deb [arch=amd64]
|
||||
http://repo.radeon.com/rocm/apt/debian/ xenial main' |
|
||||
The number of columns of matrix C.
|
||||
|
||||
sudo tee /etc/apt/sources.list.d/rocm.list
|
||||
|
||||
The gpg key may change; ensure it is updated when installing a new release. If the key signature verification fails while updating, re-add the key from the ROCm apt repository.
|
||||
• [inout] D: pointer to real type. Array on the GPU of dimension n.
|
||||
|
||||
The current rocm.gpg.key is not available in a standard key ring distribution, but has the following sha1sum hash:
|
||||
On entry, the diagonal elements of B. On exit, if info = 0, the singular values of B in decreasing order; if info > 0, the diagonal elements of a bidiagonal matrix orthogonally equivalent to B.
|
||||
|
||||
e85a40d1a43453fe37d63aa6899bc96e08f2817a rocm.gpg.key
|
||||
|
||||
• [inout] E: pointer to real type. Array on the GPU of dimension n-1.
|
||||
|
||||
3. Install the ROCm meta-package.
|
||||
Update the appropriate repository list and install the rocm-dkms meta-package:
|
||||
On entry, the off-diagonal elements of B. On exit, if info > 0, the off-diagonal elements of a bidiagonal matrix orthogonally equivalent to B (if info = 0 this matrix converges to zero).
|
||||
|
||||
sudo apt update
|
||||
|
||||
sudo apt install rocm-dkms
|
||||
• [inout] V: pointer to type. Array on the GPU of dimension ldv*nv.
|
||||
|
||||
On entry, the matrix V. On exit, it is overwritten with Vb’*V. (Not referenced if nv = 0).
|
||||
|
||||
4. Set permissions.
|
||||
To access the GPU, you must be a user in the video group. Ensure your user account is a member of the video group prior to using ROCm. To identify the groups you are a member of, use the following command:
|
||||
|
||||
groups
|
||||
|
||||
|
||||
5. To add your user to the video group, use the following command for the sudo password:
|
||||
|
||||
sudo usermod -a -G video $LOGNAME
|
||||
• [in] ldv: rocblas_int. ldv >= n if nv > 0, or ldv >=1 if nv = 0.
|
||||
|
||||
6. By default, add any future users to the video group. Run the following command to add users to the video group:
|
||||
Specifies the leading dimension of V.
|
||||
|
||||
echo 'ADD_EXTRA_GROUPS=1' | sudo tee -a /etc/adduser.conf
|
||||
|
||||
echo 'EXTRA_GROUPS=video' | sudo tee -a /etc/adduser.conf
|
||||
|
||||
7. Restart the system.
|
||||
• [inout] U: pointer to type. Array on the GPU of dimension ldu*n.
|
||||
|
||||
8. Test the basic ROCm installation.
|
||||
On entry, the matrix U. On exit, it is overwritten with U*Ub. (Not referenced if nu = 0).
|
||||
|
||||
9. After restarting the system, run the following commands to verify that the ROCm installation is successful. If you see your GPUs listed by both commands, the installation is considered successful.
|
||||
• [in] ldu: rocblas_int. ldu >= nu.
|
||||
|
||||
/opt/rocm/bin/rocminfo
|
||||
/opt/rocm/opencl/bin/x86_64/clinfo
|
||||
Specifies the leading dimension of U.
|
||||
|
||||
Note: To run the ROCm programs more efficiently, add the ROCm binaries in your PATH.
|
||||
• [inout] C: pointer to type. Array on the GPU of dimension ldc*nc.
|
||||
|
||||
echo 'export PATH=$PATH:/opt/rocm/bin:/opt/rocm/profiler/bin:/opt/rocm/opencl/bin/x86_64' |
|
||||
sudo tee -a /etc/profile.d/rocm.sh
|
||||
On entry, the matrix C. On exit, it is overwritten with Ub’*C. (Not referenced if nc = 0).
|
||||
|
||||
If you have an installation issue, refer the FAQ at:
|
||||
https://rocm.github.io/install_issues.html
|
||||
• [in] ldc: rocblas_int. ldc >= n if nc > 0, or ldc >=1 if nc = 0.
|
||||
|
||||
Specifies the leading dimension of C.
|
||||
|
||||
• [out] info: pointer to a rocblas_int on the GPU.
|
||||
|
||||
### Uninstalling ROCm Packages from Ubuntu
|
||||
To uninstall the ROCm packages from Ubuntu 1v6.04 or Ubuntu v18.04, run the following command:
|
||||
If info = 0, successful exit. If info = i > 0, i elements of E have not converged to zero.
|
||||
|
||||
sudo apt autoremove rocm-dkms rocm-dev rocm-utils
|
||||
For more information, see
|
||||
https://rocsolver.readthedocs.io/en/latest/userguide_api.html#rocsolver-type-bdsqr
|
||||
|
||||
|
||||
### Installing Development Packages for Cross Compilation
|
||||
It is recommended that you develop and test development packages on different systems. For example, some development or build systems may not have an AMD GPU installed. In this scenario, you must avoid installing the ROCk kernel driver on the development system.
|
||||
### rocSPARSE_gemmi\() Operations for Sparse Matrices
|
||||
|
||||
Instead, install the following development subset of packages:
|
||||
This enhancement provides a dense matrix sparse matrix multiplication using the CSR storage format.
|
||||
rocsparse_gemmi multiplies the scalar αα with a dense m×km×k matrix AA and the sparse k×nk×n matrix BB defined in the CSR storage format, and adds the result to the dense m×nm×n matrix CC that is multiplied by the scalar ββ, such that
|
||||
C:=α⋅op(A)⋅op(B)+β⋅CC:=α⋅op(A)⋅op(B)+β⋅C
|
||||
with
|
||||
|
||||
sudo apt update
|
||||
sudo apt install rocm-dev
|
||||
op(A)=⎧⎩⎨⎪⎪A,AT,AH,if trans_A == rocsparse_operation_noneif trans_A == rocsparse_operation_transposeif trans_A == rocsparse_operation_conjugate_transposeop(A)={A,if trans_A == rocsparse_operation_noneAT,if trans_A == rocsparse_operation_transposeAH,if trans_A == rocsparse_operation_conjugate_transpose
|
||||
|
||||
Note: To execute ROCm enabled applications, you must install the full ROCm driver stack on your system.
|
||||
and
|
||||
|
||||
op(B)=⎧⎩⎨⎪⎪B,BT,BH,if trans_B == rocsparse_operation_noneif trans_B == rocsparse_operation_transposeif trans_B == rocsparse_operation_conjugate_transposeop(B)={B,if trans_B == rocsparse_operation_noneBT,if trans_B == rocsparse_operation_transposeBH,if trans_B == rocsparse_operation_conjugate_transpose
|
||||
Note: This function is non-blocking and executed asynchronously with the host. It may return before the actual computation has finished.
|
||||
|
||||
### Using Debian-based ROCm with Upstream Kernel Drivers
|
||||
You can install the ROCm user-level software without installing the AMD's custom ROCk kernel driver. To use the upstream kernels, run the following commands instead of installing rocm-dkms:
|
||||
For more information and examples, see
|
||||
https://rocsparse.readthedocs.io/en/master/usermanual.html#rocsparse-gemmi
|
||||
|
||||
|
||||
sudo apt update
|
||||
sudo apt install rocm-dev
|
||||
echo 'SUBSYSTEM=="kfd", KERNEL=="kfd", TAG+="uaccess", GROUP="video"' | sudo tee /etc/udev/rules.d/70-kfd.rules
|
||||
# Known Issues
|
||||
The following are the known issues in this release.
|
||||
|
||||
## (AOMP) ‘Undefined Hidden Symbol’ Linker Error Causes Compilation Failure in HIP
|
||||
|
||||
The HIP example device_lib fails to compile due to unreferenced symbols with Link Time Optimization resulting in ‘undefined hidden symbol’ errors.
|
||||
|
||||
## CentOS RHEL
|
||||
This issue is under investigation and there is no known workaround at this time.
|
||||
|
||||
This section describes how to install ROCm on supported RPM-based systems such as CentOS v7.6.
|
||||
|
||||
Note: The following instructions may not work on unsupported RPM-based distributions. For example, Fedora may not be compatible with the rock-dkms kernel driver. You can exclude the rocm-dkms and rock-dkms packages and use the upstream kernel driver instead.
|
||||
## MIGraphX Fails for fp16 Datatype
|
||||
The MIGraphX functionality does not work for the fp16 datatype.
|
||||
|
||||
Note: Although support for CentOS/RHEL v7 was added in ROCm v1.8, ROCm requires a special runtime environment provided by the RHEL Software Collections and additional dkms support packages to install and run correctly.
|
||||
The following workaround is recommended:
|
||||
|
||||
For more details, refer:
|
||||
https://github.com/RadeonOpenCompute/ROCm/blob/master/README.md#rocm-binary-package-structure
|
||||
Use the AMD ROCm v3.3 of MIGraphX
|
||||
|
||||
### Preparing RHEL v7 (7.6) for Installation
|
||||
RHEL is a subscription-based operating system. You must enable the external repositories to install on the devtoolset-7 environment and the dkms support files.
|
||||
Or
|
||||
|
||||
Note: The following steps do not apply to the CentOS installation.
|
||||
Build MIGraphX v3.7 from the source using AMD ROCm v3.3
|
||||
|
||||
1. The subscription for RHEL must be enabled and attached to a pool ID. See the Obtaining an RHEL image and license page for instructions on registering your system with the RHEL subscription server and attaching to a pool id.
|
||||
## Missing Google Test Installation May Cause RCCL Unit Test Compilation Failure
|
||||
Users of the RCCL install.sh script may encounter an RCCL unit test compilation error. It is recommended to use CMAKE directly instead of install.sh to compile RCCL. Ensure Google Test 1.10+ is available in the CMAKE search path.
|
||||
|
||||
2. Enable the following repositories:
|
||||
|
||||
sudo subscription-manager repos --enable rhel-server-rhscl-7-rpms
|
||||
sudo subscription-manager repos --enable rhel-7-server-optional-rpms
|
||||
sudo subscription-manager repos --enable rhel-7-server-extras-rpms
|
||||
As a workaround, use the latest RCCL from the GitHub development branch at:
|
||||
https://github.com/ROCmSoftwarePlatform/rccl/pull/237
|
||||
|
||||
3. Enable additional repositories by downloading and installing the epel-release-latest-7 repository RPM:
|
||||
|
||||
sudo rpm -ivh
|
||||
## Issue with Peer-to-Peer Transfers
|
||||
Using peer-to-peer (P2P) transfers on systems without the hardware P2P assistance may produce incorrect results.
|
||||
|
||||
For more details, see
|
||||
https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm
|
||||
Ensure the hardware supports peer-to-peer transfers and enable the peer-to-peer setting in the hardware to resolve this issue.
|
||||
|
||||
4. Install and set up Devtoolset-7.
|
||||
|
||||
To setup the Devtoolset-7 environment, follow the instructions on this page:
|
||||
https://www.softwarecollections.org/en/scls/rhscl/devtoolset-7/
|
||||
## Partial Loss of Tracing Events for Large Applications
|
||||
An internal tracing buffer allocation issue can cause a partial loss of some tracing events for large applications.
|
||||
|
||||
Note: devtoolset-7 is a software collections package and is not supported by AMD.
|
||||
As a workaround, rebuild the roctracer/rocprofiler libraries from the GitHub ‘roc-3.7’ branch at:
|
||||
• https://github.com/ROCm-Developer-Tools/rocprofiler
|
||||
• https://github.com/ROCm-Developer-Tools/roctracer
|
||||
|
||||
### Installing CentOS/RHEL (v7.6) for DKMS
|
||||
|
||||
Use the dkms tool to install the kernel drivers on CentOS/RHEL v7.6:
|
||||
## GPU Kernel C++ Names Not Demangled
|
||||
GPU kernel C++ names in the profiling traces and stats produced by ‘—hsa-trace’ option are not demangled.
|
||||
|
||||
sudo yum install -y epel-release
|
||||
sudo yum install -y dkms kernel-headers-`uname -r` kernel-devel-`uname -r`
|
||||
As a workaround, users may choose to demangle the GPU kernel C++ names as required.
|
||||
|
||||
|
||||
## ROCm Installation
|
||||
### Installing ROCm
|
||||
## ‘rocprof’ option ‘--parallel-kernels’ Not Supported in This Release
|
||||
|
||||
To install ROCm on your system, follow the instructions below:
|
||||
‘rocprof’ option ‘--parallel-kernels’ is available in the options list, however, it is not fully validated and supported in this release.
|
||||
|
||||
1. Delete the previous versions of ROCm before installing the latest version.
|
||||
2. Create a /etc/yum.repos.d/rocm.repo file with the following contents:
|
||||
## Random Soft Hang Observed When Running ResNet-Based Models
|
||||
|
||||
[ROCm]
|
||||
name=ROCm
|
||||
baseurl=http://repo.radeon.com/rocm/yum/rpm
|
||||
enabled=1
|
||||
gpgcheck=0
|
||||
A random soft hang is observed when running ResNet-based models for a loop run of more than 25 to 30 hours. The issue is observed on both PyTorch and TensorFlow frameworks.
|
||||
You can terminate the unresponsive process to temporarily resolve the issue.
|
||||
|
||||
Note: The URL of the repository must point to the location of the repositories’ repodata database.
|
||||
There is no known workaround at this time.
|
||||
|
||||
3. Install ROCm components using the following command:
|
||||
|
||||
sudo yum install rocm-dkms
|
||||
|
||||
4.Restart the system.
|
||||
The rock-dkms component is installed and the /dev/kfd device is now available.
|
||||
# Deploying ROCm
|
||||
AMD hosts both Debian and RPM repositories for the ROCm v3.7.x packages.
|
||||
|
||||
### Setting Permissions
|
||||
To configure permissions, following the instructions below:
|
||||
For more information on ROCM installation on all platforms, see
|
||||
|
||||
1. Ensure that your user account is a member of the "video" or "wheel" group prior to using the ROCm driver. You can find which groups you are a member of with the following command:
|
||||
https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
|
||||
|
||||
groups
|
||||
|
||||
2. Add your user to the video (or wheel) group you will need the sudo password and can use the following command:
|
||||
|
||||
sudo usermod -a -G video $LOGNAME
|
||||
|
||||
Note: All future users must be added to the "video" group by default. To add the users to the group, run the following commands
|
||||
|
||||
echo 'ADD_EXTRA_GROUPS=1' | sudo tee -a /etc/adduser.conf
|
||||
echo 'EXTRA_GROUPS=video' | sudo tee -a /etc/adduser.conf
|
||||
|
||||
Note: The current release supports CentOS/RHEL v7.6. Before updating to the latest version of the operating system, delete the ROCm packages to avoid DKMS-related issues.
|
||||
|
||||
3. Restart the system.
|
||||
|
||||
### Testing the ROCm Installation
|
||||
After restarting the system, run the following commands to verify that the ROCm installation is successful. If you see your GPUs listed, you are good to go!
|
||||
|
||||
/opt/rocm/bin/rocminfo
|
||||
/opt/rocm/opencl/bin/x86_64/clinfo
|
||||
|
||||
Note: Add the ROCm binaries in your PATH for easy implementation of the ROCm programs.
|
||||
|
||||
echo 'export PATH=$PATH:/opt/rocm/bin:/opt/rocm/profiler/bin:/opt/rocm/opencl/bin/x86_64' | sudo tee -a /etc/profile.d/rocm.sh
|
||||
|
||||
For more information about installation issues, see:
|
||||
https://rocm.github.io/install_issues.html
|
||||
|
||||
|
||||
### Performing an OpenCL-only Installation of ROCm
|
||||
Some users may want to install a subset of the full ROCm installation. If you are trying to install on a system with a limited amount of storage space, or which will only run a small collection of known applications, you may want to install only the packages that are required to run OpenCL applications. To do that, you can run the following installation command instead of the command to install rocm-dkms.
|
||||
|
||||
sudo yum install rock-dkms rocm-opencl-devel
|
||||
|
||||
#### Compiling Applications Using HCC, HIP, and Other ROCm Software
|
||||
To compile applications or samples, run the following command to use gcc-7.2 provided by the devtoolset-7 environment:
|
||||
|
||||
scl enable devtoolset-7 bash
|
||||
|
||||
### Uninstalling ROCm from CentOS/RHEL v7.6
|
||||
To uninstall the ROCm packages, run the following command:
|
||||
|
||||
sudo yum autoremove rocm-dkms rock-dkms
|
||||
|
||||
### Installing Development Packages for Cross Compilation
|
||||
You can develop and test ROCm packages on different systems. For example, some development or build systems may not have an AMD GPU installed. In this scenario, you can avoid installing the ROCm kernel driver on your development system. Instead, install the following development subset of packages:
|
||||
|
||||
sudo yum install rocm-dev
|
||||
|
||||
Note: To execute ROCm-enabled applications, you will require a system installed with the full ROCm driver stack.
|
||||
|
||||
### Using ROCm with Upstream Kernel Drivers
|
||||
You can install ROCm user-level software without installing AMD's custom ROCk kernel driver. To use the upstream kernel drivers, run the following commands
|
||||
|
||||
sudo yum install rocm-dev
|
||||
echo 'SUBSYSTEM=="kfd", KERNEL=="kfd", TAG+="uaccess", GROUP="video"' | sudo tee /etc/udev/rules.d/70-kfd.rules
|
||||
|
||||
Note: You can use this command instead of installing rocm-dkms.
|
||||
|
||||
|
||||
### ROCm Installation - Known Issues and Workarounds
|
||||
#### Docker container environment variable setting
|
||||
|
||||
Issue: Applications fail when a Docker container is launched on a NUMA system without --security-opt seccomp=unconfined.
|
||||
|
||||
Resolution: Set "--security-opt seccomp=unconfined" to fix this issue.
|
||||
|
||||
#### Closed source components
|
||||
The ROCm platform relies on some closed source components to provide functionalities like HSA image support. These components are only available through the ROCm repositories, and they may be deprecated or become open source components in the future. These components are made available in the following packages:
|
||||
|
||||
• hsa-ext-rocr-dev
|
||||
|
||||
|
||||
## Getting the ROCm Source Code
|
||||
AMD ROCm is built from open source software. It is, therefore, possible to modify the various components of ROCm by downloading the source code and rebuilding the components. The source code for ROCm components can be cloned from each of the GitHub repositories using git. For easy access to download the correct versions of each of these tools, the ROCm repository contains a repo manifest file called default.xml. You can use this manifest file to download the source code for ROCm software.
|
||||
|
||||
### Installing the Repo
|
||||
The repo tool from Google® allows you to manage multiple git repositories simultaneously. Run the following commands to install the repo:
|
||||
|
||||
mkdir -p ~/bin/
|
||||
curl https://storage.googleapis.com/git-repo-downloads/repo > ~/bin/repo
|
||||
chmod a+x ~/bin/repo
|
||||
|
||||
Note: You can choose a different folder to install the repo into if you desire. ~/bin/ is used as an example.
|
||||
|
||||
### Downloading the ROCm Source Code
|
||||
The following example shows how to use the repo binary to download the ROCm source code. If you choose a directory other than ~/bin/ to install the repo, you must use that chosen directory in the code as shown below:
|
||||
|
||||
mkdir -p ~/ROCm/
|
||||
cd ~/ROCm/
|
||||
~/bin/repo init -u https://github.com/RadeonOpenCompute/ROCm.git -b roc-2.10.0
|
||||
repo sync
|
||||
|
||||
Note: Using this sample code will cause the repo to download the open source code associated with this ROCm release. Ensure that you have ssh-keys configured on your machine for your GitHub ID prior to the download.
|
||||
|
||||
### Building the ROCm Source Code
|
||||
Each ROCm component repository contains directions for building that component. You can access the desired component for instructions to build the repository.
|
||||
|
||||
|
||||
|
||||
### Hardware and Software Support
|
||||
# Hardware and Software Support
|
||||
ROCm is focused on using AMD GPUs to accelerate computational tasks such as machine learning, engineering workloads, and scientific computing.
|
||||
In order to focus our development efforts on these domains of interest, ROCm supports a targeted set of hardware configurations which are detailed further in this section.
|
||||
|
||||
@@ -530,7 +351,7 @@ As described in the next section, GFX8 GPUs require PCI Express 3.0 (PCIe 3.0) w
|
||||
|
||||
The integrated GPUs in AMD APUs are not officially supported targets for ROCm.
|
||||
As described [below](#limited-support), "Carrizo", "Bristol Ridge", and "Raven Ridge" APUs are enabled in our upstream drivers and the ROCm OpenCL runtime.
|
||||
However, they are not enabled in our HCC or HIP runtimes, and may not work due to motherboard or OEM hardware limitations.
|
||||
However, they are not enabled in the HIP runtime, and may not work due to motherboard or OEM hardware limitations.
|
||||
As such, they are not yet officially supported targets for ROCm.
|
||||
|
||||
For a more detailed list of hardware support, please see [the following documentation](https://rocm.github.io/hardware.html).
|
||||
@@ -558,7 +379,7 @@ GFX9 GPUs can now be run on CPUs without PCIe atomics and on older PCIe generati
|
||||
This is not supported on GPUs below GFX9, e.g. GFX8 cards in the Fiji and Polaris families.
|
||||
|
||||
If you are using any PCIe switches in your system, please note that PCIe Atomics are only supported on some switches, such as Broadcom PLX.
|
||||
When you install your GPUs, make sure you install them in a PCIe 3.0 x16, x8, x4, or x1 slot attached either directly to the CPU's Root I/O controller or via a PCIe switch directly attached to the CPU's Root I/O controller.
|
||||
When you install your GPUs, make sure you install them in a PCIe 3.1.0 x16, x8, x4, or x1 slot attached either directly to the CPU's Root I/O controller or via a PCIe switch directly attached to the CPU's Root I/O controller.
|
||||
|
||||
In our experience, many issues stem from trying to use consumer motherboards which provide physical x16 connectors that are electrically connected as e.g. PCIe 2.0 x4, PCIe slots connected via the Southbridge PCIe I/O controller, or PCIe slots connected through a PCIe switch that does
|
||||
not support PCIe atomics.
|
||||
@@ -576,12 +397,12 @@ from the list provided above for compatibility purposes.
|
||||
##### Limited support
|
||||
|
||||
* ROCm 2.9.x should support PCIe 2.0 enabled CPUs such as the AMD Opteron, Phenom, Phenom II, Athlon, Athlon X2, Athlon II and older Intel Xeon and Intel Core Architecture and Pentium CPUs. However, we have done very limited testing on these configurations, since our test farm has been catering to CPUs listed above. This is where we need community support. _If you find problems on such setups, please report these issues_.
|
||||
* Thunderbolt 1, 2, and 3 enabled breakout boxes should now be able to work with ROCm. Thunderbolt 1 and 2 are PCIe 2.0 based, and thus are only supported with GPUs that do not require PCIe 3.0 atomics (e.g. Vega 10). However, we have done no testing on this configuration and would need community support due to limited access to this type of equipment.
|
||||
* AMD "Carrizo" and "Bristol Ridge" APUs are enabled to run OpenCL, but do not yet support HCC, HIP, or our libraries built on top of these compilers and runtimes.
|
||||
* Thunderbolt 1, 2, and 3 enabled breakout boxes should now be able to work with ROCm. Thunderbolt 1 and 2 are PCIe 2.0 based, and thus are only supported with GPUs that do not require PCIe 3.1.0 atomics (e.g. Vega 10). However, we have done no testing on this configuration and would need community support due to limited access to this type of equipment.
|
||||
* AMD "Carrizo" and "Bristol Ridge" APUs are enabled to run OpenCL, but do not yet support HIP or our libraries built on top of these compilers and runtimes.
|
||||
* As of ROCm 2.1, "Carrizo" and "Bristol Ridge" require the use of upstream kernel drivers.
|
||||
* In addition, various "Carrizo" and "Bristol Ridge" platforms may not work due to OEM and ODM choices when it comes to key configurations parameters such as inclusion of the required CRAT tables and IOMMU configuration parameters in the system BIOS.
|
||||
* Before purchasing such a system for ROCm, please verify that the BIOS provides an option for enabling IOMMUv2 and that the system BIOS properly exposes the correct CRAT table. Inquire with your vendor about the latter.
|
||||
* AMD "Raven Ridge" APUs are enabled to run OpenCL, but do not yet support HCC, HIP, or our libraries built on top of these compilers and runtimes.
|
||||
* AMD "Raven Ridge" APUs are enabled to run OpenCL, but do not yet support HIP or our libraries built on top of these compilers and runtimes.
|
||||
* As of ROCm 2.1, "Raven Ridge" requires the use of upstream kernel drivers.
|
||||
* In addition, various "Raven Ridge" platforms may not work due to OEM and ODM choices when it comes to key configurations parameters such as inclusion of the required CRAT tables and IOMMU configuration parameters in the system BIOS.
|
||||
* Before purchasing such a system for ROCm, please verify that the BIOS provides an option for enabling IOMMUv2 and that the system BIOS properly exposes the correct CRAT table. Inquire with your vendor about the latter.
|
||||
@@ -593,14 +414,6 @@ from the list provided above for compatibility purposes.
|
||||
* As such, we do not support AMD Carrizo and Kaveri APUs as hosts for such GPUs.
|
||||
* Thunderbolt 1 and 2 enabled GPUs are not supported by GFX8 GPUs on ROCm. Thunderbolt 1 & 2 are based on PCIe 2.0.
|
||||
|
||||
### Supported Operating Systems - New operating systems available
|
||||
|
||||
The ROCm 2.9.x platform supports the following operating systems:
|
||||
|
||||
* Ubuntu 16.04.5(Kernel 4.15) and 18.04.3(Kernel 4.15 and Kernel 4.18)
|
||||
* CentOS 7.6 (Using devtoolset-7 runtime support)
|
||||
* RHEL 7.6 (Using devtoolset-7 runtime support)
|
||||
|
||||
#### ROCm support in upstream Linux kernels
|
||||
|
||||
As of ROCm 1.9.0, the ROCm user-level software is compatible with the AMD drivers in certain upstream Linux kernels.
|
||||
@@ -621,187 +434,15 @@ For users that have the option of using either AMD's or the upstreamed driver, t
|
||||
| | Supported GPUs enabled regardless of kernel version | |
|
||||
| | Includes the latest GPU firmware | |
|
||||
| Cons | May not work on all Linux distributions or versions | Features and hardware support varies depending on kernel version |
|
||||
| | Not currently supported on kernels newer than 4.18 | Limits GPU's usage of system memory to 3/8 of system memory |
|
||||
| | Not currently supported on kernels newer than 5.4 | Limits GPU's usage of system memory to 3/8 of system memory (before 5.6). For 5.6 and beyond, both DKMS and upstream kernels allow use of 15/16 of system memory. |
|
||||
| | | IPC and RDMA capabilities are not yet enabled |
|
||||
| | | Not tested by AMD to the same level as `rock-dkms` package |
|
||||
| | | Does not include most up-to-date firmware |
|
||||
|
||||
|
||||
## Software Support
|
||||
As of AMD ROCm v1.9.0, the ROCm user-level software is compatible with the AMD drivers in certain upstream Linux kernels. You have the following options:
|
||||
|
||||
• Use the ROCk kernel driver that is a part of AMD’s ROCm repositories
|
||||
or
|
||||
• Use the upstream driver and only install ROCm user-level utilities from AMD’s ROCm repositories
|
||||
|
||||
The releases of the upstream Linux kernel support the following GPUs in ROCm:
|
||||
|
||||
• Fiji, Polaris 10, Polaris 11
|
||||
• Fiji, Polaris 10, Polaris 11, Vega10
|
||||
• Fiji, Polaris 10, Polaris 11, Vega10, Vega 7nm
|
||||
|
||||
#### Supported Products
|
||||
|
||||
• CUDA v8
|
||||
|
||||
|
||||
## Machine Learning and High Performance Computing Software Stack for AMD GPU
|
||||
|
||||
ROCm Version 2.10
|
||||
For an updated version of the software stack for AMD GPU, see
|
||||
|
||||
### ROCm Binary Package Structure
|
||||
|
||||
ROCm is a collection of software ranging from drivers and runtimes to libraries and developer tools.
|
||||
In AMD's package distributions, these software projects are provided as a separate packages.
|
||||
This allows users to install only the packages they need, if they do not wish to install all of ROCm.
|
||||
These packages will install most of the ROCm software into `/opt/rocm/` by default.
|
||||
|
||||
The packages for each of the major ROCm components are:
|
||||
|
||||
* ROCm Core Components
|
||||
- ROCk Kernel Driver: `rock-dkms`
|
||||
- ROCr Runtime: `hsa-rocr-dev`, `hsa-ext-rocr-dev`
|
||||
- ROCt Thunk Interface: `hsakmt-roct`, `hsakmt-roct-dev`
|
||||
* ROCm Support Software
|
||||
- ROCm SMI: `rocm-smi`
|
||||
- ROCm cmake: `rocm-cmake`
|
||||
- rocminfo: `rocminfo`
|
||||
- ROCm Bandwidth Test: `rocm_bandwidth_test`
|
||||
* ROCm Development Tools
|
||||
- HCC compiler: `hcc`
|
||||
- HIP: `hip_base`, `hip_doc`, `hip_hcc`, `hip_samples`
|
||||
- ROCm Device Libraries: `rocm-device-libs`
|
||||
- ROCm OpenCL: `rocm-opencl`, `rocm-opencl-devel` (on RHEL/CentOS), `rocm-opencl-dev` (on Ubuntu)
|
||||
- ROCM Clang-OCL Kernel Compiler: `rocm-clang-ocl`
|
||||
- Asynchronous Task and Memory Interface (ATMI): `atmi`
|
||||
- ROCr Debug Agent: `rocr_debug_agent`
|
||||
- ROCm Code Object Manager: `comgr`
|
||||
- ROC Profiler: `rocprofiler-dev`
|
||||
- ROC Tracer: `roctracer-dev`
|
||||
- Radeon Compute Profiler: `rocm-profiler`
|
||||
* ROCm Libraries
|
||||
- rocALUTION: `rocalution`
|
||||
- rocBLAS: `rocblas`
|
||||
- hipBLAS: `hipblas`
|
||||
- hipCUB: `hipCUB`
|
||||
- rocFFT: `rocfft`
|
||||
- rocRAND: `rocrand`
|
||||
- rocSPARSE: `rocsparse`
|
||||
- hipSPARSE: `hipsparse`
|
||||
- ROCm SMI Lib: `rocm_smi_lib64`
|
||||
- rocThrust: `rocThrust`
|
||||
- MIOpen: `MIOpen-HIP` (for the HIP version), `MIOpen-OpenCL` (for the OpenCL version)
|
||||
- MIOpenGEMM: `miopengemm`
|
||||
- MIVisionX: `mivisionx`
|
||||
- RCCL: `rccl`
|
||||
|
||||
To make it easier to install ROCm, the AMD binary repositories provide a number of meta-packages that will automatically install multiple other packages.
|
||||
For example, `rocm-dkms` is the primary meta-package that is used to install most of the base technology needed for ROCm to operate.
|
||||
It will install the `rock-dkms` kernel driver, and another meta-package (`rocm-dev`) which installs most of the user-land ROCm core components, support software, and development tools.
|
||||
|
||||
The `rocm-utils` meta-package will install useful utilities that, while not required for ROCm to operate, may still be beneficial to have.
|
||||
Finally, the `rocm-libs` meta-package will install some (but not all) of the libraries that are part of ROCm.
|
||||
|
||||
The chain of software installed by these meta-packages is illustrated below
|
||||
|
||||
```
|
||||
rocm-dkms
|
||||
|--rock-dkms
|
||||
\--rocm-dev
|
||||
|--hsa-rocr-dev
|
||||
|--hsa-ext-rocr-dev
|
||||
|--hsakmt-roct
|
||||
|--hsakmt-roct-dev
|
||||
|--rocm-cmake
|
||||
|--rocm-device-libs
|
||||
|--hcc
|
||||
|--hip_base
|
||||
|--hip_doc
|
||||
|--hip_hcc
|
||||
|--hip_samples
|
||||
|--rocm-smi
|
||||
|--hsa-amd-aqlprofile
|
||||
|--comgr
|
||||
|--rocr_debug_agent
|
||||
\--rocm-utils
|
||||
|--rocminfo
|
||||
\--rocm-clang-ocl # This will cause OpenCL to be installed
|
||||
|
||||
rocm-libs
|
||||
|--rocalution
|
||||
|--hipblas
|
||||
|--rocblas
|
||||
|--rocfft
|
||||
|--rocrand
|
||||
|--hipsparse
|
||||
\--rocsparse
|
||||
```
|
||||
|
||||
These meta-packages are not required but may be useful to make it easier to install ROCm on most systems.
|
||||
|
||||
Note:Some users may want to skip certain packages. For instance, a user that wants to use the upstream kernel drivers (rather than those supplied by AMD) may want to skip the `rocm-dkms` and `rock-dkms` packages, and instead directly install `rocm-dev`.
|
||||
|
||||
Similarly, a user that only wants to install OpenCL support instead of HCC and HIP may want to skip the `rocm-dkms` and `rocm-dev` packages. Instead, they could directly install `rock-dkms`, `rocm-opencl`, and `rocm-opencl-dev` and their dependencies.
|
||||
|
||||
|
||||
### ROCm Platform Packages
|
||||
|
||||
Drivers, ToolChains, Libraries, and Source Code
|
||||
|
||||
The latest supported version of the drivers, tools, libraries and source code for the ROCm platform have been released and are available from the following GitHub repositories:
|
||||
|
||||
#### ROCm Core Components
|
||||
- [ROCk Kernel Driver](https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver/tree/roc-2.10.0)
|
||||
- [ROCr Runtime](https://github.com/RadeonOpenCompute/ROCR-Runtime/tree/roc-2.10.0)
|
||||
- [ROCt Thunk Interface](https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/tree/roc-2.10.0)
|
||||
|
||||
|
||||
#### ROCm Support Software
|
||||
- [ROCm SMI](https://github.com/RadeonOpenCompute/ROC-smi/tree/roc-2.10.0)
|
||||
- [ROCm cmake](https://github.com/RadeonOpenCompute/rocm-cmake/tree/roc-2.10.0)
|
||||
- [rocminfo](https://github.com/RadeonOpenCompute/rocminfo/tree/roc-2.10.0)
|
||||
- [ROCm Bandwidth Test](https://github.com/RadeonOpenCompute/rocm_bandwidth_test/tree/roc-2.10.0)
|
||||
|
||||
#### ROCm Development ToolChains
|
||||
- [HCC compiler](https://github.com/RadeonOpenCompute/hcc/tree/roc-hcc-2.10.0)
|
||||
- [HIP](https://github.com/ROCm-Developer-Tools/HIP/tree/roc-2.10.0)
|
||||
- [ROCm Device Libraries](https://github.com/RadeonOpenCompute/ROCm-Device-Libs/tree/roc-hcc-2.10.0)
|
||||
- ROCm OpenCL, which is created from the following components:
|
||||
- [ROCm OpenCL Runtime](http://github.com/RadeonOpenCompute/ROCm-OpenCL-Runtime/tree/roc-2.10.0)
|
||||
- [ROCm OpenCL Driver](http://github.com/RadeonOpenCompute/ROCm-OpenCL-Driver/tree/roc-2.10.0)
|
||||
- The ROCm OpenCL compiler, which is created from the following components:
|
||||
- [ROCm LLVM OCL](http://github.com/RadeonOpenCompute/llvm/tree/roc-ocl-2.10.0)
|
||||
- [ROCm LLVM HCC](http://github.com/RadeonOpenCompute/llvm/tree/roc-hcc-2.10.0)
|
||||
- [ROCm Clang](http://github.com/RadeonOpenCompute/clang/tree/roc-2.10.0)
|
||||
- [ROCm lld OCL](http://github.com/RadeonOpenCompute/lld/tree/roc-ocl-2.10.0)
|
||||
- [ROCm lld HCC](http://github.com/RadeonOpenCompute/lld/tree/roc-hcc-2.10.0)
|
||||
- [ROCm Device Libraries](https://github.com/RadeonOpenCompute/ROCm-Device-Libs/tree/roc-ocl-2.10.0)
|
||||
- [ROCM Clang-OCL Kernel Compiler](https://github.com/RadeonOpenCompute/clang-ocl/tree/roc-2.10.0)
|
||||
- [Asynchronous Task and Memory Interface (ATMI)](https://github.com/RadeonOpenCompute/atmi/tree/rocm_2.10.0)
|
||||
- [ROCr Debug Agent](https://github.com/ROCm-Developer-Tools/rocr_debug_agent/tree/roc-2.10.0)
|
||||
- [ROCm Code Object Manager](https://github.com/RadeonOpenCompute/ROCm-CompilerSupport/tree/roc-2.10.0)
|
||||
- [ROC Profiler](https://github.com/ROCm-Developer-Tools/rocprofiler/tree/roc-2.10.0)
|
||||
- [ROC Tracer](https://github.com/ROCm-Developer-Tools/roctracer/tree/roc-2.10.x)
|
||||
- [Radeon Compute Profiler](https://github.com/GPUOpen-Tools/RCP/tree/3a49405)
|
||||
- Example Applications:
|
||||
- [HCC Examples](https://github.com/ROCm-Developer-Tools/HCC-Example-Application/tree/ffd65333)
|
||||
- [HIP Examples](https://github.com/ROCm-Developer-Tools/HIP-Examples/tree/roc-2.10.0)
|
||||
|
||||
#### ROCm Libraries
|
||||
- [rocBLAS](https://github.com/ROCmSoftwarePlatform/rocBLAS/tree/rocm-2.10)
|
||||
- [hipBLAS](https://github.com/ROCmSoftwarePlatform/hipBLAS/tree/rocm-2.10)
|
||||
- [rocFFT](https://github.com/ROCmSoftwarePlatform/rocFFT/tree/rocm-2.10)
|
||||
- [rocRAND](https://github.com/ROCmSoftwarePlatform/rocRAND/tree/2.10.0)
|
||||
- [rocSPARSE](https://github.com/ROCmSoftwarePlatform/rocSPARSE/tree/rocm-2.10)
|
||||
- [hipSPARSE](https://github.com/ROCmSoftwarePlatform/hipSPARSE/tree/rocm-2.10)
|
||||
- [rocALUTION](https://github.com/ROCmSoftwarePlatform/rocALUTION/tree/rocm-2.10)
|
||||
- [MIOpenGEMM](https://github.com/ROCmSoftwarePlatform/MIOpenGEMM/tree/6275a879)
|
||||
- [MIOpen](https://github.com/ROCmSoftwarePlatform/MIOpen/tree/roc-2.10.0)
|
||||
- [rocThrust](https://github.com/ROCmSoftwarePlatform/rocThrust/tree/2.10.0)
|
||||
- [ROCm SMI Lib](https://github.com/RadeonOpenCompute/rocm_smi_lib/tree/roc-2.10.0)
|
||||
- [RCCL](https://github.com/ROCmSoftwarePlatform/rccl/tree/2.10.0)
|
||||
- [MIVisionX](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/1.5)
|
||||
- [hipCUB](https://github.com/ROCmSoftwarePlatform/hipCUB/tree/2.10.0)
|
||||
|
||||
|
||||
Features and enhancements introduced in previous versions of ROCm can be found in [version_history.md](version_history.md)
|
||||
https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html#machine-learning-and-high-performance-computing-software-stack-for-amd-gpu-v3-5-0
|
||||
|
||||
444
ROCm_Installation_Guide_v3.7.md
Normal file
444
ROCm_Installation_Guide_v3.7.md
Normal file
@@ -0,0 +1,444 @@
|
||||

|
||||
|
||||
|
||||
# AMD ROCm Installation Guide v3.7
|
||||
|
||||
## Install AMD ROCm
|
||||
|
||||
|
||||
- [Deploying ROCm](#deploying-rocm)
|
||||
|
||||
- [Prerequisites](#prerequisites-1)
|
||||
|
||||
- [Install ROCm on Supported Operating Systems](#supported-operating-systems)
|
||||
|
||||
- [Ubuntu](#ubuntu)
|
||||
- [CentOS RHEL](#centos-rhel)
|
||||
- [SLES 15 Service Pack 1](#sles-15-service-pack-1)
|
||||
|
||||
- [ROCm Installation Known Issues and
|
||||
Workarounds](#rocm-installation-known-issues-and-workarounds)
|
||||
|
||||
|
||||
## Deploying ROCm
|
||||
|
||||
AMD hosts both Debian and RPM repositories for the ROCm v3.x packages.
|
||||
|
||||
The following directions show how to install ROCm on supported Debian-based systems such as Ubuntu 18.04.x
|
||||
|
||||
**Note**: These directions may not work as written on unsupported Debian-based distributions. For example, newer versions of Ubuntu may
|
||||
not be compatible with the rock-dkms kernel driver. In this case, you can exclude the rocm-dkms and rock-dkms packages.
|
||||
|
||||
|
||||
## Prerequisites
|
||||
|
||||
In this release, AMD ROCm extends support to Ubuntu 20.04, including dual kernel.
|
||||
|
||||
The AMD ROCm platform is designed to support the following operating systems:
|
||||
|
||||
- Ubuntu 20.04 (5.4 and 5.6-oem) and 18.04.4 (Kernel 5.3)
|
||||
- CentOS 7.8 & RHEL 7.8 (Kernel 3.10.0-1127) (Using devtoolset-7
|
||||
runtime support)
|
||||
- CentOS 8.2 & RHEL 8.2 (Kernel 4.18.0 ) (devtoolset is not required)
|
||||
- SLES 15 SP1
|
||||
|
||||
### FRESH INSTALLATION OF AMD ROCm V3.7 RECOMMENDED
|
||||
|
||||
A fresh and clean installation of AMD ROCm v3.7 is recommended. An upgrade from previous releases to AMD ROCm v3.7 is not supported.
|
||||
|
||||
**Note**: AMD ROCm release v3.3 or prior releases are not fully compatible with AMD ROCm v3.5 and higher versions. You must perform a
|
||||
fresh ROCm installation if you want to upgrade from AMD ROCm v3.3 or older to 3.5 or higher versions and vice-versa.
|
||||
|
||||
**Note**: *render group* is required only for Ubuntu v20.04. For all other ROCm supported operating systems, continue to use *video group*.
|
||||
|
||||
- For ROCm v3.5 and releases thereafter, the *clinfo* path is changed
|
||||
to - */opt/rocm/opencl/bin/clinfo*.
|
||||
|
||||
- For ROCm v3.3 and older releases, the *clinfo* path remains unchanged - */opt/rocm/opencl/bin/x86\_64/clinfo*.
|
||||
|
||||
|
||||
## Supported Operating Systems
|
||||
|
||||
### Ubuntu
|
||||
|
||||
**Installing a ROCm Package from a Debian Repository**
|
||||
|
||||
To install from a Debian Repository:
|
||||
|
||||
1. Run the following code to ensure that your system is up to date:
|
||||
|
||||
```
|
||||
sudo apt update
|
||||
|
||||
sudo apt dist-upgrade
|
||||
|
||||
sudo apt install libnuma-dev
|
||||
|
||||
sudo reboot
|
||||
|
||||
```
|
||||
|
||||
2. Add the ROCm apt repository.
|
||||
|
||||
For Debian-based systems like Ubuntu, configure the Debian ROCm repository as follows:
|
||||
|
||||
**Note**: The public key has changed to reflect the new location. You must update to the new location as the old key will be removed in a
|
||||
future release.
|
||||
|
||||
- Old Key: <http://repo.radeon.com/rocm/apt/debian/rocm.gpg.key>
|
||||
- New Key: <http://repo.radeon.com/rocm/rocm.gpg.key>
|
||||
|
||||
|
||||
```
|
||||
wget -q -O - http://repo.radeon.com/rocm/rocm.gpg.key | sudo apt-key add -
|
||||
|
||||
echo 'deb [arch=amd64] http://repo.radeon.com/rocm/apt/debian/ xenial main' | sudo tee /etc/apt/sources.list.d/rocm.list
|
||||
|
||||
```
|
||||
|
||||
The gpg key may change; ensure it is updated when installing a new release. If the key signature verification fails while updating, re-add
|
||||
the key from the ROCm apt repository.
|
||||
|
||||
The current rocm.gpg.key is not available in a standard key ring distribution, but has the following sha1sum hash:
|
||||
|
||||
e85a40d1a43453fe37d63aa6899bc96e08f2817a rocm.gpg.key
|
||||
|
||||
3. Install the ROCm meta-package. Update the appropriate repository list and install the rocm-dkms meta-package:
|
||||
|
||||
```
|
||||
sudo apt update
|
||||
|
||||
sudo apt install rocm-dkms && sudo reboot
|
||||
```
|
||||
|
||||
4. Set permissions. To access the GPU, you must be a user in the video and render groups. Ensure your user account is a member of the video
|
||||
and render groups prior to using ROCm. To identify the groups you are a member of, use the following command:
|
||||
|
||||
```
|
||||
groups
|
||||
|
||||
```
|
||||
|
||||
5. To add your user to the video and render groups, use the following command with the sudo password:
|
||||
|
||||
```
|
||||
sudo usermod -a -G video $LOGNAME
|
||||
|
||||
sudo usermod -a -G render $LOGNAME
|
||||
|
||||
```
|
||||
|
||||
6. By default, you must add any future users to the video and render groups. To add future users to the video and render groups, run the
|
||||
following command:
|
||||
|
||||
```
|
||||
echo 'ADD_EXTRA_GROUPS=1' | sudo tee -a /etc/adduser.conf
|
||||
|
||||
echo 'EXTRA_GROUPS=video' | sudo tee -a /etc/adduser.conf
|
||||
|
||||
echo 'EXTRA_GROUPS=render' | sudo tee -a /etc/adduser.conf
|
||||
|
||||
```
|
||||
|
||||
7. Restart the system.
|
||||
|
||||
8. After restarting the system, run the following commands to verify that the ROCm installation is successful. If you see your GPUs
|
||||
listed by both commands, the installation is considered successful.
|
||||
|
||||
```
|
||||
/opt/rocm/bin/rocminfo
|
||||
/opt/rocm/opencl/bin/clinfo
|
||||
|
||||
```
|
||||
|
||||
**Note**: To run the ROCm programs, add the ROCm binaries in your PATH.
|
||||
|
||||
```
|
||||
|
||||
echo 'export PATH=$PATH:/opt/rocm/bin:/opt/rocm/profiler/bin:/opt/rocm/opencl/bin' | sudo tee -a /etc/profile.d/rocm.sh
|
||||
|
||||
```
|
||||
|
||||
#### Uninstalling ROCm Packages from Ubuntu
|
||||
|
||||
To uninstall the ROCm packages from Ubuntu 16.04.6 or Ubuntu 18.04.4, run the following command:
|
||||
|
||||
sudo apt autoremove rocm-opencl rocm-dkms rocm-dev rocm-utils && sudo reboot
|
||||
|
||||
#### Installing Development Packages for Cross Compilation
|
||||
|
||||
It is recommended that you develop and test development packages on different systems. For example, some development or build systems may
|
||||
not have an AMD GPU installed. In this scenario, you must avoid installing the ROCk kernel driver on the development system.
|
||||
|
||||
Instead, install the following development subset of packages:
|
||||
|
||||
sudo apt update
|
||||
sudo apt install rocm-dev
|
||||
|
||||
**Note**: To execute ROCm enabled applications, you must install the full ROCm driver stack on your system.
|
||||
|
||||
#### Using Debian-based ROCm with Upstream Kernel Drivers
|
||||
|
||||
You can install the ROCm user-level software without installing the AMD\'s custom ROCk kernel driver. To use the upstream kernels, run the
|
||||
following commands instead of installing rocm-dkms:
|
||||
|
||||
sudo apt update
|
||||
sudo apt install rocm-dev
|
||||
echo 'SUBSYSTEM=="kfd", KERNEL=="kfd", TAG+="uaccess", GROUP="video"' | sudo tee /etc/udev/rules.d/70-kfd.rules
|
||||
|
||||
|
||||
### CentOS RHEL
|
||||
|
||||
#### CentOS v7.7/RHEL v7.8 and CentOS/RHEL 8.1
|
||||
|
||||
This section describes how to install ROCm on supported RPM-based systems such as CentOS v7.7/RHEL v7.8 and CentOS/RHEL v8.1.
|
||||
|
||||
#### Preparing RHEL for Installation
|
||||
|
||||
RHEL is a subscription-based operating system. You must enable the external repositories to install on the devtoolset-7 environment and the
|
||||
dkms support files.
|
||||
|
||||
**Note**: The following steps do not apply to the CentOS installation.
|
||||
|
||||
1. The subscription for RHEL must be enabled and attached to a pool ID. See the Obtaining an RHEL image and license page for instructions on
|
||||
registering your system with the RHEL subscription server and attaching to a pool id.
|
||||
|
||||
2. Enable the following repositories for RHEL v7.x:
|
||||
|
||||
```
|
||||
sudo subscription-manager repos --enable rhel-server-rhscl-7-rpms
|
||||
sudo subscription-manager repos --enable rhel-7-server-optional-rpms
|
||||
sudo subscription-manager repos --enable rhel-7-server-extras-rpms
|
||||
|
||||
```
|
||||
|
||||
3. Enable additional repositories by downloading and installing the epel-release-latest-7/epel-release-latest-8 repository RPM:
|
||||
|
||||
```
|
||||
sudo rpm -ivh <repo>
|
||||
```
|
||||
|
||||
For more details,
|
||||
|
||||
- For RHEL v7.x, see
|
||||
<https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm>
|
||||
|
||||
- For RHEL v8.x, see
|
||||
<https://dl.fedoraproject.org/pub/epel/epel-release-latest-8.noarch.rpm>
|
||||
|
||||
|
||||
4. Install and set up Devtoolset-7.
|
||||
|
||||
**Note**: Devtoolset is not required for CentOS/RHEL v8.x
|
||||
|
||||
To setup the Devtoolset-7 environment, follow the instructions on this page: <https://www.softwarecollections.org/en/scls/rhscl/devtoolset-7/>
|
||||
|
||||
**Note**: devtoolset-7 is a software collections package and is not supported by AMD.
|
||||
|
||||
### Installing CentOS v7.7/v8.1 for DKMS
|
||||
|
||||
Use the dkms tool to install the kernel drivers on CentOS/RHEL:
|
||||
|
||||
sudo yum install -y epel-release
|
||||
sudo yum install -y dkms kernel-headers-`uname -r` kernel-devel-`uname -r`
|
||||
|
||||
|
||||
#### Installing ROCm
|
||||
|
||||
To install ROCm on your system, follow the instructions below:
|
||||
|
||||
1. Delete the previous versions of ROCm before installing the latest version.
|
||||
|
||||
2. Create a /etc/yum.repos.d/rocm.repo file with the following contents:
|
||||
|
||||
- CentOS/RHEL 7.x : <http://repo.radeon.com/rocm/yum/rpm>
|
||||
- CentOS/RHEL 8.x : <http://repo.radeon.com/rocm/centos8/rpm>
|
||||
|
||||
```
|
||||
[ROCm]
|
||||
name=ROCm
|
||||
baseurl=http://repo.radeon.com/rocm/yum/rpm
|
||||
enabled=1
|
||||
gpgcheck=1
|
||||
gpgkey=http://repo.radeon.com/rocm/rocm.gpg.key
|
||||
|
||||
```
|
||||
|
||||
**Note**: The URL of the repository must point to the location of the repositories' repodata database.
|
||||
|
||||
3. Install ROCm components using the following command:
|
||||
|
||||
**Note**: This step is applicable only for CentOS/RHEL v8.1 and is not required for v7.8.
|
||||
|
||||
```
|
||||
sudo yum install rocm-dkms && sudo reboot
|
||||
|
||||
```
|
||||
|
||||
4. Restart the system. The rock-dkms component is installed and the /dev/kfd device is now available.
|
||||
|
||||
5. Set permissions. To access the GPU, you must be a user in the video group. Ensure your user account is a member of the video group prior
|
||||
to using ROCm. To identify the groups you are a member of, use the following command:
|
||||
|
||||
```
|
||||
groups
|
||||
|
||||
```
|
||||
|
||||
6. To add your user to the video group, use the following command with the sudo password:
|
||||
|
||||
```
|
||||
sudo usermod -a -G video $LOGNAME
|
||||
```
|
||||
|
||||
7. By default, add any future users to the video group. Run the following command to add users to the video group:
|
||||
|
||||
```
|
||||
echo 'ADD_EXTRA_GROUPS=1' | sudo tee -a /etc/adduser.conf
|
||||
echo 'EXTRA_GROUPS=video' | sudo tee -a /etc/adduser.conf
|
||||
```
|
||||
|
||||
**Note**: Before updating to the latest version of the operating system, delete the ROCm packages to avoid DKMS-related issues.
|
||||
|
||||
8. Restart the system.
|
||||
|
||||
9. Test the ROCm installation.
|
||||
|
||||
#### Testing the ROCm Installation
|
||||
|
||||
After restarting the system, run the following commands to verify that the ROCm installation is successful. If you see your GPUs listed, you
|
||||
are good to go!
|
||||
|
||||
/opt/rocm/bin/rocminfo
|
||||
/opt/rocm/opencl/bin/clinfo
|
||||
|
||||
**Note**: Add the ROCm binaries in your PATH for easy implementation of the ROCm programs.
|
||||
|
||||
echo 'export PATH=$PATH:/opt/rocm/bin:/opt/rocm/profiler/bin:/opt/rocm/opencl/bin' | sudo tee -a /etc/profile.d/rocm.sh
|
||||
|
||||
#### Compiling Applications Using HCC, HIP, and Other ROCm Software
|
||||
|
||||
To compile applications or samples, run the following command to use gcc-7.2 provided by the devtoolset-7 environment:
|
||||
|
||||
scl enable devtoolset-7 bash
|
||||
|
||||
|
||||
#### Uninstalling ROCm from CentOS/RHEL
|
||||
|
||||
To uninstall the ROCm packages, run the following command:
|
||||
|
||||
sudo yum autoremove rocm-opencl rocm-dkms rock-dkms
|
||||
|
||||
#### Installing Development Packages for Cross Compilation
|
||||
|
||||
You can develop and test ROCm packages on different systems. For example, some development or build systems may not have an AMD GPU
|
||||
installed. In this scenario, you can avoid installing the ROCm kernel driver on your development system. Instead, install the following
|
||||
development subset of packages:
|
||||
|
||||
sudo yum install rocm-dev
|
||||
|
||||
**Note**: To execute ROCm-enabled applications, you will require a system installed with the full ROCm driver stack.
|
||||
|
||||
|
||||
#### Using ROCm with Upstream Kernel Drivers
|
||||
|
||||
You can install ROCm user-level software without installing AMD\'s custom ROCk kernel driver. To use the upstream kernel drivers, run the
|
||||
following commands
|
||||
|
||||
sudo yum install rocm-dev
|
||||
echo 'SUBSYSTEM=="kfd", KERNEL=="kfd", TAG+="uaccess", GROUP="video"' | sudo tee /etc/udev/rules.d/70-kfd.rules
|
||||
sudo reboot
|
||||
|
||||
**Note**: You can use this command instead of installing rocm-dkms.
|
||||
|
||||
**Note**: Ensure you restart the system after ROCm installation.
|
||||
|
||||
|
||||
### SLES 15 Service Pack 1
|
||||
|
||||
The following section tells you how to perform an install and uninstall ROCm on SLES 15 SP 1.
|
||||
|
||||
**Installation**
|
||||
|
||||
1. Install the \"dkms\" package.
|
||||
|
||||
```
|
||||
sudo SUSEConnect --product PackageHub/15.1/x86_64
|
||||
sudo zypper install dkms
|
||||
```
|
||||
2. Add the ROCm repo.
|
||||
|
||||
```
|
||||
sudo zypper clean –all
|
||||
sudo zypper addrepo http://repo.radeon.com/rocm/zyp/zypper/ rocm
|
||||
sudo zypper ref
|
||||
sudo rpm --import http://repo.radeon.com/rocm/rocm.gpg.key
|
||||
sudo zypper --gpg-auto-import-keys install rocm-dkms
|
||||
sudo reboot
|
||||
```
|
||||
3. Run the following command once
|
||||
|
||||
```
|
||||
cat <<EOF | sudo tee /etc/modprobe.d/10-unsupported-modules.conf
|
||||
allow_unsupported_modules 1
|
||||
EOF
|
||||
sudo modprobe amdgpu
|
||||
```
|
||||
4. Verify the ROCm installation.
|
||||
|
||||
5. Run /opt/rocm/bin/rocminfo and /opt/rocm/opencl/bin/clinfo commands to list the GPUs and verify that the ROCm installation is
|
||||
successful.
|
||||
|
||||
6. Set permissions. To access the GPU, you must be a user in the video group. Ensure your user account is a member of the video group prior to using ROCm. To identify the groups you are a member of, use the following command:
|
||||
|
||||
groups
|
||||
|
||||
7. To add your user to the video group, use the following command with the sudo password:
|
||||
|
||||
```
|
||||
sudo usermod -a -G video $LOGNAME
|
||||
```
|
||||
8. By default, add any future users to the video group. Run the following command to add users to the video group:
|
||||
|
||||
```
|
||||
echo 'ADD_EXTRA_GROUPS=1' | sudo tee -a /etc/adduser.conf
|
||||
echo 'EXTRA_GROUPS=video' | sudo tee -a /etc/adduser.conf
|
||||
```
|
||||
9. Restart the system.
|
||||
|
||||
10. Test the basic ROCm installation.
|
||||
|
||||
11. After restarting the system, run the following commands to verify that the ROCm installation is successful. If you see your GPUs
|
||||
listed by both commands, the installation is considered successful.
|
||||
|
||||
```
|
||||
/opt/rocm/bin/rocminfo
|
||||
/opt/rocm/opencl/bin/clinfo
|
||||
```
|
||||
**Note**: To run the ROCm programs more efficiently, add the ROCm binaries in your PATH.
|
||||
|
||||
echo \'export
|
||||
PATH=\$PATH:/opt/rocm/bin:/opt/rocm/profiler/bin:/opt/rocm/opencl/bin\'\|sudo
|
||||
tee -a /etc/profile.d/rocm.sh
|
||||
|
||||
#### Uninstallation
|
||||
|
||||
To uninstall, use the following command:
|
||||
|
||||
sudo zypper remove rocm-opencl rocm-dkms rock-dkms
|
||||
|
||||
**Note**: Ensure all other installed packages/components are removed.
|
||||
|
||||
**Note**: Ensure all the content in the /opt/rocm directory is completely removed. If the command does not remove all the ROCm components/packages, ensure
|
||||
you remove them individually.
|
||||
|
||||
|
||||
## ROCm Installation Known Issues and Workarounds
|
||||
|
||||
### Closed source components
|
||||
|
||||
The ROCm platform relies on some closed source components to provide functionalities like HSA image support. These components are only
|
||||
available through the ROCm repositories, and they may be deprecated or become open source components in the future. These components are made
|
||||
available in the following packages:
|
||||
|
||||
- hsa-ext-rocr-dev
|
||||
BIN
amdblack.jpg
Normal file
BIN
amdblack.jpg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 6.2 KiB |
93
default.xml
93
default.xml
@@ -1,6 +1,5 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<manifest>
|
||||
|
||||
<remote name="roc-github"
|
||||
fetch="http://github.com/RadeonOpenCompute/" />
|
||||
<remote name="rocm-devtools"
|
||||
@@ -11,66 +10,70 @@
|
||||
fetch="https://github.com/GPUOpen-ProfessionalCompute-Libraries/" />
|
||||
<remote name="gpuopen-tools"
|
||||
fetch="https://github.com/GPUOpen-Tools/" />
|
||||
|
||||
<default revision="refs/tags/roc-2.10.0"
|
||||
<remote name="KhronosGroup"
|
||||
fetch="https://github.com/KhronosGroup/" />
|
||||
<default revision="refs/tags/rocm-3.7.0"
|
||||
remote="roc-github"
|
||||
sync-c="true"
|
||||
sync-j="4" />
|
||||
|
||||
<!--list of projects for ROCM-->
|
||||
<project name="ROCK-Kernel-Driver" />
|
||||
<project name="ROCT-Thunk-Interface" />
|
||||
<project name="ROCR-Runtime" />
|
||||
<project name="ROC-smi" />
|
||||
<project name="rocm_smi_lib" remote="roc-github" />
|
||||
<project name="rocm-cmake" />
|
||||
<project name="rocminfo" />
|
||||
|
||||
<project name="rocprofiler" remote="rocm-devtools" revision="refs/tags/roc-2.10.0" />
|
||||
<project name="roctracer" remote="rocm-devtools" revision="roc-2.10.x" />
|
||||
<!-- If you want to get the full OpenCL runtime, there is a separate repo
|
||||
manifest that is more authoritative than the copy in this file. It can
|
||||
be found at the following URL:
|
||||
https://github.com/RadeonOpenCompute/ROCm-OpenCL-Runtime/blob/roc-2.0.0/opencl.xml -->
|
||||
<remote name="KhronosGroup" fetch="https://github.com/KhronosGroup/" />
|
||||
<project name="rocprofiler" remote="rocm-devtools" />
|
||||
<project name="roctracer" remote="rocm-devtools" />
|
||||
<project name="ROCm-OpenCL-Runtime" />
|
||||
<project path="ROCm-OpenCL-Runtime/compiler/driver" name="ROCm-OpenCL-Driver"/>
|
||||
<project path="ROCm-OpenCL-Runtime/compiler/llvm" name="llvm" revision="refs/tags/roc-ocl-2.10.0" />
|
||||
<project path="ROCm-OpenCL-Runtime/compiler/llvm/tools/clang" name="clang" />
|
||||
<project path="ROCm-OpenCL-Runtime/compiler/llvm/tools/lld" name="lld" revision="refs/tags/roc-ocl-2.10.0" />
|
||||
<project path="ROCm-OpenCL-Runtime/library/amdgcn" name="ROCm-Device-Libs" revision="refs/tags/roc-ocl-2.10.0" />
|
||||
|
||||
<project path="ROCm-OpenCL-Runtime/api/opencl/khronos/icd" name="OpenCL-ICD-Loader" remote="KhronosGroup" revision="6c03f8b58fafd9dd693eaac826749a5cfad515f8" />
|
||||
<project name="clang-ocl" />
|
||||
<!-- HCC needs to be recursively synced to get it submodules -->
|
||||
<project name="hcc" sync-s="true" revision="refs/tags/roc-hcc-2.10.0" />
|
||||
<project name="HCC-Example-Application" remote="rocm-devtools" revision="ffd6533305e79eed667badd3c4cdb7879a1281b8" />
|
||||
<project name="HIP" remote="rocm-devtools" revision="refs/tags/roc-2.10.0" />
|
||||
<!--HIP Projects-->
|
||||
<project name="HIP" remote="rocm-devtools" />
|
||||
<project name="HIP-Examples" remote="rocm-devtools" />
|
||||
<project name="ROCclr" remote="rocm-devtools" />
|
||||
<project name="HIPIFY" remote="rocm-devtools" />
|
||||
<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
|
||||
<project name="llvm" path="llvm_amd-common" revision="refs/tags/roc-ocl-2.10.0" />
|
||||
<project name="lld" path="llvm_amd-common/lld" revision="refs/tags/roc-ocl-2.10.0" />
|
||||
<project name="clang" path="llvm_amd-common/clang" />
|
||||
<project name="ROCm-Device-Libs" revision="refs/tags/roc-ocl-2.10.0" />
|
||||
<project name="atmi" revision="refs/tags/rocm_2.10.0" />
|
||||
<project name="llvm-project" path="llvm_amd-stg-open" />
|
||||
<project name="ROCm-Device-Libs" />
|
||||
<project name="atmi" />
|
||||
<project name="ROCm-CompilerSupport" />
|
||||
<project name="rocr_debug_agent" remote="rocm-devtools" />
|
||||
<project name="rocr_debug_agent" remote="rocm-devtools" revision="refs/tags/roc-3.7.0" />
|
||||
<project name="rocm_bandwidth_test" />
|
||||
<project name="RCP" remote="gpuopen-tools" revision="3a49405a1500067c49d181844ec90aea606055bb" />
|
||||
|
||||
<!-- gdb projects -->
|
||||
<project name="ROCgdb" remote="rocm-devtools" />
|
||||
<project name="ROCdbgapi" remote="rocm-devtools" />
|
||||
<!-- ROCm Libraries -->
|
||||
<project name="rocBLAS" remote="rocm-swplat" revision="refs/tags/rocm-2.10" />
|
||||
<project name="hipBLAS" remote="rocm-swplat" revision="refs/tags/rocm-2.10" />
|
||||
<project name="rocFFT" remote="rocm-swplat" revision="refs/tags/rocm-2.10" />
|
||||
<project name="rocRAND" remote="rocm-swplat" revision="refs/tags/2.10.0" />
|
||||
<project name="rocSPARSE" remote="rocm-swplat" revision="refs/tags/rocm-2.10" />
|
||||
<project name="hipSPARSE" remote="rocm-swplat" revision="refs/tags/rocm-2.10" />
|
||||
<project name="rocALUTION" remote="rocm-swplat" revision="refs/tags/rocm-2.10" />
|
||||
<project name="MIOpenGEMM" remote="rocm-swplat" revision="6275a879995b58a6e0b8cca7b1ad8421a5e02ade" />
|
||||
<project name="MIOpen" remote="rocm-swplat" revision="refs/tags/roc-2.10.0" />
|
||||
<project name="rocm_smi_lib" />
|
||||
<project name="rccl" remote="rocm-swplat" revision="refs/tags/2.10.0" />
|
||||
<project name="MIVisionX" remote="gpuopen-libs" revision="refs/tags/1.5" />
|
||||
<project name="rocThrust" remote="rocm-swplat" revision="refs/tags/2.10.0" />
|
||||
<project name="hipCUB" remote="rocm-swplat" revision="refs/tags/2.10.0" />
|
||||
<project name="rocPRIM" remote="rocm-swplat" revision="refs/tags/2.10.0" />
|
||||
|
||||
<project name="rocBLAS" remote="rocm-swplat" />
|
||||
<project name="hipBLAS" remote="rocm-swplat" />
|
||||
<project name="rocFFT" remote="rocm-swplat" />
|
||||
<project name="rocRAND" remote="rocm-swplat" />
|
||||
<project name="rocSPARSE" remote="rocm-swplat" />
|
||||
<project name="rocSOLVER" remote="rocm-swplat" />
|
||||
<project name="hipSPARSE" remote="rocm-swplat" />
|
||||
<project name="rocALUTION" remote="rocm-swplat" />
|
||||
<project name="MIOpenGEMM" remote="rocm-swplat" />
|
||||
<project name="MIOpen" remote="rocm-swplat" />
|
||||
<project name="rccl" remote="rocm-swplat" />
|
||||
<project name="MIVisionX" remote="gpuopen-libs" />
|
||||
<project name="rocThrust" remote="rocm-swplat" />
|
||||
<project name="hipCUB" remote="rocm-swplat" />
|
||||
<project name="rocPRIM" remote="rocm-swplat" />
|
||||
<project name="AMDMIGraphX" remote="rocm-swplat" revision="e66968a25f9342a28af1157b06cbdbf8579c5519" />
|
||||
<project name="ROCmValidationSuite" remote="rocm-devtools" />
|
||||
<!-- Projects for AOMP -->
|
||||
<project name="ROCT-Thunk-Interface" path="aomp/roct-thunk-interface" remote="roc-github" />
|
||||
<project name="ROCR-Runtime" path="aomp/rocr-runtime" remote="roc-github" />
|
||||
<project name="ROCm-Device-Libs" path="aomp/rocm-device-libs" remote="roc-github" />
|
||||
<project name="ROCm-CompilerSupport" path="aomp/rocm-compilersupport" remote="roc-github" />
|
||||
<project name="rocminfo" path="aomp/rocminfo" remote="roc-github" />
|
||||
<project name="HIP" path="aomp/hip-on-vdi" remote="rocm-devtools" />
|
||||
<project name="aomp" path="aomp/aomp" remote="rocm-devtools" />
|
||||
<project name="aomp-extras" path="aomp/aomp-extras" remote="rocm-devtools" />
|
||||
<project name="flang" path="aomp/flang" remote="rocm-devtools" />
|
||||
<project name="amd-llvm-project" path="aomp/amd-llvm-project" remote="rocm-devtools" />
|
||||
<project name="ROCclr" path="aomp/vdi" remote="rocm-devtools" />
|
||||
<project name="ROCm-OpenCL-Runtime" path="aomp/opencl-on-vdi" remote="roc-github" />
|
||||
</manifest>
|
||||
|
||||
@@ -1,7 +1,10 @@
|
||||
## ROCm Version History
|
||||
This file contains archived version history information for the [ROCm project](https://github.com/RadeonOpenCompute/ROCm)
|
||||
|
||||
### Current ROCm Version: 2.10
|
||||
### Current ROCm Version: 3.3
|
||||
- [New features and enhancements in ROCm v3.1](#new-features-and-enhancements-in-rocm-v31)
|
||||
- [New features and enhancements in ROCm v3.0](#new-features-and-enhancements-in-rocm-v30)
|
||||
- [New features and enhancements in ROCm v2.10](#new-features-and-enhancements-in-rocm-v210)
|
||||
- [New features and enhancements in ROCm 2.9](#new-features-and-enhancements-in-rocm-29)
|
||||
- [New features and enhancements in ROCm 2.8](#new-features-and-enhancements-in-rocm-28)
|
||||
- [New features and enhancements in ROCm 2.7.2](#new-features-and-enhancements-in-rocm-272)
|
||||
@@ -23,7 +26,65 @@ This file contains archived version history information for the [ROCm project](h
|
||||
- [New Features as of ROCm 1.5](#new-features-as-of-rocm-15)
|
||||
|
||||
|
||||
## New features and enhancements in ROCm v3.2
|
||||
The AMD ROCm v3.2 release was not productized.
|
||||
|
||||
## New features and enhancements in ROCm v3.1
|
||||
### Change in ROCm Installation Directory Structure
|
||||
|
||||
A fresh installation of the ROCm toolkit installs the packages in the /opt/rocm-<version> folder. Previously, ROCm toolkit packages were installed in the /opt/rocm folder.
|
||||
|
||||
### Reliability, Accessibility, and Serviceability Support for Vega 7nm
|
||||
|
||||
The Reliability, Accessibility, and Serviceability (RAS) support for Vega7nm is now available.
|
||||
|
||||
### SLURM Support for AMD GPU
|
||||
|
||||
SLURM (Simple Linux Utility for Resource Management) is an open source, fault-tolerant, and highly scalable cluster management and job scheduling system for large and small Linux clusters.
|
||||
|
||||
|
||||
## New features and enhancements in ROCm v3.0
|
||||
### Support for CentOS RHEL v7.7 <a id="centos-anchor"></a>
|
||||
Support is extended for CentOS/RHEL v7.7 in the ROCm v3.0 release. For more information about the CentOS/RHEL v7.7 release, see:
|
||||
|
||||
[CentOS/RHEL](https://centos.org/forums/viewtopic.php?t=71657)
|
||||
|
||||
|
||||
### Initial distribution of AOMP 0.7-5 in ROCm v3.0 <a id="aomp-anchor"></a>
|
||||
The code base for this release of AOMP is the Clang/LLVM 9.0 sources as of October 8th, 2019. The LLVM-project branch used to build this release is AOMP-191008. It is now locked. With this release, an artifact tarball of the entire source tree is created. This tree includes a Makefile in the root directory used to build AOMP from the release tarball. You can use Spack to build AOMP from this source tarball or build manually without Spack.
|
||||
|
||||
For more information about AOMP 0.7-5, see: [AOMP](https://github.com/ROCm-Developer-Tools/aomp/tree/roc-3.0.0)
|
||||
|
||||
|
||||
### Fast Fourier Transform Updates
|
||||
The Fast Fourier Transform (FFT) is an efficient algorithm for computing the Discrete Fourier Transform. Fast Fourier transforms are used in signal processing, image processing, and many other areas. The following real FFT performance change is made in the ROCm v3.0 release:
|
||||
|
||||
• Implement efficient real/complex 2D transforms for even lengths.
|
||||
|
||||
Other improvements:
|
||||
|
||||
• More 2D test coverage sizes.
|
||||
|
||||
• Fix buffer allocation error for large 1D transforms.
|
||||
|
||||
• C++ compatibility improvements.
|
||||
|
||||
### MemCopy Enhancement for rocProf
|
||||
In the v3.0 release, the rocProf tool is enhanced with an additional capability to dump asynchronous GPU memcopy information into a .csv file. You can use the '-hsa-trace' option to create the results_mcopy.csv file.
|
||||
Future enhancements will include column labels.
|
||||
|
||||
|
||||
### New features and enhancements in ROCm v2.10
|
||||
#### rocBLAS Support for Complex GEMM
|
||||
The rocBLAS library is a gpu-accelerated implementation of the standard Basic Linear Algebra Subroutines (BLAS). rocBLAS is designed to enable you to develop algorithms, including high performance computing, image analysis, and machine learning.
|
||||
|
||||
In the AMD ROCm release v2.10, support is extended to the General Matrix Multiply (GEMM) routine for multiple small matrices processed simultaneously for rocBLAS in AMD Radeon Instinct MI50. Both single and double precision, CGEMM and ZGEMM, are now supported in rocBLAS.
|
||||
|
||||
#### Support for SLES 15 SP1
|
||||
In the AMD ROCm v2.10 release, support is added for SUSE Linux® Enterprise Server (SLES) 15 SP1. SLES is a modular operating system for both multimodal and traditional IT.
|
||||
|
||||
#### Code Marker Support for rocProfiler and rocTracer Libraries
|
||||
Code markers provide the external correlation ID for the calling thread. This function indicates that the calling thread is entering and leaving an external API region.
|
||||
|
||||
### New features and enhancements in ROCm 2.9
|
||||
|
||||
|
||||
Reference in New Issue
Block a user