Compare commits

..

7 Commits

Author SHA1 Message Date
James Edwards
0631df24e8 Change extraction protocol to http. 2018-06-13 11:07:17 -05:00
Kent Russell
725415b566 Update README to reference roc-1.3.1
Change-Id: I0db7bd9ee83cc9e7cdf821f94f911cc1e1f0c518
2016-11-29 11:35:36 -05:00
Kent Russell
67bdbcfde4 Update README.md to use roc-1.3.1 branch
Change-Id: Ie596ea94e9a0b3e0c64b7128c7dc53dc0cf572d5
2016-11-29 11:33:54 -05:00
Kent Russell
c5eba0cf61 Update default.xml to 1.3.1
Change-Id: I972a18db0b456922a733e34955c4fb3c293a46b3
2016-11-15 07:03:15 -05:00
Kent Russell
bf2f4ddf4b README: update for 1.3 release
Change-Id: I901192123c7876c6ca1a40e90c72415488252e88
2016-11-10 11:09:29 -05:00
James Edwards
3e5f9fc8c9 Update default.xml
Remove / delimiter from revision name.
2016-08-25 15:53:14 -05:00
James Edwards
98e035f0ce Update default.xml 2016-08-25 12:26:00 -05:00
2 changed files with 44 additions and 401 deletions

423
README.md
View File

@@ -1,395 +1,36 @@
## Are You Ready to ROCK?
The ROCm Platform brings a rich foundation to advanced computing by seamlessly
integrating the CPU and GPU with the goal of solving real-world problems.
The ROCm Platform bringing a rich foundation to advanced computing by better
integrating the CPU and GPU to solve real-world problems.
#### Supported CPUs
On April 25th, 2016, we delivered ROCm 1.0 built around three core foundation
elements:
Open Hetrogenous Computing Platform (Linux(R) Driver and Runtime Stack)
optimized for HPC & Ultra-scale class computing Heterogeneous C and C++
Single Source to better address the whole system computation not just a GPU
device HIP acknowledging the need for platform choice when utilizing GPU
computing API
Starting with ROCm 1.8 we have relaxed the use of PCIe Atomics and also PCIe lane choice for Vega10/GFX9 class GPU. So now you can support CPU without PCIe Atomics and also use Gen2 x1 lanes.
Using our knowledge of the HSA Standards and, more importantly, the HSA
Runtime we have been able to successfully extended support to the dGPU with
critical features for NUMA class acceleration. As a result, the ROCK driver is
composed of several components based on our efforts to develop the
Heterogeneous System Architecture for APUs, including the new AMDGPU driver,
the Kernel Fusion Driver (KFD), the HSA+ Runtime and an LLVM based compilation
stack for the building of key language support. This support starts with AMDs
Fiji Family of dGPU, and has expanded to include the Hawaii dGPU Family in
ROCm 1.2.
Currently our GFX8 GPU's (Fiji & Polaris family) still need to use PCIe Gen 3 and PCIe Atomics, but are looking at relaxing this in a future release, once we have fully tested firmware.
Current CPUs which support PCIe Gen3 + PCIe Atomics are:
* AMD Ryzen CPUs;
* AMD EPYC CPUs;
* Intel Xeon E7 V3 or newer CPUs;
* Intel Xeon E5 v3 or newer CPUs;
* Intel Xeon E3 v3 or newer CPUs;
* Intel Core i7 v4, Core i5 v4, Core i3 v4 or newer CPUs (i.e. Haswell family or newer).
For Fiji and Polaris GPU's the ROCm platform leverages PCIe Atomics (Fetch and Add, Compare and Swap,
Unconditional Swap, AtomicsOp Completion).
PCIe Atomics are only supported on PCIe Gen3 enabled CPUs and PCIe Gen3 switches like
Broadcom PLX. When you install your GPUs make sure you install them in a fully
PCIe Gen3 x16 or 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 Gen2 x4 connected via the
Southbridge PCIe I/O controller.
Experimental support for our GFX7 GPUs Radeon R9 290, R9 390, AMD FirePro S9150, S9170 note they do not support or
take advantage of PCIe Atomics. However, we still recommend that you use a CPU
from the list provided above.
#### Not supported or very limited support under ROCm
###### Limited support
* With ROCm 1.8 and Vega10 it should support PCIe Gen2 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. But we have done very limited testing. Since our test farm today has been catering to CPU listed above. This is where we need community support.
* Thunderbolt 1,2 and 3 enabled breakout boxes GPU's should now be able to work with ROCm. Thunderbolt 1 and 2 are PCIe Gen2 based. But we have done no testing on this config and would need comunity support do limited access to this type of equipment
###### Not supported
* We also do not support AMD Carrizo and Kaveri APU as host for compliant dGPU attachments.
* Thunderbolt 1 and 2 enabled GPU's are not supported by ROCm. Thunderbolt 1 & 2 are PCIe Gen2 based.
* AMD Carrizo based APUs have limited support due to OEM & ODM's choices when it comes to some key configuration parameters. On point, we have observed that Carrizo laptops, AIOs and desktop systems showed inconsistencies in exposing and enabling the System BIOS parameters required by the ROCm stack. Before purchasing a Carrizo system for ROCm, please verify that the BIOS provides an option for enabling IOMMUv2. If this is the case, the final requirement is associated with correct CRAT table support - please inquire with the OEM about the latter.
* AMD Merlin/Falcon Embedded System is also not currently supported by the public repo.
* AMD Raven Ridge APU are currently not supported
### New features to ROCm 1.8.1
#### DKMS driver installation
* Debian packages are provided for DKMS on Ubuntu
* RPM packages are provided for CentOS/RHEL 7.4 and 7.5 support
* See the [ROCT-Thunk-Interface](https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/tree/roc-1.8.x) and [ROCK-Kernel-Driver](https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver/tree/roc-1.8.x) for additional documentation on driver setup
#### New distribution suppport
* Binary package support for Ubuntu 16.04
* Binary package support for CentoOS 7.4 and 7.5
* Binary package support for RHEL 7.4 and 7.5
#### Improved OpenMPI via UCX support
* UCX support for OpenMPI
* ROCm RDMA
### The latest ROCm platform - ROCm 1.8.1
### Overview and Installation Instructions
For an overview of the ROCm stack, installation instructions, and other supporting
documentation, please refer to https://radeonopencompute.github.io
### The Latest ROCm Platform - ROCm 1.3
The latest tested version of the drivers, tools, libraries and source code for
the ROCm platform have been released and are available under the roc-1.8.x or rocm-1.8.x tag
of the following GitHub repositories:
* [ROCK-Kernel-Driver](https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver/tree/roc-1.8.x)
* [ROCR-Runtime](https://github.com/RadeonOpenCompute/ROCR-Runtime/tree/roc-1.8.x)
* [ROCT-Thunk-Interface](https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/tree/roc-1.8.x)
* [ROC-smi](https://github.com/RadeonOpenCompute/ROC-smi/tree/roc-1.8.x)
* [HCC compiler](https://github.com/RadeonOpenCompute/hcc/tree/roc-1.8.x)
* [compiler-runtime](https://github.com/RadeonOpenCompute/compiler-rt/tree/roc-1.8.x)
* [HIP](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/tree/roc-1.8.x)
* [HIP-Examples](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP-Examples/tree/roc-1.8.x)
* [atmi](https://github.com/RadeonOpenCompute/atmi/tree/0.3.7)
Additionally, the following mirror repositories that support the HCC compiler
are also available on GitHub, and frozen for the rocm-1.8.0 release:
* [llvm](https://github.com/RadeonOpenCompute/llvm/tree/roc-1.8.x)
* [ldd](https://github.com/RadeonOpenCompute/lld/tree/roc-1.8.x)
* [hcc-clang-upgrade](https://github.com/RadeonOpenCompute/hcc-clang-upgrade/tree/roc-1.8.x)
* [ROCm-Device-Libs](https://github.com/RadeonOpenCompute/ROCm-Device-Libs/tree/roc-1.8.x)
#### Supported Operating Systems - New operating systems available
The ROCm 1.8.1 platform has been tested on the following operating systems:
* Ubuntu 16.04
* CentOS 7.4 (Using devetoolset-7 runtime support)
* RHEL 7.4 (Using devetoolset-7 runtime support)
### Installing from AMD ROCm repositories
AMD is hosting both Debian and RPM repositories for the ROCm 1.8.1 packages at this time.
The packages in the Debian repository have been signed to ensure package integrity.
#### Installing from a Debian repository
##### First make sure your system is up to date
```shell
sudo apt update
sudo apt dist-upgrade
sudo apt install libnuma-dev
sudo reboot
```
##### Optional: Upgrade to 4.13 kernel
Although not required, it is recommended as of ROCm 1.8.0 that the system's kernel is upgraded to the latest 4.13 version available:
```shell
sudo apt install linux-headers-4.13.0-32-generic linux-image-4.13.0-32-generic linux-image-extra-4.13.0-32-generic linux-signed-image-4.13.0-32-generic
sudo reboot
```
##### Add the ROCm apt repository
For Debian based systems, like Ubuntu, configure the Debian ROCm repository as
follows:
```shell
wget -qO - http://repo.radeon.com/rocm/apt/debian/rocm.gpg.key | sudo apt-key add -
sudo sh -c 'echo deb [arch=amd64] http://repo.radeon.com/rocm/apt/debian/ xenial main > /etc/apt/sources.list.d/rocm.list'
```
The gpg key might change, so it may need to be updated when installing a new
release. The current rocm.gpg.key is not avialable in a standard key ring distribution,
but has the following sha1sum hash:
f0d739836a9094004b0a39058d046349aacc1178 rocm.gpg.key
##### Install
Next, update the apt repository list and install the rocm package:
>**Warning**: Before proceeding, make sure to completely
>[uninstall any previous ROCm package](https://github.com/RadeonOpenCompute/ROCm#removing-pre-release-packages):
```shell
sudo apt update
sudo apt install rocm-dkms
```
###### Next set your permissions
With move to upstreaming the KFD driver and the support of DKMS, for all Console aka headless user, you will need to add all your users to the 'video" group by setting the Unix permissions
Configure
Ensure that your user account is a member of the "video" group prior to using the ROCm driver. You can find which groups you are a member of with the following command:
```shell
groups
```
To add yourself to the video group you will need the sudo password and can use the following command:
```shell
sudo usermod -a -G video $LOGNAME
```
Once complete, reboot your system.
Upon Reboot run
```shell
rocminfo
clinfo
```
If you have an [Install Issue ](https://rocm.github.io/install_issues.html) please read this FAQ .
###### Upon restart, to test your OpenCL instance
Build and run Hello World OCL app.
HelloWorld sample:
```shell
wget https://raw.githubusercontent.com/bgaster/opencl-book-samples/master/src/Chapter_2/HelloWorld/HelloWorld.cpp
wget https://raw.githubusercontent.com/bgaster/opencl-book-samples/master/src/Chapter_2/HelloWorld/HelloWorld.cl
```
Build it using the default ROCm OpenCL include and library locations:
```shell
g++ -I /opt/rocm/opencl/include/ ./HelloWorld.cpp -o HelloWorld -L/opt/rocm/opencl/lib/x86_64 -lOpenCL
```
Run it:
```shell
./HelloWorld
```
##### How to un-install from Ubuntu 16.04
To un-install the entire rocm development package execute:
```shell
sudo apt autoremove rocm-dkms
```
##### Installing development packages for cross compilation
It is often useful to develop and test on different systems. In this scenario,
you may prefer to avoid installing the ROCm Kernel to your development system.
In this case, install the development subset of packages:
```shell
sudo apt update
sudo apt install rocm-dev
```
>**Note:** To execute ROCm enabled apps you will require a system with the full
>ROCm driver stack installed
##### Removing pre-release packages
If you installed any of the ROCm pre-release packages from github, they will
need to be manually un-installed:
```shell
sudo apt purge libhsakmt
sudo apt purge compute-firmware
sudo apt purge $(dpkg -l | grep 'kfd\|rocm' | grep linux | grep -v libc | awk '{print $2}')
```
If possible, we would recommend starting with a fresh OS install.
### CentOS/RHEL 7 (both 7.4 and 7.5) Support
Support for CentOS/RHEL 7 has been added in ROCm 1.8, but requires a special
runtime environment provided by the RHEL Software Collections and additional
dkms support packages to properly install in run.
#### Preparing RHEL 7 for installation
RHEL is a subscription based operating system, and must enable several external
repositories to enable installation of the devtoolset-7 environment and the DKMS
support files. These steps are not required for CentOS.
First, the subscription for RHEL must be enabled and attached to a pool id. Please
see Obtaining an RHEL image and license page for instructions on registering your
system with the RHEL subscription server and attaching to a pool id.
Second, enable the following repositories:
```shell
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
```
Third, enable additional repositories by downloading and installing the epel-release-latest-7 repository RPM:
```shell
sudo rpm -ivh https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm
```
#### Install and setup Devtoolset-7
To setup the Devtoolset-7 environment, follow the instructions on this page:
https://www.softwarecollections.org/en/scls/rhscl/devtoolset-7/
Note that devtoolset-7 is a Software Collections package, and is not supported by AMD.
#### Prepare CentOS/RHEL 7.4 for DKMS Install
Installing kernel drivers on CentOS/RHEL 7.4 requires dkms tool being installed:
```shell
sudo yum install -y epel-release
sudo yum install -y dkms kernel-headers-`uname -r`
```
At this point they system can install ROCm using the DKMS drivers.
Installing ROCm on the system
At this point ROCm can be installed on the target system. Create a /etc/yum.repos.d/rocm.repo file with the following contents:
```shell
[ROCm]
name=ROCm
baseurl=http://repo.radeon.com/rocm/yum/rpm
enabled=1
gpgcheck=0
```
The repo's URL should point to the location of the repositories repodata database. Install ROCm components using these commands:
```shell
sudo yum install rocm-dkms
```
The rock-dkms component should be installed and the /dev/kfd device should be available on reboot.
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:
```shell
groups
```
To add yourself to the video (or wheel) group you will need the sudo password and can use the
following command:
```shell
sudo usermod -a -G video $LOGNAME
```
Current release supports up to CentOS/RHEL 7.4 and 7.5. Users should update to the latest version of the OS:
```shell
sudo yum update
```
#### Compiling applications using hcc, hip, etc.
To compile applications or samples, please use gcc-7.2 provided by the devtoolset-7 environment.
To do this, compile all applications after running this command:
```shell
scl enable devtoolset-7 bash
```
#### How to un-install ROCm from CentOS/RHEL 7.4
To un-install the entire rocm development package execute:
```shell
sudo yum autoremove rocm-dkms
```
#### Known Issues / Workarounds
##### If you Plan to Run with X11 - we are seeing X freezes under load
ROCm 1.8.1 a kernel parameter noretry has been set to 1 to improve overall system performance. However it has been proven to bring instability to graphics driver shipped with Ubuntu. This is an ongoing issue and we are looking into it.
Before that, please try apply this change by changing noretry bit to 0.
```shell
echo 0 | sudo tee /sys/module/amdkfd/parameters/noretry
```
Files under /sys won't be preserved after reboot so you'll need to do it every time.
One way to keep noretry=0 is to change /etc/modprobe.d/amdkfd.conf and make it be:
options amdkfd noretry=0
Once it's done, run sudo update-initramfs -u. Reboot and verify /sys/module/amdkfd/parameters/noretry stays as 0.
##### If you are you are using hipCaffe Alexnet training on ImageNet - we are seeing sporadic hangs of hipCaffe during training
##### Users without PCIe atomic support must set HSA_ENABLE_SDMA=0
Some GPUs will work with ROCm if they do not support PCIe atomics. However, these cards cannot use SDMA functionality.
#### Closed source components
The ROCm platform relies on a few closed source components to provide legacy
functionality like HSAIL finalization and debugging/profiling support. These
components are only available through the ROCm repositories, and will either be
deprecated or become open source components in the future. These components are
made available in the following packages:
* hsa-ext-rocr-dev
### Getting ROCm source code
Modifications can be made to the ROCm 1.8 components by modifying the open
source code base and rebuilding the components. Source code can be cloned from
each of the GitHub repositories using git, or users can use the repo command
and the ROCm 1.8 manifest file to download the entire ROCm 1.8 source code.
the ROCm platform have been released and are available under the roc-1.3.1 tag.
The repo tool can be used to checkout the full software stack.
#### Installing repo
Google's repo tool allows you to manage multiple git repositories
simultaneously. You can install it by executing the following commands:
@@ -400,15 +41,17 @@ chmod a+x ~/bin/repo
Note: make sure ~/bin exists and it is part of your PATH
#### Cloning the code
```shell
mkdir ROCm && cd ROCm
repo init -u https://github.com/RadeonOpenCompute/ROCm.git -b roc-1.8.1
repo init -u https://github.com/RadeonOpenCompute/ROCm.git -b roc-1.3.1
repo sync
```
These series of commands will pull all of the open source code associated with
the ROCm 1.8 release. Please ensure that ssh-keys are configured for the
target machine on GitHub for your GitHub ID.
* OpenCL Runtime and Compiler will be submitted to the Khronos Group, prior to
the final release, for conformance testing.
#### Closed Source Components
The ROCm platform relies on a few closed source components to provide legacy
functionality like HSAIL finalization and debugging/profiling support. These
components are only available through the ROCm repositories, and will either be
deprecated or become open source components in the future. These components are
made available in the following packages:
* hsa-ext-rocr-dev

View File

@@ -6,22 +6,22 @@
<remote name="pctools-github"
fetch="http://git@github.com/GPUOpen-ProfessionalCompute-Tools/" />
<default revision="roc-1.8.x"
<default revision="refs/tags/roc-1.3.1"
remote="roc-github"
sync-j="4" />
<project path="ROCK-Kernel-Driver" name="ROCK-Kernel-Driver" />
<project path="ROCT-Thunk-Interface" name="ROCT-Thunk-Interface" />
<project path="ROC-smi" name="ROC-smi" />
<project path="ROCR-Runtime" name="ROCR-Runtime" />
<project path="llvm" name="llvm" />
<project path="llvm-amdgpu-assembler-extra" name="LLVM-AMDGPU-Assembler-Extra" />
<project path="clang" name="clang" />
<project path="hcc" name="hcc" />
<project path="compiler-rt" name="compiler-rt" />
<project path="ROCT-Thunk-Interface" name="ROCT-Thunk-Interface" />
<project path="ROCK-Kernel-Driver" name="ROCK-Kernel-Driver" />
<project path="ROC-smi" name="ROC-smi" />
<project path="ROCnRDMA" name="ROCnRDMA" />
<project path="rdma-perftest" name="rdma-perftest" />
<project path="ROCR-Runtime" name="ROCR-Runtime" />
<project path="HIP" remote="pctools-github" name="HIP" />
<project path="HIP-Examples" remote="pctools-github" name="HIP-Examples" />
<project path="atmi" name="atmi" revision="master" />
<project path="llvm" name="llvm" />
<project path="lld" name="lld" />
<project path="hcc-clang-upgrade" name="hcc-clang-upgrade" />
<project path="ROCm-Device-Libs" name="ROCm-Device-Libs" />
</manifest>