mirror of
https://github.com/ROCm/ROCm.git
synced 2026-01-09 22:58:17 -05:00
Compare commits
97 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
56a992b2eb | ||
|
|
e96a57b0f4 | ||
|
|
dd58fdc330 | ||
|
|
d4ccc7729e | ||
|
|
f5685a4be4 | ||
|
|
682e8995f0 | ||
|
|
64d1a35b5a | ||
|
|
f2e4c22410 | ||
|
|
239b9ee77e | ||
|
|
c6763c13c4 | ||
|
|
dd33dc7742 | ||
|
|
0df4c34855 | ||
|
|
8ca2db6528 | ||
|
|
26526b6853 | ||
|
|
030455ef47 | ||
|
|
f02621bc8a | ||
|
|
2a4c16ee51 | ||
|
|
4dec756b2d | ||
|
|
77cc24a773 | ||
|
|
7bfed202a0 | ||
|
|
980738d46e | ||
|
|
d7c97882e1 | ||
|
|
c4eb6cd4be | ||
|
|
3e4bda88e7 | ||
|
|
8512273309 | ||
|
|
a1bb81003b | ||
|
|
fbcc9809de | ||
|
|
b834187cae | ||
|
|
260cb81efd | ||
|
|
62c11b68f7 | ||
|
|
c7ea2df946 | ||
|
|
3b442534f8 | ||
|
|
84a097d55d | ||
|
|
7cc5548ea3 | ||
|
|
cf7c039199 | ||
|
|
648af6f3f8 | ||
|
|
4f8d605b12 | ||
|
|
783eec4643 | ||
|
|
dfdb135954 | ||
|
|
2b19ff91a6 | ||
|
|
ac4bd217aa | ||
|
|
7c07ce6e89 | ||
|
|
17dce4c250 | ||
|
|
5a113b7799 | ||
|
|
36d82f83f1 | ||
|
|
2d09dfa9ca | ||
|
|
ae280c5745 | ||
|
|
af228d3b64 | ||
|
|
620a4af0b3 | ||
|
|
549042b40e | ||
|
|
a6e1b016fa | ||
|
|
ca40c6ff09 | ||
|
|
9959f915b3 | ||
|
|
94ef8cd402 | ||
|
|
f8af328270 | ||
|
|
d8e77a4181 | ||
|
|
8b91b9c980 | ||
|
|
378cf1eb7d | ||
|
|
73bb1da071 | ||
|
|
cd4ea291e2 | ||
|
|
eeae755296 | ||
|
|
9f8d733da1 | ||
|
|
389750df8c | ||
|
|
93301e03e2 | ||
|
|
7f15331a67 | ||
|
|
3f4e60c4d0 | ||
|
|
f558960c7e | ||
|
|
c1e71f0dcc | ||
|
|
cf622281f4 | ||
|
|
08257cbca7 | ||
|
|
88d4832e84 | ||
|
|
4a77b8ec63 | ||
|
|
47cb66122f | ||
|
|
cb75f9faeb | ||
|
|
8c1d89e69f | ||
|
|
1a315e093f | ||
|
|
42e58efc65 | ||
|
|
04628c0e85 | ||
|
|
883df8b9f5 | ||
|
|
d46888fe1e | ||
|
|
5dd391eb49 | ||
|
|
04534f7b52 | ||
|
|
3e82c69b04 | ||
|
|
39c0ecbbda | ||
|
|
95c6ddd586 | ||
|
|
3b73215554 | ||
|
|
39ebe697ba | ||
|
|
b6c6392ee4 | ||
|
|
6e5b253e67 | ||
|
|
a93a3fe488 | ||
|
|
dfff4e0f40 | ||
|
|
8bd9db4e8e | ||
|
|
bb158e9d7f | ||
|
|
3387f5b9d8 | ||
|
|
42ed737183 | ||
|
|
eab9718cb8 | ||
|
|
4c7d3cdd4c |
577
README.md
577
README.md
@@ -1,299 +1,515 @@
|
||||
## 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.
|
||||
integrating the CPU and GPU with the goal of solving real-world problems.
|
||||
This software enables the high-performance operation of AMD GPUs for computationally-oriented tasks in the Linux operating system.
|
||||
|
||||
On April 25th, 2016, we delivered ROCm 1.0 built around three pillars:
|
||||
### Current ROCm Version: 1.9.0
|
||||
|
||||
1) Open Heterogeneous Computing Platform (Linux Driver and Runtime Stack),
|
||||
optimized for HPC & Ultra-scale class computing;
|
||||
|
||||
2) Heterogeneous C and C++ Single Source Compiler, to approach computation
|
||||
holistically, on a system level, rather than as a discrete GPU artifact;
|
||||
|
||||
3) HIP, acknowledging the need for freedom of choice when it comes to platforms
|
||||
and APIs for GPU computing.
|
||||
- [Hardware Support](#hardware-support)
|
||||
* [Supported GPUs](#supported-gpus)
|
||||
* [Supported CPUs](#supported-cpus)
|
||||
* [Not supported or very limited support under ROCm](#not-supported-or-very-limited-support-under-rocm)
|
||||
- [New features and enhancements in ROCm 1.9.0](#new-features-and-enhancements-in-rocm-190)
|
||||
- [The latest ROCm platform - ROCm 1.9.0](#the-latest-rocm-platform---rocm-190)
|
||||
- [Installing from AMD ROCm repositories](#installing-from-amd-rocm-repositories)
|
||||
* [Ubuntu Support - Installing from a Debian repository](#ubuntu-support---installing-from-a-debian-repository)
|
||||
* [CentOS/RHEL 7 (both 7.4 and 7.5) Support](#centosrhel-7-both-74-and-75-support)
|
||||
- [Known Issues / Workarounds](#known-issues--workarounds)
|
||||
- [Closed source components](#closed-source-components)
|
||||
- [Getting ROCm source code](#getting-rocm-source-code)
|
||||
|
||||
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 accelerating NUMA computation. 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 which provides support for key languages. This support starts with AMD’s
|
||||
Fiji family of dGPUs, and has expanded to include the Hawaii dGPU family in ROCm
|
||||
1.2. ROCm 1.3 further extends support to include the Polaris family of ASICs.
|
||||
### Hardware 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
|
||||
|
||||
#### Supported GPUs
|
||||
Because the ROCm Platform has a focus on particular computational domains, we offer official support for a selection of AMD GPUs that are designed to offer good performance and price in these domains.
|
||||
|
||||
ROCm officially supports AMD GPUs that have use following chips:
|
||||
* GFX8 GPUs
|
||||
* "Fiji" chips, such as on the the AMD Radeon R9 Fury X and Radeon Instinct MI8
|
||||
* "Polaris 10" chips, such as on the AMD Radeon RX 580 and Radeon Instinct MI6
|
||||
* "Polaris 11" chips, such as on the AMD Radeon RX 570 and Radeon Pro WX 4100
|
||||
* GFX9 GPUs
|
||||
* "Vega 10" chips, such as on the AMD Radeon Radeon RX Vega 64 and Radeon Instinct MI25
|
||||
|
||||
ROCm is a collection of software ranging from drivers and runtimnes to libraries and developer tools.
|
||||
Some of this software may work with more GPUs than the "officially supported" list above, though AMD does not make any official claims of support for these devices on the ROCm software platform.
|
||||
The following list of GPUs are likely to work within ROCm, though full support is not guaranteed:
|
||||
* GFX7 GPUs
|
||||
* "Hawaii" chips, such as the AMD Radeon R9 390X and FirePro W9100
|
||||
|
||||
As described in the next section, GFX8 GPUs require PCIe gen 3 with support for PCIe atomics. This requires both CPU and motherboard support. GFX9 GPUs, by default, also require PCIe gen 3 with support for PCIe atomics; if you want to avoid using PCIe atomics, please set the environment variable `HSA_ENABLE_SDMA=0`. GFX7 GPUs do not require PCIe atomics.
|
||||
|
||||
At this time, the integrated GPUs in AMD APUs are not officially supported targets for ROCm.
|
||||
|
||||
For a more detailed list of hardware support, please see [the following documentation](https://rocm.github.io/hardware.html).
|
||||
|
||||
#### Supported CPUs
|
||||
The ROCm Platform leverages PCIe Atomics (Fetch ADD, Compare and SWAP,
|
||||
Unconditional SWAP, AtomicsOpCompletion).
|
||||
[PCIe atomics](https://github.com/RadeonOpenCompute/RadeonOpenCompute.github.io/blob/master/ROCmPCIeFeatures.md)
|
||||
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 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. This typically occurs when connecting via the
|
||||
Southbridge PCIe I/O controller. If you motherboard is part of this category,
|
||||
please do not use this connector for your GPUs, if you intend to exploit ROCm.
|
||||
|
||||
|
||||
Our GFX8 GPU's (Fiji & Polaris Family) use PCIe Gen 3 and PCIe Atomics.
|
||||
As described above, GFX8 and GFX9 GPUs require PCI Express 3.0 with PCIe atomics in the default ROCm configuration.
|
||||
In particular, the CPU and every active PCIe point between the CPU and GPU require support for PCIe gen 3 and PCIe atomics.
|
||||
The CPU root must indicate PCIe AtomicOp Completion capabilities and any intermediate switch must indicate PCIe AtomicOp Routing capabilities.
|
||||
|
||||
Current CPUs which support PCIe Gen3 + PCIe Atomics are:
|
||||
* Intel Xeon E5 v3 or newer CPUs;
|
||||
* Intel Xeon E3 v3 or newer CPUs;
|
||||
* Intel Core i7 v3, Core i5 v3, Core i3 v3 or newer CPUs (i.e. Haswell family or newer).
|
||||
* AMD Ryzen CPUs;
|
||||
|
||||
Upcoming CPUs which will support PCIe Gen3 + PCIe Atomics are:
|
||||
* AMD Naples Server CPUs;
|
||||
* Cavium Thunder X Server Processor.
|
||||
* AMD Ryzen APUs;
|
||||
* AMD Ryzen Threadripper 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).
|
||||
|
||||
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.
|
||||
Beginning with ROCm 1.8, we have relaxed the requirements for PCIe Atomics on GFX9 GPUs such as Vega 10.
|
||||
We have similarly opened up more options for number of PCIe lanes.
|
||||
GFX9 GPUs can now be run on CPUs without PCIe atomics and on older PCIe generations such as gen 2.
|
||||
To enable this option, please set the environment variable `HSA_ENABLE_SDMA=0`.
|
||||
This is not supported on GPUs below GFX9, e.g. GFX8 cards in 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 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, PCIe slots connected via the Southbridge PCIe I/O controller, or PCIe slots connected through a PCIe switch that does
|
||||
not support PCIe atomics.
|
||||
|
||||
If you attempt to run ROCm on a system without proper PCIe atomic support, you may see an error in the kernel log (`dmesg`):
|
||||
```
|
||||
kfd: skipped device 1002:7300, PCI rejects atomics
|
||||
```
|
||||
|
||||
Experimental support for our Hawaii (GFX7) GPUs (Radeon R9 290, R9 390, FirePro W9100, S9150, S9170)
|
||||
does not require or take advantage of PCIe Atomics. However, we still recommend that you use a CPU
|
||||
from the list provided above for compatibility purposes.
|
||||
|
||||
Reminder: if you are using gfx9 GPUs, you can bypass this requirement by setting the environment variable `HSA_ENABLE_SDMA=0`.
|
||||
However, this disables the use of DMA engines to move data between the CPU and GPU memory. This can reduce performance.
|
||||
|
||||
#### Not supported or very limited support under ROCm
|
||||
* We do not support ROCm with PCIe Gen 2 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.
|
||||
* 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.
|
||||
###### Limited support
|
||||
|
||||
#### Support for future APUs
|
||||
We are well aware of the excitement and anticipation built around using ROCm
|
||||
with an APU system which fully exposes Shared Virtual Memory alongside and cache
|
||||
coherency between the CPU and GPU. To this end, in mid 2017 we plan on testing
|
||||
commercial AM4 motherboards for the Bristol Ridge and Raven Ridge families of
|
||||
APUs. Just like you, we still waiting for access to them! Once we have the first
|
||||
boards in the lab we will detail our experiences via our blog, as well as build
|
||||
a list of motherboard that are qualified for use with ROCm.
|
||||
* ROCm 1.9 and Vega10 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. However, we have done very limited testing on these configurations, since our test farm has been catering to CPU 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 Gen2 based, and thus are only supported with GPUs that do not require PCIe Gen 3 atomics (i.e. Vega 10). However, we have done no testing on this configuration and would need comunity support due to limited access to this type of equipment
|
||||
|
||||
### New Features to ROCm
|
||||
###### Not supported
|
||||
|
||||
#### Developer preview of the new OpenCL 1.2 compatible language runtime and compiler
|
||||
* "Tonga", "Iceland", "Polaris 12", and "Vega M" GPUs are not supported in ROCm 1.9.0
|
||||
* We do not support GFX8-class GPUs (Fiji, Polaris, etc.) on CPUs that do not have PCIe Gen 3 with PCIe atomics.
|
||||
* As such, 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 PCIe Gen2 based.
|
||||
* AMD Carrizo based APUs have limited support due to OEM & ODM's choices when it comes to some key configuration parameters. In particular, 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 and that the system BIOS properly exposes the correct CRAT table - please inquire with the OEM about the latter.
|
||||
* AMD Merlin/Falcon Embedded System is not currently supported by the public repo.
|
||||
* AMD Raven Ridge APU are currently not supported
|
||||
|
||||
* OpenCL 2.0 compatible kernel language support with OpenCL 1.2 compatible
|
||||
runtime
|
||||
* Supports offline ahead of time compilation today;
|
||||
during the Beta phase we will add in-process/in-memory compilation.
|
||||
* Binary Package support for Ubuntu 16.04 and Fedora 24
|
||||
* Dropping binary package support for Ubuntu 14.04 and Fedora 23
|
||||
### New features and enhancements in ROCm 1.9.0
|
||||
|
||||
#### Preview for Vega 7nm
|
||||
* Enables developer preview support for Vega 7nm
|
||||
|
||||
#### System Management Interface
|
||||
* Adds support for the ROCm SMI (System Management Interface) library, which provides monitoring and management capabilities for AMD GPUs.
|
||||
|
||||
#### Improvements to HIP/HCC
|
||||
* Support for gfx906
|
||||
* Added deprecation warning for C++AMP. This will be the last version of HCC supporting C++AMP.
|
||||
* Improved optimization for global address space pointers passing into a GPU kernel
|
||||
* Fixed several race conditions in the HCC runtime
|
||||
* Performance tuning to the unpinned copy engine
|
||||
* Several codegen enhancement fixes in the compiler backend
|
||||
|
||||
#### Preview for rocprof Profiling Tool
|
||||
Developer preview (alpha) of profiling tool 'rpl_run.sh', cmd-line front-end for rocProfiler, enables:
|
||||
* Cmd-line tool for dumping public per kernel perf-counters/metrics and kernel timestamps
|
||||
* Input file with counters list and kernels selecting parameters
|
||||
* Multiple counters groups and app runs supported
|
||||
* Output results in CSV format
|
||||
The tool location is: /opt/rocm/rocprofiler/bin/rpl_run.sh
|
||||
|
||||
#### Preview for rocr Debug Agent rocr_debug_agent
|
||||
The ROCr Debug Agent is a library that can be loaded by ROCm Platform Runtime to provide the following functionality:
|
||||
* Print the state for wavefronts that report memory violation or upon executing a "s_trap 2" instruction.
|
||||
* Allows SIGINT (`ctrl c`) or SIGTERM (`kill -15`) to print wavefront state of aborted GPU dispatches.
|
||||
* It is enabled on Vega10 GPUs on ROCm1.9.
|
||||
The ROCm1.9 release will install the ROCr Debug Agent library at /opt/rocm/lib/librocr_debug_agent64.so
|
||||
|
||||
|
||||
#### New distribution support
|
||||
|
||||
* Binary package support for Ubuntu 18.04
|
||||
|
||||
#### ROCm 1.9 is ABI compatible with KFD in upstream Linux kernels.
|
||||
Upstream Linux kernels support the following GPUs in these releases:
|
||||
4.17: Fiji, Polaris 10, Polaris 11
|
||||
4.18: Fiji, Polaris 10, Polaris 11, Vega10
|
||||
|
||||
Some ROCm features are not available in the upstream KFD:
|
||||
* More system memory available to ROCm applications
|
||||
* Interoperability between graphics and compute
|
||||
* RDMA
|
||||
* IPC
|
||||
|
||||
To try ROCm with an upstream kernel, install ROCm as normal, but do not install the rock-dkms package. Also add a udev rule to control /dev/kfd permissions:
|
||||
|
||||
echo 'SUBSYSTEM=="kfd", KERNEL=="kfd", TAG+="uaccess", GROUP="video"' | sudo tee /etc/udev/rules.d/70-kfd.rules
|
||||
|
||||
|
||||
### New features as of ROCm 1.8.3
|
||||
|
||||
* ROCm 1.8.3 is a minor update meant to fix compatibility issues on Ubuntu releases running kernel 4.15.0-33
|
||||
|
||||
### New features as of ROCm 1.8.2
|
||||
|
||||
#### 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 support
|
||||
|
||||
* Binary package support for Ubuntu 16.04 and 18.04
|
||||
* Binary package support for CentOS 7.4 and 7.5
|
||||
* Binary package support for RHEL 7.4 and 7.5
|
||||
|
||||
#### IPC support
|
||||
#### Improved OpenMPI via UCX support
|
||||
|
||||
* UCX support for OpenMPI
|
||||
* ROCm RDMA
|
||||
|
||||
### The latest ROCm platform - ROCm 1.9.0
|
||||
|
||||
### The latest ROCm platform - ROCm 1.6
|
||||
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-1.6.0 or rocm-1.6.0 tag
|
||||
the ROCm platform have been released and are available under the roc-1.9.0 or rocm-1.9.x tag
|
||||
of the following GitHub repositories:
|
||||
|
||||
* [ROCK-Kernel-Driver](https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver/tree/roc-1.6.0)
|
||||
* [ROCR-Runtime](https://github.com/RadeonOpenCompute/ROCR-Runtime/tree/roc-1.6.0)
|
||||
* [ROCT-Thunk-Interface](https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/tree/roc-1.6.0)
|
||||
* [ROC-smi](https://github.com/RadeonOpenCompute/ROC-smi/tree/roc-1.6.0)
|
||||
* [HCC compiler](https://github.com/RadeonOpenCompute/hcc/tree/rocm-1.6.0)
|
||||
* [compiler-runtime](https://github.com/RadeonOpenCompute/compiler-rt/tree/rocm-1.6.0)
|
||||
* [HIP](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/tree/roc-1.6.0)
|
||||
* [HIP-Examples](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP-Examples/tree/roc-1.6.0)
|
||||
* [ROCK-Kernel-Driver](https://github.com/RadeonOpenCompute/ROCK-Kernel-Driver/tree/roc-1.9.x)
|
||||
* [ROCR-Runtime](https://github.com/RadeonOpenCompute/ROCR-Runtime/tree/roc-1.9.x)
|
||||
* [ROCT-Thunk-Interface](https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/tree/roc-1.9.x)
|
||||
* [ROC-smi](https://github.com/RadeonOpenCompute/ROC-smi/tree/roc-1.9.x)
|
||||
* [HCC compiler](https://github.com/RadeonOpenCompute/hcc/tree/roc-1.9.x)
|
||||
* [compiler-runtime](https://github.com/RadeonOpenCompute/compiler-rt/tree/roc-1.9.x)
|
||||
* [HIP](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/tree/roc-1.9.x)
|
||||
* [HIP-Examples](https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP-Examples/tree/roc-1.9.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-1.6.0 release:
|
||||
are also available on GitHub, and frozen for the rocm-1.9.0 release:
|
||||
|
||||
* [llvm](https://github.com/RadeonOpenCompute/llvm/tree/rocm-1.6.0)
|
||||
* [lld](https://github.com/RadeonOpenCompute/lld/tree/rocm-1.6.0)
|
||||
* [hcc-clang-upgrade](https://github.com/RadeonOpenCompute/hcc-clang-upgrade/tree/rocm-1.6.0)
|
||||
* [ROCm-Device-Libs](https://github.com/RadeonOpenCompute/ROCm-Device-Libs/tree/rocm-1.6.0)
|
||||
* [llvm](https://github.com/RadeonOpenCompute/llvm/tree/roc-1.9.x)
|
||||
* [ldd](https://github.com/RadeonOpenCompute/lld/tree/roc-1.9.x)
|
||||
* [hcc-clang-upgrade](https://github.com/RadeonOpenCompute/hcc-clang-upgrade/tree/roc-1.9.x)
|
||||
* [ROCm-Device-Libs](https://github.com/RadeonOpenCompute/ROCm-Device-Libs/tree/roc-1.9.x)
|
||||
|
||||
#### Supported Operating Systems
|
||||
#### Supported Operating Systems - New operating systems available
|
||||
|
||||
The ROCm platform has been tested on the following operating systems:
|
||||
* Ubuntu 16.04
|
||||
* Fedora 24
|
||||
The ROCm 1.9.0 platform has been tested on the following operating systems:
|
||||
* Ubuntu 16.04 &. 18.04
|
||||
* CentOS 7.4 &. 7.5 (Using devetoolset-7 runtime support)
|
||||
* RHEL 7.4. &. 7.5 (Using devetoolset-7 runtime support)
|
||||
|
||||
### Installing from AMD ROCm repositories
|
||||
AMD is hosting both debian and rpm repositories for the ROCm 1.6 packages.
|
||||
|
||||
AMD is hosting both Debian and RPM repositories for the ROCm 1.9.0 packages at this time.
|
||||
|
||||
The packages in the Debian repository have been signed to ensure package integrity.
|
||||
Directions for each repository are given below:
|
||||
|
||||
#### Packaging server update
|
||||
The packaging server has been changed from the old http://packages.amd.com
|
||||
to the new repository site http://repo.radeon.com.
|
||||
#### Ubuntu Support - installing from a Debian repository
|
||||
|
||||
#### Debian repository - apt-get
|
||||
##### First make sure your system is up to date
|
||||
|
||||
```shell
|
||||
sudo apt update
|
||||
sudo apt dist-upgrade
|
||||
sudo apt install libnuma-dev
|
||||
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'
|
||||
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 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:
|
||||
The gpg key might change, so it may need to be updated when installing a new release.
|
||||
If the key signature verification is failed while update, please re-add the key from
|
||||
ROCm apt repository. The current rocm.gpg.key is not avialable in a standard key ring
|
||||
distribution, but has the following sha1sum hash:
|
||||
|
||||
f0d739836a9094004b0a39058d046349aacc1178 rocm.gpg.key
|
||||
f7f8147431c75e505c58a6f3a3548510869357a6 rocm.gpg.key
|
||||
|
||||
##### Install or Update
|
||||
Next, update the apt-get repository list and install/update the rocm package:
|
||||
##### 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-get update
|
||||
sudo apt-get install rocm
|
||||
sudo apt update
|
||||
sudo apt install rocm-dkms
|
||||
```
|
||||
Then, make the ROCm kernel your default kernel. If using grub2 as your
|
||||
bootloader, you can edit the `GRUB_DEFAULT` variable in the following file:
|
||||
|
||||
###### 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
|
||||
sudo vi /etc/default/grub
|
||||
sudo update-grub
|
||||
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 $LOGNAME
|
||||
```
|
||||
|
||||
You may want to ensure that any future users you add to your system are put into the "video" group by default. To do that, you can run the following commands:
|
||||
```shell
|
||||
echo 'ADD_EXTRA_GROUPS=1' | sudo tee -a /etc/adduser.conf
|
||||
echo 'EXTRA_GROUPS=video' | sudo tee -a /etc/adduser.conf
|
||||
```
|
||||
|
||||
Once complete, reboot your system.
|
||||
|
||||
We recommend you [verify your installation](https://github.com/RadeonOpenCompute/ROCm#verify-installation) to make sure everything completed successfully.
|
||||
Upon Reboot run the following commands to verify that the ROCm installation waas successful. If you see your GPUs listed by both of these commands, you should be ready to go!
|
||||
```shell
|
||||
/opt/rocm/bin/rocminfo
|
||||
/opt/rocm/opencl/bin/x86_64/clinfo
|
||||
```
|
||||
|
||||
#### To install ROCm with Developer Preview of OpenCL
|
||||
Note that, to make running ROCm programs easier, you may wish to put the ROCm libraries in your LD_LIBRARY_PATH environment variable and the ROCm binaries in your PATH.
|
||||
```shell
|
||||
echo 'export LD_LIBRARY_PATH=/opt/rocm/opencl/lib/x86_64:/opt/rocm/hsa/lib:$LD_LIBRARY_PATH' | sudo tee -a /etc/profile.d/rocm.sh
|
||||
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
|
||||
```
|
||||
|
||||
##### Start by following the instruction of installing ROCm with Debian repository:
|
||||
If you have an [Install Issue](https://rocm.github.io/install_issues.html) please read this FAQ .
|
||||
|
||||
at the step "sudo apt-get install rocm" replace it with:
|
||||
|
||||
```shell
|
||||
sudo apt-get install rocm rocm-opencl
|
||||
```
|
||||
|
||||
To install the development kit for OpenCL, which includes the OpenCL header files, execute this installation command:
|
||||
|
||||
```shell
|
||||
sudo apt-get install rocm-opencl-dev
|
||||
```
|
||||
|
||||
Then follow the direction for Debian Repository
|
||||
|
||||
###### Upon restart, To test your OpenCL instance
|
||||
###### Vega10 users who want to run ROCm on a system that does not support PCIe atomics must set HSA_ENABLE_SDMA=0
|
||||
|
||||
Build and run Hello World OCL app..
|
||||
Currently, if you want to run ROCm on a Vega10 GPU (GFX9) on a system without PCIe atomics, you must turn off SDMA functionality.
|
||||
|
||||
```shell
|
||||
export HSA_ENABLE_SDMA=0
|
||||
```
|
||||
|
||||
###### Performing an OpenCL-only Installation of ROCm
|
||||
|
||||
Some users may want to install a subset of the full ROCm installation. In particular, 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`.
|
||||
|
||||
```shell
|
||||
sudo apt-get install dkms rock-dkms rocm-opencl
|
||||
```
|
||||
|
||||
###### 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
|
||||
```
|
||||
|
||||
##### Un-install
|
||||
##### How to un-install from Ubuntu 16.04 or Ubuntu 18.04
|
||||
|
||||
To un-install the entire rocm development package execute:
|
||||
|
||||
```shell
|
||||
sudo apt-get autoremove rocm
|
||||
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-get update
|
||||
sudo apt-get install rocm-dev
|
||||
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
|
||||
It is recommended to [remove previous rocm installations](https://github.com/RadeonOpenCompute/ROCm#how-to-un-install-from-ubuntu-1604) before installing the latest version to ensure a smooth installation.
|
||||
|
||||
If you installed any of the ROCm pre-release packages from github, they will
|
||||
need to be manually un-installed:
|
||||
|
||||
```shell
|
||||
sudo apt-get purge libhsakmt
|
||||
sudo apt-get purge radeon-firmware
|
||||
sudo apt-get purge $(dpkg -l | grep 'kfd\|rocm' | grep linux | grep -v libc | awk '{print $2}')
|
||||
sudo apt purge hsakmt-roct
|
||||
sudo apt purge hsakmt-roct-dev
|
||||
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.
|
||||
|
||||
#### RPM repository - dnf (yum)
|
||||
#### CentOS/RHEL 7 (both 7.4 and 7.5) Support
|
||||
|
||||
A dnf (yum) repository is also available for installation of rpm packages.
|
||||
To configure a system to use the ROCm rpm directory create the file
|
||||
/etc/yum.repos.d/rocm.repo with the following contents:
|
||||
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
|
||||
[remote]
|
||||
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
|
||||
```
|
||||
|
||||
name=ROCm Repo
|
||||
Third, enable additional repositories by downloading and installing the epel-release-latest-7 repository RPM:
|
||||
|
||||
baseurl=http://repo.radeon.com/rocm/yum/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 or 7.5 for DKMS Install
|
||||
|
||||
Installing kernel drivers on CentOS/RHEL 7.4/7.5 requires dkms tool being installed:
|
||||
|
||||
```shell
|
||||
sudo yum install -y epel-release
|
||||
sudo yum install -y dkms kernel-headers-`uname -r` kernel-devel-`uname -r`
|
||||
```
|
||||
|
||||
|
||||
##### Installing ROCm on the system
|
||||
|
||||
It is recommended to [remove previous rocm installations](https://github.com/RadeonOpenCompute/ROCm#how-to-un-install-rocm-from-centosrhel-74) before installing the latest version to ensure a smooth installation.
|
||||
|
||||
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
|
||||
```
|
||||
Execute the following commands:
|
||||
|
||||
The repo's URL should point to the location of the repositories repodata database. Install ROCm components using these commands:
|
||||
|
||||
```shell
|
||||
sudo dnf clean all
|
||||
sudo dnf install rocm
|
||||
sudo yum install rocm-dkms
|
||||
```
|
||||
|
||||
As with the debian packages, it is possible to install rocm-dev individually.
|
||||
To uninstall the packages execute:
|
||||
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
|
||||
sudo dnf remove rocm
|
||||
groups
|
||||
```
|
||||
|
||||
Just like Ubuntu installs, the ROCm kernel must be the default kernel used at boot time.
|
||||
|
||||
#### Manual installation steps for Fedora
|
||||
|
||||
A fully functional Fedora installation requires a few manual steps to properly
|
||||
setup, including:
|
||||
* [Building compatible libc++ and libc++abi libraries for Fedora](https://github.com/RadeonOpenCompute/hcc/wiki#fedora)
|
||||
|
||||
#### Verify installation
|
||||
|
||||
To verify that the ROCm stack completed successfully you can execute to HSA
|
||||
vectory\_copy sample application (we do recommend that you copy it to a
|
||||
separate folder and invoke make therein):
|
||||
To add yourself to the video (or wheel) group you will need the sudo password and can use the
|
||||
following command:
|
||||
|
||||
```shell
|
||||
cd /opt/rocm/hsa/sample
|
||||
make
|
||||
./vector_copy
|
||||
sudo usermod -a -G video $LOGNAME
|
||||
```
|
||||
|
||||
#### Closed source components
|
||||
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
|
||||
```
|
||||
###### Vega10 users who want to run ROCm on a system that does not support PCIe atomics must set HSA_ENABLE_SDMA=0
|
||||
|
||||
Currently, if you want to run ROCm on a Vega10 GPU (GFX9) on a system without PCIe atomics, you must turn off SDMA functionality.
|
||||
|
||||
```shell
|
||||
export HSA_ENABLE_SDMA=0
|
||||
```
|
||||
|
||||
###### Performing an OpenCL-only Installation of ROCm
|
||||
|
||||
Some users may want to install a subset of the full ROCm installation. In particular, 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`.
|
||||
|
||||
```shell
|
||||
sudo yum install rock-dkms rocm-opencl
|
||||
```
|
||||
|
||||
##### 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 and 7.5
|
||||
|
||||
To un-install the entire rocm development package execute:
|
||||
|
||||
```shell
|
||||
sudo yum autoremove rocm-dkms
|
||||
```
|
||||
|
||||
### Known Issues / Workarounds
|
||||
|
||||
#### Radeon Compute Profiler does not run
|
||||
|
||||
rcprof -A <HSA_application> fails with error message: Radeon Compute Profiler could not be enabled. Version mismatch between HSA runtime and libhsa-runtime-tools64.so.1.
|
||||
|
||||
#### Running OCLPerfCounters test results in LLVM ERROR: out of memory
|
||||
|
||||
#### HipCaffe is supported on single GPU configurations
|
||||
|
||||
#### The ROCm SMI library calls to rsmi_dev_power_cap_set() and rsmi_dev_power_profile_set() will not work for all but the first gpu in multi-gpu set ups.
|
||||
|
||||
#### Vega10 users who want to run ROCm on a system that does not support PCIe atomics must set HSA_ENABLE_SDMA=0
|
||||
|
||||
Currently, if you want to run ROCm on a Vega10 GPU (GFX9) on a system without PCIe atomics, you must turn off SDMA functionality.
|
||||
|
||||
```shell
|
||||
export HSA_ENABLE_SDMA=0
|
||||
```
|
||||
|
||||
### 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
|
||||
@@ -303,12 +519,14 @@ made available in the following packages:
|
||||
* hsa-ext-rocr-dev
|
||||
|
||||
### Getting ROCm source code
|
||||
Modifications can be made to the ROCm 1.6 components by modifying the open
|
||||
|
||||
Modifications can be made to the ROCm 1.9 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 1.6 manifest file to download the entire ROCm 1.6 source code.
|
||||
and the ROCm 1.9 manifest file to download the entire ROCm 1.9 source code.
|
||||
|
||||
#### Installing repo
|
||||
|
||||
Google's repo tool allows you to manage multiple git repositories
|
||||
simultaneously. You can install it by executing the following commands:
|
||||
|
||||
@@ -319,13 +537,14 @@ 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-1.6.0
|
||||
repo init -u https://github.com/RadeonOpenCompute/ROCm.git -b roc-1.9.0
|
||||
repo sync
|
||||
```
|
||||
These series of commands will pull all of the open source code associated with
|
||||
the ROCm 1.6 release. Please ensure that ssh-keys are configured for the
|
||||
the ROCm 1.9 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
|
||||
|
||||
@@ -2,11 +2,11 @@
|
||||
<manifest>
|
||||
|
||||
<remote name="roc-github"
|
||||
fetch="ssh://git@github.com/RadeonOpenCompute/" />
|
||||
fetch="http://git@github.com/RadeonOpenCompute/" />
|
||||
<remote name="pctools-github"
|
||||
fetch="ssh://git@github.com/GPUOpen-ProfessionalCompute-Tools/" />
|
||||
fetch="http://git@github.com/GPUOpen-ProfessionalCompute-Tools/" />
|
||||
|
||||
<default revision="roc-1.6.x"
|
||||
<default revision="roc-1.9.x"
|
||||
remote="roc-github"
|
||||
sync-j="4" />
|
||||
|
||||
|
||||
Reference in New Issue
Block a user