Compare commits

...

7 Commits

Author SHA1 Message Date
zhang2amd
fac29ca466 Update default.xml for ROCm 5.0.2 release 2022-03-04 15:28:19 -08:00
Roopa Malavally
986ba19e80 Update README.md 2022-03-04 15:13:47 -08:00
Roopa Malavally
e00f7f6d59 Update README.md 2022-03-04 15:12:54 -08:00
Roopa Malavally
cac8ecf2bc Update README.md 2022-02-23 21:23:18 -08:00
Roopa Malavally
2653e081e2 Delete Hardware_and_Software_Support.md 2022-02-23 21:22:43 -08:00
Roopa Malavally
34eb2a85f3 Update Hardware_and_Software_Support.md 2022-02-23 18:30:44 -08:00
Roopa Malavally
164129954e Create Hardware_and_Software_Support.md 2022-02-23 18:29:53 -08:00
2 changed files with 22 additions and 128 deletions

148
README.md
View File

@@ -6,6 +6,27 @@ Beginning ROCm release v5.0, AMD ROCm documentation has a new portal at https://
For documentation prior to ROCm v4.5, you may continue to access https://rocmdocs.amd.com.
# AMD ROCm™ v5.0.2 Release Notes
## Fixed Defects in This Release
The following defects are fixed in the ROCm v5.0.2 release.
### Issue with hostcall Facility in HIP Runtime
In ROCm v5.0, when using the “assert()” call in a HIP kernel, the compiler may sometimes fail to emit kernel metadata related to the hostcall facility, which results in incomplete initialization of the hostcall facility in the HIP runtime. This can cause the HIP kernel to crash when it attempts to execute the “assert()” call.
The root cause was an incorrect check in the compiler to determine whether the hostcall facility is required by the kernel. This is fixed in the ROCm v5.0.2 release.
The resolution includes a compiler change, which emits the required metadata by default, unless the compiler can prove that the hostcall facility is not required by the kernel. This ensures that the “assert()” call never fails.
**Note**: This fix may lead to breakage in some OpenMP offload use cases, which use print inside a target region and result in an abort in device code. The issue will be fixed in a future release.
### Compatibility Matrix Updates to ROCm Deep Learning Guide
The compatibility matrix in the AMD Deep Learning Guide is updated for ROCm v5.0.2.
For more information and documentation updates, refer to https://docs.amd.com.
# AMD ROCm™ v5.0.1 Release Notes
@@ -711,134 +732,7 @@ The current default is code object version 4.
MIOpenTensile will be deprecated in a future release.
# 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.
**Note:** The AMD ROCm™ open software platform is a compute stack for headless system deployments. GUI-based software applications are currently not supported.
#### 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.
**Note:** The integrated GPUs of Ryzen are not officially supported targets for ROCm.
ROCm officially supports AMD GPUs that use following chips:
* GFX9 GPUs
- "Vega 10" chips, such as on the AMD Radeon RX Vega 64 and Radeon Instinct MI25
- "Vega 7nm" chips, such as on the Radeon Instinct MI50, Radeon Instinct MI60 or AMD Radeon VII, Radeon Pro VII
* CDNA GPUs
- MI100 chips such as on the AMD Instinct™ MI100
ROCm is a collection of software ranging from drivers and runtimes 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 enabled in the ROCm software, though full support is not guaranteed:
* GFX8 GPUs
* "Polaris 11" chips, such as on the AMD Radeon RX 570 and Radeon Pro WX 4100
* "Polaris 12" chips, such as on the AMD Radeon RX 550 and Radeon RX 540
* GFX7 GPUs
* "Hawaii" chips, such as the AMD Radeon R9 390X and FirePro W9100
As described in the next section, GFX8 GPUs require PCI Express 3.0 (PCIe 3.0) with support for PCIe atomics. This requires both CPU and motherboard support. GFX9 GPUs require PCIe 3.0 with support for PCIe atomics by default, but they can operate in most cases without this capability.
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 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://en.wikipedia.org/wiki/List_of_AMD_graphics_processing_units).
#### Supported CPUs
As described above, GFX8 GPUs require PCIe 3.0 with PCIe atomics in order to run ROCm.
In particular, the CPU and every active PCIe point between the CPU and GPU require support for PCIe 3.0 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:
* AMD Ryzen CPUs
* The CPUs in 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)
* Some Ivy Bridge-E systems
Beginning with ROCm 1.8, GFX9 GPUs (such as Vega 10) no longer require PCIe atomics.
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 PCIe 2.0.
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 3.1.0 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.
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.
#### Not supported or limited support under ROCm
##### Limited support
* ROCm 4.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 3.1.0 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 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.
##### Not supported
* "Tonga", "Iceland", "Vega M", and "Vega 12" GPUs are not supported.
* We do not support GFX8-class GPUs (Fiji, Polaris, etc.) on CPUs that do not have PCIe 3.0 with PCIe atomics.
* 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.
In the default ROCm configuration, GFX8 and GFX9 GPUs require PCI Express 3.0 with PCIe atomics. The ROCm platform leverages these advanced capabilities to allow features such as user-level submission of work from the host to the GPU. This includes PCIe atomic Fetch and Add, Compare and Swap, Unconditional Swap, and AtomicOp Completion.
#### 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.
As such, users have the option of either using the ROCK kernel driver that are part of AMD's ROCm repositories or using the upstream driver and only installing ROCm user-level utilities from AMD's ROCm repositories.
These releases of the upstream Linux kernel support the following GPUs in ROCm:
* 4.17: Fiji, Polaris 10, Polaris 11
* 4.18: Fiji, Polaris 10, Polaris 11, Vega10
* 4.20: Fiji, Polaris 10, Polaris 11, Vega10, Vega 7nm
The upstream driver may be useful for running ROCm software on systems that are not compatible with the kernel driver available in AMD's repositories.
For users that have the option of using either AMD's or the upstreamed driver, there are various tradeoffs to take into consideration:
| | Using AMD's `rock-dkms` package | Using the upstream kernel driver |
| ---- | ------------------------------------------------------------| ----- |
| Pros | More GPU features, and they are enabled earlier | Includes the latest Linux kernel features |
| | Tested by AMD on supported distributions | May work on other distributions and with custom kernels |
| | 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 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 |
# Disclaimer

View File

@@ -12,7 +12,7 @@ fetch="https://github.com/GPUOpen-ProfessionalCompute-Libraries/" />
fetch="https://github.com/GPUOpen-Tools/" />
<remote name="KhronosGroup"
fetch="https://github.com/KhronosGroup/" />
<default revision="refs/tags/rocm-5.0.1"
<default revision="refs/tags/rocm-5.0.2"
remote="roc-github"
sync-c="true"
sync-j="4" />