diff --git a/RELEASE.md b/RELEASE.md index f61fdda17..fb920abbb 100644 --- a/RELEASE.md +++ b/RELEASE.md @@ -660,6 +660,8 @@ The following sections describe key changes to ROCm components. - `amdsmi_get_gpu_process_isolation` and `amdsmi_clean_gpu_local_data` commands do not work. They will be supported in a future release. +See [issue #3500](https://github.com/ROCm/ROCm/issues/3500) on GitHub. + ```{note} See the [detailed AMD SMI changelog](https://github.com/ROCm/amdsmi/blob/docs/6.2.0/CHANGELOG.md) on GitHub for more information. @@ -1274,6 +1276,8 @@ unsigned long istring = 0 // Initialize the input to __shfl return __shfl(istring, 0, 64) ``` +See [issue #3499](https://github.com/ROCm/ROCm/issues/3499) on GitHub. + ### **MIGraphX** (2.10.0) #### Changes @@ -1413,6 +1417,8 @@ return __shfl(istring, 0, 64) As a workaround, install these Python requirements manually: `pip install /opt/rocm-6.2.0/libexec/omniperf/requirements.txt`. +See [issue #3498](https://github.com/ROCm/ROCm/issues/3498) on GitHub. + ### **OpenMP** (17.0.0) #### Changes @@ -1962,6 +1968,9 @@ If unsure of the default processor affinity settings for your environment, run t bash -c "echo taskset -p \$\$" ``` + +See [issue #3493](https://github.com/ROCm/ROCm/issues/3493) on GitHub. + ### Display issues on servers with Instinct MI300-series accelerators when loading AMDGPU driver AMD Instinct MI300-series accelerators and third-party GPUs such as the Matrox G200 have an issue impacting video @@ -1973,11 +1982,15 @@ this includes both the local video output and remote access via iDRAC. The displ the `amdgpu` driver modules. Video output impacts both terminal access when running in `runlevel 3` and GUI access when running in `runlevel 5`. Server functionality can still be accessed via SSH or other remote connection methods. +See [issue #3494](https://github.com/ROCm/ROCm/issues/3494) on GitHub. + ### KFDTest failure on Instinct MI300X with Oracle Linux 8.9 The `KFDEvictTest.QueueTest` is failing on the MI300X platform during KFD (Kernel Fusion Driver) tests, causing the full suite to not execute properly. This issue is suspected to be hardware-related. +See [issue #3495](https://github.com/ROCm/ROCm/issues/3495) on GitHub. + ### Bandwidth limitation in gang and non-gang modes on Instinct MI300A Expected target peak non-gang performance (~60GB/s) and target peak gang performance (~90GB/s) are not achieved. Both gang @@ -1985,6 +1998,8 @@ and non-gang performance are observed to be limited at 45GB/s. This issue will be addressed in a future ROCm release. +See [issue #3496](https://github.com/ROCm/ROCm/issues/3496) on GitHub. + ### rocm-llvm-alt ROCm provides an optional package -- `rocm-llvm-alt` -- that provides a closed-source compiler for @@ -1994,6 +2009,8 @@ LLVM consumer-producer mismatch and the compilation will fail. There is no worka use of the closed-source compiler. It is recommended to compile using the default open-source compiler, which generates high-quality AMD CPU and AMD GPU code. +See [issue #3492](https://github.com/ROCm/ROCm/issues/3492) on GitHub. + ## ROCm upcoming changes The section notes upcoming changes to the ROCm software stack. For upcoming changes related to individual components, review diff --git a/tools/autotag/templates/extra_components/6.2.0.md b/tools/autotag/templates/extra_components/6.2.0.md index c5d1467e9..d14474b2a 100644 --- a/tools/autotag/templates/extra_components/6.2.0.md +++ b/tools/autotag/templates/extra_components/6.2.0.md @@ -1,7 +1,7 @@ ## Detailed component changes -The following sections briefly describe key changes to ROCm components. +The following sections describe key changes to ROCm components. ### **AMD SMI** (24.6.2) @@ -48,6 +48,8 @@ The following sections briefly describe key changes to ROCm components. - `amdsmi_get_gpu_process_isolation` and `amdsmi_clean_gpu_local_data` commands do not work. They will be supported in a future release. +See [issue #3500](https://github.com/ROCm/ROCm/issues/3500) on GitHub. + ```{note} See the [detailed AMD SMI changelog](https://github.com/ROCm/amdsmi/blob/docs/6.2.0/CHANGELOG.md) on GitHub for more information. @@ -89,7 +91,7 @@ on GitHub for more information. - `hipStreamBeginCaptureToGraph` begins graph capture on a stream to an existing graph. - `hipGraphInstantiateWithParams` creates an executable graph from a graph. -- Added a new flag integrated support in device property +- Added a new flag `integrated` -- supported in device property. - The integrated flag is added in the struct `hipDeviceProp_t`. On the integrated APU system, the runtime driver detects and sets this flag to `1`, in which case the API `hipDeviceGetAttribute` returns enum `hipDeviceAttribute_t` for @@ -106,7 +108,7 @@ on GitHub for more information. #### Upcoming changes -- The `_sync()` version of crosslane builtins such as `shfl_sync()`, `__all_sync()`, and `__any_sync()` will be unconditionally in a future HIP release. +- The `_sync()` version of crosslane builtins such as `shfl_sync()`, `__all_sync()`, and `__any_sync()` will be enabled unconditionally in a future HIP release. ### **hipBLAS** (2.2.0) @@ -142,7 +144,7 @@ on GitHub for more information. #### Changes -* Split `hipcc` package into 2 packages for different hardware platforms. +* Split `hipcc` package into two packages for different hardware platforms. * Cleaned up references to environment variables. @@ -662,6 +664,8 @@ unsigned long istring = 0 // Initialize the input to __shfl return __shfl(istring, 0, 64) ``` +See [issue #3499](https://github.com/ROCm/ROCm/issues/3499) on GitHub. + ### **MIGraphX** (2.10.0) #### Changes @@ -801,6 +805,8 @@ return __shfl(istring, 0, 64) As a workaround, install these Python requirements manually: `pip install /opt/rocm-6.2.0/libexec/omniperf/requirements.txt`. +See [issue #3498](https://github.com/ROCm/ROCm/issues/3498) on GitHub. + ### **OpenMP** (17.0.0) #### Changes @@ -1305,3 +1311,4 @@ on GitHub for more information. - Fixed for newer windows vcpkg msgpack and vcpkg version package name. - Fixed an error with DisableKernelPieces + 32bit ShadowLimit. - Ignore asm cap check for kernel arg preload for rocm6.0 and older. + diff --git a/tools/autotag/templates/upcoming_changes/6.2.0.md b/tools/autotag/templates/upcoming_changes/6.2.0.md index 191951f81..2152ac1c1 100644 --- a/tools/autotag/templates/upcoming_changes/6.2.0.md +++ b/tools/autotag/templates/upcoming_changes/6.2.0.md @@ -1,7 +1,7 @@ ## ROCm known issues -ROCm known issues are noted on [{fab}`github` GitHub](https://github.com/ROCm/ROCm/labels/Verified%20Issue). For known +ROCm known issues are noted on {fab}`github` [GitHub](https://github.com/ROCm/ROCm/labels/Verified%20Issue). For known issues related to individual components, review the [Detailed component changes](detailed-component-changes). ### Default processor affinity behavior for helper threads @@ -44,11 +44,28 @@ If unsure of the default processor affinity settings for your environment, run t bash -c "echo taskset -p \$\$" ``` +See [issue #3493](https://github.com/ROCm/ROCm/issues/3493) on GitHub. + +### Display issues on servers with Instinct MI300-series accelerators when loading AMDGPU driver + +AMD Instinct MI300-series accelerators and third-party GPUs such as the Matrox G200 have an issue impacting video +output. The issue was reproduced on a Dell server model PowerEdge XE9680. Servers from other vendors utilizing Matrox +G200 cards may be impacted as well. This issue was found with ROCm 6.2.0 but is present in older ROCm versions. + +The AMDGPU driver shipped with ROCm interferes with the operation of the display card video output. On Dell systems, +this includes both the local video output and remote access via iDRAC. The display appears blank (black) after loading +the `amdgpu` driver modules. Video output impacts both terminal access when running in `runlevel 3` and GUI access when +running in `runlevel 5`. Server functionality can still be accessed via SSH or other remote connection methods. + +See [issue #3494](https://github.com/ROCm/ROCm/issues/3494) on GitHub. + ### KFDTest failure on Instinct MI300X with Oracle Linux 8.9 The `KFDEvictTest.QueueTest` is failing on the MI300X platform during KFD (Kernel Fusion Driver) tests, causing the full suite to not execute properly. This issue is suspected to be hardware-related. +See [issue #3495](https://github.com/ROCm/ROCm/issues/3495) on GitHub. + ### Bandwidth limitation in gang and non-gang modes on Instinct MI300A Expected target peak non-gang performance (~60GB/s) and target peak gang performance (~90GB/s) are not achieved. Both gang @@ -56,6 +73,8 @@ and non-gang performance are observed to be limited at 45GB/s. This issue will be addressed in a future ROCm release. +See [issue #3496](https://github.com/ROCm/ROCm/issues/3496) on GitHub. + ### rocm-llvm-alt ROCm provides an optional package -- `rocm-llvm-alt` -- that provides a closed-source compiler for @@ -65,6 +84,8 @@ LLVM consumer-producer mismatch and the compilation will fail. There is no worka use of the closed-source compiler. It is recommended to compile using the default open-source compiler, which generates high-quality AMD CPU and AMD GPU code. +See [issue #3492](https://github.com/ROCm/ROCm/issues/3492) on GitHub. + ## ROCm upcoming changes The section notes upcoming changes to the ROCm software stack. For upcoming changes related to individual components, review @@ -77,3 +98,4 @@ functionality provided by the closed-source compiler should transition to the op Once the `rocm-llvm-alt` package is removed, any compilation requesting functionality provided by the closed-source compiler will result in a Clang warning: "*[AMD] proprietary optimization compiler has been removed*". +