Added hipamd and MIOpenTensile to manifest.

Update manifest for ROCm 4.5 release.

README.md

@@ -1,30 +1,28 @@
-# AMD ROCm™ v4.1 Release Notes 
-This document describes the features, fixed issues, and information about downloading and installing the AMD ROCm™ software. It also covers known issues and deprecations in the AMD ROCm v4.1 release.
 
-- [Supported Operating Systems and Documentation Updates](#Supported-Operating-Systems-and-Documentation-Updates)
-  * [Supported Operating Systems](#Supported-Operating-Systems)
+
+# AMD ROCm™ v4.5 Release Notes 
+
+This document describes the features, fixed issues, and information about downloading and installing the AMD ROCm™ software. It also covers known issues and deprecations in this release.
+
+- Supported Operating Environments and Documentation Updates
+  * [Supported Operating Environments](#Supported-Operating-Environments)
   * [ROCm Installation Updates](#ROCm-Installation-Updates)
   * [AMD ROCm Documentation Updates](#AMD-ROCm-Documentation-Updates)
 
-- [Driver Compatibility Issue in This Release](#Driver-Compatibility-Issue-in-This-Release)
    
-- [What\'s New in This Release](#Whats-New-in-This-Release)
-  * [TargetID for Multiple Configurations](#TargetID-for-Multiple-Configurations)
-  * [ROCm Data Center Tool](#ROCm-Data-Center-Tool)
-  * [ROCm Math and Communication Libraries](#ROCm-Math-and-Communication-Libraries)
+- What\'s New in This Release
   * [HIP Enhancements](#HIP-Enhancements)
-  * [OpenMP Enhancements and Fixes](#OpenMP-Enhancements-and-Fixes)
-  * [MIOpen Tensile Integration](#MIOpen-Tensile-Integration)
+  * [Unified Memory Support in ROCm](#Unified-Memory-Support-in-ROCm)
+  * [System Management Interface](#System-Management-Interface) 
+  * [ROCm Math and Communication Libraries](#ROCm-Math-and-Communication-Libraries)
+  * [OpenMP Enhancements](#OpenMP-Enhancements)   
 
-    
-- [Known Issues](#Known-Issues)
+- Known Issues in This Release
+  * [Known Issues in This Release](#Known-Issues-in-This-Release)
 
-- [Deprecations](#Deprecations)
+- Deprecations in This Release
+  * [Deprecations](#Deprecations)
 
-  * [Compiler Generated Code Object Version 2 Deprecation ](#Compiler-Generated-Code-Object-Version-2-Deprecation)
-
-- [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)
@@ -34,459 +32,515 @@ This document describes the features, fixed issues, and information about downlo
 
 
 
-## ROCm Installation Updates 
+# ROCm Installation Updates
 
-### List of Supported Operating Systems
+This document describes the features, fixed issues, and information
+about downloading and installing the AMD ROCm™ software.
 
-The AMD ROCm platform is designed to support the following operating systems:
+It also covers known issues and deprecations in this release.
 
-* Ubuntu 20.04.1 (5.4 and 5.6-oem) and 18.04.5 (Kernel 5.4)	
-* CentOS 7.9 (3.10.0-1127) & RHEL 7.9 (3.10.0-1160.6.1.el7) (Using devtoolset-7 runtime support)
-* CentOS 8.3 (4.18.0-193.el8) and RHEL 8.3 (4.18.0-193.1.1.el8) (devtoolset is not required)
-* SLES 15 SP2
+## Supported Operating Environments
 
-### FRESH INSTALLATION OF AMD ROCM V4.1 RECOMMENDED
+The AMD ROCm platform supports the following operating systems:
 
-A complete uninstallation of previous ROCm versions is required before installing a new version of ROCm. An upgrade from previous releases to AMD ROCm v4.1 is not supported. For more information, refer to the AMD ROCm Installation Guide at
-
-https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
-
-**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 /opt/rocm/opencl/bin/x86_64/clinfo. 
- 
-### ROCM MULTI-VERSION INSTALLATION UPDATE
-
-With the AMD ROCm v4.1 release, the following ROCm multi-version installation changes apply:
-
-The meta packages rocm-dkms<version> are now deprecated for multi-version ROCm installs.  For example, rocm-dkms3.7.0, rocm-dkms3.8.0.
- 
-* Multi-version installation of ROCm should be performed by installing rocm-dev<version> using each of the desired ROCm versions. For example, rocm-dev3.7.0, rocm-dev3.8.0, rocm-dev3.9.0.   
-
-* Version files must be created for each multi-version rocm <= 4.1.0
-
- * Command: echo <version> | sudo tee /opt/rocm-<version>/.info/version
-
- * Example: echo 4.1.0 | sudo tee /opt/rocm-4.1.0/.info/version
-
-* The rock-dkms loadable kernel modules should be installed using a single rock-dkms package. 
-
-* ROCm v3.9 and above will not set any ldconfig entries for ROCm libraries for multi-version installation.  Users must set LD_LIBRARY_PATH to load the ROCm library version of choice.
-
-**NOTE**: The single version installation of the ROCm stack remains the same. The rocm-dkms package can be used for single version installs and is not deprecated at this time.
+| OS                | Kernel              |
+| ---               | ---                 |
+| SLES15 SP3        | 5.3.18-24.49        |
+| RHEL 7.9          | 3.10.0-1160.6.1.el7 |
+| CentOS 7.9        | 3.10.0-1127         |
+| RHEL 8.4          | 4.18.0-193.1.1.el8  |
+| CentOS 8.3        | 4.18.0-193.el8      |
+| Ubuntu 18.04.5    | 5.4.0-71-generic    |
+| Ubuntu 20.04.3HWE | 5.8.0-48-generic    |
+| Host OS           | Azure RS1.86        |
+| Guest OS          | Ubuntu 20.04        |
 
 
 
-# Driver Compatibility Issue in This Release
+## Enhanced Installation Process for ROCm v4.5
 
-In certain scenarios, the ROCm 4.1 run-time and userspace environment are not compatible with ROCm v4.0 and older driver implementations for 7nm-based (Vega 20) hardware (MI50 and MI60). 
+In addition to the installation method using the native Package Manager, AMD ROCm v4.5 introduces added methods to install ROCm. With this
+release, the ROCm installation uses the *amdgpu-install* and *amdgpu-uninstall* scripts. 
 
-To mitigate issues, the ROCm v4.1 or newer userspace prevents running older drivers for these GPUs.
+The *amdgpu-install* script streamlines the installation process by:
 
-Users are notified in the following scenarios:
+-   Abstracting the distribution-specific package installation logic
 
-* Bare Metal 
-* Containers
- 
-## Bare Metal
+-   Performing the repository set-up
 
-In the bare-metal environment, the following error message displays in the console: 
+-   Allowing user to specify the use case and automating the installation of all the required packages,
 
-*“HSA Error: Incompatible kernel and userspace, Vega 20 disabled. Upgrade amdgpu.”*
+-   Performing post-install checks to verify whether the installation was performed successfully
 
-To test the compatibility, run the ROCm v4.1 version of rocminfo using the following instruction: 
+-   Installing the uninstallation script
 
-*/opt/rocm-4.1.0/bin/rocminfo 2>&1 | less*
+The *amdgpu-uninstall* script allows the removal of the entire ROCm stack by using a single command.
 
-## Containers
+Some of the ROCm-specific use cases that the installer currently supports are:
 
-A container (built with error detection for this issue) using a ROCm v4.1 or newer run-time is initiated to execute on an older kernel. The container fails to start and the following warning appears:
+-   OpenCL (ROCr/KFD based) runtime
 
-*Error: Incompatible ROCm environment. The Docker container requires the latest kernel driver to operate correctly.
-Upgrade the ROCm kernel to v4.1 or newer, or use a container tagged for v4.0.1 or older.*
+-   HIP runtimes
 
-To inspect the version of the installed kernel driver,  run either: 
+-   ROCm libraries and applications
 
-* dpkg --status rock-dkms [Debian-based]
+-   ROCm Compiler and device libraries
 
-or
+-   ROCr runtime and thunk
 
-* rpm -ql rock-dkms [RHEL, SUSE, and others]
+**Note:** Graphics use cases are not supported in this release.
 
-To install or update the driver, follow the installation instructions at:
+For more details, refer to the AMD ROCm Installation Guide v4.5 at,
 
-https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
+https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation_new.html
 
 
-# AMD ROCm Documentation Updates
+# AMD ROCm Documentation Updates 
 
 ## AMD ROCm Installation Guide 
 
-The AMD ROCm Installation Guide in this release includes:
+The AMD ROCm Installation Guide in this release includes the following
+updates:
 
-* Supported Environments
+-   New - Installation Guide for ROCm v4.5
 
-* Installation Instructions for v4.1
-
-* HIP Installation Instructions 
-
-For more information, refer to the ROCm documentation website at:
-
-https://rocmdocs.amd.com/en/latest/
+    https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation_new.html
 
 
-## AMD ROCm - HIP Documentation Updates
+## AMD Instinct™ High Performance Computing and Tuning
 
-* HIP Programming Guide v4.1 
+- New - AMD Instinct™ High Performance Computing and Tuning Guide 
 
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_Programming_Guide_v4.1.pdf
+   https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD%20Instinct%E2%84%A2High%20Performance%20Computing%20and%20Tuning%20Guide.pdf
+   
+   
+## HIP Documentation
 
-* HIP API Guide v4.1
+-  HIP installation instructions
 
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_API_Guide_v4.1.pdf
+   https://rocmdocs.amd.com/en/latest/Installation_Guide/HIP-Installation.html
+
+-   HIP Programming Guide
+
+    https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_Programming_Guide.pdf
+
+-   HIP API Guide
+
+    https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD-HIP-API-4.5.pdf
+
+-   HIP-Supported CUDA API Reference Guide
+
+    https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_Supported_CUDA_API_Reference_Guide.pdf
+
+-   AMD ROCm Compiler Reference Guide
+
+    https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_Compiler_Reference_Guide_v4.5.pdf
+
+-   HIP FAQ
+
+    <https://rocmdocs.amd.com/en/latest/Programming_Guides/HIP-FAQ.html#hip-faq>
+   
+
+## System Interface Management
+
+-   System Interface Management (SMI)
+
+    https://rocmdocs.amd.com/en/latest/ROCm_System_Managment/ROCm-System-Managment.html
+    
+
+## AMD ROCm Data Center Tool
+
+- AMD ROCm Data Center Tool API Guide
+
+  https://github.com/RadeonOpenCompute/ROCm/blob/master/RDC_API_Manual_4.5.pdf
   
+- AMD ROCm Data Center Tool User Guide
 
-* HIP-Supported CUDA API Reference Guide v4.1
+  https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_ROCm_DataCenter_Tool_User_Guide_v4.5.pdf
 
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/HIP_Supported_CUDA_API_Reference_Guide_v4.1.pdf
+## ROCm SMI API Guide
 
-* HIP FAQ  
+-   ROCm SMI API Guide
 
-  For more information, refer to
+    https://github.com/RadeonOpenCompute/ROCm/blob/master/ROCm_SMI_Manual_4.5.pdf
 
-  https://rocmdocs.amd.com/en/latest/Programming_Guides/HIP-FAQ.html#hip-faq
-
-
-## ROCm Data Center User and API Guide
-
-* ROCm Data Center Tool User Guide
-
-   - Grafana Plugin Integration
-
-  For more information, refer to the ROCm Data Center User Guide at,
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_ROCm_DataCenter_Tool_User_Guide_v4.1.pdf
-  
-
-* ROCm Data Center Tool API Guide
-
-  For more information, refer to the ROCm Data Center API Guide at,
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/ROCm_Data_Center_Tool_API_Manual_4.1.pdf
-
-
-## ROCm SMI API Documentation Updates 
-
-* ROCm SMI API Guide 
-
-  For more information, refer to the ROCm SMI API Guide at,
-
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/ROCm_SMI_API_GUIDE_v4.1.pdf
-  
 ## ROC Debugger User and API Guide 
 
-* ROC Debugger User Guide 
+-   ROCDebugger User Guide
 
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/Debugging%20with%20ROCGDB%20User%20Guide%20v4.1.pdf
-  
+    https://github.com/RadeonOpenCompute/ROCm/blob/master/ROCDebugger_User_Guide.pdf
 
-* Debugger API Guide 
+-   Debugger API Guide
 
-  https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD-Debugger%20API%20Guide%20v4.1.pdf
-
-
-## General AMD ROCm Documentation Links
-
-Access the following links for more information:
-
-* For AMD ROCm documentation, see 
-
-  https://rocmdocs.amd.com/en/latest/
-
-* For installation instructions on supped platforms, see
-
-  https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
-
-* For AMD ROCm binary structure, see
-
-  https://rocmdocs.amd.com/en/latest/Installation_Guide/Software-Stack-for-AMD-GPU.html
-  
-
-* For AMD ROCm Release History, see
-
- https://rocmdocs.amd.com/en/latest/Current_Release_Notes/ROCm-Version-History.html
-
-
-
-# What\'s New in This Release
-
-## TARGETID FOR MULTIPLE CONFIGURATIONS
-
-The new TargetID functionality allows compilations to specify various configurations of the supported hardware. 
-
-Previously, ROCm supported only a single configuration per target. 
-
-With the TargetID enhancement, ROCm supports configurations for Linux, PAL and associated configurations such as XNACK. This feature addresses configurations for the same target in different modes and allows applications to build executables that specify the supported configurations, including the option to be agnostic for the desired setting.
-
-
-### New Code Object Format Version for TargetID
-
-* A new clang option -mcode-object-version can be used to request the legacy code object version 3 or code object version 2. For more information, refer to
-
-  https://llvm.org/docs/AMDGPUUsage.html#elf-code-object
-
-* A new clang --offload-arch= option is introduced to specify the offload target architecture(s) for the HIP language.
-
-* The clang --offload-arch= and -mcpu options accept a new Target ID syntax. This allows both the processor and target feature settings to be specified. For more details, refer to
-
-  https://llvm.org/docs/AMDGPUUsage.html#amdgpu-target-id
-
-    - If a target feature is not specified, it defaults to a new concept of "any". The compiler, then, produces code, 
-      which executes on a target configured for either value of the setting impacting the overall performance. 
-      
-      It is recommended to explicitly specify the setting for more efficient performance. 
-
-    - In particular, the setting for XNACK now defaults to produce less performant code than previous ROCm releases.
-
-    - The legacy clang -mxnack, -mno-xnack, -msram-ecc, and -mno-sram-ecc options are deprecated. They are still 
-      supported, however, they will be removed in a future release. 
-
-    - The new Target ID syntax renames the SRAM ECC feature from sram-ecc to sramecc.
-
-* The clang offload bundler uses the new offload hipv4 for HIP code object version 4. For more information, see 
-https://clang.llvm.org/docs/ClangOffloadBundler.html
-
-* ROCm v4.1 corrects code object loading to enforce target feature settings of the code object to match the setting of the agent. It also corrects the recording of target feature settings in the code object. As a consequence, the legacy code objects may no longer load due to mismatches.
-
-* gfx802, gfx803, and gfx805 do not support the XNACK target feature in the ROCm v4.1 release.
-
-
-### New Code Object Tools
-
-AMD ROCm v4.1 provides new code object tools *roc-obj-ls* and *roc-obj-extract*. These tools allow for the listing and extraction of AMD GPU ROCm code objects that are embedded in HIP executables and shared objects. Each tool supports a --help option that provides more information. 
-
-Refer to the HIP Programming Guide v4.1 for additional information and examples.
-
-https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_Programming_Guide_v4.1.pdf
-
-**Note**
-
-The extractkernel tool in previous AMD ROCm releases has been removed from the AMD ROCm v4.1 release 
-and will no longer be  supported.
-
-**Note**
- 
- The roc-obj-ls and roc-obj-extract tools may generate an error about the following missing Perl modules: 
-
-* File::Which
-* File::BaseDir
-* File::Copy
-* URI::Encode
-
-This error is due to the missing dependencies in the hip-base installer package.  As a workaround, you may use the 
-following instructions to install the Perl modules:  
-
-*Ubuntu*
-     
-     apt-get install libfile-which-perl libfile-basedir-perl libfile-copy-recursive-perl liburi-encode-perl
-   
-*CentOS*
-            
-      yum install “ perl(File::Which) perl(File::BaseDir) perl(File::Copy) perl(URI::Encode)
-
-
-
-## ROCm Data Center Tool 
-
-### Grafana Integration
-
-The ROCm Data Center (RDC) Tool is enhanced with the Grafana plugin. Grafana is a common monitoring stack used for storing and visualizing time series data. Prometheus acts as the storage backend, and Grafana is used as the interface for analysis and visualization. Grafana has a plethora of visualization options and can be integrated with Prometheus for the ROCm Data Center (RDC) dashboard. 
-
-For more information about Grafana integration and installation, refer to the ROCm Data Center Tool User guide at:
-
-https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_ROCm_DataCenter_Tool_User_Guide_v4.1.pdf
-
-
-
-## ROCm Math and Communication Libraries 
-
-### rocSPARSE
-
-rocSPARSE extends support for:
-
-* gebsrmm
-* gebsrmv
-* gebsrsv
-* coo2dense and dense2coo
-* generic API including axpby, gather, scatter, rot, spvv, spmv, spgemm, sparsetodense, densetosparse
-* mixed indexing types in matrix formats
-
-For more information, see 
-
-https://rocsparse.readthedocs.io/en/latest/
-
-
-### rocSOLVER
-
-rocSOLVER extends support for:
-
-* Eigensolver routines for symmetric/hermitian matrices:
-  - STERF, STEQR
-  
-* Linear solvers for general non-square systems:
-  - GELS (API added with batched and strided_batched versions. Only the overdetermined non-transpose case is implemented in 
-    this release. Other cases will return rocblas_status_not_implemented status for now.)
+    https://github.com/RadeonOpenCompute/ROCm/blob/master/ROCDebugger_API_Guide.pdf
     
-* Extended test coverage for functions returning information
+## OpenMP Documentation
 
-* Changelog file
+- Updated OpenMP documentation 
 
-* Tridiagonalization routines for symmetric and hermitian matrices:
-  - LATRD
-  - SYTD2, SYTRD (with batched and strided_batched versions)
-  - HETD2, HETRD (with batched and strided_batched versions)
+  https://rocmdocs.amd.com/en/latest/Programming_Guides/openmp_support.html
   
-* Sample code and unit test for unified memory model/Heterogeneous Memory Management (HMM)
 
-For more information, see
+## AMD ROCm General Documentation Links
 
-https://rocsolver.readthedocs.io/en/latest/
+-   For AMD ROCm documentation, see
 
-### hipCUB
+    https://rocmdocs.amd.com/en/latest/
 
-The new iterator DiscardOutputIterator in hipCUB represents a special kind of pointer that ignores values written to it upon dereference.  It is useful for ignoring the output of certain algorithms without wasting memory capacity or bandwidth.  DiscardOutputIterator may also be used to count the size of an algorithm's output, which was not known previously.
+-   For installation instructions on supported platforms, see
 
-For more information, see
+    https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
 
-https://hipcub.readthedocs.io/en/latest/
+-   For AMD ROCm binary structure, see
 
+    https://rocmdocs.amd.com/en/latest/Installation_Guide/Software-Stack-for-AMD-GPU.html
+
+-   For AMD ROCm release history, see
+
+    https://rocmdocs.amd.com/en/latest/Current_Release_Notes/ROCm-Version-History.html
+
+
+# What's New in This Release 
 
 ## HIP Enhancements
 
-### Support for hipEventDisableTiming Flag
+The ROCm v4.5 release consists of the following HIP enhancements:
 
-HIP now supports the hipEventDisableTiming flag for hipEventCreateWithFlags. Note, events created with this flag do not record profiling data and provide optimal performance when used for synchronization.
+### HIP Direct Dispatch
 
-### Cooperative Group Functions
+The conventional producer-consumer model where the host thread(producer) enqueues commands to a command queue (per stream), which is then
+processed by a separate, per-stream worker thread (consumer) created by the runtime, is no longer applicable.
 
-Cooperative Groups defines, synchronizes, and communicates between groups of threads and blocks for efficiency and ease of management. HIP now supports the following kernel language Cooperative Groups types and functions:
+In this release, for Direct Dispatch, the runtime directly queues a packet to the AQL queue (user mode queue to GPU) in Dispatch and some of
+the synchronization. This new functionality indicates the total latency of the HIP Dispatch API and the latency to launch the first wave on the
+GPU.
 
-![Screenshot](https://github.com/Rmalavally/ROCm/blob/master/images/CG1.PNG)
-![Screenshot](https://github.com/Rmalavally/ROCm/blob/master/images/CG2.PNG)
-![Screenshot](https://github.com/Rmalavally/ROCm/blob/master/images/CG3.PNG)
+In addition, eliminating the threads in runtime has reduced the variance in the dispatch numbers as the thread scheduling delays and
+atomics/locks synchronization latencies are reduced.
+
+This feature can be disabled by setting the following environment variable,
+
+```     
+     AMD_DIRECT_DISPATCH=0
+
+```
+
+### Support for HIP Graph 
+
+ROCm v4.5 extends support for HIP Graph. For details, refer to the HIP
+API Guide at
+
+https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD-HIP-API-4.5.pdf
+
+### Enhanced *launch_bounds* Check Error Log Message 
+
+When a kernel is launched with HIP APIs, for example, hipModuleLaunchKernel(), HIP validates to check that input kernel
+dimension size is not larger than specified launch_bounds.
+
+If exceeded, HIP returns launch failure if AMD_LOG_LEVEL is set with the proper value. Users can find more information in the error log message,
+including launch parameters of kernel dim size, launch bounds, and the name of the faulting kernel. It is helpful to figure out the faulting
+kernel. Besides, the kernel dim size and launch bounds values will also assist in debugging such failures.
+
+For more details, refer to the HIP Programming Guide at
+
+https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_Programming_Guide.pdf
 
 
-###  Support for Extern Shared Declarations
+### HIP Runtime Compilation
 
-Previously, it was required to declare dynamic shared memory using the HIP_DYNAMIC_SHARED macro for accuracy as using static shared memory in the same kernel could result in overlapping memory ranges and data-races.
-Now, the HIP-Clang compiler provides support for extern shared declarations, and the HIP_DYNAMIC_SHARED option is no longer required. 
+HIP now supports runtime compilation (hipRTC), the usage of which will provide the possibility of optimizations and performance improvement
+compared with other APIs via regular offline static compilation. 
 
-You may use the standard extern definition:
+hipRTC APIs accept HIP source files in character string format as input parameters and create handles of programs by compiling the HIP source
+files without spawning separate processes.
 
-    extern __shared__ type var[];
+For more details on hipRTC APIs, refer to the HIP API Guide at
+
+https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD-HIP-API-4.5.pdf
+
+### New Flag for Backwards Compatibility on float/double atomicAdd Function
+
+In the ROCm4.5 release, a new compilation flag is introduced as an
+option in the CMAKE file. This flag ensures backwards compatibility in
+float/double atomicAdd functions.
+
+```   
+     \_\_HIP_USE_CMPXCHG_FOR_FP_ATOMICS
+```   
+
+This compilation flag is not set("0") by default, so the HIP runtime uses the current float/double atomicAdd functions.
+
+If this compilation flag is set to "1" with the CMAKE option, the existing float/double atomicAdd functions is used for compatibility with
+compilers that do not support floating point atomics.
+
+```  
+     D\_\_HIP_USE_CMPXCHG_FOR_FP_ATOMICS=1
+```  
+For details on how to build the HIP runtime, refer to the HIP Programming Guide at
+
+https://github.com/RadeonOpenCompute/ROCm/blob/master/AMD_HIP_Programming_Guide.pdf
 
 
-## OpenMP Enhancements and Fixes
 
-This release includes the following OpenMP changes:
+### Updated HIP Version Definition
 
-* Usability Enhancements
-* Fixes to Internal Clang Math Headers
-* OpenMP Defect Fixes
+The HIP version definition is updated as follows:
 
-### Usability Enhancements
+```  
+     HIP_VERSION=HIP_VERSION_MAJOR \* 10000000 + HIP_VERSION_MINOR \*
+     100000 + HIP_VERSION_PATCH)
+```  
 
-* OMPD updates for flang
-* To support OpenMP debugging, the selected OpenMP runtime sources are included in lib-debug/src/openmp. The ROCgdb debugger 
-  will find these automatically.
-* Threadsafe hsa plugin for libomptarget
-* Support multiple devices with malloc and hostrpc
-* Improve hostrpc version check
-* Add max reduction offload feature to flang
-* Integration of changes to support HPC Toolkit
-* Support for fprintf
-* Initial support for GPU malloc and Free. The internal (device rtl) is required for GPU malloc and Free for nested parallelism.  
-  GPU malloc and Free are now replaced, which improves the device memory footprint.
-* Increase detail of debug printing controlled by LIBOMPTARGET_KERNEL_TRACE environment variable
-* Add support for -gpubnames in Flang Driver
-* Increase detail of debug printing controlled by LIBOMPTARGET_KERNEL_TRACE environment variable
-* Add support for -gpubnames in Flang Driver
+The HIP version can be queried from the following HIP API call,
 
-###  Fixes to Internal Clang Math Headers
+```  
+     hipRuntimeGetVersion(&runtimeVersion);
+```  
 
-This release includes a set of changes applied to Clang internal headers to support OpenMP C, C++, FORTRAN, and HIP C. This establishes consistency between NVPTX and AMDGCN offloading, and OpenMP, HIP, and CUDA. OpenMP uses function variants and header overlays to define device versions of functions. This causes Clang LLVM IR codegen to mangle names of variants in both the definition and callsites of functions defined in the internal Clang headers. The changes apply to headers found in the installation subdirectory lib/clang/11.0.0/include.
+The version returned is always greater than the versions in the previous
+ROCm releases.
 
-The changes also temporarily eliminate the use of the libm bitcode libraries for C and C++. Although math functions are now defined with internal clang headers, a bitcode library of the C functions defined in the headers is still built for the FORTRAN toolchain linking. This is because FORTRAN cannot use C math headers. This bitcode library is installed in lib/libdevice/libm-.bc. The source build of the bitcode library is implemented with the aomp-extras repository and the component-built script build_extras.sh. 
-
-### OpenMP Defect Fixes
-
-The following OpenMP defects are fixed in this release:
-
-* Openmpi configuration issue with real16. 
-* [flang] The AOMP 11.7-1 Fortran compiler claims to support the -isystem flag, but ignores it.
-* [flang] producing internal compiler error when the character is used with KIND.
-* [flang] openmp map clause on complex allocatable expressions !$omp target data map( chunk%tiles(1)%field%density0).
-* Add a fatal error if missing -Xopenmp-target or -march options when -fopenmp-targets is specified. However, this requirement is not 
-  applicable for offloading to the host when there is only a single target and that target is the host.
-* Openmp error message output for no_rocm_device_lib was asserting.
-* Linkage on constant per-kernel symbols from external to weaklinkageonly to prevent duplicate symbols when building kokkos.
-* Add environment variables ROCM_LLD_ARGS ROCM_LINK_ARGS ROCM_SELECT_ARGS to test driver options without compiler rebuild.  
-* Fix problems with device math functions being ambiguous, especially the pow function.ix aompcc to accept file type cxx. 
-* Fix a latent race between host runtime and devicertl.
-
-## MIOPEN TENSILE INTEGRATION
-
-MIOpenTensile provides host-callable interfaces to the Tensile library and supports the HIP programming model. You may use the Tensile feature in the HIP backend by setting the building environment variable value to ON.
-
-    MIOPEN_USE_MIOPENTENSILE=ON
-
-MIOpenTensile is an open-source collaboration tool where external entities can submit source pull requests (PRs) for updates. MIOpenTensile maintainers review and approve the PRs using standard open-source practices. 
-
-For more information about the sources and the build system, see
-
-https://github.com/ROCmSoftwarePlatform/MIOpenTensile
+**Note:** The version definition of the HIP runtime is different from that of CUDA. The function returns the HIP runtime version on the AMD
+platform, while on the NVIDIA platform, it returns the CUDA runtime version. There is no mapping or a correlation between the HIP and CUDA
+versions.
 
 
-# Known Issues 
+
+### Planned HIP Enhancements and Fixes
+
+#### Changes to hiprtc implementation to match nvrtc behavior
+
+In this release, there are changes to the *hiprtc* implementation to
+match the *nvrtc* behavior.
+
+**Impact:** Applications can no longer explicitly include HIP runtime header files. Minor code changes are required to remove the HIP runtime
+header files.
+
+#### HIP device attribute enumeration
+
+In a future release, there will be a breaking change in the HIP device attribute enumeration. Enum values are being rearranged to accommodate
+future enhancements and additions.
+
+**Impact:** This will require users to rebuild their applications. No code changes are required.
+
+#### Changes to behavior of hipGetLastError() and hipPeekAtLastError() to match CUDA behavior available
+
+In a later release, changes to behavior of hipGetLastError() and hipPeekAtLastError() to match CUDA behavior will be available.
+
+**Impact:** Applications relying on the previous behavior will be impacted and may require some code changes.
+
+## Unified Memory Support in ROCm
+
+Unified memory allows applications to map and migrate data between CPU and GPU seamlessly without explicitly copying it between different
+allocations. This enables a more complete implementation of *hipMallocManaged*, *hipMemAdvise*, *hipMemPrefetchAsync* and related
+APIs. Without unified memory, these APIs only support system memory. With unified memory, the driver can automatically migrate such memory to
+GPU memory for faster access.
+
+### Supported Operating Systems and Versions
+
+This feature is only supported on recent Linux kernels. Currently, it works on Ubuntu versions with 5.6 or newer kernels and the DKMS driver
+from ROCm. Current releases of RHEL and SLES do not support this feature yet. Future releases of those distributions will add support for this.
+The unified memory feature is also supported in the KFD driver included with upstream kernels starting from Linux 5.14.
+
+Unified memory only works on GFXv9 and later GPUs, including Vega10 and MI100. Fiji, Polaris and older GPUs are not supported. To check whether
+unified memory is enabled, look in the kernel log for this message:
+
+```  
+     \$ dmesg \| grep \"HMM registered"
+```  
+
+If unified memory is enabled, there should be a message like "HMM registered xyzMB device memory". If unified memory is not supported on
+your GPU or kernel version, this message is missing.
+
+### Unified Memory Support and XNACK
+
+Unified memory support comes in two flavours, XNACK-enabled and XNACK-disabled. XNACK refers to the ability of the GPU to handle page
+faults gracefully and retry a memory access. In XNACK-enabled mode, the GPU can handle retry after page-faults, which enables mapping and
+migrating data on demand, as well as memory overcommitment. In XNACK-disabled mode, all memory must be resident and mapped in the GPU
+page tables when the GPU is executing application code. Any migrations involve temporary preemption of the GPU queues by the driver. Both page
+fault handling and preemptions, happen automatically and are transparent to the applications.
+
+XNACK-enabled mode only has experimental support. XNACK-enabled mode requires compiling shader code differently. By default, the ROCm
+compiler builds code that works in both modes. Code can be optimized for one specific mode with compiler options:
+
+OpenCL:
+
+```  
+     clang \... -mcpu=gfx908:***xnack+***:sramecc- \... // xnack on, sramecc off\
+     clang \... -mcpu=gfx908:***xnack-***:sramecc+ \... // xnack off, sramecc on
+```  
+
+HIP:
+```  
+     clang \... \--cuda-gpu-arch=gfx906:xnack+ \... // xnack on\
+     clang \... \--cuda-gpu-arch=gfx906:xnack- \... // xnack off
+```  
+Not all the math libraries included in ROCm support XNACK-enabled mode on current hardware. Applications will fail to run if their shaders are
+compiled in the incorrect mode.
+
+On current hardware, the XNACK mode can be chosen at boot-time by a module parameter amdgpu.noretry. The default is XNACK-disabled
+(amdgpu.noretry=1).
+
+## System Management Interface 
+
+### Enhanced ROCm SMI --setpoweroverdrive Functionality
+
+The ROCm System Management Interface (SMI) *--setpoweroverdrive* functionality is used to lower the power cap on a device without needing
+to enable the OverDrive functionality in the driver. Similarly, even with the OverDrive driver functionality enabled, it is possible to
+request a lower power cap than the card's default.
+
+Currently, any use of the *--setpoweroverdrive* functionality in rocm-smi prints an out-of-spec warning to the screen and requires the
+user to agree that using this functionality potentially voids their warranty. However, this warning should only be printed when users are
+trying to set the power cap to higher than the card's default, which requires the OverDrive driver functionality to be enabled.
+
+For example:
+
+The default power cap is 225.0W before any changes.
+
+```
+
+     \[atitest\@rhel85 smi\]\$ ./rocm_smi.py --resetpoweroverdrive
+     ======================= ROCm System Management Interface =======================
+
+     ========================== Reset GPU Power OverDrive ===========================
+
+     GPU\[0\] : Successfully reset Power OverDrive to: 225W
+     ============================ End of ROCm SMI Log ============================
+
+     Now, after using --setpoweroverdrive to lower the power cap to 123
+     watts:
+
+     \[atitest\@rhel85 smi\]\$ ./rocm_smi.py --setpoweroverdrive 123
+     ======================= ROCm System Management Interface =======================
+
+     =========================== Set GPU Power OverDrive ============================
+
+     GPU\[0\] : Successfully set power to: 123W
+     ======================= End of ROCm SMI Log ==============================
+
+     Setting a power cap lower than the default of 225.0W (in this case,
+     123W) does not give a warning.
+
+     To verify that the power is set to the correct value:
+
+     \[atitest\@rhel85 smi\]\$ ./rocm_smi.py --showmaxpower
+     ======================= ROCm System Management Interface =======================
+
+     ======================== Power Cap ===================================
+
+     GPU\[0\] : Max Graphics Package Power (W): 123.0
+     ========================End of ROCm SMI Log ==============================
+```
+
+
+## OpenMP Enhancements
+
+The ROCm installation includes an LLVM-based implementation, which fully
+supports OpenMP 4.5 standard and a subset of the OpenMP 5.0 standard.
+Fortran and C/C++ compilers and corresponding runtime libraries are
+included. Along with host APIs, the OpenMP compilers support offloading
+code and data onto GPU devices.
+
+For more information, refer to
+
+<https://rocmdocs.amd.com/en/latest/Programming_Guides/openmp_support.html>
+
+## ROCm Math and Communication Libraries
+
+In this release, ROCm Math and Communication Libraries consists of the
+following enhancements and fixes:
+
+| Library   | Changes                                                  |
+| ---       | ---                                                      |
+| rocBLAS | **Optimizations** <ul><li>Improved performance of non-batched and batched syr for all sizes and data types</li><li>Improved performance of non-batched and batched hemv for all sizes and data types</li><li>Improved performance of non-batched and batched symv for all sizes and data types</li><li>Improved memory utilization in rocblas-bench, rocblas-test gemm functions, increasing possible runtime sizes.</li></ul>**Changes** <ul><li>Update from C++14 to C++17.</li>  <li>Packaging split into a runtime package (called rocblas) and a development package (called rocblas-dev for .deb packages, and rocblas-devel for .rpm packages). The development package depends on runtime. The runtime package suggests the development package for all supported OSes except CentOS 7 to aid in the transition. The 'suggest' feature in packaging is introduced as a deprecated feature and will be removed in a future ROCm release.</li></ul> **Fixed**<ul><li>For function geam avoid overflow in offset calculation.</li>  <li> For function syr avoid overflow in offset calculation.</li> <li>For function gemv (Transpose-case) avoid overflow in offset calculation.</li> <li>For functions ssyrk and dsyrk, allow conjugate-transpose case to match legacy BLAS. Behavior is the same as the transpose case.</li></ul> |
+| hipBLAS| **Added**<ul><li>More support for hipblas-bench</li></ul>**Fixed**<ul><li>Avoid large offset overflow for gemv and hemv in hipblas-test</li></ul>**Changed**<ul><li>Packaging split into a runtime package called hipblas and a development package called hipblas-devel. The development package depends on runtime. The runtime package suggests the development package for all supported OSes except CentOS 7 to aid in the transition. The 'suggests' feature in packaging is a transitional feature and will be removed in a future rocm release.</li></ul> |
+| rocFFT | **Optimizations**<ul><li>Optimized SBCC kernels of length 52, 60, 72, 80, 84, 96, 104, 108, 112, 160, 168, 208, 216, 224, 240 with new kernel generator.</li></ul>**Added**<ul><li>Split 2D device code into separate libraries.</li> </ul>**Changed**<ul><li>Packaging split into a runtime package called rocfft and a development package called rocfft-devel. The development package depends on runtime. The runtime package suggests the development package for all supported OSes except CentOS 7 to aid in the transition. The suggests feature in packaging is introduced as a deprecated feature and will be removed in a future rocm release.</li></ul>**Fixed**<ul><li>Fixed a few validation failures of even-length R2C inplace. 2D, 3D cubics sizes such as 100^2 (or ^3), 200^2 (or ^3), 256^2 (or ^3)...etc. We don't combine the three kernels (stockham-r2c-transpose). We only combine two kernels (r2c-transpose) instead.</li></ul> |
+| hipFFT | **Changed**  <ul><li>Packaging split into a runtime package called hipfft and a development package called hipfft-devel. The development package depends on runtime. The runtime package suggests the development package for all supported OSes except CentOS 7 to aid in the transition. The 'suggests' feature in packaging is a transitional feature and will be removed in a future rocm release.</li></ul> |
+| rocSPARSE | **Added** <ul><li>Triangular solve for multiple right-hand sides using BSR format</li> <li>SpMV for BSRX format</li> <li>SpMM in CSR format enhanced to work with transposed A</li> <li>Matrix coloring for CSR matrices </li><li>Added batched tridiagonal solve (gtsv_strided_batch)</li></ul> **Improved** <ul><li>Fixed a bug with gemvi on Navi21 </li><li>Optimization for pivot based gtsv</li></ul> |
+| hipSPARSE | **Added** <ul><li>Triangular solve for multiple right-hand sides using BSR format</li> <li>SpMV for BSRX format</li> <li>SpMM in CSR format enhanced to work with transposed A</li> <li>Matrix coloring for CSR matrices </li>  <li>Added batched tridiagonal solve (gtsv_strided_batch)</li></ul> **Improved** <ul><li>Fixed a bug with gemvi on Navi21</li> <li>Optimization for pivot based gtsv</li></ul> |
+| rocALUTION | **Changed** <ul><li>Packaging split into a runtime package called rocalution and a development package called rocalution-devel. The development package depends on runtime. The runtime package suggests the development package for all supported OSes except CentOS 7 to aid in the transition. The 'suggests' feature in packaging is a transitional feature and will be removed in a future rocm release.</li></ul> **Improved** <ul><li>(A)MG solving phase optimization</li></ul> |
+| rocTHRUST | **Changed**  <ul><li>Packaging changed to a development package (called rocthrust-dev for .deb packages, and rocthrust-devel for .rpm packages). As rocThrust is a header-only library, there is no runtime package. To aid in the transition, the development package sets the "provides" field to provide the package rocthrust, so that existing packages depending on rocthrust can continue to work. The 'provides' feature is a transitional feature and will be removed in a future ROCm release.</li></ul> |
+| rocSOLVER | **Added** <ul><li>RQ factorization routines:</li><li>GERQ2, GERQF (with batched and strided_batchedversions)</li>  <li>Linear solvers for general square systems:</li> <li>GESV (with batched and strided_batched versions)</li><li>Linear solvers for symmetric/hermitian positive definite systems:</li> <li>POTRS (with batched and strided_batched versions)</li> <li>POSV (with batched and strided_batched versions) </li> <li>Inverse of symmetric/hermitian positive definite matrices:</li><li>POTRI (with batched and strided_batched versions)</li> <li>General matrix inversion without pivoting:  </li>  <li>GETRI_NPVT (with batched and strided_batched versions)</li> <li>GETRI_NPVT_OUTOFPLACE (with batched and  strided_batched versions)</li></ul>**Optimized**<ul><li>Improved performance of LU factorization (especially for large matrix sizes)</li> <li>Changed</li>  <li>Raised reference LAPACK version used for rocSOLVER test and benchmark clients to v3.9.1</li>  <li>Minor CMake improvements for users building from source without install.sh:</li> <li>Removed fmt::fmt from rocsolver\'s public usage requirements</li> <li>Enabled small-size optimizations by default </li>  <li>Split packaging into a runtime package ('rocsolver') and a development package ('rocsolver-devel'). The development package depends on the runtime package. To aid in the transition, the runtime package suggests the development package (except on CentOS 7). This use of the 'suggests feature' is transitional and will be removed in a future ROCm release.</li></ul> **Fixed** <ul><li>Use of the GCC / Clang __attribute__((deprecated(...))) extension is now guarded by compiler detection macros. |
+| hipSOLVER | The following functions were added in this release:<ul><li>gesv</li><ul><li>hipsolverSSgesv_bufferSize, hipsolverDDgesv_bufferSize, hipsolverCCgesv_bufferSize, hipsolverZZgesv_bufferSize</li><li>hipsolverSSgesv, hipsolverDDgesv, hipsolverCCgesv, hipsolverZZgesv</li></ul><li>potrs</li><ul><li>hipsolverSpotrs_bufferSize, hipsolverDpotrs_bufferSize, hipsolverCpotrs_bufferSize, hipsolverZpotrs_bufferSize</li><li>hipsolverSpotrs, hipsolverDpotrs, hipsolverCpotrs, hipsolverZpotrs</li></ul><li>potrsBatched</li><ul><li>hipsolverSpotrsBatched_bufferSize, hipsolverDpotrsBatched_bufferSize, hipsolverCpotrsBatched_bufferSize, hipsolverZpotrsBatched_bufferSize</li><li>hipsolverSpotrsBatched, hipsolverDpotrsBatched, hipsolverCpotrsBatched, hipsolverZpotrsBatched</li></ul><li>potri</li><ul><li>hipsolverSpotri_bufferSize, hipsolverDpotri_bufferSize, hipsolverCpotri_bufferSize, hipsolverZpotri_bufferSize</li><li>hipsolverSpotri, hipsolverDpotri, hipsolverCpotri, hipsolverZpotri</li></ul></ul></li></ul> |
+| RCCL | **Added** <ul><li>Compatibility with NCCL 2.9.9 </li></ul>**Changed**  <ul><li>Packaging split into a runtime package called rccl and a development package called rccl-devel. The development package depends on runtime. The runtime package suggests the development package for all supported OSes except CentOS 7 to aid in the transition. The 'suggests' feature in packaging is a tranistional feature and will be removed in a future rocm release.</li></ul> |
+| hipCUB | **Changed**  <ul><li>Packaging changed to a development package (called hipcub-dev for .deb packages, and hipcub-devel for .rpm packages). As hipCUB is a header-only library, there is no runtime package. To aid in the transition, the development package sets the "provides" field to provide the package hipcub, so that existing packages depending on hipcub can continue to work. This provides feature is introduced as a deprecated feature and will be removed in a future ROCm release.</li></ul> |
+| rocPRIM| **Added** <ul><li>bfloat16 support added.</li></ul> **Changed**  <ul><li>Packaging split into a runtime package called rocprim and a development package called rocprim-devel. The development package depends on runtime. The runtime package suggests the development package for all supported OSes except CentOS 7 to aid in the transition. The suggests feature in packaging is introduced as a deprecated feature and will be removed in a future rocm release.</li> <li>As rocPRIM is a header-only library, the runtime package is an empty placeholder used to aid in the transition. This package is also a deprecated feature and will be removed in a future rocm release.</li></ul> **Deprecated** <ul><li>The warp_size() function is now deprecated; please switch to host_warp_size() and device_warp_size() for host and device references respectively.</li></ul> |
+| rocRAND| **Changed**  <ul><li>Packaging split into a runtime package called rocrand and a development package called rocrand-devel. The development package depends on runtime. The runtime package suggests the development package for all supported OSes except CentOS 7 to aid in the transition. The suggests feature in packaging is introduced as a deprecated feature and will be removed in a future rocm release.</li></ul> **Fixed** <ul><li>Fix for mrg_uniform_distribution_double generating incorrect range of values</li> <li>Fix for order of state calls for log_normal, normal, and uniform</li></ul> **Known issues**  <ul><li>kernel_xorwow test is failing for certain GPU architectures.</li></ul> |
+
+For more information about ROCm Libraries, refer to the documentation at
+
+<https://rocmdocs.amd.com/en/latest/ROCm_Libraries/ROCm_Libraries.html>
+
+# Known Issues in This Release 
 
 The following are the known issues in this release.
 
-## Upgrade to AMD ROCm v4.1 Not Supported
+## clinfo and rocminfo Do Not Display Marketing Name
 
-An upgrade from previous releases to AMD ROCm v4.1 is not supported. A complete uninstallation of previous ROCm versions is required before installing a new version of ROCm.
+clinfo and rocminfo display a blank field for Marketing Name. 
 
-## Performance Impact for Kernel Launch Bound Attribute
+This is due to a missing package that is not yet available from ROCm. This package will be distributed in future ROCm releases.
 
-Kernels without the *__launch_bounds__* attribute assume the default maximum threads per block value. In the previous ROCm release, this value was 256. In the ROCm v4.1 release, it is changed to 1024. The objective of this change ensures the actual threads per block value used to launch a kernel, by default, are always within the launch bounds, thus, establishing the correctness of HIP programs. 
+## Compiler Support for Function Pointers and Virtual Functions
 
-**NOTE**: Using the above-mentioned approach may incur performance degradation in certain cases. Users must add a minimum launch bound to each kernel, which covers all possible threads per block values used to launch that kernel for correctness and performance. 
+A known issue in the compiler support for function pointers and virtual functions on the GPU may cause undefined behavior due to register
+corruption. 
 
-The recommended workaround to recover the performance is to add *--gpu-max-threads-per-block=256* to the compilation options for HIP programs.
+A temporary workaround is to compile the affected application with this option:
 
-## Issue with Passing a Subset of GPUs in a Multi-GPU System
+```
+     -mllvm -amdgpu-fixed-function-abi=1
+     
+ ```
 
-ROCm support for passing individual GPUs via the docker --device flag in a Docker run command has a known issue when passing a subset of GPUs in a multi-GPU system. The command runs without any warning or error notification. However, all GPU executable run outputs are randomly corrupted. 
+**Note:** This is an internal compiler flag and may be removed without notice once the issue is addressed in a future release.
 
-Using GPU targeting via the Docker command is not recommended for users of ROCm 4.1. There is no workaround for this issue currently. 
 
-## Performance Impact for LDS-Bound Kernels
+## Debugger Process Exit May Cause ROCgdb Internal Error
 
-The compiler in ROCm v4.1 generates LDS load and stores instructions that incorrectly assume equal performance between aligned and misaligned accesses. While this does not impact code correctness, it may result in sub-optimal performance.
+If the debugger process exits during debugging, ROCgdb may report internal errors. This issue occurs as it attempts to access the AMD GPU
+state for the exited process. To recover, users must restart ROCgdb.
+ 
+As a workaround, users can set breakpoints to prevent the debugged process from exiting. For example, users can set breakpoints at the last
+statement of the main function and in the abort() and exit() functions. This temporary solution allows the application to be re-run without
+restarting ROCgdb.
+
+This issue is currently under investigation and will be fixed in a future release.
+
+For more information, refer to the ROCgdb User Guide at,
+
+https://github.com/RadeonOpenCompute/ROCm/blob/master/ROCDebugger_User_Guide.pdf
+
+## Cache Issues with ROCProfiler
+
+When the same kernel is launched back-to-back multiple times on a GPU, a cache flush is executed each time the kernel finishes when profiler data is collected. The cache flush is inserted by ROCprofiler for each kernel. This prevents kernel from being cached, instead it is being read each time it is launched. As a result the cache hit rate from rocprofiler is reported as 0% or very low.
+
+This issue is under investigation and will be fixed in a future release. 
+
+## Stability Issue on LAMMPS-KOKKOS Applications
+
+On mGPU machines, lammps-kokkos applications experience a stability issue (AMD Instinct MI100™). 
+
+As a workaround, perform a Translation LookAside Buffer (TLB) flush. 
+
+The issue is under active investigation and will be resolved in a future release.
 
-This issue is under investigation, and there is no known workaround at this time.
 
 
 # Deprecations
 
-This section describes deprecations and removals in AMD ROCm.
+## AMD Instinct MI25 End of Life
 
-## Compiler Generated Code Object Version 2 Deprecation 
+ROCm release v4.5 is the final release to support AMD Instinct MI25. AMD Instinct MI25 has reached End of Life (EOL). ROCm 4.5 represents the
+last certified release for software and driver support. AMD will continue to provide technical support and issue resolution for AMD
+Instinct MI25 on ROCm v4.5 for a period of 12 months from the software GA date. 
+
+## Planned Deprecation for Code Object Versions 2 and 3 
+
+With the ROCm v4.5 release, the generation of code object versions 2 and 3 is being deprecated and may be removed in a future release. This deprecation notice does not impact support for the execution of AMD GPU code object versions.
+
+The -mcode-object-version Clang option can be used to instruct the compiler to generate a specific AMD GPU code object version. In ROCm v4.5, the compiler can generate AMD GPU code object version 2, 3, and 4, with version 4 being the default if not specified. 
 
-Compiler-generated code object version 2 is no longer supported and has been completely removed. Support for loading code object version 2 is also deprecated with no announced removal release.
 
 
 # Deploying ROCm
@@ -502,7 +556,7 @@ https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html
 
 For an updated version of the software stack for AMD GPU, see
 
-https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html#software-stack-for-amd-gpu
+https://rocmdocs.amd.com/en/latest/Installation_Guide/Software-Stack-for-AMD-GPU.html
 
 
 
@@ -639,15 +693,15 @@ For users that have the option of using either AMD's or the upstreamed driver, t
 
 # Disclaimer
 
-AMD®, the AMD Arrow logo, AMD Instinct™, Radeon™, ROCm® and combinations thereof are trademarks of Advanced Micro Devices, Inc.
+The information presented in this document is for informational purposes only and may contain technical inaccuracies, omissions, and typographical errors.  The information contained herein is subject to change and may be rendered inaccurate for many reasons, including but not limited to product and roadmap changes, component and motherboard versionchanges, new  model and/or product releases, product differences between differing manufacturers, software changes, BIOS flashes, firmware upgrades, or the like. Any computer system has risks of security vulnerabilities that cannot be completely prevented or mitigated.AMD  assumes  no  obligation  to  update  or  otherwise  correct  or  revise  this  information.  However, AMD reserves the right to revise this information and to make changes from time to time to the content hereof without obligation of AMD to notify any person of such revisions or changes.THIS INFORMATION IS PROVIDED ‘AS IS.” AMD MAKES NO REPRESENTATIONS OR WARRANTIES WITH RESPECT  TO  THE  CONTENTS  HEREOF  AND  ASSUMES  NO  RESPONSIBILITY  FOR  ANY  INACCURACIES, ERRORS, OR OMISSIONS THAT MAY APPEAR IN THIS INFORMATION. AMD SPECIFICALLY DISCLAIMS ANY IMPLIED WARRANTIES OF NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR ANY PARTICULAR PURPOSE.  IN NO EVENT WILL AMD BE LIABLE TO ANY PERSON FOR ANY RELIANCE, DIRECT, INDIRECT, SPECIAL,  OR  OTHER  CONSEQUENTIAL  DAMAGES  ARISING  FROM  THE  USE  OF  ANY  INFORMATION CONTAINED HEREIN, EVEN IF AMD IS EXPRESSLY ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.AMD,  the  AMD  Arrow  logo,[insert  all  other  AMD  trademarks  used  in  the  material  here  perAMD Trademarks]and combinations thereof are trademarks of Advanced Micro Devices, Inc.Other product names  used  in  this  publication  are  for  identification  purposes  only  and  may  be  trademarks  of  their respective  companies. [Insert  any  third  party  trademark  attribution  here  per  AMD'sThird  Party Trademark List.]
+©[2021]Advanced Micro Devices, Inc.All rights reserved.
 
-Linux® is the registered trademark of Linus Torvalds in the U.S. and other countries.
+Third-party Disclaimer
+Third-party content is licensed to you directly by the third party that owns the content and is not licensed to you by AMD.  ALL LINKED THIRD-PARTY CONTENT IS PROVIDED “AS IS” WITHOUT A WARRANTY OF ANY KIND.  USE OF SUCH THIRD-PARTY CONTENT IS DONE AT YOUR SOLE DISCRETION AND UNDER NO CIRCUMSTANCES WILL AMD BE LIABLE TO YOU FOR ANY THIRD-PARTY CONTENT.  YOU ASSUME ALL RISK AND ARE SOLELY RESPONSIBLE FOR ANY DAMAGES THAT MAY ARISE FROM YOUR USE OF THIRD-PARTY CONTENT. 
 
-PCIe® is a registered trademark of PCI-SIG Corporation. Other product names used in this publication are for identification purposes only and may be trademarks of their respective companies.  
 
-Google®  is a registered trademark of Google LLC.
 
-Ubuntu and the Ubuntu logo are registered trademarks of Canonical Ltd.
+## Disclaimer
+Third-party content is licensed to you directly by the third party that owns the content and is not licensed to you by AMD.  ALL LINKED THIRD-PARTY CONTENT IS PROVIDED “AS IS” WITHOUT A WARRANTY OF ANY KIND.  USE OF SUCH THIRD-PARTY CONTENT IS DONE AT YOUR SOLE DISCRETION AND UNDER NO CIRCUMSTANCES WILL AMD BE LIABLE TO YOU FOR ANY THIRD-PARTY CONTENT.  YOU ASSUME ALL RISK AND ARE SOLELY RESPONSIBLE FOR ANY DAMAGES THAT MAY ARISE FROM YOUR USE OF THIRD-PARTY CONTENT.
 
-Other product names used in this publication are for identification purposes only and may be trademarks of their respective companies.
 

default.xml

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="roc-github"
-fetch="http://github.com/RadeonOpenCompute/" />
+fetch="https://github.com/RadeonOpenCompute/" />
     <remote name="rocm-devtools"
 fetch="https://github.com/ROCm-Developer-Tools/" />
     <remote name="rocm-swplat"
@@ -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-4.1.0"
+    <default revision="refs/tags/rocm-4.5.0"
      remote="roc-github"
      sync-c="true"
      sync-j="4" />
@@ -20,7 +20,6 @@ fetch="https://github.com/KhronosGroup/" />
     <project name="ROCK-Kernel-Driver" />
     <project name="ROCT-Thunk-Interface" />
     <project name="ROCR-Runtime" />
-    <project name="ROC-smi" />
     <project name="rocm_smi_lib" />
     <project name="rocm-cmake" />
     <project name="rocminfo" />
@@ -31,6 +30,7 @@ fetch="https://github.com/KhronosGroup/" />
     <project name="clang-ocl" />
 <!--HIP Projects-->
     <project name="HIP" remote="rocm-devtools" />
+    <project name="hipamd" remote="rocm-devtools" />
     <project name="HIP-Examples" remote="rocm-devtools" />
     <project name="ROCclr" remote="rocm-devtools" />
     <project name="HIPIFY" remote="rocm-devtools" />
@@ -47,18 +47,21 @@ fetch="https://github.com/KhronosGroup/" />
     <project name="ROCgdb" remote="rocm-devtools" />
     <project name="ROCdbgapi" remote="rocm-devtools" />
 <!-- ROCm Libraries -->
-    <project name="rdc" remote="roc-github" />
+    <project name="rdc" />
     <project name="rocBLAS" remote="rocm-swplat" />
     <project name="Tensile" remote="rocm-swplat" />
     <project name="hipBLAS" remote="rocm-swplat" />
     <project name="rocFFT" remote="rocm-swplat" />
+    <project name="hipFFT" remote="rocm-swplat" />
     <project name="rocRAND" remote="rocm-swplat" />
     <project name="rocSPARSE" remote="rocm-swplat" />
     <project name="rocSOLVER" remote="rocm-swplat" />
+    <project name="hipSOLVER" 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="MIOpenTensile" remote="rocm-swplat" />
     <project name="rccl" remote="rocm-swplat" />
     <project name="MIVisionX" remote="gpuopen-libs" />
     <project name="rocThrust" remote="rocm-swplat" />

images/test.rst

@@ -0,0 +1 @@
+