GPA 3.12 updates

Author: PLohrmannAMD

README.md

@@ -31,10 +31,16 @@ Prebuilt binaries can be downloaded from the Releases page: https://github.com/G
 * Provides access to some raw hardware counters. See [Raw Hardware Counters](#raw-hardware-counters) for more information.
 
 ## What's New
-### Version 3.11.1 (07/27/22)
-  * Updated OpenGL support for the Adrenalin 22.7.1 driver.
-  * Added L2CacheHit counter for OpenGL on Radeon RX 5000 Series hardware.
-  * Improved GPA integration into GLTriangle sample application.
+### Version 3.12 (12/14/22)
+* Add support for AMD Radeon™ RX 7900 XTX and AMD Radeon™ RX 7900 XT GPUs.
+* Add support for compiling with Visual Studio 2022.
+* Reduced binary sizes by an average of 75%.
+* Bug Fixes:
+  * AMD Radeon RX 6800, DX12: HiZ and PreZ counters are now reporting correct values (requires Adrenalin 22.7.1 or newer driver).
+  * AMD Radeon RX 6800: CSThreadgroups is now reporting the correct values (requires Adrenalin 22.7.1 or newer driver).
+  * AMD Radeon RX 6000 Series: PostTessellation counters now only show results in pipelines using tessellation.
+  * AMD Radeon RX 5000 Series: PreTessellation counters now only show results in pipelines using tessellation.
+  * Sample apps: Fix implementation of passes in D3D11Triangle, and improve general error handling.
 
 ## System Requirements
 * An AMD Radeon GPU or APU based on Graphics IP version 8 and newer.
@@ -95,8 +101,6 @@ It was discovered that the improvements introduced in Vega, RDNA, and RDNA2 arch
 ## Known Issues
 ### Counter Validity on Specific Hardware
 There are some counters that are returning unexpected results on specific hardware with certain APIs.
-* AMD Radeon RX 6800, DX12: HiZ and PreZ counters may consistently report 33% higher than expected.
-* AMD Radeon RX 6800, DX11: CSThreadGroups may consistently report 33% higher than expected.
 * AMD Radeon RX 6700M, DX11: CSLDSBankConflict and CSLDSBankConflictCycles may consistently report as much as 30x higher than expected.
 * AMD Radeon RX 480, DX12: CulledPrims and PSPixelsOut may inconsistently report higher than expected.
 

ReleaseNotes.md

@@ -1,6 +1,17 @@
 # GPU Performance API Release Notes
 ---
 
+## Version 3.12 (12/14/22)
+  * Add support for AMD Radeon™ RX 7900 XTX and AMD Radeon™ RX 7900 XT GPUs.
+  * Add support for compiling with Visual Studio 2022.
+  * Reduced binary sizes by an average of 75%.
+  * Bug Fixes:
+    * AMD Radeon RX 6800, DX12: HiZ and PreZ counters are now reporting correct values (requires Adrenalin 22.7.1 or newer driver).
+    * AMD Radeon RX 6800: CSThreadgroups is now reporting the correct values (requires Adrenalin 22.7.1 or newer driver).
+    * AMD Radeon RX 6000 Series: PostTessellation counters now only show results in pipelines using tessellation.
+    * AMD Radeon RX 5000 Series: PreTessellation counters now only show results in pipelines using tessellation.
+    * Sample apps: Fix implementation of passes in D3D11Triangle, and improve general error handling.
+
 ## Version 3.11.1 (07/27/22)
   * Updated OpenGL support for the Adrenalin 22.7.1 driver.
   * Added L2CacheHit counter for OpenGL on Radeon RX 5000 Series hardware.

build/cmake_modules/build_flags.cmake

@@ -1,12 +1,10 @@
-## Copyright (c) 2018-2019 Advanced Micro Devices, Inc. All rights reserved.
+## Copyright (c) 2018-2022 Advanced Micro Devices, Inc. All rights reserved.
 cmake_minimum_required(VERSION 3.5.1)
 
 ## GPA has only Debug and Release
 set(CMAKE_CONFIGURATION_TYPES Debug Release)
 set(DEPTH "./")
 
-include(${GPA_CMAKE_MODULES_DIR}/defs.cmake)
-
 if(NOT DEFINED usingscript)
     set(usingscript OFF CACHE BOOL "Turn on to indicate CMake is called using script" FORCE)
 endif()

build/cmake_modules/common.cmake

@@ -1,12 +1,16 @@
-## Copyright (c) 2018-2019 Advanced Micro Devices, Inc. All rights reserved.
+## Copyright (c) 2018-2022 Advanced Micro Devices, Inc. All rights reserved.
 cmake_minimum_required(VERSION 3.5.1)
 
-include(${GPA_CMAKE_MODULES_DIR}/defs.cmake)
 include (${GPA_CMAKE_MODULES_DIR}/utils.cmake)
 
 # Include global cmake common file
 include(${CMAKE_COMMON_SRC_GLOBAL_CMAKE_MODULE})
 
+# Check for required variables from other cmake files.
+if (${GPA_OUTPUT_DIR} STREQUAL "")
+    message(FATAL_ERROR "No output directory is defined, make sure defs.cmake is included before common.cmake")
+endif()
+
 # Global compiler options
 add_compile_options(${COMMON_COMPILATION_FLAGS})
 

build/cmake_modules/defs.cmake

@@ -3,8 +3,8 @@ cmake_minimum_required(VERSION 3.5.1)
 
 ## Define the GPA version
 set(GPA_MAJOR_VERSION 3)
-set(GPA_MINOR_VERSION 11)
-set(GPA_UPDATE_VERSION 1)
+set(GPA_MINOR_VERSION 12)
+set(GPA_UPDATE_VERSION 0)
 
 if(NOT DEFINED GPA_BUILD_NUMBER)
     set(GPA_BUILD_NUMBER 0)

build/cmake_modules/gpa_version.cmake

@@ -27,7 +27,13 @@ set(GPA_VERSION_HEADER_FILE_CONTENT "//=========================================
 #define GPA_BUILD_NUMBER ${GPA_BUILD_NUMBER}
 
 #define GPA_STR_VALUE(s) #s                     ///< Macro to stringify a value.
-#define GPA_VERSION_STRING(s) GPA_STR_VALUE(s)  ///< Macro to stringify a version value.
+#ifdef WIN32
+#define GPA_STR_EMPTY()                         ///< Macro to stringify an empty value.
+#define GPA_GET_MACRO(_0, _1, MACRO, ...) MACRO ///< Macro to select between GPA_STR_VALUE and GPA_STR_EMPTY.
+#define GPA_VERSION_STRING(s) GPA_GET_MACRO(_0, ##__VA_ARGS__, GPA_STR_VALUE, GPA_STR_EMPTY)(__VA_ARGS__)  ///< Macro to stringify a version value.
+#else
+#define GPA_VERSION_STRING(s) GPA_STR_VALUE(s)  ///< Macro to stringify a version value
+#endif // !WIN32
 
 #define GPA_MAJOR_VERSION_STR GPA_VERSION_STRING(GPA_MAJOR_VERSION)    ///< Macro for major version string.
 #define GPA_MINOR_VERSION_STR GPA_VERSION_STRING(GPA_MINOR_VERSION)    ///< Macro for minor version string.

build/cmake_modules/targets.cmake

@@ -5,7 +5,6 @@ cmake_minimum_required(VERSION 3.5.1)
 set(CMAKE_CONFIGURATION_TYPES Debug Release)
 set(DEPTH "./")
 
-include(${GPA_CMAKE_MODULES_DIR}/defs.cmake)
 include(${GPA_CMAKE_MODULES_DIR}/build_flags.cmake)
 
 include(CTest)

build/cmake_modules/utils.cmake

@@ -49,11 +49,16 @@ macro(SET_EXECUTABLE_NAME EXECUTABLE_NAME)
     endif()
 endmacro()
 
-## Macro to define additional compile defintion to GPA user
+## Macro to define additional compile definition to GPA user
 macro(ADD_GPA_USER_COMPILE_DEFINITIONS)
     set_property(TARGET ${GPA_PROJECT_NAME} PROPERTY COMPILE_DEFINITIONS $<$<CONFIG:DEBUG>:USE_DEBUG_GPA> ${ADDITIONAL_INTERNAL_DEFINITION})
 endmacro()
 
+## Macro to define additional compile definitions to a named GPA Target project.
+macro(ADD_GPA_COMPILE_DEFINITIONS TARGET_NAME)
+    set_property(TARGET ${ARGV0} PROPERTY COMPILE_DEFINITIONS $<$<CONFIG:DEBUG>:USE_DEBUG_GPA> ${ADDITIONAL_INTERNAL_DEFINITION})
+endmacro()
+
 if(CMAKE_GENERATOR MATCHES "Visual Studio")
     set(EXCLUDE_FROM_BUILD EXCLUDE_FROM_DEFAULT_BUILD)
 else()

docs/sphinx/source/compute_counter_tables_gfx11.rst

@@ -0,0 +1,51 @@
+.. Copyright(c) 2018-2022 Advanced Micro Devices, Inc.All rights reserved.
+.. Compute Performance Counters for RDNA3
+
+.. *** Note, this is an auto-generated file. Do not edit. Execute PublicCounterCompiler to rebuild.
+
+RDNA3 Counters
+++++++++++++++
+
+General Group
+%%%%%%%%%%%%%
+
+.. csv-table::
+    :header: "Counter Name", "Usage", "Brief Description"
+    :widths: 15, 10, 75
+
+    "Wavefronts", "Items", "Total wavefronts."
+    "VALUInsts", "Items", "The average number of vector ALU instructions executed per work-item (affected by flow control)."
+    "SALUInsts", "Items", "The average number of scalar ALU instructions executed per work-item (affected by flow control)."
+    "VFetchInsts", "Items", "The average number of vector fetch instructions from the video memory executed per work-item (affected by flow control). Excludes FLAT instructions that fetch from video memory."
+    "SFetchInsts", "Items", "The average number of scalar fetch instructions from the video memory executed per work-item (affected by flow control)."
+    "VWriteInsts", "Items", "The average number of vector write instructions to the video memory executed per work-item (affected by flow control). Excludes FLAT instructions that write to video memory."
+    "GDSInsts", "Items", "The average number of GDS read or GDS write instructions executed per work item (affected by flow control)."
+    "VALUUtilization", "Percentage", "The percentage of active vector ALU threads in a wave. A lower number can mean either more thread divergence in a wave or that the work-group size is not a multiple of the wave size. Value range: 0% (bad), 100% (ideal - no thread divergence)."
+    "VALUBusy", "Percentage", "The percentage of GPUTime vector ALU instructions are processed. Value range: 0% (bad) to 100% (optimal)."
+    "SALUBusy", "Percentage", "The percentage of GPUTime scalar ALU instructions are processed. Value range: 0% (bad) to 100% (optimal)."
+
+LocalMemory Group
+%%%%%%%%%%%%%%%%%
+
+.. csv-table::
+    :header: "Counter Name", "Usage", "Brief Description"
+    :widths: 15, 10, 75
+
+    "LDSInsts", "Items", "The average number of LDS read or LDS write instructions executed per work item (affected by flow control)."
+    "LDSBankConflict", "Percentage", "The percentage of GPUTime LDS is stalled by bank conflicts. Value range: 0% (optimal) to 100% (bad)."
+
+GlobalMemory Group
+%%%%%%%%%%%%%%%%%%
+
+.. csv-table::
+    :header: "Counter Name", "Usage", "Brief Description"
+    :widths: 15, 10, 75
+
+    "FetchSize", "Kilobytes", "The total kilobytes fetched from the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."
+    "WriteSize", "Kilobytes", "The total kilobytes written to the video memory. This is measured with all extra fetches and any cache or memory effects taken into account."
+    "L0CacheHit", "Percentage", "The percentage of fetch, write, atomic, and other instructions that hit the data in L0 cache. Value range: 0% (no hit) to 100% (optimal)."
+    "L1CacheHit", "Percentage", "The percentage of fetch, write, atomic, and other instructions that hit the data in L1 cache. Writes and atomics always miss this cache. Value range: 0% (no hit) to 100% (optimal)."
+    "L2CacheHit", "Percentage", "The percentage of fetch, write, atomic, and other instructions that hit the data in L2 cache. Value range: 0% (no hit) to 100% (optimal)."
+    "MemUnitBusy", "Percentage", "The percentage of GPUTime the memory unit is active. The result includes the stall time (MemUnitStalled). This is measured with all extra fetches and writes and any cache or memory effects taken into account. Value range: 0% to 100% (fetch-bound)."
+    "MemUnitStalled", "Percentage", "The percentage of GPUTime the memory unit is stalled. Try reducing the number or size of fetches and writes if possible. Value range: 0% (optimal) to 100% (bad)."
+    "WriteUnitStalled", "Percentage", "The percentage of GPUTime the Write unit is stalled. Value range: 0% to 100% (bad)."

docs/sphinx/source/conf.py

@@ -61,9 +61,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = u'3.11'
+version = u'3.12'
 # The full version, including alpha/beta/rc tags.
-release = u'3.11'
+release = u'3.12'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.