6.2 mergeback into develop (#524)

* Update device-specific config headers with benchmark tuning results (#483)

I ran the benchmark tuning code and scripts on the remaining
architectures in our GPU support matrix. This change updates
the config headers with the results.

* Updates and test coverage for hipGraph support in rocRAND (#439) (#482)

This change allows device-side generators to be used inside of hipGraphs.
More specifically, you can wrap calls to rocrand_generate_* inside of a hipGraph. There are a few things to be aware of:
  - Generator creation (rocrand_create_generator), initialization (rocrand_initialize_generator), and destruction (rocrand_destroy_generator) must still happen outside the hipGraph.
  - After the generator is created, you may call API functions to set its seed, offset, and order.
  - After the generator is initialized (but before stream capture or manual graph creation begins), use rocrand_set_stream to set the stream the generator will use within the graph.
  - A generator's seed, offset, and stream may not be changed from within the hipGraph. Attempting to do so may result in unpredicable behaviour.
  - API calls for the poisson distribution (eg. rocrand_generate_poisson) are not yet supported inside of hipGraphs.

I've added a note to the changelog that mentions these details.
In addition to the changes necessary to support the behaviour described above, this change also:
- updates the changelog to alert the user to the restrictions mentioned above
- adds new unit test coverage to exercises generators and distributions within hipGraphs.

* workaround for regression in sobol kernel (#485) (#487)

introduced by generic codepath for host and device generator

Co-authored-by: Nol Moonen <[email protected]>

* Rename test_config_dispatch.cpp to test_rocrand_config_dispatch.cpp (#496)

* fix(lfsr113,mgr,,mtgp32,philox4x32,threefry,xorwow): force inline generate function (#495) (#497)

A compiler change caused the generate function to no longer be inlined which caused a performance regression. Force inlining resolves this.

Co-authored-by: Nara <[email protected]>

* cmake: don't set CMAKE_C_COMPILER, as rocRAND is a CXX project (#502)

* cherry picking documentation from develop into 6.2 (#507)

* organizing docs into subfolders

* update license and index

* Update LICENSE.txt

Co-authored-by: Nara <[email protected]>

* removing what-is-rocRAND

* Update Read the Docs configuration to use Python 3.10 and latest rocm-docs-core (#503)

* Bump urllib3 from 2.2.1 to 2.2.2 in /docs/sphinx (#505)

Bumps [urllib3](https://github.com/urllib3/urllib3) from 2.2.1 to 2.2.2.
- [Release notes](https://github.com/urllib3/urllib3/releases)
- [Changelog](https://github.com/urllib3/urllib3/blob/main/CHANGES.rst)
- [Commits](urllib3/urllib3@2.2.1...2.2.2)

---
updated-dependencies:
- dependency-name: urllib3
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

---------

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: Nara <[email protected]>
Co-authored-by: Sam Wu <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Add an option for using TBB for host-side generators

* Add package dependencies on TBB if used

* Correct dependencies for RHEL / SLES

---------

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: Wayne Franz <[email protected]>
Co-authored-by: Nol Moonen <[email protected]>
Co-authored-by: Nara <[email protected]>
Co-authored-by: Steve Leung <[email protected]>
Co-authored-by: srawat <[email protected]>
Co-authored-by: Nara <[email protected]>
Co-authored-by: Sam Wu <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Lauren Wrubleski <[email protected]>

.gitlab-ci.yml

@@ -598,7 +598,6 @@ test:nvcc-parity:
       -D BUILD_SHARED_LIBS="$BUILD_SHARED_LIBS"
       -D BUILD_TEST=ON
       -D CMAKE_BUILD_TYPE=Release
-      -D CMAKE_C_COMPILER:FILEPATH="$ROCM_PATH/bin/clang.exe"
       -D CMAKE_CXX_COMPILER:FILEPATH="$ROCM_PATH/bin/clang++.exe"
       -D CMAKE_INSTALL_PREFIX:PATH="$CI_PROJECT_DIR/build/install"
       -D CMAKE_PREFIX_PATH:PATH="$ROCM_PATH/lib/cmake"

cmake/Dependencies.cmake

@@ -63,15 +63,12 @@ if(BUILD_TEST)
     if(DEFINED CMAKE_CXX_COMPILER)
       set(CXX_COMPILER_OPTION "-DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}")
     endif()
-    if(DEFINED CMAKE_C_COMPILER)
-      set(C_COMPILER_OPTION "-DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}")
-    endif()
     download_project(
       PROJ                googletest
       GIT_REPOSITORY      https://github.com/google/googletest.git
       GIT_TAG             release-1.11.0
       INSTALL_DIR         ${GTEST_ROOT}
-      CMAKE_ARGS          -DBUILD_GTEST=ON -DINSTALL_GTEST=ON -Dgtest_force_shared_crt=ON -DBUILD_SHARED_LIBS=OFF -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR> ${CXX_COMPILER_OPTION} ${C_COMPILER_OPTION} -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
+      CMAKE_ARGS          -DBUILD_GTEST=ON -DINSTALL_GTEST=ON -Dgtest_force_shared_crt=ON -DBUILD_SHARED_LIBS=OFF -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR> ${CXX_COMPILER_OPTION} -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
       LOG_DOWNLOAD        TRUE
       LOG_CONFIGURE       TRUE
       LOG_BUILD           TRUE

library/CMakeLists.txt

@@ -87,7 +87,7 @@ if (ROCRAND_HAVE_ASM_INCBIN)
     enable_language(ASM)
     list(TRANSFORM SOBOL_PRECOMPUTED_SOURCES APPEND ".S")
     set_source_files_properties(${SOBOL_PRECOMPUTED_SOURCES} PROPERTIES
-                                INCLUDE_DIRECTORIES ${CMAKE_CURRENT_SOURCE_DIR}/src) 
+                                INCLUDE_DIRECTORIES ${CMAKE_CURRENT_SOURCE_DIR}/src)
 else()
     list(TRANSFORM SOBOL_PRECOMPUTED_SOURCES APPEND ".cpp")
 endif()
@@ -123,12 +123,17 @@ else()
     target_link_libraries(rocrand PUBLIC hip::host)
 endif()
 
-if(NOT WIN32)
+option(ROCRAND_USE_TBB "Use TBB for host-side generators if available." ON)
+if(NOT WIN32 AND ROCRAND_USE_TBB)
     find_package(TBB QUIET)
     if(NOT TARGET TBB::tbb)
         message(WARNING "TBB is not found. Building without parallel STL support")
     else()
         target_link_libraries(rocrand PRIVATE TBB::tbb)
+        rocm_package_add_deb_dependencies("libtbb-dev")
+        set(CPACK_DEB_PACKAGE_REQUIRES "${CPACK_DEB_PACKAGE_REQUIRES}" PARENT_SCOPE)
+        rocm_package_add_rpm_dependencies("(tbb-devel or tbb)")
+        set(CPACK_RPM_PACKAGE_REQUIRES "${CPACK_RPM_PACKAGE_REQUIRES}" PARENT_SCOPE)
 
         # Older libstdc++ headers require TBB to be installed to be able to #include <execution>
         target_compile_definitions(rocrand PRIVATE ROCRAND_PARALLEL_STL)
@@ -187,7 +192,7 @@ if (WIN32)
     install (TARGETS rocrand DESTINATION "${CMAKE_INSTALL_PREFIX}/bin")
     if (BUILD_TEST)
 	    add_custom_command(
-		    TARGET rocrand 
+		    TARGET rocrand
 		    POST_BUILD
 		    COMMAND ${CMAKE_COMMAND} -E copy
 			    $<TARGET_FILE:rocrand>
@@ -196,13 +201,13 @@ if (WIN32)
     endif()
     if (BUILD_BENCHMARK)
 	    add_custom_command(
-		    TARGET rocrand 
+		    TARGET rocrand
 		    POST_BUILD
 		    COMMAND ${CMAKE_COMMAND} -E copy
 			    $<TARGET_FILE:rocrand>
 			    ${PROJECT_BINARY_DIR}/benchmark/$<TARGET_FILE_NAME:rocrand>
 	    )
-    endif()	
+    endif()
 endif()
 
 # Fortran wrappers for rocRAND

test/cpp_wrapper/cmake/Dependencies.cmake

@@ -56,15 +56,12 @@ if(NOT TARGET GTest::GTest AND NOT TARGET GTest::gtest)
   if(DEFINED CMAKE_CXX_COMPILER)
     set(CXX_COMPILER_OPTION "-DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}")
   endif()
-  if(DEFINED CMAKE_C_COMPILER)
-    set(C_COMPILER_OPTION "-DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}")
-  endif()
   download_project(
     PROJ                googletest
     GIT_REPOSITORY      https://github.com/google/googletest.git
     GIT_TAG             release-1.11.0
     INSTALL_DIR         ${GTEST_ROOT}
-    CMAKE_ARGS          -DBUILD_GTEST=ON -DINSTALL_GTEST=ON -Dgtest_force_shared_crt=ON -DBUILD_SHARED_LIBS=OFF -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR> ${CXX_COMPILER_OPTION} ${C_COMPILER_OPTION} -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
+    CMAKE_ARGS          -DBUILD_GTEST=ON -DINSTALL_GTEST=ON -Dgtest_force_shared_crt=ON -DBUILD_SHARED_LIBS=OFF -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR> ${CXX_COMPILER_OPTION} -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
     LOG_DOWNLOAD        TRUE
     LOG_CONFIGURE       TRUE
     LOG_BUILD           TRUE

toolchain-linux.cmake

@@ -16,10 +16,3 @@ if (NOT DEFINED ENV{CXX})
 else()
   set(CMAKE_CXX_COMPILER "$ENV{CXX}" CACHE PATH "Path to the C++ compiler")
 endif()
-
-if (NOT DEFINED ENV{CC})
-  set(CMAKE_C_COMPILER "${rocm_bin}/amdclang" CACHE PATH "Path to the C compiler")
-  set(CMAKE_CXX_FLAGS "-mllvm -amdgpu-early-inline-all=true -mllvm -amdgpu-function-calls=false")
-else()
-  set(CMAKE_C_COMPILER "$ENV{CC}" CACHE PATH "Path to the C compiler")
-endif()

toolchain-windows.cmake

@@ -15,7 +15,6 @@ else()
 endif()
 
 set(CMAKE_CXX_COMPILER "${rocm_bin}/clang++.exe")
-set(CMAKE_C_COMPILER "${rocm_bin}/clang.exe")
 
 if (NOT python)
   set(python "python3") # take default for windows