Merge pull request #72 from SC-SGS/Kokkos

Add new Kokkos backend

.clang-format

@@ -1,4 +1,7 @@
 ---
+Language: Json
+DisableFormat: true
+---
 Language: Cpp
 AccessModifierOffset: -2
 AlignAfterOpenBracket: Align
@@ -79,7 +82,7 @@ IncludeBlocks: Regroup
 IncludeCategories:
   - Regex: '^"plssvm/'
     Priority: 1
-  - Regex: '^"(cuda|hip|CL|sycl|omp|hpx)'
+  - Regex: '^"(cuda|hip|CL|sycl|omp|hpx|Kokkos)'
     Priority: 2
   - Regex: '^"(tests|bindings)/'
     Priority: 3

CMakeLists.txt

@@ -72,6 +72,7 @@ endif ()
 ########################################################################################################################
 ## set base sources
 set(PLSSVM_BASE_SOURCES
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/plssvm/backends/Kokkos/execution_space.cpp
     ${CMAKE_CURRENT_SOURCE_DIR}/src/plssvm/backends/SYCL/implementation_types.cpp
     ${CMAKE_CURRENT_SOURCE_DIR}/src/plssvm/backends/SYCL/kernel_invocation_types.cpp
     ${CMAKE_CURRENT_SOURCE_DIR}/src/plssvm/backends/stdpar/implementation_types.cpp
@@ -411,6 +412,13 @@ if (PLSSVM_ENABLE_SYCL_BACKEND MATCHES "AUTO" OR PLSSVM_ENABLE_SYCL_BACKEND)
     add_subdirectory(src/plssvm/backends/SYCL)
 endif ()
 
+## check for Kokkos backend
+set(PLSSVM_ENABLE_KOKKOS_BACKEND AUTO CACHE STRING "Enable SYCL Backend")
+set_property(CACHE PLSSVM_ENABLE_KOKKOS_BACKEND PROPERTY STRINGS AUTO ON OFF)
+if (PLSSVM_ENABLE_KOKKOS_BACKEND MATCHES "AUTO" OR PLSSVM_ENABLE_KOKKOS_BACKEND)
+    add_subdirectory(src/plssvm/backends/Kokkos)
+endif ()
+
 ## check if ANY backend is available/has been enabled
 get_target_property(PLSSVM_LINKED_BACKENDS ${PLSSVM_ALL_LIBRARY_NAME} INTERFACE_LINK_LIBRARIES)
 if (NOT PLSSVM_LINKED_BACKENDS)
@@ -642,7 +650,7 @@ if (PLSSVM_ENABLE_FORMATTING)
     list(APPEND CMAKE_MESSAGE_INDENT "Formatting:  ")
 
     ## install library to add a clang-format target
-    set(PLSSVM_format_VERSION 7021abbf066e2e577926731c3fa4141f456c5024)
+    set(PLSSVM_format_VERSION d22c36043bea6ef85f3eb68b823f50703bd1cc21)
     find_package(format QUIET)
     if (format_FOUND)
         message(STATUS "Found package format.")
@@ -734,6 +742,10 @@ if (TARGET ${PLSSVM_SYCL_BACKEND_LIBRARY_NAME})
     endforeach ()
     list(APPEND PLSSVM_BACKEND_NAME_LIST "sycl")
 endif ()
+if (TARGET ${PLSSVM_KOKKOS_BACKEND_LIBRARY_NAME})
+    message(STATUS "${PLSSVM_KOKKOS_BACKEND_SUMMARY_STRING}")
+    list(APPEND PLSSVM_BACKEND_NAME_LIST "kokkos")
+endif ()
 message(STATUS "")
 
 ########################################################################################################################
@@ -758,8 +770,8 @@ message(STATUS "Generating manpage files.")
 string(TIMESTAMP PLSSVM_CURRENT_BUILD_TIME "%d. %B %Y")
 string(REPLACE ";" "|" PLSSVM_PLATFORM_NAME_LIST "${PLSSVM_PLATFORM_NAME_LIST}")
 string(REPLACE ";" "|" PLSSVM_BACKEND_NAME_LIST "${PLSSVM_BACKEND_NAME_LIST}")
-string(REPLACE ";" "|" PLSSVM_SYCL_BACKEND_NAME_LIST "${PLSSVM_SYCL_BACKEND_NAME_LIST}")
 if (TARGET ${PLSSVM_SYCL_BACKEND_LIBRARY_NAME})
+    string(REPLACE ";" "|" PLSSVM_SYCL_BACKEND_NAME_LIST "${PLSSVM_SYCL_BACKEND_NAME_LIST}")
     set(PLSSVM_SYCL_IMPLEMENTATION_TYPE_MANPAGE_ENTRY "
 .TP
 .B --sycl_implementation_type
@@ -772,6 +784,15 @@ choose the kernel invocation type when using SYCL as backend: automatic|nd_range
 ")
 endif ()
 set(PLSSVM_SYCL_MANPAGE_ENTRY "${PLSSVM_SYCL_KERNEL_INVOCATION_TYPE_MANPAGE_ENTRY}${PLSSVM_SYCL_IMPLEMENTATION_TYPE_MANPAGE_ENTRY}")
+## assemble the Kokkos manpage entry
+if (TARGET ${PLSSVM_KOKKOS_BACKEND_LIBRARY_NAME})
+    string(REPLACE ";" "|" PLSSVM_KOKKOS_BACKEND_AVAILABLE_EXECUTION_SPACES "${PLSSVM_KOKKOS_BACKEND_AVAILABLE_EXECUTION_SPACES}")
+    set(PLSSVM_KOKKOS_MANPAGE_ENTRY "
+.TP
+.B --kokkos_execution_space
+choose the Kokkos execution space to be used in the Kokkos backend: automatic|${PLSSVM_KOKKOS_BACKEND_AVAILABLE_EXECUTION_SPACES} (default: automatic)
+")
+endif ()
 ## assemble the performance tracker manpage entry
 if (PLSSVM_ENABLE_PERFORMANCE_TRACKING)
     set(PLSSVM_PERFORMANCE_TRACKER_MANPAGE_ENTRY "
@@ -787,6 +808,7 @@ configure_file(
         ${CMAKE_CURRENT_SOURCE_DIR}/docs/plssvm-train.1
         @ONLY
 )
+# update manpage entry since plssvm-predict can't recognize the SYCL kernel invocation type
 set(PLSSVM_SYCL_MANPAGE_ENTRY "${PLSSVM_SYCL_IMPLEMENTATION_TYPE_MANPAGE_ENTRY}")
 configure_file(
         ${CMAKE_CURRENT_SOURCE_DIR}/docs/plssvm-predict.1.in
@@ -866,6 +888,7 @@ install(FILES
         "${CMAKE_CURRENT_SOURCE_DIR}/cmake/plssvm/plssvmHPXTargets.cmake"
         "${CMAKE_CURRENT_SOURCE_DIR}/cmake/plssvm/plssvmAdaptiveCppTargets.cmake"
         "${CMAKE_CURRENT_SOURCE_DIR}/cmake/plssvm/plssvmDPCPPTargets.cmake"
+        "${CMAKE_CURRENT_SOURCE_DIR}/cmake/plssvm/plssvmKokkosTargets.cmake"
         "${CMAKE_CURRENT_SOURCE_DIR}/cmake/plssvm/plssvmstdparTargets.cmake"
         DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/plssvm/cmake
 )

CMakePresets.json

@@ -14,6 +14,7 @@
     "cmake/presets/opencl.json",
     "cmake/presets/acpp.json",
     "cmake/presets/dpcpp.json",
+    "cmake/presets/kokkos.json",
     "cmake/presets/all.json"
   ]
 }

README.md

@@ -65,6 +65,7 @@ The main highlights of our SVM implementations are:
    - [HIP](https://github.com/ROCm-Developer-Tools/HIP)
    - [OpenCL](https://www.khronos.org/opencl/)
    - [SYCL](https://www.khronos.org/sycl/) (supported implementations are [DPC++](https://github.com/intel/llvm) and [AdaptiveCpp](https://github.com/AdaptiveCpp/AdaptiveCpp) (formerly known as hipSYCL); specifically the versions [sycl-nightly/20231201](https://github.com/intel/llvm/tree/sycl-nightly/20230110) and AdaptiveCpp release [v24.06.0](https://github.com/AdaptiveCpp/AdaptiveCpp/releases/tag/v23.10.0))
+   - [Kokkos](https://github.com/kokkos/kokkos) (all execution spaces supported except `OpenMPTarget` and `OpenACC`); specifically the version [4.5.00](https://github.com/kokkos/kokkos/releases/tag/4.5.00)
 3. Six different kernel functions to be able to classify a large variety of different problems:
    - linear: $\vec{u}^T$ $\cdot$ $\vec{v}$
    - polynomial: $(\gamma$ $\cdot$ $\vec{u}^T$ $\cdot$ $\vec{v}$ $+$ $coef0)^{d}$
@@ -128,6 +129,10 @@ Additional dependencies for the SYCL backend:
 
 - the code must be compiled with a SYCL capable compiler; currently supported are [DPC++](https://github.com/intel/llvm) and [AdaptiveCpp](https://github.com/AdaptiveCpp/AdaptiveCpp)
 
+Additional dependencies for the Kokkos backend:
+
+- a Kokkos installation with the respective execution spaces enabled; currently all execution spaces are supported except `OpenMPTarget` and `OpenACC`
+
 Additional dependencies for the stdpar backend:
 
 - the code must be compiled with a stdpar capable compiler; currently supported are [nvc++](https://developer.nvidia.com/hpc-sdk), [roc-stdpar](https://github.com/ROCm/roc-stdpar), [icpx](https://www.intel.com/content/www/us/en/developer/tools/oneapi/dpc-compiler.html), [AdaptiveCpp](https://github.com/AdaptiveCpp/AdaptiveCpp), and [GNU GCC](https://gcc.gnu.org/))
@@ -243,6 +248,11 @@ The `[optional_options]` can be one or multiple of:
   - `AUTO`: check for the OpenMP backend but **do not** fail if not available
   - `OFF`: do not check for the OpenMP backend
 
+- `PLSSVM_ENABLE_HPX_BACKEND=ON|OFF|AUTO` (default: `AUTO`):
+    - `ON`: check for the HPX backend and fail if not available
+    - `AUTO`: check for the HPX backend but **do not** fail if not available
+    - `OFF`: do not check for the HPX backend
+
 - `PLSSVM_ENABLE_STDPAR_BACKEND=ON|OFF|AUTO` (default: `AUTO`):
     - `ON`: check for the stdpar backend and fail if not available
     - `AUTO`: check for the stdpar backend but **do not** fail if not available
@@ -268,6 +278,11 @@ The `[optional_options]` can be one or multiple of:
   - `AUTO`: check for the SYCL backend but **do not** fail if not available
   - `OFF`: do not check for the SYCL backend
 
+- `PLSSVM_ENABLE_KOKKOS_BACKEND=ON|OFF|AUTO` (default: `AUTO`):
+    - `ON`: check for the Kokkos backend and fail if not available
+    - `AUTO`: check for the Kokkos backend but **do not** fail if not available
+    - `OFF`: do not check for the Kokkos backend
+
 **Attention:** at least one backend must be enabled and available!
 
 - `PLSSVM_ENABLE_FAST_MATH=ON|OFF` (default depending on `CMAKE_BUILD_TYPE`: `ON` for Release or RelWithDebInfo, `OFF` otherwise): enable `fast-math` compiler flags for all backends
@@ -344,6 +359,10 @@ If more than one SYCL implementation is available the environment variables `PLS
 
 - `PLSSVM_SYCL_BACKEND_PREFERRED_IMPLEMENTATION` (`dpcpp`|`adaptivecpp`): specify the preferred SYCL implementation if the `sycl_implementation_type` option is set to `automatic`; additional the specified SYCL implementation is used in the `plssvm::sycl` namespace, the other implementations are available in the `plssvm::dpcpp` and `plssvm::adaptivecpp` namespace respectively
 
+If the Kokkos backend is available the following additional option is available (**note**: this option takes only effect if the Kokkos SYCL execution space is available):
+
+- `PLSSVM_KOKKOS_BACKEND_INTEL_LLVM_ENABLE_AOT` (default: `ON`): enable Ahead-of-Time (AOT) compilation for the specified target platforms
+
 If the stdpar backend is available, an additional options can be set.
 
 - `PLSSVM_STDPAR_BACKEND_IMPLEMENTATION` (default: `AUTO`): explicitly specify the used stdpar implementation; must be one of: `AUTO`, `NVHPC`, `roc-stdpar`, `IntelLLVM`, `ACPP`, `GNU_TBB`.
@@ -363,24 +382,6 @@ Available configure presets:
   "hpx"                     - HPX backend
   "hpx_python"              - HPX backend + Python bindings
   "hpx_test"                - HPX backend tests
-  "cuda"                    - CUDA backend
-  "cuda_python"             - CUDA backend + Python bindings
-  "cuda_test"               - CUDA backend tests
-  "hip"                     - HIP backend
-  "hip_python"              - HIP backend + Python bindings
-  "hip_test"                - HIP backend tests
-  "opencl"                  - OpenCL backend
-  "opencl_python"           - OpenCL backend + Python bindings
-  "opencl_test"             - OpenCL backend tests
-  "acpp"                    - AdaptiveCpp SYCL backend
-  "acpp_python"             - AdaptiveCpp SYCL backend + Python bindings
-  "acpp_test"               - AdaptiveCpp SYCL backend tests
-  "dpcpp"                   - DPC++/icpx SYCL backend
-  "dpcpp_python"            - DPC++/icpx backend + Python bindings
-  "dpcpp_test"              - DPC++/icpx backend tests
-  "all"                     - All available backends
-  "all_python"              - All available backends + Python bindings
-  "all_test"                - All available backends tests
   "stdpar"                  - stdpar backend
   "stdpar_python"           - stdpar backend + Python bindings
   "stdpar_test"             - stdpar backend tests
@@ -399,6 +400,27 @@ Available configure presets:
   "stdpar_intelllvm"        - stdpar IntelLLVM (icpx) backend
   "stdpar_intelllvm_python" - stdpar IntelLLVM (icpx) backend + Python bindings
   "stdpar_intelllvm_test"   - stdpar IntelLLVM (icpx) backend tests
+  "cuda"                    - CUDA backend
+  "cuda_python"             - CUDA backend + Python bindings
+  "cuda_test"               - CUDA backend tests
+  "hip"                     - HIP backend
+  "hip_python"              - HIP backend + Python bindings
+  "hip_test"                - HIP backend tests
+  "opencl"                  - OpenCL backend
+  "opencl_python"           - OpenCL backend + Python bindings
+  "opencl_test"             - OpenCL backend tests
+  "acpp"                    - AdaptiveCpp SYCL backend
+  "acpp_python"             - AdaptiveCpp SYCL backend + Python bindings
+  "acpp_test"               - AdaptiveCpp SYCL backend tests
+  "dpcpp"                   - DPC++/icpx SYCL backend
+  "dpcpp_python"            - DPC++/icpx backend + Python bindings
+  "dpcpp_test"              - DPC++/icpx backend tests
+  "kokkos"                  - Kokkos backend
+  "kokkos_python"           - Kokkos backend + Python bindings
+  "kokkos_test"             - Kokkos backend tests
+  "all"                     - All available backends
+  "all_python"              - All available backends + Python bindings
+  "all_test"                - All available backends tests
 ```
 
 With these presets, building and testing, e.g., our CUDA backend is as simple as typing (in the PLSSVM root directory):
@@ -553,12 +575,14 @@ Usage:
   -i, --max_iter arg            set the maximum number of CG iterations (default: num_features)
   -l, --solver arg              choose the solver: automatic|cg_explicit|cg_implicit (default: automatic)
   -a, --classification arg      the classification strategy to use for multi-class classification: oaa|oao (default: oaa)
-  -b, --backend arg             choose the backend: automatic|openmp|hpx|cuda|hip|opencl|sycl|stdpar (default: automatic)
+  -b, --backend arg             choose the backend: automatic|openmp|hpx|cuda|hip|opencl|sycl|kokkos|stdpar (default: automatic)
   -p, --target_platform arg     choose the target platform: automatic|cpu|gpu_nvidia|gpu_amd|gpu_intel (default: automatic)
       --sycl_kernel_invocation_type arg
                                 choose the kernel invocation type when using SYCL as backend: automatic|nd_range (default: automatic)
       --sycl_implementation_type arg
                                 choose the SYCL implementation to be used in the SYCL backend: automatic|dpcpp|adaptivecpp (default: automatic)
+      --kokkos_execution_space arg
+                                choose the Kokkos execution space to be used in the Kokkos backend: automatic|Cuda|OpenMP|Serial (default: automatic)
       --performance_tracking arg
                                 the output YAML file where the performance tracking results are written to; if not provided, the results are dumped to stderr
       --use_strings_as_labels   use strings as labels instead of plane numbers
@@ -594,10 +618,10 @@ Another example targeting NVIDIA GPUs using the SYCL backend looks like:
 
 The `--backend=automatic` option works as follows:
 
-- if the `gpu_nvidia` target is available, check for existing backends in order `cuda` 🠦 `hip` 🠦 `opencl` 🠦 `sycl` 🠦 `stdpar`
-- otherwise, if the `gpu_amd` target is available, check for existing backends in order `hip` 🠦 `opencl` 🠦 `sycl` 🠦 `stdpar`
-- otherwise, if the `gpu_intel` target is available, check for existing backends in order `sycl` 🠦 `opencl` 🠦 `stdpar`
-- otherwise, if the `cpu` target is available, check for existing backends in order `sycl` 🠦 `opencl` 🠦 `openmp` 🠦 `hpx` 🠦 `stdpar`
+- if the `gpu_nvidia` target is available, check for existing backends in order `cuda` 🠦 `hip` 🠦 `opencl` 🠦 `sycl` 🠦 `kokkos` 🠦 `stdpar`
+- otherwise, if the `gpu_amd` target is available, check for existing backends in order `hip` 🠦 `opencl` 🠦 `sycl` 🠦 `kokkos` 🠦 `stdpar`
+- otherwise, if the `gpu_intel` target is available, check for existing backends in order `sycl` 🠦 `opencl` 🠦 `kokkos` 🠦 `stdpar`
+- otherwise, if the `cpu` target is available, check for existing backends in order `sycl` 🠦 `kokkos` 🠦 `opencl` 🠦 `openmp` 🠦 `hpx` 🠦 `stdpar`
 
 Note that during CMake configuration it is guaranteed that at least one of the above combinations does exist.
 
@@ -609,11 +633,13 @@ The `--target_platform=automatic` option works for the different backends as fol
 - `HIP`: always selects an AMD GPU (if no AMD GPU is available, throws an exception)
 - `OpenCL`: tries to find available devices in the following order: NVIDIA GPUs 🠦 AMD GPUs 🠦 Intel GPUs 🠦 CPU
 - `SYCL`: tries to find available devices in the following order: NVIDIA GPUs 🠦 AMD GPUs 🠦 Intel GPUs 🠦 CPU
+- `Kokkos`: checks which execution spaces are available and which target platforms they support and then tries to find available devices in the following order: NVIDIA GPUs 🠦 AMD GPUs 🠦 Intel GPUs 🠦 CPU
 - `stdpar`: target device must be selected at compile time (using `PLSSVM_TARGET_PLATFORMS`) or using environment variables at runtime
 
 The `--sycl_kernel_invocation_type` and `--sycl_implementation_type` flags are only used if the `--backend` is `sycl`, otherwise a warning is emitted on `stderr`.
 If the `--sycl_kernel_invocation_type` is `automatic`, the `nd_range` invocation type is currently always used.
 If the `--sycl_implementation_type` is `automatic`, the used SYCL implementation is determined by the `PLSSVM_SYCL_BACKEND_PREFERRED_IMPLEMENTATION` CMake flag.
+If the `--kokkos_execution_space` is `automatic`, uses the best fitting execution space based on the provided and/or available target platforms.
 
 ### Predicting using `plssvm-predict`
 
@@ -628,10 +654,12 @@ LS-SVM with multiple (GPU-)backends
 Usage:
   ./plssvm-predict [OPTION...] test_file model_file [output_file]
 
-  -b, --backend arg             choose the backend: automatic|openmp|cuda|hip|opencl|sycl|stdpar (default: automatic)
+  -b, --backend arg             choose the backend: automatic|openmp|hpx|cuda|hip|opencl|sycl|kokkos|stdpar (default: automatic)
   -p, --target_platform arg     choose the target platform: automatic|cpu|gpu_nvidia|gpu_amd|gpu_intel (default: automatic)
       --sycl_implementation_type arg
                                 choose the SYCL implementation to be used in the SYCL backend: automatic|dpcpp|adaptivecpp (default: automatic)
+      --kokkos_execution_space arg
+                                choose the Kokkos execution space to be used in the Kokkos backend: automatic|Cuda|OpenMP|Serial (default: automatic)
       --performance_tracking arg
                                 the output YAML file where the performance tracking results are written to; if not provided, the results are dumped to stderr
       --use_strings_as_labels   use strings as labels instead of plane numbers
@@ -777,9 +805,6 @@ Roughly the same can be achieved using our Python bindings with the following Py
 import plssvm
 from sklearn.metrics import classification_report
 
-# correctly initialize and finalize environments
-environment_guard = plssvm.environment.ScopeGuard()
-
 try:
     # create a new C-SVM parameter set, explicitly overriding the default kernel function
     params = plssvm.Parameter(kernel_type=plssvm.KernelFunctionType.POLYNOMIAL)

bindings/Python/CMakeLists.txt

@@ -41,7 +41,6 @@ set(PLSSVM_PYTHON_BINDINGS_SOURCES
     ${CMAKE_CURRENT_LIST_DIR}/classification_types.cpp
     ${CMAKE_CURRENT_LIST_DIR}/csvm.cpp
     ${CMAKE_CURRENT_LIST_DIR}/data_set.cpp
-    ${CMAKE_CURRENT_LIST_DIR}/environment.cpp
     ${CMAKE_CURRENT_LIST_DIR}/file_format_types.cpp
     ${CMAKE_CURRENT_LIST_DIR}/gamma.cpp
     ${CMAKE_CURRENT_LIST_DIR}/kernel_function_types.cpp
@@ -98,6 +97,9 @@ endif ()
 if (TARGET ${PLSSVM_SYCL_BACKEND_DPCPP_LIBRARY_NAME})
     list(APPEND PLSSVM_PYTHON_BINDINGS_SOURCES ${CMAKE_CURRENT_LIST_DIR}/backends/dpcpp_csvm.cpp)
 endif ()
+if (TARGET ${PLSSVM_KOKKOS_BACKEND_LIBRARY_NAME})
+    list(APPEND PLSSVM_PYTHON_BINDINGS_SOURCES ${CMAKE_CURRENT_LIST_DIR}/backends/kokkos_csvm.cpp)
+endif ()
 
 # create pybind11 module
 set(PLSSVM_PYTHON_BINDINGS_LIBRARY_NAME plssvm)