Fix workflows post alpaka merge

.github/workflows/clang_format.yml

@@ -13,7 +13,7 @@ jobs:
     strategy:
       matrix:
         path:
-          - 'CLUEstering/include'
+          - 'CLUEstering/alpaka'
     steps:
     - uses: actions/checkout@v3
     - name: Run clang-format style check

.github/workflows/python-package-anaconda.yml

@@ -15,6 +15,8 @@ jobs:
 
     steps:
     - uses: actions/checkout@v3
+      with: 
+        submodules: true
     - name: Set up Python 3.11
       uses: actions/setup-python@v3
       with:
@@ -26,17 +28,11 @@ jobs:
     - name: Install dependencies
       run: |
         conda env update --file ${{github.workspace}}/.env/test_env.yml --name base
-    # - name: Lint with flake8
-    #   run: |
-    #     conda install flake8
-    #     # stop the build if there are Python syntax errors or undefined names
-    #     flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-    #     # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-    #     flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-    - name: Install locally
+    - name: Compile CLUEstering modules
       working-directory: ${{github.workspace}}
       run: |
-        pip install .
+        cmake -S . -B build -DCMAKE_BUILD_TYPE=Release && cmake --build build
+        cmake -B build
     - name: Test with pytest
       working-directory: ${{github.workspace}}/tests
       run: |

.github/workflows/python-package.yml

@@ -19,6 +19,8 @@ jobs:
     steps:
     # Checks out the code in the repository
     - uses: actions/checkout@v3
+      with: 
+        submodules: true
     # Sets up Python on the machine with the right version
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v3
@@ -28,21 +30,15 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install flake8 pytest
+        python -m pip install pytest
         python -m pip install scikit-learn 
         python -m pip install pandas
         python -m pip install matplotlib
-        python -m pip install pybind11
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-    - name: Install CLUEstering
+    - name: Compile CLUEstering modules
       working-directory: ${{github.workspace}}
       run: |
-        pip install .
+        cmake -S . -B build -DCMAKE_BUILD_TYPE=Release && cmake --build build
+        cmake -B build
     - name: Run tests of the Python library
       working-directory: ${{github.workspace}}/tests
       run: |

CLUEstering/CLUEstering.py

@@ -2,6 +2,7 @@
 Density based clustering algorithm developed at CERN.
 """
 
+import sys
 from dataclasses import dataclass
 from glob import glob
 import random as rnd
@@ -16,17 +17,16 @@
 from sklearn.preprocessing import StandardScaler
 from os.path import dirname, exists, join
 path = dirname(__file__)
-import sys
 sys.path.insert(1, join(path, 'lib'))
 import CLUE_Convolutional_Kernels as clue_kernels
 import CLUE_CPU_Serial as cpu_serial
-tbb_found = exists(*glob(join(path, 'lib/CLUE_CPU_TBB*.so')))
+tbb_found = exists(str(*glob(join(path, 'lib/CLUE_CPU_TBB*.so'))))
 if tbb_found:
     import CLUE_CPU_TBB as cpu_tbb
-cuda_found = exists(*glob(join(path, 'lib/CLUE_CPU_TBB*.so')))
+cuda_found = exists(str(*glob(join(path, 'lib/CLUE_CPU_CUDA*.so'))))
 if cuda_found:
     import CLUE_GPU_CUDA as gpu_cuda
-hip_found = exists(*glob(join(path, 'lib/CLUE_CPU_TBB*.so')))
+hip_found = exists(str(*glob(join(path, 'lib/CLUE_CPU_HIP*.so'))))
 if hip_found:
     import CLUE_GPU_HIP as gpu_hip
 
@@ -236,14 +236,26 @@ def _read_array(self, input_data: Union[list,np.ndarray]) -> None:
         None
         """
 
-        if len(input_data) < 2 or len(input_data) > 10:
-            raise ValueError("Inadequate data. The data must contain at least one coordinate" +
-                             " and the weight.")
-        self.clust_data = clustering_data(np.asarray(input_data[:-1]),
-                                          np.copy(np.asarray(input_data[:-1])),
-                                          np.asarray(input_data[-1]),
-                                          len(input_data[:-1]),
-                                          len(input_data[-1]))
+        # [[x0, x1, x2, ...], [y0, y1, y2, ...], ... , [weights]]
+        if isinstance(input_data[0][0], (int, float)):
+            if len(input_data) < 2 or len(input_data) > 11:
+                raise ValueError("Inadequate data. The supported dimensions are between" +
+                                 "1 and 10.")
+            self.clust_data = clustering_data(np.asarray(input_data[:-1]).T,
+                                              np.copy(np.asarray(input_data[:-1]).T),
+                                              np.asarray(input_data[-1]),
+                                              len(input_data[:-1]),
+                                              len(input_data[-1]))
+        # [[[x0, y0, z0, ...], [x1, y1, z1, ...], ...], [weights]]
+        else:
+            if len(input_data) != 2:
+                raise ValueError("Inadequate data. The data must contain a weight value" +
+                                 "for each point.")
+            self.clust_data = clustering_data(np.asarray(input_data[0]),
+                                              np.copy(np.asarray(input_data[0])),
+                                              np.asarray(input_data[-1]),
+                                              len(input_data[0][0]),
+                                              len(input_data[-1]))
 
     def _read_string(self, input_data: str) -> Union[pd.DataFrame,None]:
         """
@@ -346,7 +358,8 @@ def _rescale(self) -> None:
 
         for dim in range(self.clust_data.n_dim):
             self.clust_data.coords.T[dim] = \
-            self.scaler.fit_transform(self.clust_data.coords.T[dim].reshape(-1, 1)).reshape(1, -1)[0]
+            self.scaler.fit_transform(
+                    self.clust_data.coords.T[dim].reshape(-1, 1)).reshape(1, -1)[0]
 
     def read_data(self,
                   input_data: Union[pd.DataFrame,str,dict,list,np.ndarray]) -> None:
@@ -474,12 +487,15 @@ def choose_kernel(self,
             if len(parameters) != 2:
                 raise ValueError("Wrong number of parameters. The exponential"
                                  + " kernel requires 2 parameters.")
-            self.kernel = CLUE_Convolutional_Kernels.ExponentialKernel(parameters[0], parameters[1])
+            self.kernel = CLUE_Convolutional_Kernels.ExponentialKernel(parameters[0],
+                                                                       parameters[1])
         elif choice == "gaus":
             if len(parameters) != 3:
                 raise ValueError("Wrong number of parameters. The gaussian" +
                                  " kernel requires 3 parameters.")
-            self.kernel = CLUE_Convolutional_Kernels.GaussinKernel(parameters[0], parameters[1], parameters[2])
+            self.kernel = CLUE_Convolutional_Kernels.GaussinKernel(parameters[0],
+                                                                   parameters[1],
+                                                                   parameters[2])
         elif choice == "custom":
             if len(parameters) != 0:
                 raise ValueError("Wrong number of parameters. Custom kernels"

CLUEstering/alpaka/AlpakaCore/CachedBufAlloc.h

@@ -11,16 +11,24 @@ namespace cms::alpakatools {
   namespace traits {
 
     //! The caching memory allocator trait.
-    template <typename TElem, typename TDim, typename TIdx, typename TDev, typename TQueue, typename TSfinae = void>
+    template <typename TElem,
+              typename TDim,
+              typename TIdx,
+              typename TDev,
+              typename TQueue,
+              typename TSfinae = void>
     struct CachedBufAlloc {
-      static_assert(alpaka::meta::DependentFalseType<TDev>::value, "This device does not support a caching allocator");
+      static_assert(alpaka::meta::DependentFalseType<TDev>::value,
+                    "This device does not support a caching allocator");
     };
 
     //! The caching memory allocator implementation for the CPU device
     template <typename TElem, typename TDim, typename TIdx, typename TQueue>
     struct CachedBufAlloc<TElem, TDim, TIdx, alpaka::DevCpu, TQueue, void> {
       template <typename TExtent>
-      ALPAKA_FN_HOST static auto allocCachedBuf(alpaka::DevCpu const& dev, TQueue queue, TExtent const& extent)
+      ALPAKA_FN_HOST static auto allocCachedBuf(alpaka::DevCpu const& dev,
+                                                TQueue queue,
+                                                TExtent const& extent)
           -> alpaka::BufCpu<TElem, TDim, TIdx> {
         // non-cached host-only memory
         return alpaka::allocAsyncBuf<TElem, TIdx>(queue, extent);
@@ -35,7 +43,8 @@ namespace cms::alpakatools {
       template <typename TExtent>
       ALPAKA_FN_HOST static auto allocCachedBuf(alpaka::DevCpu const& dev,
                                                 alpaka::QueueCudaRtNonBlocking queue,
-                                                TExtent const& extent) -> alpaka::BufCpu<TElem, TDim, TIdx> {
+                                                TExtent const& extent)
+          -> alpaka::BufCpu<TElem, TDim, TIdx> {
         ALPAKA_DEBUG_MINIMAL_LOG_SCOPE;
 
         auto& allocator = getHostCachingAllocator<alpaka::QueueCudaRtNonBlocking>();
@@ -48,15 +57,18 @@ namespace cms::alpakatools {
         // use a custom deleter to return the buffer to the CachingAllocator
         auto deleter = [alloc = &allocator](TElem* ptr) { alloc->free(ptr); };
 
-        return alpaka::BufCpu<TElem, TDim, TIdx>(dev, reinterpret_cast<TElem*>(memPtr), std::move(deleter), extent);
+        return alpaka::BufCpu<TElem, TDim, TIdx>(
+            dev, reinterpret_cast<TElem*>(memPtr), std::move(deleter), extent);
       }
     };
 
     //! The caching memory allocator implementation for the CUDA device
     template <typename TElem, typename TDim, typename TIdx, typename TQueue>
     struct CachedBufAlloc<TElem, TDim, TIdx, alpaka::DevCudaRt, TQueue, void> {
       template <typename TExtent>
-      ALPAKA_FN_HOST static auto allocCachedBuf(alpaka::DevCudaRt const& dev, TQueue queue, TExtent const& extent)
+      ALPAKA_FN_HOST static auto allocCachedBuf(alpaka::DevCudaRt const& dev,
+                                                TQueue queue,
+                                                TExtent const& extent)
           -> alpaka::BufCudaRt<TElem, TDim, TIdx> {
         ALPAKA_DEBUG_MINIMAL_LOG_SCOPE;
 
@@ -88,7 +100,8 @@ namespace cms::alpakatools {
       template <typename TExtent>
       ALPAKA_FN_HOST static auto allocCachedBuf(alpaka::DevCpu const& dev,
                                                 alpaka::QueueHipRtNonBlocking queue,
-                                                TExtent const& extent) -> alpaka::BufCpu<TElem, TDim, TIdx> {
+                                                TExtent const& extent)
+          -> alpaka::BufCpu<TElem, TDim, TIdx> {
         ALPAKA_DEBUG_MINIMAL_LOG_SCOPE;
 
         auto& allocator = getHostCachingAllocator<alpaka::QueueHipRtNonBlocking>();
@@ -101,15 +114,18 @@ namespace cms::alpakatools {
         // use a custom deleter to return the buffer to the CachingAllocator
         auto deleter = [alloc = &allocator](TElem* ptr) { alloc->free(ptr); };
 
-        return alpaka::BufCpu<TElem, TDim, TIdx>(dev, reinterpret_cast<TElem*>(memPtr), std::move(deleter), extent);
+        return alpaka::BufCpu<TElem, TDim, TIdx>(
+            dev, reinterpret_cast<TElem*>(memPtr), std::move(deleter), extent);
       }
     };
 
     //! The caching memory allocator implementation for the ROCm/HIP device
     template <typename TElem, typename TDim, typename TIdx, typename TQueue>
     struct CachedBufAlloc<TElem, TDim, TIdx, alpaka::DevHipRt, TQueue, void> {
       template <typename TExtent>
-      ALPAKA_FN_HOST static auto allocCachedBuf(alpaka::DevHipRt const& dev, TQueue queue, TExtent const& extent)
+      ALPAKA_FN_HOST static auto allocCachedBuf(alpaka::DevHipRt const& dev,
+                                                TQueue queue,
+                                                TExtent const& extent)
           -> alpaka::BufHipRt<TElem, TDim, TIdx> {
         ALPAKA_DEBUG_MINIMAL_LOG_SCOPE;
 
@@ -137,7 +153,8 @@ namespace cms::alpakatools {
 
   template <typename TElem, typename TIdx, typename TExtent, typename TQueue, typename TDev>
   ALPAKA_FN_HOST auto allocCachedBuf(TDev const& dev, TQueue queue, TExtent const& extent = TExtent()) {
-    return traits::CachedBufAlloc<TElem, alpaka::Dim<TExtent>, TIdx, TDev, TQueue>::allocCachedBuf(dev, queue, extent);
+    return traits::CachedBufAlloc<TElem, alpaka::Dim<TExtent>, TIdx, TDev, TQueue>::allocCachedBuf(
+        dev, queue, extent);
   }
 
 }  // namespace cms::alpakatools