LB: Re-generate kernels

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepDoublePrecisionLeesEdwards.h

@@ -56,7 +56,7 @@ class CollideSweepDoublePrecisionLeesEdwards {
                                          BlockDataID pdfsID_, double grid_size,
                                          double omega_shear, double v_s)
       : forceID(forceID_), pdfsID(pdfsID_), grid_size_(grid_size),
-        omega_shear_(omega_shear), v_s_(v_s){};
+        omega_shear_(omega_shear), v_s_(v_s) {};
 
   void run(IBlock *block);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepDoublePrecisionLeesEdwardsAVX.h

@@ -57,7 +57,7 @@ class CollideSweepDoublePrecisionLeesEdwardsAVX {
                                             double grid_size,
                                             double omega_shear, double v_s)
       : forceID(forceID_), pdfsID(pdfsID_), grid_size_(grid_size),
-        omega_shear_(omega_shear), v_s_(v_s){};
+        omega_shear_(omega_shear), v_s_(v_s) {};
 
   void run(IBlock *block);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepDoublePrecisionLeesEdwardsCUDA.h

@@ -59,7 +59,7 @@ class CollideSweepDoublePrecisionLeesEdwardsCUDA {
                                              double grid_size,
                                              double omega_shear, double v_s)
       : forceID(forceID_), pdfsID(pdfsID_), grid_size_(grid_size),
-        omega_shear_(omega_shear), v_s_(v_s){};
+        omega_shear_(omega_shear), v_s_(v_s) {};
 
   void run(IBlock *block, gpuStream_t stream = nullptr);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepDoublePrecisionThermalized.h

@@ -60,7 +60,7 @@ class CollideSweepDoublePrecisionThermalized {
       : forceID(forceID_), pdfsID(pdfsID_), kT_(kT), omega_bulk_(omega_bulk),
         omega_even_(omega_even), omega_odd_(omega_odd),
         omega_shear_(omega_shear), seed_(seed), time_step_(time_step),
-        configured_(false){};
+        configured_(false) {};
 
   void run(IBlock *block);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepDoublePrecisionThermalizedAVX.h

@@ -61,7 +61,7 @@ class CollideSweepDoublePrecisionThermalizedAVX {
       : forceID(forceID_), pdfsID(pdfsID_), kT_(kT), omega_bulk_(omega_bulk),
         omega_even_(omega_even), omega_odd_(omega_odd),
         omega_shear_(omega_shear), seed_(seed), time_step_(time_step),
-        configured_(false){};
+        configured_(false) {};
 
   void run(IBlock *block);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepDoublePrecisionThermalizedCUDA.h

@@ -61,7 +61,7 @@ class CollideSweepDoublePrecisionThermalizedCUDA {
       : forceID(forceID_), pdfsID(pdfsID_), kT_(kT), omega_bulk_(omega_bulk),
         omega_even_(omega_even), omega_odd_(omega_odd),
         omega_shear_(omega_shear), seed_(seed), time_step_(time_step),
-        configured_(false){};
+        configured_(false) {};
 
   void run(IBlock *block, gpuStream_t stream = nullptr);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepSinglePrecisionLeesEdwards.h

@@ -56,7 +56,7 @@ class CollideSweepSinglePrecisionLeesEdwards {
                                          BlockDataID pdfsID_, float grid_size,
                                          float omega_shear, float v_s)
       : forceID(forceID_), pdfsID(pdfsID_), grid_size_(grid_size),
-        omega_shear_(omega_shear), v_s_(v_s){};
+        omega_shear_(omega_shear), v_s_(v_s) {};
 
   void run(IBlock *block);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepSinglePrecisionLeesEdwardsAVX.h

@@ -57,7 +57,7 @@ class CollideSweepSinglePrecisionLeesEdwardsAVX {
                                             float grid_size, float omega_shear,
                                             float v_s)
       : forceID(forceID_), pdfsID(pdfsID_), grid_size_(grid_size),
-        omega_shear_(omega_shear), v_s_(v_s){};
+        omega_shear_(omega_shear), v_s_(v_s) {};
 
   void run(IBlock *block);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepSinglePrecisionLeesEdwardsCUDA.h

@@ -59,7 +59,7 @@ class CollideSweepSinglePrecisionLeesEdwardsCUDA {
                                              float grid_size, float omega_shear,
                                              float v_s)
       : forceID(forceID_), pdfsID(pdfsID_), grid_size_(grid_size),
-        omega_shear_(omega_shear), v_s_(v_s){};
+        omega_shear_(omega_shear), v_s_(v_s) {};
 
   void run(IBlock *block, gpuStream_t stream = nullptr);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepSinglePrecisionThermalized.h

@@ -60,7 +60,7 @@ class CollideSweepSinglePrecisionThermalized {
       : forceID(forceID_), pdfsID(pdfsID_), kT_(kT), omega_bulk_(omega_bulk),
         omega_even_(omega_even), omega_odd_(omega_odd),
         omega_shear_(omega_shear), seed_(seed), time_step_(time_step),
-        configured_(false){};
+        configured_(false) {};
 
   void run(IBlock *block);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepSinglePrecisionThermalizedAVX.h

@@ -60,7 +60,7 @@ class CollideSweepSinglePrecisionThermalizedAVX {
       : forceID(forceID_), pdfsID(pdfsID_), kT_(kT), omega_bulk_(omega_bulk),
         omega_even_(omega_even), omega_odd_(omega_odd),
         omega_shear_(omega_shear), seed_(seed), time_step_(time_step),
-        configured_(false){};
+        configured_(false) {};
 
   void run(IBlock *block);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/CollideSweepSinglePrecisionThermalizedCUDA.h

@@ -62,7 +62,7 @@ class CollideSweepSinglePrecisionThermalizedCUDA {
       : forceID(forceID_), pdfsID(pdfsID_), kT_(kT), omega_bulk_(omega_bulk),
         omega_even_(omega_even), omega_odd_(omega_odd),
         omega_shear_(omega_shear), seed_(seed), time_step_(time_step),
-        configured_(false){};
+        configured_(false) {};
 
   void run(IBlock *block, gpuStream_t stream = nullptr);
 

src/walberla_bridge/src/lattice_boltzmann/generated_kernels/Dynamic_UBB_double_precision.cpp

@@ -17,9 +17,7 @@
 //! \\author pystencils
 //======================================================================================================================
 
-// kernel generated with pystencils v1.3.3, lbmpy v1.3.3,
-// lbmpy_walberla/pystencils_walberla from waLBerla commit
-// 04f4adbdfc0af983e2d9b72e244d775f37d77034
+// kernel generated with pystencils v1.3.3, lbmpy v1.3.3, lbmpy_walberla/pystencils_walberla from waLBerla commit 04f4adbdfc0af983e2d9b72e244d775f37d77034
 
 #include "Dynamic_UBB_double_precision.h"
 #include "core/DataTypes.h"
@@ -49,99 +47,29 @@ namespace lbm {
 #endif
 // NOLINTBEGIN(readability-non-const-parameter*)
 namespace internal_451fd042b8d7665063ea81b98853365b {
-static FUNC_PREFIX void
-dynamic_ubb_double_precision_boundary_Dynamic_UBB_double_precision(
-    uint8_t *RESTRICT const _data_indexVector, double *RESTRICT _data_pdfs,
-    int64_t const _stride_pdfs_0, int64_t const _stride_pdfs_1,
-    int64_t const _stride_pdfs_2, int64_t const _stride_pdfs_3,
-    int32_t indexVectorSize) {
-
-  const int32_t f_in_inv_dir_idx[] = {0, 2,  1,  4,  3,  6,  5,  10, 9, 8,
-                                      7, 16, 15, 18, 17, 12, 11, 14, 13};
-  const int32_t f_in_inv_offsets_x[] = {0, 0, 0, -1, 1, 0, 0, -1, 1, -1,
-                                        1, 0, 0, -1, 1, 0, 0, -1, 1};
-  const int32_t f_in_inv_offsets_y[] = {0,  1, -1, 0, 0, 0, 0,  1, 1, -1,
-                                        -1, 1, -1, 0, 0, 1, -1, 0, 0};
-  const int32_t f_in_inv_offsets_z[] = {0, 0, 0, 0, 0, 1,  -1, 0,  0, 0,
-                                        0, 1, 1, 1, 1, -1, -1, -1, -1};
-
-  const double weights[] = {
-      0.33333333333333333,  0.055555555555555556, 0.055555555555555556,
-      0.055555555555555556, 0.055555555555555556, 0.055555555555555556,
-      0.055555555555555556, 0.027777777777777778, 0.027777777777777778,
-      0.027777777777777778, 0.027777777777777778, 0.027777777777777778,
-      0.027777777777777778, 0.027777777777777778, 0.027777777777777778,
-      0.027777777777777778, 0.027777777777777778, 0.027777777777777778,
-      0.027777777777777778};
-
-  const int32_t neighbour_offset_x[] = {0, 0, 0, -1, 1, 0, 0, -1, 1, -1,
-                                        1, 0, 0, -1, 1, 0, 0, -1, 1};
-  const int32_t neighbour_offset_y[] = {0,  1, -1, 0, 0, 0, 0,  1, 1, -1,
-                                        -1, 1, -1, 0, 0, 1, -1, 0, 0};
-  const int32_t neighbour_offset_z[] = {0, 0, 0, 0, 0, 1,  -1, 0,  0, 0,
-                                        0, 1, 1, 1, 1, -1, -1, -1, -1};
+static FUNC_PREFIX void dynamic_ubb_double_precision_boundary_Dynamic_UBB_double_precision(uint8_t *RESTRICT const _data_indexVector, double *RESTRICT _data_pdfs, int64_t const _stride_pdfs_0, int64_t const _stride_pdfs_1, int64_t const _stride_pdfs_2, int64_t const _stride_pdfs_3, int32_t indexVectorSize) {
+
+  const int32_t f_in_inv_dir_idx[] = {0, 2, 1, 4, 3, 6, 5, 10, 9, 8, 7, 16, 15, 18, 17, 12, 11, 14, 13};
+  const int32_t f_in_inv_offsets_x[] = {0, 0, 0, -1, 1, 0, 0, -1, 1, -1, 1, 0, 0, -1, 1, 0, 0, -1, 1};
+  const int32_t f_in_inv_offsets_y[] = {0, 1, -1, 0, 0, 0, 0, 1, 1, -1, -1, 1, -1, 0, 0, 1, -1, 0, 0};
+  const int32_t f_in_inv_offsets_z[] = {0, 0, 0, 0, 0, 1, -1, 0, 0, 0, 0, 1, 1, 1, 1, -1, -1, -1, -1};
+
+  const double weights[] = {0.33333333333333333, 0.055555555555555556, 0.055555555555555556, 0.055555555555555556, 0.055555555555555556, 0.055555555555555556, 0.055555555555555556, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778, 0.027777777777777778};
+
+  const int32_t neighbour_offset_x[] = {0, 0, 0, -1, 1, 0, 0, -1, 1, -1, 1, 0, 0, -1, 1, 0, 0, -1, 1};
+  const int32_t neighbour_offset_y[] = {0, 1, -1, 0, 0, 0, 0, 1, 1, -1, -1, 1, -1, 0, 0, 1, -1, 0, 0};
+  const int32_t neighbour_offset_z[] = {0, 0, 0, 0, 0, 1, -1, 0, 0, 0, 0, 1, 1, 1, 1, -1, -1, -1, -1};
 
   for (int64_t ctr_0 = 0; ctr_0 < indexVectorSize; ctr_0 += 1) {
     const int32_t x = *((int32_t *)(&_data_indexVector[40 * ctr_0]));
     const int32_t y = *((int32_t *)(&_data_indexVector[40 * ctr_0 + 4]));
     const int32_t z = *((int32_t *)(&_data_indexVector[40 * ctr_0 + 8]));
     const int32_t dir = *((int32_t *)(&_data_indexVector[40 * ctr_0 + 12]));
-    const double vel0Term =
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 10 * _stride_pdfs_3] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 14 * _stride_pdfs_3] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 18 * _stride_pdfs_3] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 4 * _stride_pdfs_3] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 8 * _stride_pdfs_3];
-    const double vel1Term =
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 11 * _stride_pdfs_3] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 15 * _stride_pdfs_3] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 7 * _stride_pdfs_3] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + _stride_pdfs_3];
-    const double vel2Term =
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 12 * _stride_pdfs_3] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 13 * _stride_pdfs_3] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + 5 * _stride_pdfs_3];
-    const double rho = vel0Term + vel1Term + vel2Term +
-                       _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                                  _stride_pdfs_2 * z + 16 * _stride_pdfs_3] +
-                       _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                                  _stride_pdfs_2 * z + 17 * _stride_pdfs_3] +
-                       _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                                  _stride_pdfs_2 * z + 2 * _stride_pdfs_3] +
-                       _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                                  _stride_pdfs_2 * z + 3 * _stride_pdfs_3] +
-                       _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                                  _stride_pdfs_2 * z + 6 * _stride_pdfs_3] +
-                       _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                                  _stride_pdfs_2 * z + 9 * _stride_pdfs_3] +
-                       _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                                  _stride_pdfs_2 * z];
-    _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_0 * f_in_inv_offsets_x[dir] +
-               _stride_pdfs_1 * y + _stride_pdfs_1 * f_in_inv_offsets_y[dir] +
-               _stride_pdfs_2 * z + _stride_pdfs_2 * f_in_inv_offsets_z[dir] +
-               _stride_pdfs_3 * f_in_inv_dir_idx[dir]] =
-        -rho *
-            (6.0 * ((double)(neighbour_offset_x[dir])) *
-                 *((double *)(&_data_indexVector[40 * ctr_0 + 16])) +
-             6.0 * ((double)(neighbour_offset_y[dir])) *
-                 *((double *)(&_data_indexVector[40 * ctr_0 + 24])) +
-             6.0 * ((double)(neighbour_offset_z[dir])) *
-                 *((double *)(&_data_indexVector[40 * ctr_0 + 32]))) *
-            weights[dir] +
-        _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y +
-                   _stride_pdfs_2 * z + _stride_pdfs_3 * dir];
+    const double vel0Term = _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 10 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 14 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 18 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 4 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 8 * _stride_pdfs_3];
+    const double vel1Term = _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 11 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 15 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 7 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + _stride_pdfs_3];
+    const double vel2Term = _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 12 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 13 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 5 * _stride_pdfs_3];
+    const double rho = vel0Term + vel1Term + vel2Term + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 16 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 17 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 2 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 3 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 6 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + 9 * _stride_pdfs_3] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z];
+    _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_0 * f_in_inv_offsets_x[dir] + _stride_pdfs_1 * y + _stride_pdfs_1 * f_in_inv_offsets_y[dir] + _stride_pdfs_2 * z + _stride_pdfs_2 * f_in_inv_offsets_z[dir] + _stride_pdfs_3 * f_in_inv_dir_idx[dir]] = -rho * (6.0 * ((double)(neighbour_offset_x[dir])) * *((double *)(&_data_indexVector[40 * ctr_0 + 16])) + 6.0 * ((double)(neighbour_offset_y[dir])) * *((double *)(&_data_indexVector[40 * ctr_0 + 24])) + 6.0 * ((double)(neighbour_offset_z[dir])) * *((double *)(&_data_indexVector[40 * ctr_0 + 32]))) * weights[dir] + _data_pdfs[_stride_pdfs_0 * x + _stride_pdfs_1 * y + _stride_pdfs_2 * z + _stride_pdfs_3 * dir];
   }
 }
 } // namespace internal_451fd042b8d7665063ea81b98853365b
@@ -155,8 +83,7 @@ dynamic_ubb_double_precision_boundary_Dynamic_UBB_double_precision(
 #pragma pop
 #endif
 
-void Dynamic_UBB_double_precision::run_impl(IBlock *block,
-                                            IndexVectors::Type type) {
+void Dynamic_UBB_double_precision::run_impl(IBlock *block, IndexVectors::Type type) {
   auto *indexVectors = block->getData<IndexVectors>(indexVectorID);
   int32_t indexVectorSize = int32_c(indexVectors->indexVector(type).size());
   if (indexVectorSize == 0)
@@ -174,10 +101,7 @@ void Dynamic_UBB_double_precision::run_impl(IBlock *block,
   const int64_t _stride_pdfs_1 = int64_t(pdfs->yStride());
   const int64_t _stride_pdfs_2 = int64_t(pdfs->zStride());
   const int64_t _stride_pdfs_3 = int64_t(1 * int64_t(pdfs->fStride()));
-  internal_451fd042b8d7665063ea81b98853365b::
-      dynamic_ubb_double_precision_boundary_Dynamic_UBB_double_precision(
-          _data_indexVector, _data_pdfs, _stride_pdfs_0, _stride_pdfs_1,
-          _stride_pdfs_2, _stride_pdfs_3, indexVectorSize);
+  internal_451fd042b8d7665063ea81b98853365b::dynamic_ubb_double_precision_boundary_Dynamic_UBB_double_precision(_data_indexVector, _data_pdfs, _stride_pdfs_0, _stride_pdfs_1, _stride_pdfs_2, _stride_pdfs_3, indexVectorSize);
 }
 
 void Dynamic_UBB_double_precision::run(IBlock *block) {