Merge pull request #3859 from bernhardmgruber/unroll

Unroll interpolation

include/picongpu/algorithms/AssignedTrilinearInterpolation.hpp

@@ -19,6 +19,7 @@
 
 #pragma once
 
+#include <pmacc/attribute/unroll.hpp>
 #include <pmacc/result_of_Functor.hpp>
 #include <pmacc/types.hpp>
 
@@ -67,13 +68,17 @@ namespace picongpu
         {
             using type = typename ::pmacc::result_of::Functor<AssignedTrilinearInterpolation, T_Cursor>::type;
 
+            constexpr auto iterations = T_end - T_begin + 1;
             auto result_z = type(0.0);
+            PMACC_UNROLL(iterations)
             for(int z = T_begin; z <= T_end; ++z)
             {
                 auto result_y = type(0.0);
+                PMACC_UNROLL(iterations)
                 for(int y = T_begin; y <= T_end; ++y)
                 {
                     auto result_x = type(0.0);
+                    PMACC_UNROLL(iterations)
                     for(int x = T_begin; x <= T_end; ++x)
                         /* a form factor is the "amount of particle" that is affected by this cell
                          * so we have to sum over: cell_value * form_factor

include/picongpu/algorithms/FieldToParticleInterpolation.hpp

@@ -24,6 +24,7 @@
 
 #include "picongpu/algorithms/ShiftCoordinateSystem.hpp"
 
+#include <pmacc/attribute/unroll.hpp>
 #include <pmacc/cuSTL/algorithm/functor/GetComponent.hpp>
 #include <pmacc/cuSTL/cursor/FunctorCursor.hpp>
 #include <pmacc/math/Vector.hpp>
@@ -76,6 +77,7 @@ namespace picongpu
             using Supports = typename pmacc::math::CT::make_Int<simDim, supp>::type;
 
             typename Cursor::ValueType result;
+            PMACC_UNROLL(Cursor::ValueType::dim)
             for(uint32_t i = 0; i < Cursor::ValueType::dim; i++)
             {
                 auto fieldComponent

include/pmacc/attribute/unroll.hpp

@@ -0,0 +1,43 @@
+/* Copyright 2021 Bernhard Manfred Gruber
+ *
+ * This file is part of PMacc.
+ *
+ * PMacc is free software: you can redistribute it and/or modify
+ * it under the terms of either the GNU General Public License or
+ * the GNU Lesser General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * PMacc is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License and the GNU Lesser General Public License
+ * for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * and the GNU Lesser General Public License along with PMacc.
+ * If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+#ifndef PMACC_UNROLL
+#    define PMACC_PRAGMA(x) _Pragma(#    x)
+
+#    if defined(__clang__) || defined(__INTEL_LLVM_COMPILER) || defined(__NVCC__)
+#        define PMACC_UNROLL(var) PMACC_PRAGMA(unroll var)
+#    elif defined(__INTEL_COMPILER) // check Intel before g++, because Intel defines __GNUG__
+#        define PMACC_UNROLL(var) PMACC_PRAGMA(unroll(var))
+#    elif defined(__GNUG__)
+// g++ does support an unroll pragma but it does not accept the value of a template argument (at least until g++-11.2)
+// see also: https://stackoverflow.com/q/63404539/2406044
+// #define PMACC_UNROLL(var) PMACC_PRAGMA(GCC unroll var)
+#        define PMACC_UNROLL(var)
+#    elif defined(_MSC_VER)
+// MSVC does not support a pragma for unrolling
+#        define PMACC_UNROLL(var)
+#    else
+#        define PMACC_UNROLL(var)
+#        warning PMACC_UNROLL is not implemented for your compiler
+#    endif
+#endif