FFT Poisson Solver: Neumann and Dirichlet Boundaries

.github/workflows/intel.yml

@@ -24,11 +24,8 @@ jobs:
         restore-keys: |
              ccache-${{ github.workflow }}-${{ github.job }}-git-
     - name: Build & Install
-      # /tmp/icpx-2d34de0e47/global_vars-header-4390fb.h:25:36: error: zero size arrays are an extension [-Werror,-Wzero-length-array]
-      #    25 | const char* const kernel_names[] = {
-      #       |                                    ^
-      # 1 error generated.
-      env: {CXXFLAGS: "-fno-operator-names -Werror -Wall -Wextra -Wpedantic -Wnull-dereference -Wfloat-conversion -Wshadow -Woverloaded-virtual -Wextra-semi -Wunreachable-code -Wnon-virtual-dtor -Wno-zero-length-array"}
+      # Warnings in 2025.0: unused-variable, shadow
+      env: {CXXFLAGS: "-fno-operator-names -Werror -Wall -Wextra -Wpedantic -Wnull-dereference -Wfloat-conversion -Wshadow -Woverloaded-virtual -Wextra-semi -Wunreachable-code -Wnon-virtual-dtor -Wno-unused-variable -Wno-shadow"}
       run: |
         export CCACHE_COMPRESS=1
         export CCACHE_COMPRESSLEVEL=10
@@ -73,11 +70,8 @@ jobs:
         restore-keys: |
              ccache-${{ github.workflow }}-${{ github.job }}-git-
     - name: Build & Install
-      # /tmp/icpx-2d34de0e47/global_vars-header-4390fb.h:25:36: error: zero size arrays are an extension [-Werror,-Wzero-length-array]
-      #    25 | const char* const kernel_names[] = {
-      #       |                                    ^
-      # 1 error generated.
-      env: {CXXFLAGS: "-fno-operator-names -Werror -Wall -Wextra -Wpedantic -Wnull-dereference -Wfloat-conversion -Wshadow -Woverloaded-virtual -Wextra-semi -Wunreachable-code -Wnon-virtual-dtor -Wno-zero-length-array"}
+      # Warnings in 2025.0: unused-variable, shadow
+      env: {CXXFLAGS: "-fno-operator-names -Werror -Wall -Wextra -Wpedantic -Wnull-dereference -Wfloat-conversion -Wshadow -Woverloaded-virtual -Wextra-semi -Wunreachable-code -Wnon-virtual-dtor -Wno-unused-variable -Wno-shadow"}
       run: |
         export CCACHE_COMPRESS=1
         export CCACHE_COMPRESSLEVEL=10
@@ -124,7 +118,8 @@ jobs:
         restore-keys: |
              ccache-${{ github.workflow }}-${{ github.job }}-git-
     - name: Build & Install
-      env: {CXXFLAGS: "-fsycl -fsycl-targets=nvptx64-nvidia-cuda -Xsycl-target-backend --offload-arch=sm_80 -fno-operator-names -Werror -Wall -Wextra -Wpedantic -Wnull-dereference -Wfloat-conversion -Wshadow -Woverloaded-virtual -Wextra-semi -Wunreachable-code -Wnon-virtual-dtor"}
+      # Warnings in 2025.0: unused-variable, shadow
+      env: {CXXFLAGS: "-fsycl -fsycl-targets=nvptx64-nvidia-cuda -Xsycl-target-backend --offload-arch=sm_80 -fno-operator-names -Werror -Wall -Wextra -Wpedantic -Wnull-dereference -Wfloat-conversion -Wshadow -Woverloaded-virtual -Wextra-semi -Wunreachable-code -Wnon-virtual-dtor -Wno-unused-variable -Wno-shadow"}
       run: |
         export CCACHE_COMPRESS=1
         export CCACHE_COMPRESSLEVEL=10
@@ -173,7 +168,8 @@ jobs:
         restore-keys: |
              ccache-${{ github.workflow }}-${{ github.job }}-git-
     - name: Build & Install
-      env: {CXXFLAGS: "-fsycl -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx90a -fno-operator-names -Werror -Wall -Wextra -Wpedantic -Wnull-dereference -Wfloat-conversion -Wshadow -Woverloaded-virtual -Wextra-semi -Wunreachable-code -Wnon-virtual-dtor"}
+      # Warnings in 2025.0: unused-variable, shadow
+      env: {CXXFLAGS: "-fsycl -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx90a -fno-operator-names -Werror -Wall -Wextra -Wpedantic -Wnull-dereference -Wfloat-conversion -Wshadow -Woverloaded-virtual -Wextra-semi -Wunreachable-code -Wnon-virtual-dtor -Wno-unused-variable -Wno-shadow"}
       run: |
         export CCACHE_COMPRESS=1
         export CCACHE_COMPRESSLEVEL=10

Docs/sphinx_documentation/source/FFT.rst

@@ -47,7 +47,9 @@ Below are examples of using :cpp:`FFT:R2C`.
             sp *= scaling;
         });
 
-    cMultiFab cmf(...);
+    // Use R2C provided spectral data layout.
+    auto const& [cba, cdm] = r2c.getSpectralDataLayout();
+    cMultiFab cmf(cba, cdm, 1, 0);
     FFT::R2C<Real,FFT::Direction::forward> r2c_forward(geom.Domain());
     r2c_forward(mfin, cmf);
 
@@ -56,16 +58,57 @@ Below are examples of using :cpp:`FFT:R2C`.
 
 Note that using :cpp:`forwardThenBackward` is expected to be more efficient
 than separate calls to :cpp:`forward` and :cpp:`backward` because some
-parallel communication can be avoided. It should also be noted that a lot of
+parallel communication can be avoided. For the spectral data, the example
+above builds :cpp:`cMultiFab` using :cpp:`FFT::R2C` provided layout. You can
+also use your own :cpp:`BoxArray` and :cpp:`DistributionMapping`, but it
+might result in extra communication. It should also be noted that a lot of
 preparation works are done in the construction of an :cpp:`FFT::R2C`
-object. Therefore, one should cache it for reuse if possible.
+object. Therefore, one should cache it for reuse if possible. Although
+:cpp:`FFT::R2C` does not have a default constructor, one could always use
+:cpp:`std::unique_ptr<FFT::R2C<Real>>` to store an object in one's class.
 
 
 Poisson Solver
 ==============
 
-AMReX provides FFT based Poisson solvers. :cpp:`FFT::Poisson` supports all
-periodic boundaries using purely FFT. :cpp:`FFT::PoissonHybrid` is a 3D only
-solver that supports periodic boundaries in the first two dimensions and
-Neumann boundary in the last dimension. Similar to :cpp:`FFT::R2C`, the
-Poisson solvers should be cached for reuse.
+AMReX provides FFT based Poisson solvers. :cpp:`FFT::Poisson` supports
+periodic (:cpp:`FFT::Boundary::periodic`), homogeneous Neumann
+(:cpp:`FFT::Boundary::even`), and homogeneous Dirichlet
+(:cpp:`FFT::Boundary::odd`) boundaries using FFT. Below is an example of
+using the solver.
+
+.. highlight:: c++
+
+::
+
+    Geometry geom(...);
+    MultiFab soln(...);
+    MultiFab rhs(...);
+
+    Array<std::pair<FFT::Boundary,FFT::Boundary>,AMREX_SPACEDIM>
+            fft_bc{...};
+
+    bool has_dirichlet = false;
+    for (int idim = 0; idim < AMREX_SPACEDIM; ++idim) {
+        has_dirichlet = has_dirichlet ||
+            fft_bc[idim].first == FFT::Boundary::odd ||
+            fft_bc[idim].second == FFT::Boundary::odd;
+    }
+    if (! has_dirichlet) {
+        // Shift rhs so that its sum is zero.
+        auto rhosum = rhs.sum(0);
+        rhs.plus(-rhosum/geom.Domain().d_numPts(), 0, 1);
+    }
+
+    FFT::Poisson fft_poisson(geom, fft_bc);
+    fft_poisson.solve(soln, rhs);
+
+:cpp:`FFT::PoissonHybrid` is a 3D only solver that supports periodic
+boundaries in the first two dimensions and Neumann boundary in the last
+dimension. The last dimension is solved with a tridiagonal solver that can
+support non-uniform cell size in the z-direction. For most applications,
+:cpp:`FFT::Poisson` should be used.
+
+Similar to :cpp:`FFT::R2C`, the Poisson solvers should be cached for reuse,
+and one might need to use :cpp:`std::unique_ptr<FFT::Poisson<MultiFab>>`
+because there is no default constructor.

Src/Base/AMReX_GpuDevice.cpp

@@ -35,6 +35,13 @@
 #include <roctracer/roctx.h>
 #endif
 #endif
+#if defined(AMREX_USE_FFT)
+#  if __has_include(<rocfft/rocfft.h>)  // ROCm 5.3+
+#    include <rocfft/rocfft.h>
+#  else
+#    include <rocfft.h>
+#  endif
+#endif
 #endif
 
 #ifdef AMREX_USE_ACC
@@ -310,6 +317,10 @@ Device::Initialize ()
     }
 #endif /* AMREX_USE_MPI */
 
+#if defined(AMREX_USE_HIP) && defined(AMREX_USE_FFT)
+    AMREX_ROCFFT_SAFE_CALL(rocfft_setup());
+#endif
+
     if (amrex::Verbose()) {
 #if defined(AMREX_USE_CUDA)
         amrex::Print() << "CUDA"
@@ -349,6 +360,10 @@ Device::Finalize ()
 #ifdef AMREX_USE_GPU
     Device::profilerStop();
 
+#if defined(AMREX_USE_HIP) && defined(AMREX_USE_FFT)
+    AMREX_ROCFFT_SAFE_CALL(rocfft_cleanup());
+#endif
+
 #ifdef AMREX_USE_SYCL
     for (auto& s : gpu_stream_pool) {
         delete s.queue;