Loading include/dca/config/cmake_options.hpp +2 −2 Original line number Diff line number Diff line Loading @@ -50,7 +50,7 @@ struct CMakeOptions { static void print(); }; } // config } // dca } // namespace config } // namespace dca #endif // DCA_CONFIG_CMAKE_OPTIONS_HPP include/dca/linalg/vector.hpp +2 −2 Original line number Diff line number Diff line Loading @@ -406,7 +406,7 @@ std::size_t Vector<ScalarType, device_name, Allocator>::deviceFingerprint() cons return device_name == GPU ? capacity_ * sizeof(ScalarType) : 0; } } // linalg } // dca } // namespace linalg } // namespace dca #endif // DCA_LINALG_VECTOR_HPP include/dca/math/function_transform/special_transforms/space_transform_2D_gpu.hpp +4 −5 Original line number Diff line number Diff line Loading @@ -145,8 +145,7 @@ void SpaceTransform2DGpu<RDmn, KDmn, Real>::execute(RMatrix& M) { } template <class RDmn, class KDmn, typename Real> void SpaceTransform2DGpu<RDmn, KDmn, Real>::phaseFactorsAndRearrange(const RMatrix& in, RMatrix& out) { void SpaceTransform2DGpu<RDmn, KDmn, Real>::phaseFactorsAndRearrange(const RMatrix& in, RMatrix& out) { out.resizeNoCopy(in.size()); const Complex* const phase_factors_ptr = BaseClass::hasPhaseFactors() ? getPhaseFactors().ptr() : nullptr; Loading Loading @@ -181,8 +180,8 @@ const auto& SpaceTransform2DGpu<RDmn, KDmn, Real>::getPhaseFactors() { return phase_factors_dev; } } // transform } // math } // dca } // namespace transform } // namespace math } // namespace dca #endif // DCA_MATH_FUNCTION_TRANSFORM_SPECIAL_TRANSFORMS_SPACE_TRANSFORM_2D_GPU include/dca/phys/dca_step/cluster_solver/shared_tools/accumulation/tp/g4_helper.cuh +8 −8 Original line number Diff line number Diff line Loading @@ -26,8 +26,8 @@ namespace details { class G4Helper { public: static void set(int nb, int nk, int nw_pos, const std::vector<int>& k_ex_indices, const std::vector<int>& w_ex_indices, const int* add_k, int lda, const int* sub_k, int lds, int k0); const std::vector<int>& w_ex_indices, const int* add_k, int lda, const int* sub_k, int lds, int k0); // Returns the index of k + k_ex. __device__ inline int addKex(int k_idx, int k_ex_idx) const; Loading Loading @@ -122,10 +122,10 @@ inline __device__ int G4Helper::g4Index(int k1, int k2, int k_ex, int w1, int w2 sbdm_steps_[8] * w2 + sbdm_steps_[9] * w_ex; } } // details } // accumulator } // solver } // phys } // dca } // namespace details } // namespace accumulator } // namespace solver } // namespace phys } // namespace dca #endif // DCA_INCLUDE_DCA_PHYS_DCA_STEP_CLUSTER_SOLVER_SHARED_TOOLS_ACCUMULATION_TP_G4_HELPER_CUH include/dca/phys/dca_step/cluster_solver/shared_tools/accumulation/tp/kernels_interface.hpp +7 −8 Original line number Diff line number Diff line Loading @@ -38,11 +38,10 @@ void updateG4(std::complex<Real> *G4, const std::complex<Real> *G_up, const int const int nw_pos, const int nw_exchange, const int nk_exchange, const int sign, bool atomic, cudaStream_t stream); } // details } // accumulator } // solver } // phys } // dca } // namespace details } // namespace accumulator } // namespace solver } // namespace phys } // namespace dca #endif // DCA_INCLUDE_DCA_PHYS_DCA_STEP_CLUSTER_SOLVER_SHARED_TOOLS_ACCUMULATION_TP_KERNELS_INTERFACE_HPP Loading
include/dca/config/cmake_options.hpp +2 −2 Original line number Diff line number Diff line Loading @@ -50,7 +50,7 @@ struct CMakeOptions { static void print(); }; } // config } // dca } // namespace config } // namespace dca #endif // DCA_CONFIG_CMAKE_OPTIONS_HPP
include/dca/linalg/vector.hpp +2 −2 Original line number Diff line number Diff line Loading @@ -406,7 +406,7 @@ std::size_t Vector<ScalarType, device_name, Allocator>::deviceFingerprint() cons return device_name == GPU ? capacity_ * sizeof(ScalarType) : 0; } } // linalg } // dca } // namespace linalg } // namespace dca #endif // DCA_LINALG_VECTOR_HPP
include/dca/math/function_transform/special_transforms/space_transform_2D_gpu.hpp +4 −5 Original line number Diff line number Diff line Loading @@ -145,8 +145,7 @@ void SpaceTransform2DGpu<RDmn, KDmn, Real>::execute(RMatrix& M) { } template <class RDmn, class KDmn, typename Real> void SpaceTransform2DGpu<RDmn, KDmn, Real>::phaseFactorsAndRearrange(const RMatrix& in, RMatrix& out) { void SpaceTransform2DGpu<RDmn, KDmn, Real>::phaseFactorsAndRearrange(const RMatrix& in, RMatrix& out) { out.resizeNoCopy(in.size()); const Complex* const phase_factors_ptr = BaseClass::hasPhaseFactors() ? getPhaseFactors().ptr() : nullptr; Loading Loading @@ -181,8 +180,8 @@ const auto& SpaceTransform2DGpu<RDmn, KDmn, Real>::getPhaseFactors() { return phase_factors_dev; } } // transform } // math } // dca } // namespace transform } // namespace math } // namespace dca #endif // DCA_MATH_FUNCTION_TRANSFORM_SPECIAL_TRANSFORMS_SPACE_TRANSFORM_2D_GPU
include/dca/phys/dca_step/cluster_solver/shared_tools/accumulation/tp/g4_helper.cuh +8 −8 Original line number Diff line number Diff line Loading @@ -26,8 +26,8 @@ namespace details { class G4Helper { public: static void set(int nb, int nk, int nw_pos, const std::vector<int>& k_ex_indices, const std::vector<int>& w_ex_indices, const int* add_k, int lda, const int* sub_k, int lds, int k0); const std::vector<int>& w_ex_indices, const int* add_k, int lda, const int* sub_k, int lds, int k0); // Returns the index of k + k_ex. __device__ inline int addKex(int k_idx, int k_ex_idx) const; Loading Loading @@ -122,10 +122,10 @@ inline __device__ int G4Helper::g4Index(int k1, int k2, int k_ex, int w1, int w2 sbdm_steps_[8] * w2 + sbdm_steps_[9] * w_ex; } } // details } // accumulator } // solver } // phys } // dca } // namespace details } // namespace accumulator } // namespace solver } // namespace phys } // namespace dca #endif // DCA_INCLUDE_DCA_PHYS_DCA_STEP_CLUSTER_SOLVER_SHARED_TOOLS_ACCUMULATION_TP_G4_HELPER_CUH
include/dca/phys/dca_step/cluster_solver/shared_tools/accumulation/tp/kernels_interface.hpp +7 −8 Original line number Diff line number Diff line Loading @@ -38,11 +38,10 @@ void updateG4(std::complex<Real> *G4, const std::complex<Real> *G_up, const int const int nw_pos, const int nw_exchange, const int nk_exchange, const int sign, bool atomic, cudaStream_t stream); } // details } // accumulator } // solver } // phys } // dca } // namespace details } // namespace accumulator } // namespace solver } // namespace phys } // namespace dca #endif // DCA_INCLUDE_DCA_PHYS_DCA_STEP_CLUSTER_SOLVER_SHARED_TOOLS_ACCUMULATION_TP_KERNELS_INTERFACE_HPP