| ► include | |
| ► kernels | |
| blas_core.cuh | |
| block_orthogonalize.cuh | |
| clover_deriv.cuh | |
| clover_invert.cuh | |
| clover_sigma_outer_product.cuh | |
| coarse_op_kernel.cuh | |
| coarse_op_preconditioned.cuh | |
| color_spinor_pack.cuh | |
| contraction.cuh | |
| copy_gauge.cuh | |
| covDev.cuh | |
| dslash_coarse.cuh | |
| dslash_domain_wall_4d.cuh | |
| dslash_domain_wall_5d.cuh | |
| dslash_domain_wall_m5.cuh | |
| dslash_ndeg_twisted_mass.cuh | |
| dslash_ndeg_twisted_mass_preconditioned.cuh | |
| dslash_pack.cuh | |
| dslash_staggered.cuh | |
| dslash_twisted_clover_preconditioned.cuh | |
| dslash_twisted_mass.cuh | |
| dslash_twisted_mass_preconditioned.cuh | |
| dslash_wilson.cuh | |
| dslash_wilson_clover.cuh | |
| dslash_wilson_clover_preconditioned.cuh | |
| field_strength_tensor.cuh | |
| gauge_ape.cuh | |
| gauge_plaq.cuh | |
| gauge_qcharge.cuh | |
| gauge_stout.cuh | |
| laplace.cuh | |
| multi_blas_core.cuh | |
| multi_reduce_core.cuh | |
| reduce_core.cuh | |
| restrictor.cuh | |
| atomic.cuh | |
| blas_cublas.h | |
| blas_helper.cuh | |
| blas_magma.h | |
| blas_quda.h | |
| clover_field.h | |
| clover_field_order.h | Main header file for host and device accessors to CloverFields |
| color_spinor.h | |
| color_spinor_field.h | |
| color_spinor_field_order.h | |
| comm_quda.h | |
| complex_quda.h | |
| contract_quda.h | |
| convert.h | |
| cub_helper.cuh | |
| dbldbl.h | |
| deflation.h | |
| dirac_quda.h | |
| double_single.h | |
| dslash.h | |
| dslash_helper.cuh | |
| dslash_quda.h | |
| eigensolve_quda.h | |
| enum_quda.h | |
| enum_quda_fortran.h | |
| fast_intdiv.h | |
| float_vector.h | |
| gamma.cuh | |
| gauge_field.h | |
| gauge_field_order.h | Main header file for host and device accessors to GaugeFields |
| gauge_force_quda.h | |
| gauge_tools.h | |
| gauge_update_quda.h | |
| hw_quda.h | |
| index_helper.cuh | |
| inline_ptx.h | |
| invert_quda.h | |
| jitify_helper.cuh | Helper file when using jitify run-time compilation. This file should be included in source code, and not jitify.hpp directly |
| ks_force_quda.h | |
| ks_improved_force.h | |
| lattice_field.h | |
| launch_kernel.cuh | |
| layout_hyper.h | |
| linalg.cuh | |
| llfat_quda.h | |
| malloc_quda.h | |
| math_helper.cuh | Helper math routines used in QUDA |
| matrix_field.h | |
| momentum.h | |
| mpi_comm_handle.h | |
| multigrid.h | |
| multigrid_helper.cuh | |
| numa_affinity.h | |
| object.h | |
| pgauge_monte.h | |
| qio_field.h | |
| qio_util.h | |
| quda.h | Main header file for the QUDA library |
| quda_arpack_interface.h | |
| quda_constants.h | |
| quda_cuda_api.h | |
| quda_fortran.h | Fortran interface functions |
| quda_internal.h | |
| quda_matrix.h | |
| quda_milc_interface.h | |
| quda_new_interace.h | |
| random_quda.h | |
| register_traits.h | Provides precision abstractions and defines the register precision given the storage precision using C++ traits |
| shared_memory_cache_helper.cuh | |
| staggered_oprod.h | |
| su3_project.cuh | |
| texture.h | |
| texture_helper.cuh | |
| thrust_helper.cuh | |
| timer.h | |
| transfer.h | |
| trove_helper.cuh | |
| tune_key.h | |
| tune_quda.h | |
| uint_to_char.h | |
| unitarization_links.h | |
| util_quda.h | |
| worker.h | |
| ► lib | |
| ► generate | |
| wrap.py | |
| blas_cublas.cu | |
| blas_magma.cu | |
| blas_magma_nopiv.cu | |
| blas_quda.cu | |
| block_orthogonalize.cu | |
| check_params.h | |
| checksum.cu | |
| clover_deriv_quda.cu | This kernel has been a bit of a pain to optimize since it is excessively register bound. To reduce register pressure we use shared memory to help offload some of this pressure. Annoyingly, the optimal approach for CUDA 8.0 is not the same as CUDA 7.5, so implementation is compiler version dependent. The CUDA 8.0 optimal code runs 10x slower on 7.5, though the 7.5 code runs fine on 8.0 |
| clover_field.cpp | |
| clover_invert.cu | |
| clover_outer_product.cu | |
| clover_quda.cu | |
| clover_sigma_outer_product.cu | |
| clover_trace_quda.cu | |
| coarse_op.cu | |
| coarse_op.cuh | |
| coarse_op_preconditioned.cu | |
| coarsecoarse_op.cu | |
| color_spinor_field.cpp | |
| color_spinor_pack.cu | This is the implementation of the color-spinor halo packer for an arbitrary field. This implementation uses the fine-grained accessors and should support all field types reqgardless of precision, number of color or spins etc |
| color_spinor_util.cu | |
| color_spinor_wuppertal.cu | |
| comm_common.cpp | |
| comm_mpi.cpp | |
| comm_qmp.cpp | |
| comm_single.cpp | |
| contract.cu | |
| copy_clover.cu | |
| copy_color_spinor.cu | |
| copy_color_spinor.cuh | |
| copy_color_spinor_dd.cu | |
| copy_color_spinor_dh.cu | |
| copy_color_spinor_dq.cu | |
| copy_color_spinor_ds.cu | |
| copy_color_spinor_hd.cu | |
| copy_color_spinor_hh.cu | |
| copy_color_spinor_hq.cu | |
| copy_color_spinor_hs.cu | |
| copy_color_spinor_mg.cuh | |
| copy_color_spinor_mg_dd.cu | |
| copy_color_spinor_mg_ds.cu | |
| copy_color_spinor_mg_hh.cu | |
| copy_color_spinor_mg_hq.cu | |
| copy_color_spinor_mg_hs.cu | |
| copy_color_spinor_mg_qh.cu | |
| copy_color_spinor_mg_qq.cu | |
| copy_color_spinor_mg_qs.cu | |
| copy_color_spinor_mg_sd.cu | |
| copy_color_spinor_mg_sh.cu | |
| copy_color_spinor_mg_sq.cu | |
| copy_color_spinor_mg_ss.cu | |
| copy_color_spinor_qd.cu | |
| copy_color_spinor_qh.cu | |
| copy_color_spinor_qq.cu | |
| copy_color_spinor_qs.cu | |
| copy_color_spinor_sd.cu | |
| copy_color_spinor_sh.cu | |
| copy_color_spinor_sq.cu | |
| copy_color_spinor_ss.cu | |
| copy_gauge.cu | |
| copy_gauge_double.cu | |
| copy_gauge_extended.cu | |
| copy_gauge_half.cu | |
| copy_gauge_helper.cuh | |
| copy_gauge_inc.cu | |
| copy_gauge_mg.cu | |
| copy_gauge_quarter.cu | |
| copy_gauge_single.cu | |
| copy_quda.cu | |
| covDev.cu | |
| cpu_color_spinor_field.cpp | |
| cpu_gauge_field.cpp | |
| cuda_color_spinor_field.cpp | |
| cuda_gauge_field.cpp | |
| CUFFT_Plans.h | |
| deflation.cpp | |
| dirac.cpp | |
| dirac_clover.cpp | |
| dirac_coarse.cpp | |
| dirac_domain_wall.cpp | |
| dirac_domain_wall_4d.cpp | |
| dirac_improved_staggered.cpp | |
| dirac_mobius.cpp | |
| dirac_staggered.cpp | |
| dirac_twisted_clover.cpp | |
| dirac_twisted_mass.cpp | |
| dirac_wilson.cpp | |
| dslash5_domain_wall.cu | |
| dslash_coarse.cu | |
| dslash_constants.h | |
| dslash_domain_wall_4d.cu | |
| dslash_domain_wall_5d.cu | |
| dslash_improved_staggered.cu | |
| dslash_index.cuh | |
| dslash_ndeg_twisted_mass.cu | |
| dslash_ndeg_twisted_mass_preconditioned.cu | |
| dslash_pack2.cu | |
| dslash_policy.cuh | |
| dslash_quda.cu | |
| dslash_quda.cuh | |
| dslash_staggered.cu | |
| dslash_twisted_clover.cu | |
| dslash_twisted_clover_preconditioned.cu | |
| dslash_twisted_mass.cu | |
| dslash_twisted_mass_preconditioned.cu | |
| dslash_wilson.cu | |
| dslash_wilson_clover.cu | |
| dslash_wilson_clover_preconditioned.cu | |
| eigensolve_quda.cpp | |
| extended_color_spinor_utilities.cu | |
| extract_gauge_ghost.cu | |
| extract_gauge_ghost_extended.cu | |
| extract_gauge_ghost_helper.cuh | |
| extract_gauge_ghost_mg.cu | |
| gauge_ape.cu | |
| gauge_covdev.cpp | |
| gauge_field.cpp | |
| gauge_field_strength_tensor.cu | |
| gauge_fix_fft.cu | |
| gauge_fix_ovr.cu | |
| gauge_fix_ovr_extra.cu | |
| gauge_fix_ovr_extra.h | |
| gauge_fix_ovr_hit_devf.cuh | |
| gauge_force.cu | |
| gauge_laplace.cpp | |
| gauge_phase.cu | |
| gauge_plaq.cu | |
| gauge_qcharge.cu | |
| gauge_random.cu | |
| gauge_stout.cu | |
| gauge_update_quda.cu | |
| generic_blas.cuh | |
| generic_reduce.cuh | |
| hisq_paths_force_quda.cu | |
| interface_quda.cpp | |
| inv_bicgstab_quda.cpp | |
| inv_bicgstabl_quda.cpp | |
| inv_ca_cg.cpp | |
| inv_ca_gcr.cpp | |
| inv_cg3_quda.cpp | |
| inv_cg3ne_quda.cpp | |
| inv_cg_quda.cpp | |
| inv_eigcg_quda.cpp | |
| inv_gcr_quda.cpp | |
| inv_gmresdr_quda.cpp | |
| inv_mpbicgstab_quda.cpp | |
| inv_mpcg_quda.cpp | |
| inv_mr_quda.cpp | |
| inv_mre.cpp | |
| inv_msrc_cg_quda.cpp | |
| inv_multi_cg_quda.cpp | |
| inv_pcg_quda.cpp | |
| inv_sbicgstab_quda.cpp | |
| inv_sd_quda.cpp | |
| inv_xsd_quda.cpp | |
| ks_force_quda.cu | |
| laplace.cu | |
| lattice_field.cpp | |
| layout_hyper.c | |
| llfat_quda.cu | |
| malloc.cpp | |
| max_clover.cu | |
| max_gauge.cu | |
| milc_interface.cpp | |
| momentum.cu | |
| multi_blas_quda.cu | |
| multi_reduce_quda.cu | |
| multigrid.cpp | |
| numa_affinity.cpp | |
| nvtx_pmpi.c | |
| pgauge_det_trace.cu | |
| pgauge_exchange.cu | |
| pgauge_heatbath.cu | |
| pgauge_init.cu | |
| prolongator.cu | |
| qio_field.cpp | |
| qio_util.cpp | |
| quda_arpack_interface.cpp | |
| quda_cuda_api.cpp | |
| random.cu | |
| reduce_quda.cu | |
| restrictor.cu | |
| shift_quark_field.cu | |
| solver.cpp | |
| spinor_noise.cu | |
| staggered_oprod.cu | |
| svd_quda.h | |
| timer.cpp | |
| transfer.cpp | |
| tune.cpp | |
| unitarize_force_quda.cu | |
| unitarize_links_quda.cu | |
| util_quda.cpp | |
| version.cpp | |
| ► tests | |
| blas_reference.cpp | |
| blas_reference.h | |
| blas_test.cu | |
| clover_reference.cpp | |
| contract_reference.h | |
| contract_test.cpp | |
| covdev_reference.cpp | |
| covdev_reference.h | |
| covdev_test.cpp | |
| deflated_invert_test.cpp | |
| domain_wall_dslash_reference.cpp | |
| domain_wall_dslash_reference.h | |
| dslash_ctest.cpp | |
| dslash_test.cpp | |
| dslash_util.h | |
| eigensolve_test.cpp | |
| face_gauge.cpp | |
| gauge_alg_test.cpp | |
| gauge_force_reference.cpp | |
| gauge_force_reference.h | |
| gauge_force_test.cpp | |
| heatbath_test.cpp | |
| hisq_force_reference.cpp | |
| hisq_force_reference.h | |
| hisq_force_reference2.cpp | |
| hisq_paths_force_test.cpp | |
| hisq_stencil_test.cpp | |
| hisq_unitarize_force_test.cpp | |
| invert_test.cpp | |
| invertmsrc_test.cpp | |
| llfat_reference.cpp | |
| llfat_reference.h | |
| llfat_test.cpp | |
| misc.cpp | |
| misc.h | |
| multigrid_benchmark_test.cu | |
| multigrid_evolve_test.cpp | |
| multigrid_invert_test.cpp | |
| new_half.cu | |
| pack_test.cpp | |
| plaq_test.cpp | |
| short.h | |
| staggered_dslash_ctest.cpp | |
| staggered_dslash_reference.cpp | |
| staggered_dslash_reference.h | |
| staggered_dslash_test.cpp | |
| staggered_eigensolve_test.cpp | |
| staggered_gauge_utils.cpp | |
| staggered_gauge_utils.h | |
| staggered_invert_test.cpp | |
| staggered_invertmsrc_test.cpp | |
| su3_test.cpp | |
| test_util.cpp | |
| test_util.h | |
| unitarize_link_test.cpp | |
| wilson_dslash_reference.cpp | |
| wilson_dslash_reference.h | |
| .cmake-format.py | |
1.8.13
