/dports/science/libgeodecomp/libgeodecomp-0.4.0/lib/libflatarray/examples/lbm/ |
H A D | util.h | 70 dim3 dimBlock; in exec() local 72 gen_dims(&dimBlock, &dimGrid, dim); in exec() 74 return cudaExec(dim, dimBlock, dimGrid, repeats); in exec() 79 dim3 dimBlock; in gridSize() local 81 gen_dims(&dimBlock, &dimGrid, dim); in gridSize() 83 return dimGrid.x * dimBlock.x * dimGrid.y * dimBlock.y * (256 - 4); in gridSize() 88 void gen_dims(dim3 *dimBlock, dim3 *dimGrid, int dim) in gen_dims() argument 95 *dimBlock = dim3(blockWidth, 2, 1); in gen_dims() 96 *dimGrid = dim3(dim / dimBlock->x, dim / dimBlock->y, 1); in gen_dims() 103 virtual long long cudaExec(int dim, dim3 dimBlock, dim3 dimGrid, int repeats) in cudaExec() argument [all …]
|
/dports/devel/libflatarray/libflatarray-0.3.0/examples/lbm/ |
H A D | util.h | 77 dim3 dimBlock; in exec() local 79 gen_dims(&dimBlock, &dimGrid, dim); in exec() 81 return cudaExec(dim, dimBlock, dimGrid, repeats); in exec() 86 dim3 dimBlock; in gridSize() local 88 gen_dims(&dimBlock, &dimGrid, dim); in gridSize() 90 return dimGrid.x * dimBlock.x * dimGrid.y * dimBlock.y * (256 - 4); in gridSize() 95 void gen_dims(dim3 *dimBlock, dim3 *dimGrid, int dim) in gen_dims() argument 102 *dimBlock = dim3(blockWidth, 2, 1); in gen_dims() 103 *dimGrid = dim3(dim / dimBlock->x, dim / dimBlock->y, 1); in gen_dims() 113 virtual long long cudaExec(int dim, dim3 dimBlock, dim3 dimGrid, int repeats) in cudaExec() argument [all …]
|
/dports/science/PETSc/petsc-3.14.1/src/benchmarks/streams/ |
H A D | CUDAVersion.cu | 447 if (N % dimBlock.x != 0) dimGrid.x+=1; in runStream() 450 set_array<<<dimGrid,dimBlock>>>(d_a, 2.f, N); in runStream() 451 set_array<<<dimGrid,dimBlock>>>(d_b, .5f, N); in runStream() 452 set_array<<<dimGrid,dimBlock>>>(d_c, .5f, N); in runStream() 559 set_array<<<dimGrid,dimBlock>>>(d_a, 2.f, N); in runStream() 560 set_array<<<dimGrid,dimBlock>>>(d_b, .5f, N); in runStream() 561 set_array<<<dimGrid,dimBlock>>>(d_c, .5f, N); in runStream() 573 set_array<<<dimGrid,dimBlock>>>(d_a, 2.f, N); in runStream() 574 set_array<<<dimGrid,dimBlock>>>(d_b, .5f, N); in runStream() 575 set_array<<<dimGrid,dimBlock>>>(d_c, .5f, N); in runStream() [all …]
|
/dports/science/qmcpack/qmcpack-3.11.0/src/QMCWaveFunctions/detail/CUDA/ |
H A D | delayed_update_helper.cu | 47 dim3 dimBlock(BS); in applyW_stageV_cuda() local 60 dim3 dimBlock(BS); in applyW_stageV_cuda() local 73 dim3 dimBlock(BS); in applyW_stageV_cuda() local 86 dim3 dimBlock(BS); in applyW_stageV_cuda() local 135 dim3 dimBlock(BS); in make_identity_matrix_cuda() local 145 dim3 dimBlock(BS); in make_identity_matrix_cuda() local 164 dim3 dimBlock(BS); in extract_matrix_diagonal_cuda() local 174 dim3 dimBlock(BS); in extract_matrix_diagonal_cuda() local 199 dim3 dimBlock(BS); in copy_matrix_cuda() local 211 dim3 dimBlock(BS); in copy_matrix_cuda() local [all …]
|
H A D | matrix_update_helper.cu | 88 dim3 dimBlock(COLBS); in copyAinvRow_saveGL_cuda() local 112 dim3 dimBlock(COLBS); in copyAinvRow_saveGL_cuda() local 136 dim3 dimBlock(COLBS); in copyAinvRow_saveGL_cuda() local 160 dim3 dimBlock(COLBS); in copyAinvRow_saveGL_cuda() local 216 dim3 dimBlock(COLBS); in calcGradients_cuda() local 233 dim3 dimBlock(COLBS); in calcGradients_cuda() local 250 dim3 dimBlock(COLBS); in calcGradients_cuda() local 267 dim3 dimBlock(COLBS); in calcGradients_cuda() local 384 dim3 dimBlock(COLBS); in add_delay_list_save_sigma_VGL_batched() local 413 dim3 dimBlock(COLBS); in add_delay_list_save_sigma_VGL_batched() local [all …]
|
/dports/misc/mxnet/incubator-mxnet-1.9.0/3rdparty/mshadow/mshadow/cuda/ |
H A D | tensor_gpu-inl.cuh | 74 if (dimBlock.x * dimBlock.y * dimBlock.z > static_cast<unsigned>(kMaxThreadsPerBlock) || in CheckLaunchParam() 80 << dimBlock.x << "," in CheckLaunchParam() 81 << dimBlock.y << "," in CheckLaunchParam() 82 << dimBlock.z << "]"; in CheckLaunchParam() 222 dim3 dimBlock(kBaseThreadNum); in MapReduceKeepDim1() local 249 dim3 dimBlock(kBaseThreadNum); in GetBatchedView() local 400 dim3 dimBlock(kBaseThreadNum); in Softmax() local 417 dim3 dimBlock(kBaseThreadNum); in SoftmaxGrad() local 437 dim3 dimBlock(kBaseThreadNum); in SmoothSoftmaxGrad() local 458 dim3 dimBlock(kBaseThreadNum); in SoftmaxGrad() local [all …]
|
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/3rdparty/mshadow/mshadow/cuda/ |
H A D | tensor_gpu-inl.cuh | 74 if (dimBlock.x * dimBlock.y * dimBlock.z > static_cast<unsigned>(kMaxThreadsPerBlock) || in CheckLaunchParam() 80 << dimBlock.x << "," in CheckLaunchParam() 81 << dimBlock.y << "," in CheckLaunchParam() 82 << dimBlock.z << "]"; in CheckLaunchParam() 222 dim3 dimBlock(kBaseThreadNum); in MapReduceKeepDim1() local 249 dim3 dimBlock(kBaseThreadNum); in GetBatchedView() local 400 dim3 dimBlock(kBaseThreadNum); in Softmax() local 417 dim3 dimBlock(kBaseThreadNum); in SoftmaxGrad() local 437 dim3 dimBlock(kBaseThreadNum); in SmoothSoftmaxGrad() local 458 dim3 dimBlock(kBaseThreadNum); in SoftmaxGrad() local [all …]
|
/dports/science/qmcpack/qmcpack-3.11.0/src/QMCWaveFunctions/detail/CUDA_legacy/ |
H A D | delayed_update.cu | 1281 dim3 dimBlock(BLOCKSIZE); in update_onemove() local 1315 dim3 dimBlock(BLOCKSIZE); in update_onemove() local 1354 dim3 dimBlock(BLOCKSIZE); in multi_row_copy() local 1590 dim3 dimBlock(4); in calc_gradlapl_and_collect() local 1605 dim3 dimBlock(4); in calc_gradlapl_and_collect() local 1632 dim3 dimBlock(3); in calc_gradient_delayed() local 1639 dim3 dimBlock(3); in calc_gradient_delayed() local 1897 dim3 dimBlock(4); in calc_gradlapl_and_collect() local 1920 dim3 dimBlock(4); in calc_gradlapl_and_collect() local 1940 dim3 dimBlock(3); in calc_gradient_delayed() local [all …]
|
H A D | determinant_update.cu | 1173 dim3 dimBlock(N); in determinant_ratios_cuda() local 1202 dim3 dimBlock(N); in determinant_ratios_cuda() local 1230 dim3 dimBlock(N); in determinant_ratios_cuda() local 1290 dim3 dimBlock(N); in determinant_ratios_cuda() local 1517 dim3 dimBlock(BS); in determinant_ratios_grad_lapl_cuda() local 1539 dim3 dimBlock(BS); in determinant_ratios_grad_lapl_cuda() local 1562 dim3 dimBlock(BS); in determinant_ratios_grad_lapl_cuda() local 1586 dim3 dimBlock(BS); in determinant_ratios_grad_lapl_cuda() local 1611 dim3 dimBlock(BS); in determinant_ratios_grad_lapl_cuda() local 1633 dim3 dimBlock(BS); in determinant_ratios_grad_lapl_cuda() local [all …]
|
H A D | BsplineJastrowCuda.cu | 221 dim3 dimBlock(BS); in two_body_sum() local 242 dim3 dimBlock(BS); in two_body_sum() local 343 dim3 dimBlock(BS); in two_body_ratio() local 364 dim3 dimBlock(128); in two_body_ratio() local 501 dim3 dimBlock(BS); in two_body_ratio_grad() local 524 dim3 dimBlock(BS); in two_body_ratio_grad() local 705 dim3 dimBlock(BS); in two_body_NLratios() local 729 dim3 dimBlock(BS); in two_body_NLratios() local 842 dim3 dimBlock(BS); in two_body_grad_lapl() local 872 dim3 dimBlock(BS); in two_body_grad_lapl() local [all …]
|
H A D | BsplineJastrowCudaPBC.cu | 680 dim3 dimBlock(BS); in two_body_sum_PBC() local 712 dim3 dimBlock(BS); in two_body_sum_PBC() local 832 dim3 dimBlock(BS); in two_body_ratio_PBC() local 1124 dim3 dimBlock(BS); in two_body_ratio_grad_PBC() local 1186 dim3 dimBlock(BS); in two_body_ratio_grad_PBC() local 1454 dim3 dimBlock(BS); in two_body_NLratios_PBC() local 1487 dim3 dimBlock(BS); in two_body_NLratios_PBC() local 1519 dim3 dimBlock(32); in two_body_update_PBC() local 1526 dim3 dimBlock(3); in two_body_update_PBC() local 2023 dim3 dimBlock(BS); in two_body_gradient_PBC() local [all …]
|
H A D | AtomicOrbitalCuda.cu | 183 dim3 dimBlock(BS); in MakeHybridJobList() local 364 dim3 dimBlock(BS); in evaluateHybridSplineReal() local 754 dim3 dimBlock(BS); in evaluateHybridSplineReal() local 1138 dim3 dimBlock(BS); in evaluateHybridSplineComplexToReal() local 1721 dim3 dimBlock(BS); in evaluateHybridSplineComplexToReal() local 2104 dim3 dimBlock(BS); in CalcYlmRealCuda() local 2134 dim3 dimBlock(BS); in CalcYlmComplexCuda() local 2626 dim3 dimBlock(BS); in evaluate3DSplineReal() local 2743 dim3 dimBlock(BS); in evaluate3DSplineReal() local 3057 dim3 dimBlock(BS); in evaluate3DSplineComplexToReal() local [all …]
|
H A D | PhaseFactors.cu | 496 dim3 dimBlock(BS); in apply_phase_factors() local 506 phase_factor_kernel<float,BS><<<dimGrid,dimBlock, 0, gpu::kernelStream>>> in apply_phase_factors() 520 dim3 dimBlock(BS); in apply_phase_factors() local 533 dim3 dimBlock(BS); in apply_phase_factors() local 561 dim3 dimBlock(BS); in apply_phase_factors() local 582 dim3 dimBlock(BS); in apply_phase_factors() local 596 dim3 dimBlock(BS); in apply_phase_factors() local 769 dim3 dimBlock(BS); in apply_phase_factors() local 788 dim3 dimBlock(BS); in apply_phase_factors() local 809 dim3 dimBlock(BS); in apply_phase_factors() local [all …]
|
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/src/operator/ |
H A D | pad.cu | 72 dim3 dimBlock(kBaseThreadNum); in image_pad_edge() local 114 dim3 dimBlock(kBaseThreadNum); in image_pad_edge_grad() local 162 dim3 dimBlock(kBaseThreadNum); in image_pad_constant() local 199 dim3 dimBlock(kBaseThreadNum); in image_pad_constant_grad() local 255 dim3 dimBlock(kBaseThreadNum); in image_pad_reflect() local 306 dim3 dimBlock(kBaseThreadNum); in image_pad_reflect_grad() local 365 dim3 dimBlock(kBaseThreadNum); in image_pad_edge() local 416 dim3 dimBlock(kBaseThreadNum); in image_pad_edge_grad() local 475 dim3 dimBlock(kBaseThreadNum); in image_pad_constant() local 517 dim3 dimBlock(kBaseThreadNum); in image_pad_constant_grad() local [all …]
|
/dports/misc/mxnet/incubator-mxnet-1.9.0/src/operator/ |
H A D | pad.cu | 72 dim3 dimBlock(kBaseThreadNum); in image_pad_edge() local 114 dim3 dimBlock(kBaseThreadNum); in image_pad_edge_grad() local 162 dim3 dimBlock(kBaseThreadNum); in image_pad_constant() local 199 dim3 dimBlock(kBaseThreadNum); in image_pad_constant_grad() local 255 dim3 dimBlock(kBaseThreadNum); in image_pad_reflect() local 306 dim3 dimBlock(kBaseThreadNum); in image_pad_reflect_grad() local 365 dim3 dimBlock(kBaseThreadNum); in image_pad_edge() local 416 dim3 dimBlock(kBaseThreadNum); in image_pad_edge_grad() local 475 dim3 dimBlock(kBaseThreadNum); in image_pad_constant() local 517 dim3 dimBlock(kBaseThreadNum); in image_pad_constant_grad() local [all …]
|
/dports/science/qmcpack/qmcpack-3.11.0/src/Particle/ |
H A D | accept_kernel.cu | 56 dim3 dimBlock(BS); in accept_move_GPU_cuda() local 58 …accept_kernel<float, BS><<<dimGrid, dimBlock, 0, gpu::kernelStream>>>(Rlist, new_pos, toAccept, ia… in accept_move_GPU_cuda() 66 dim3 dimBlock(BS); in accept_move_GPU_cuda() local 68 …accept_kernel<double, BS><<<dimGrid, dimBlock, 0, gpu::kernelStream>>>(Rlist, new_pos, toAccept, i… in accept_move_GPU_cuda() 97 dim3 dimBlock(BS); in NL_move_cuda() local 99 NL_move_kernel<float, BS><<<dimGrid, dimBlock>>>(Rlist, new_pos, N); in NL_move_cuda() 106 dim3 dimBlock(BS); in NL_move_cuda() local 108 NL_move_kernel<double, BS><<<dimGrid, dimBlock>>>(Rlist, new_pos, N); in NL_move_cuda()
|
/dports/science/qmcpack/qmcpack-3.11.0/src/QMCHamiltonians/ |
H A D | CudaCoulomb.cu | 451 dim3 dimBlock(BS); in CoulombAA_SR_Sum() local 469 dim3 dimBlock(BS); in CoulombAA_SR_Sum() local 487 dim3 dimBlock(BS); in CoulombAA_SR_Sum() local 497 dim3 dimBlock(BS); in CoulombAA_Sum() local 506 dim3 dimBlock(BS); in CoulombAA_Sum() local 602 dim3 dimBlock(BS); in MPC_SR_Sum() local 611 dim3 dimBlock(BS); in MPC_SR_Sum() local 726 dim3 dimBlock(BS); in MPC_LR_Sum() local 735 dim3 dimBlock(BS); in MPC_LR_Sum() local 832 dim3 dimBlock(BS); in CoulombAB_SR_Sum() local [all …]
|
/dports/science/pcmsolver/pcmsolver-1.3.0/src/solver/ |
H A D | IEFSolver.cpp | 67 int dimBlock = cav.irreducible_size(); in buildAnisotropicMatrix() local 69 utils::symmetryPacking(blockTepsilon_, Tepsilon_, dimBlock, nrBlocks); in buildAnisotropicMatrix() 70 utils::symmetryPacking(blockRinfinity_, Rinfinity_, dimBlock, nrBlocks); in buildAnisotropicMatrix() 86 int dimBlock = cav.irreducible_size(); in buildIsotropicMatrix() local 88 utils::symmetryPacking(blockTepsilon_, Tepsilon_, dimBlock, nrBlocks); in buildIsotropicMatrix() 89 utils::symmetryPacking(blockRinfinity_, Rinfinity_, dimBlock, nrBlocks); in buildIsotropicMatrix()
|
/dports/science/pcmsolver/pcmsolver-1.3.0/src/bi_operators/ |
H A D | IBoundaryIntegralOperator.cpp | 59 int dimBlock = cav.irreducible_size(); in computeS() local 62 symmetryBlocking(biop, cavitySize, dimBlock, nrBlocks); in computeS() 78 int dimBlock = cav.irreducible_size(); in computeD() local 81 symmetryBlocking(biop, cavitySize, dimBlock, nrBlocks); in computeD()
|
/dports/science/qmcpack/qmcpack-3.11.0/src/einspline/ |
H A D | multi_bspline_cuda_c_impl.h | 77 dim3 dimBlock(SPLINE_BLOCK_SIZE); in eval_multi_multi_UBspline_1d_c_cuda() 158 dim3 dimBlock(SPLINE_BLOCK_SIZE); in eval_multi_multi_UBspline_1d_c_vgl_cuda() 629 dim3 dimBlock(threadsPerBlock); in eval_multi_multi_UBspline_3d_c_cuda() 630 dim3 dimGrid((2 * num_splines + dimBlock.x - 1) / dimBlock.x, num); in eval_multi_multi_UBspline_3d_c_cuda() 652 dim3 dimBlock(threadsPerBlock); in eval_multi_multi_UBspline_3d_c_cudasplit() 653 dim3 dimGrid((2 * num_splines + dimBlock.x - 1) / dimBlock.x, num); in eval_multi_multi_UBspline_3d_c_cudasplit() 666 dim3 dimGrid((2 * spline->num_splines + dimBlock.x - 1) / dimBlock.x, num); in eval_multi_multi_UBspline_3d_c_vgh_cuda() 689 dim3 dimBlock(threadsPerBlock); in eval_multi_multi_UBspline_3d_c_vgl_cuda() 690 dim3 dimGrid((2 * num_splines + dimBlock.x - 1) / dimBlock.x, num); in eval_multi_multi_UBspline_3d_c_vgl_cuda() 714 dim3 dimBlock(threadsPerBlock); in eval_multi_multi_UBspline_3d_c_vgl_cudasplit() [all …]
|
/dports/x11-toolkits/gtksourceview3/gtksourceview-3.24.11/tests/syntax-highlighting/ |
H A D | file.cu | 22 dim3 dimBlock(threads, 1, 1); in reduce() local 33 reduce0<T><<< dimGrid, dimBlock, smemSize >>>(d_idata, d_odata, size); in reduce() 37 reduce1<T><<< dimGrid, dimBlock, smemSize >>>(d_idata, d_odata, size); in reduce()
|
/dports/x11-toolkits/gtksourceview4/gtksourceview-4.8.1/tests/syntax-highlighting/ |
H A D | file.cu | 22 dim3 dimBlock(threads, 1, 1); in reduce() local 33 reduce0<T><<< dimGrid, dimBlock, smemSize >>>(d_idata, d_odata, size); in reduce() 37 reduce1<T><<< dimGrid, dimBlock, smemSize >>>(d_idata, d_odata, size); in reduce()
|
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/src/operator/contrib/ |
H A D | proposal.cu | 468 dim3 dimBlock(kMaxThreadsPerBlock); in Forward() local 470 ProposalGridKernel<<<dimGrid, dimBlock>>>( in Forward() 489 CheckLaunchParam(dimGrid, dimBlock, "BBoxPred"); in Forward() 491 IoUPredKernel<<<dimGrid, dimBlock>>>( in Forward() 496 BBoxPredKernel<<<dimGrid, dimBlock>>>( in Forward() 504 CheckLaunchParam(dimGrid, dimBlock, "FilterBox"); in Forward() 505 FilterBoxKernel<<<dimGrid, dimBlock>>>( in Forward() 517 CheckLaunchParam(dimGrid, dimBlock, "CopyScore"); in Forward() 518 CopyScoreKernel<<<dimGrid, dimBlock>>>( in Forward() 539 ReorderProposalsKernel<<<dimGrid, dimBlock>>>( in Forward() [all …]
|
H A D | multi_proposal.cu | 472 dim3 dimBlock(kMaxThreadsPerBlock); in Forward() local 474 ProposalGridKernel<<<dimGrid, dimBlock>>>( in Forward() 480 CheckLaunchParam(dimGrid, dimBlock, "BBoxPred"); in Forward() 482 IoUPredKernel<<<dimGrid, dimBlock>>>( in Forward() 486 BBoxPredKernel<<<dimGrid, dimBlock>>>( in Forward() 493 CheckLaunchParam(dimGrid, dimBlock, "FilterBox"); in Forward() 494 FilterBoxKernel<<<dimGrid, dimBlock>>>( in Forward() 501 dimBlock = dim3(kMaxThreadsPerBlock); in Forward() 520 CheckLaunchParam(dimGrid, dimBlock, "CopyScore"); in Forward() 521 CopyScoreKernel << <dimGrid, dimBlock >> >( in Forward() [all …]
|
/dports/misc/mxnet/incubator-mxnet-1.9.0/src/operator/contrib/ |
H A D | proposal.cu | 468 dim3 dimBlock(kMaxThreadsPerBlock); in Forward() local 470 ProposalGridKernel<<<dimGrid, dimBlock>>>( in Forward() 489 CheckLaunchParam(dimGrid, dimBlock, "BBoxPred"); in Forward() 491 IoUPredKernel<<<dimGrid, dimBlock>>>( in Forward() 496 BBoxPredKernel<<<dimGrid, dimBlock>>>( in Forward() 504 CheckLaunchParam(dimGrid, dimBlock, "FilterBox"); in Forward() 505 FilterBoxKernel<<<dimGrid, dimBlock>>>( in Forward() 517 CheckLaunchParam(dimGrid, dimBlock, "CopyScore"); in Forward() 518 CopyScoreKernel<<<dimGrid, dimBlock>>>( in Forward() 539 ReorderProposalsKernel<<<dimGrid, dimBlock>>>( in Forward() [all …]
|