nvmath-python 0.9.0__cp314-cp314-win_amd64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- nvmath/__init__.pxd +0 -0
- nvmath/__init__.py +45 -0
- nvmath/_internal/__init__.py +0 -0
- nvmath/_internal/attribute_ifc_factory.py +330 -0
- nvmath/_internal/layout.py +70 -0
- nvmath/_internal/templates.py +383 -0
- nvmath/_utils.py +150 -0
- nvmath/bindings/__init__.py +51 -0
- nvmath/bindings/_internal/__init__.pxd +0 -0
- nvmath/bindings/_internal/__init__.py +0 -0
- nvmath/bindings/_internal/cublas.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/cublas.pxd +530 -0
- nvmath/bindings/_internal/cublasLt.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/cublasLt.pxd +59 -0
- nvmath/bindings/_internal/cublasMp.pxd +52 -0
- nvmath/bindings/_internal/cudss.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/cudss.pxd +47 -0
- nvmath/bindings/_internal/cufft.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/cufft.pxd +70 -0
- nvmath/bindings/_internal/cufftMp.pxd +77 -0
- nvmath/bindings/_internal/curand.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/curand.pxd +42 -0
- nvmath/bindings/_internal/cusolver.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/cusolver.pxd +15 -0
- nvmath/bindings/_internal/cusolverDn.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/cusolverDn.pxd +406 -0
- nvmath/bindings/_internal/cusparse.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/cusparse.pxd +277 -0
- nvmath/bindings/_internal/cusparseLt.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/cusparseLt.pxd +48 -0
- nvmath/bindings/_internal/cutensor.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/cutensor.pxd +58 -0
- nvmath/bindings/_internal/mathdx.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/mathdx.pxd +116 -0
- nvmath/bindings/_internal/nvshmem.pxd +29 -0
- nvmath/bindings/_internal/utils.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/_internal/utils.pxd +179 -0
- nvmath/bindings/_internal/utils.pyi +10 -0
- nvmath/bindings/cublas.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cublas.pxd +558 -0
- nvmath/bindings/cublas.pyi +746 -0
- nvmath/bindings/cublasLt.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cublasLt.pxd +109 -0
- nvmath/bindings/cublasLt.pyi +1337 -0
- nvmath/bindings/cublasMp.pxd +85 -0
- nvmath/bindings/cublasMp.pyi +219 -0
- nvmath/bindings/cudss.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cudss.pxd +86 -0
- nvmath/bindings/cudss.pyi +282 -0
- nvmath/bindings/cufft.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cufft.pxd +118 -0
- nvmath/bindings/cufft.pyi +241 -0
- nvmath/bindings/cufftMp.pxd +124 -0
- nvmath/bindings/cufftMp.pyi +260 -0
- nvmath/bindings/curand.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/curand.pxd +71 -0
- nvmath/bindings/curand.pyi +159 -0
- nvmath/bindings/cusolver.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cusolver.pxd +62 -0
- nvmath/bindings/cusolver.pyi +242 -0
- nvmath/bindings/cusolverDn.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cusolverDn.pxd +430 -0
- nvmath/bindings/cusolverDn.pyi +416 -0
- nvmath/bindings/cusparse.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cusparse.pxd +338 -0
- nvmath/bindings/cusparse.pyi +659 -0
- nvmath/bindings/cusparseLt.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cusparseLt.pxd +99 -0
- nvmath/bindings/cusparseLt.pyi +198 -0
- nvmath/bindings/cutensor.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cutensor.pxd +98 -0
- nvmath/bindings/cutensor.pyi +294 -0
- nvmath/bindings/cycublas.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycublas.pxd +684 -0
- nvmath/bindings/cycublasLt.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycublasLt.pxd +1055 -0
- nvmath/bindings/cycublasMp.pxd +183 -0
- nvmath/bindings/cycudss.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycudss.pxd +224 -0
- nvmath/bindings/cycufft.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycufft.pxd +326 -0
- nvmath/bindings/cycufftMp.pxd +334 -0
- nvmath/bindings/cycurand.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycurand.pxd +146 -0
- nvmath/bindings/cycusolver.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycusolver.pxd +154 -0
- nvmath/bindings/cycusolverDn.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycusolverDn.pxd +446 -0
- nvmath/bindings/cycusparse.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycusparse.pxd +470 -0
- nvmath/bindings/cycusparseLt.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycusparseLt.pxd +150 -0
- nvmath/bindings/cycutensor.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cycutensor.pxd +192 -0
- nvmath/bindings/cymathdx.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/cymathdx.pxd +552 -0
- nvmath/bindings/cynvshmem.pxd +126 -0
- nvmath/bindings/mathdx.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/mathdx.pxd +182 -0
- nvmath/bindings/mathdx.pyi +1244 -0
- nvmath/bindings/nvpl/__init__.pxd +0 -0
- nvmath/bindings/nvpl/__init__.py +13 -0
- nvmath/bindings/nvpl/_internal/__init__.pxd +0 -0
- nvmath/bindings/nvpl/_internal/__init__.py +0 -0
- nvmath/bindings/nvpl/_internal/blas.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/nvpl/_internal/blas.pxd +125 -0
- nvmath/bindings/nvpl/_internal/fft.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/nvpl/_internal/fft.pxd +36 -0
- nvmath/bindings/nvpl/blas.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/nvpl/blas.pxd +85 -0
- nvmath/bindings/nvpl/blas.pyi +122 -0
- nvmath/bindings/nvpl/cyblas.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/nvpl/cyblas.pxd +166 -0
- nvmath/bindings/nvpl/cyfft.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/nvpl/cyfft.pxd +92 -0
- nvmath/bindings/nvpl/fft.cp314-win_amd64.pyd +0 -0
- nvmath/bindings/nvpl/fft.pxd +100 -0
- nvmath/bindings/nvpl/fft.pyi +100 -0
- nvmath/bindings/nvshmem.pxd +54 -0
- nvmath/bindings/nvshmem.pyi +179 -0
- nvmath/device/__init__.py +21 -0
- nvmath/device/_deprecated.py +33 -0
- nvmath/device/common.py +313 -0
- nvmath/device/common_backend.py +131 -0
- nvmath/device/common_cuda.py +201 -0
- nvmath/device/common_numba.py +310 -0
- nvmath/device/common_opaque_tensor.py +201 -0
- nvmath/device/cublasdx.py +1805 -0
- nvmath/device/cublasdx_backend.py +807 -0
- nvmath/device/cublasdx_numba.py +1612 -0
- nvmath/device/cufftdx.py +510 -0
- nvmath/device/cufftdx_backend.py +196 -0
- nvmath/device/cufftdx_numba.py +196 -0
- nvmath/device/curand_kernel.py +9147 -0
- nvmath/device/cusolverdx.py +2690 -0
- nvmath/device/cusolverdx_backend.py +440 -0
- nvmath/device/cusolverdx_numba.py +1624 -0
- nvmath/device/llvm_array.py +29 -0
- nvmath/device/random.py +445 -0
- nvmath/device/random_helpers.py +23 -0
- nvmath/device/random_states.py +187 -0
- nvmath/device/types.py +147 -0
- nvmath/device/vector_types_numba.py +203 -0
- nvmath/distributed/__init__.py +205 -0
- nvmath/distributed/_internal/__init__.py +0 -0
- nvmath/distributed/_internal/nvshmem.py +302 -0
- nvmath/distributed/_internal/tensor_ifc.py +67 -0
- nvmath/distributed/_internal/tensor_ifc_cupy.py +62 -0
- nvmath/distributed/_internal/tensor_ifc_host_device.py +165 -0
- nvmath/distributed/_internal/tensor_ifc_numpy.py +41 -0
- nvmath/distributed/_internal/tensor_ifc_torch.py +141 -0
- nvmath/distributed/_internal/tensor_wrapper.py +78 -0
- nvmath/distributed/_utils.py +167 -0
- nvmath/distributed/distribution.py +770 -0
- nvmath/distributed/fft/__init__.py +7 -0
- nvmath/distributed/fft/_configuration.py +79 -0
- nvmath/distributed/fft/fft.py +2801 -0
- nvmath/distributed/linalg/__init__.py +12 -0
- nvmath/distributed/linalg/_internal/__init__.py +3 -0
- nvmath/distributed/linalg/_internal/epilog_protocol.py +496 -0
- nvmath/distributed/linalg/_internal/matmul_desc_ifc.py +28 -0
- nvmath/distributed/linalg/advanced/__init__.py +8 -0
- nvmath/distributed/linalg/advanced/_configuration.py +166 -0
- nvmath/distributed/linalg/advanced/matmulmod.py +2908 -0
- nvmath/distributed/process_group.py +408 -0
- nvmath/distributed/reshape/__init__.py +6 -0
- nvmath/distributed/reshape/_configuration.py +39 -0
- nvmath/distributed/reshape/reshape.py +1256 -0
- nvmath/fft/__init__.py +7 -0
- nvmath/fft/_configuration.py +208 -0
- nvmath/fft/_exec_utils.py +109 -0
- nvmath/fft/_helpers.py +237 -0
- nvmath/fft/fft.py +2903 -0
- nvmath/internal/__init__.pxd +3 -0
- nvmath/internal/__init__.py +10 -0
- nvmath/internal/_bindings.cp314-win_amd64.pyd +0 -0
- nvmath/internal/_bindings.pxd +12 -0
- nvmath/internal/_device_utils.py +54 -0
- nvmath/internal/enum_utils.py +142 -0
- nvmath/internal/formatters.py +87 -0
- nvmath/internal/mem_limit.py +51 -0
- nvmath/internal/memory.cp314-win_amd64.pyd +0 -0
- nvmath/internal/memory.pxd +10 -0
- nvmath/internal/memory.pyi +46 -0
- nvmath/internal/ndbuffer/__init__.pxd +3 -0
- nvmath/internal/ndbuffer/__init__.py +7 -0
- nvmath/internal/ndbuffer/copy_kernel/args.h +34 -0
- nvmath/internal/ndbuffer/copy_kernel/copy_kernel_impl/array_view.h +52 -0
- nvmath/internal/ndbuffer/copy_kernel/copy_kernel_impl/elementwise.h +68 -0
- nvmath/internal/ndbuffer/copy_kernel/copy_kernel_impl/grid_indexer.h +69 -0
- nvmath/internal/ndbuffer/copy_kernel/copy_kernel_impl/transposed.h +240 -0
- nvmath/internal/ndbuffer/copy_kernel/copy_kernel_impl/type_utils.h +39 -0
- nvmath/internal/ndbuffer/copy_kernel/copy_kernel_impl/utils.h +132 -0
- nvmath/internal/ndbuffer/copy_kernel/copy_kernel_impl/vec.h +159 -0
- nvmath/internal/ndbuffer/copy_kernel/elementwise.h +53 -0
- nvmath/internal/ndbuffer/copy_kernel/transposed.h +58 -0
- nvmath/internal/ndbuffer/copy_kernel.cp314-win_amd64.pyd +0 -0
- nvmath/internal/ndbuffer/copy_kernel.pxd +9 -0
- nvmath/internal/ndbuffer/copy_kernel.pyi +9 -0
- nvmath/internal/ndbuffer/data_layout.cp314-win_amd64.pyd +0 -0
- nvmath/internal/ndbuffer/data_layout.pxd +72 -0
- nvmath/internal/ndbuffer/data_layout.pyi +23 -0
- nvmath/internal/ndbuffer/jit.cp314-win_amd64.pyd +0 -0
- nvmath/internal/ndbuffer/jit.pxd +7 -0
- nvmath/internal/ndbuffer/jit.pyi +6 -0
- nvmath/internal/ndbuffer/ndbuffer.cp314-win_amd64.pyd +0 -0
- nvmath/internal/ndbuffer/ndbuffer.pxd +36 -0
- nvmath/internal/ndbuffer/ndbuffer.pyi +41 -0
- nvmath/internal/ndbuffer/package_utils.cp314-win_amd64.pyd +0 -0
- nvmath/internal/ndbuffer/package_utils.pxd +11 -0
- nvmath/internal/ndbuffer/package_utils.pyi +12 -0
- nvmath/internal/package_ifc.py +147 -0
- nvmath/internal/package_ifc_cuda.py +49 -0
- nvmath/internal/package_ifc_cupy.py +49 -0
- nvmath/internal/package_ifc_torch.py +31 -0
- nvmath/internal/package_wrapper.py +14 -0
- nvmath/internal/tensor_ifc.py +194 -0
- nvmath/internal/tensor_ifc_cupy.py +241 -0
- nvmath/internal/tensor_ifc_ndbuffer.py +153 -0
- nvmath/internal/tensor_ifc_numpy.py +183 -0
- nvmath/internal/tensor_ifc_torch.py +176 -0
- nvmath/internal/tensor_wrapper.py +157 -0
- nvmath/internal/typemaps.py +162 -0
- nvmath/internal/utils.py +771 -0
- nvmath/linalg/__init__.py +46 -0
- nvmath/linalg/_internal/__init__.py +3 -0
- nvmath/linalg/_internal/algo_cap_ifc.py +82 -0
- nvmath/linalg/_internal/algo_config_ifc.py +43 -0
- nvmath/linalg/_internal/batch.py +217 -0
- nvmath/linalg/_internal/enum_to_tuples.py +64 -0
- nvmath/linalg/_internal/epilog_protocol.py +766 -0
- nvmath/linalg/_internal/layout.py +624 -0
- nvmath/linalg/_internal/matmul_desc_ifc.py +28 -0
- nvmath/linalg/_internal/matmul_pref_ifc.py +27 -0
- nvmath/linalg/_internal/matrix_layout_ifc.py +26 -0
- nvmath/linalg/_internal/typemaps.py +144 -0
- nvmath/linalg/_internal/utils.py +134 -0
- nvmath/linalg/advanced/__init__.py +8 -0
- nvmath/linalg/advanced/_algorithmmod.py +149 -0
- nvmath/linalg/advanced/_configuration.py +349 -0
- nvmath/linalg/advanced/helpers/__init__.py +5 -0
- nvmath/linalg/advanced/helpers/matmul.py +1348 -0
- nvmath/linalg/advanced/matmulmod.py +3937 -0
- nvmath/linalg/generic/__init__.py +43 -0
- nvmath/linalg/generic/_configuration/__init__.py +37 -0
- nvmath/linalg/generic/_configuration/layout.py +263 -0
- nvmath/linalg/generic/_configuration/match.py +609 -0
- nvmath/linalg/generic/_configuration/qualifiers.py +494 -0
- nvmath/linalg/generic/_configuration/wrap.py +217 -0
- nvmath/linalg/generic/_dtype.py +15 -0
- nvmath/linalg/generic/matmulmod.py +1060 -0
- nvmath/memory.py +282 -0
- nvmath/sparse/__init__.py +38 -0
- nvmath/sparse/_internal/__init__.py +21 -0
- nvmath/sparse/_internal/common_utils.py +144 -0
- nvmath/sparse/_internal/cudss_config_ifc.py +741 -0
- nvmath/sparse/_internal/cudss_data_ifc.py +399 -0
- nvmath/sparse/_internal/cudss_utils.py +445 -0
- nvmath/sparse/_internal/cusparse_utils.py +382 -0
- nvmath/sparse/_internal/sparse_bsc_ifc.py +300 -0
- nvmath/sparse/_internal/sparse_bsr_ifc.py +303 -0
- nvmath/sparse/_internal/sparse_coo_ifc.py +254 -0
- nvmath/sparse/_internal/sparse_csc_ifc.py +266 -0
- nvmath/sparse/_internal/sparse_csr_ifc.py +266 -0
- nvmath/sparse/_internal/sparse_dia_ifc.py +239 -0
- nvmath/sparse/_internal/sparse_format_helpers.py +601 -0
- nvmath/sparse/_internal/sparse_tensor_ifc.py +121 -0
- nvmath/sparse/_internal/sparse_ust_ifc.py +146 -0
- nvmath/sparse/_internal/utils.py +56 -0
- nvmath/sparse/advanced/__init__.py +7 -0
- nvmath/sparse/advanced/_configuration.py +230 -0
- nvmath/sparse/advanced/direct_solver.py +1884 -0
- nvmath/sparse/generic/__init__.py +7 -0
- nvmath/sparse/generic/_configuration.py +129 -0
- nvmath/sparse/generic/_helpers.py +137 -0
- nvmath/sparse/generic/_thunks.py +21 -0
- nvmath/sparse/generic/matmulmod.py +2426 -0
- nvmath/sparse/ust/__init__.py +7 -0
- nvmath/sparse/ust/_converters.py +378 -0
- nvmath/sparse/ust/_drawer.py +552 -0
- nvmath/sparse/ust/_emitter.py +553 -0
- nvmath/sparse/ust/_jit.py +212 -0
- nvmath/sparse/ust/_kernel.py +346 -0
- nvmath/sparse/ust/_semiring.py +71 -0
- nvmath/sparse/ust/_utils.py +102 -0
- nvmath/sparse/ust/interfaces/__init__.py +0 -0
- nvmath/sparse/ust/interfaces/torch_interface.py +476 -0
- nvmath/sparse/ust/semiring_ops.py +71 -0
- nvmath/sparse/ust/tensor.py +1027 -0
- nvmath/sparse/ust/tensor_drawer.py +552 -0
- nvmath/sparse/ust/tensor_emitter.py +558 -0
- nvmath/sparse/ust/tensor_format.py +935 -0
- nvmath/sparse/ust/tensor_jit.py +212 -0
- nvmath/sparse/ust/tensor_kernel.py +348 -0
- nvmath/sparse/ust/tensor_utils.py +380 -0
- nvmath/tensor/__init__.py +6 -0
- nvmath/tensor/_configuration.py +95 -0
- nvmath/tensor/_internal/__init__.py +3 -0
- nvmath/tensor/_internal/cutensor_config_ifc.py +247 -0
- nvmath/tensor/_internal/cutensor_utils.py +162 -0
- nvmath/tensor/_internal/data.py +43 -0
- nvmath/tensor/_internal/einsum_parser.py +444 -0
- nvmath/tensor/_internal/typemaps.py +96 -0
- nvmath/tensor/contract.py +1861 -0
- nvmath_python-0.9.0.dist-info/METADATA +127 -0
- nvmath_python-0.9.0.dist-info/RECORD +309 -0
- nvmath_python-0.9.0.dist-info/WHEEL +5 -0
- nvmath_python-0.9.0.dist-info/licenses/LICENSE +177 -0
- nvmath_python-0.9.0.dist-info/top_level.txt +2 -0
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
Binary file
|
|
@@ -0,0 +1,125 @@
|
|
|
1
|
+
# Copyright (c) 2024-2026, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
|
|
2
|
+
#
|
|
3
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
4
|
+
#
|
|
5
|
+
# This code was automatically generated with version 25.5, generator version 0.3.1.dev1303+g031f1197f. Do not modify it directly.
|
|
6
|
+
|
|
7
|
+
from ..cyblas cimport *
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
###############################################################################
|
|
11
|
+
# Wrapper functions
|
|
12
|
+
###############################################################################
|
|
13
|
+
|
|
14
|
+
cdef int _MKL_mkl_set_num_threads_local(int nth) except?-42 nogil
|
|
15
|
+
cdef void _MKL_mkl_set_num_threads(int nth) except* nogil
|
|
16
|
+
cdef void _openblas_openblas_set_num_threads(int num_threads) except* nogil
|
|
17
|
+
cdef int _openblas_openblas_set_num_threads_local(int num_threads) except?-42 nogil
|
|
18
|
+
cdef int _nvpl_blas_get_version() except?-42 nogil
|
|
19
|
+
cdef int _nvpl_blas_get_max_threads() except?-42 nogil
|
|
20
|
+
cdef void _nvpl_blas_set_num_threads(int nthr) except* nogil
|
|
21
|
+
cdef int _nvpl_blas_set_num_threads_local(int nthr_local) except?-42 nogil
|
|
22
|
+
cdef void _cblas_sgemv(const CBLAS_ORDER order, const CBLAS_TRANSPOSE TransA, const nvpl_int_t M, const nvpl_int_t N, const float alpha, const float* A, const nvpl_int_t lda, const float* X, const nvpl_int_t incX, const float beta, float* Y, const nvpl_int_t incY) except* nogil
|
|
23
|
+
cdef void _cblas_sgbmv(const CBLAS_ORDER order, const CBLAS_TRANSPOSE TransA, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t KL, const nvpl_int_t KU, const float alpha, const float* A, const nvpl_int_t lda, const float* X, const nvpl_int_t incX, const float beta, float* Y, const nvpl_int_t incY) except* nogil
|
|
24
|
+
cdef void _cblas_strmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const float* A, const nvpl_int_t lda, float* X, const nvpl_int_t incX) except* nogil
|
|
25
|
+
cdef void _cblas_stbmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const nvpl_int_t K, const float* A, const nvpl_int_t lda, float* X, const nvpl_int_t incX) except* nogil
|
|
26
|
+
cdef void _cblas_stpmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const float* Ap, float* X, const nvpl_int_t incX) except* nogil
|
|
27
|
+
cdef void _cblas_strsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const float* A, const nvpl_int_t lda, float* X, const nvpl_int_t incX) except* nogil
|
|
28
|
+
cdef void _cblas_stbsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const nvpl_int_t K, const float* A, const nvpl_int_t lda, float* X, const nvpl_int_t incX) except* nogil
|
|
29
|
+
cdef void _cblas_stpsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const float* Ap, float* X, const nvpl_int_t incX) except* nogil
|
|
30
|
+
cdef void _cblas_dgemv(const CBLAS_ORDER order, const CBLAS_TRANSPOSE TransA, const nvpl_int_t M, const nvpl_int_t N, const double alpha, const double* A, const nvpl_int_t lda, const double* X, const nvpl_int_t incX, const double beta, double* Y, const nvpl_int_t incY) except* nogil
|
|
31
|
+
cdef void _cblas_dgbmv(const CBLAS_ORDER order, const CBLAS_TRANSPOSE TransA, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t KL, const nvpl_int_t KU, const double alpha, const double* A, const nvpl_int_t lda, const double* X, const nvpl_int_t incX, const double beta, double* Y, const nvpl_int_t incY) except* nogil
|
|
32
|
+
cdef void _cblas_dtrmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const double* A, const nvpl_int_t lda, double* X, const nvpl_int_t incX) except* nogil
|
|
33
|
+
cdef void _cblas_dtbmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const nvpl_int_t K, const double* A, const nvpl_int_t lda, double* X, const nvpl_int_t incX) except* nogil
|
|
34
|
+
cdef void _cblas_dtpmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const double* Ap, double* X, const nvpl_int_t incX) except* nogil
|
|
35
|
+
cdef void _cblas_dtrsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const double* A, const nvpl_int_t lda, double* X, const nvpl_int_t incX) except* nogil
|
|
36
|
+
cdef void _cblas_dtbsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const nvpl_int_t K, const double* A, const nvpl_int_t lda, double* X, const nvpl_int_t incX) except* nogil
|
|
37
|
+
cdef void _cblas_dtpsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const double* Ap, double* X, const nvpl_int_t incX) except* nogil
|
|
38
|
+
cdef void _cblas_cgemv(const CBLAS_ORDER order, const CBLAS_TRANSPOSE TransA, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
39
|
+
cdef void _cblas_cgbmv(const CBLAS_ORDER order, const CBLAS_TRANSPOSE TransA, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t KL, const nvpl_int_t KU, const void* alpha, const void* A, const nvpl_int_t lda, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
40
|
+
cdef void _cblas_ctrmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const void* A, const nvpl_int_t lda, void* X, const nvpl_int_t incX) except* nogil
|
|
41
|
+
cdef void _cblas_ctbmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const nvpl_int_t K, const void* A, const nvpl_int_t lda, void* X, const nvpl_int_t incX) except* nogil
|
|
42
|
+
cdef void _cblas_ctpmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const void* Ap, void* X, const nvpl_int_t incX) except* nogil
|
|
43
|
+
cdef void _cblas_ctrsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const void* A, const nvpl_int_t lda, void* X, const nvpl_int_t incX) except* nogil
|
|
44
|
+
cdef void _cblas_ctbsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const nvpl_int_t K, const void* A, const nvpl_int_t lda, void* X, const nvpl_int_t incX) except* nogil
|
|
45
|
+
cdef void _cblas_ctpsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const void* Ap, void* X, const nvpl_int_t incX) except* nogil
|
|
46
|
+
cdef void _cblas_zgemv(const CBLAS_ORDER order, const CBLAS_TRANSPOSE TransA, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
47
|
+
cdef void _cblas_zgbmv(const CBLAS_ORDER order, const CBLAS_TRANSPOSE TransA, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t KL, const nvpl_int_t KU, const void* alpha, const void* A, const nvpl_int_t lda, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
48
|
+
cdef void _cblas_ztrmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const void* A, const nvpl_int_t lda, void* X, const nvpl_int_t incX) except* nogil
|
|
49
|
+
cdef void _cblas_ztbmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const nvpl_int_t K, const void* A, const nvpl_int_t lda, void* X, const nvpl_int_t incX) except* nogil
|
|
50
|
+
cdef void _cblas_ztpmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const void* Ap, void* X, const nvpl_int_t incX) except* nogil
|
|
51
|
+
cdef void _cblas_ztrsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const void* A, const nvpl_int_t lda, void* X, const nvpl_int_t incX) except* nogil
|
|
52
|
+
cdef void _cblas_ztbsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const nvpl_int_t K, const void* A, const nvpl_int_t lda, void* X, const nvpl_int_t incX) except* nogil
|
|
53
|
+
cdef void _cblas_ztpsv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t N, const void* Ap, void* X, const nvpl_int_t incX) except* nogil
|
|
54
|
+
cdef void _cblas_ssymv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const float alpha, const float* A, const nvpl_int_t lda, const float* X, const nvpl_int_t incX, const float beta, float* Y, const nvpl_int_t incY) except* nogil
|
|
55
|
+
cdef void _cblas_ssbmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const nvpl_int_t K, const float alpha, const float* A, const nvpl_int_t lda, const float* X, const nvpl_int_t incX, const float beta, float* Y, const nvpl_int_t incY) except* nogil
|
|
56
|
+
cdef void _cblas_sspmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const float alpha, const float* Ap, const float* X, const nvpl_int_t incX, const float beta, float* Y, const nvpl_int_t incY) except* nogil
|
|
57
|
+
cdef void _cblas_sger(const CBLAS_ORDER order, const nvpl_int_t M, const nvpl_int_t N, const float alpha, const float* X, const nvpl_int_t incX, const float* Y, const nvpl_int_t incY, float* A, const nvpl_int_t lda) except* nogil
|
|
58
|
+
cdef void _cblas_ssyr(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const float alpha, const float* X, const nvpl_int_t incX, float* A, const nvpl_int_t lda) except* nogil
|
|
59
|
+
cdef void _cblas_sspr(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const float alpha, const float* X, const nvpl_int_t incX, float* Ap) except* nogil
|
|
60
|
+
cdef void _cblas_ssyr2(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const float alpha, const float* X, const nvpl_int_t incX, const float* Y, const nvpl_int_t incY, float* A, const nvpl_int_t lda) except* nogil
|
|
61
|
+
cdef void _cblas_sspr2(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const float alpha, const float* X, const nvpl_int_t incX, const float* Y, const nvpl_int_t incY, float* A) except* nogil
|
|
62
|
+
cdef void _cblas_dsymv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const double alpha, const double* A, const nvpl_int_t lda, const double* X, const nvpl_int_t incX, const double beta, double* Y, const nvpl_int_t incY) except* nogil
|
|
63
|
+
cdef void _cblas_dsbmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const nvpl_int_t K, const double alpha, const double* A, const nvpl_int_t lda, const double* X, const nvpl_int_t incX, const double beta, double* Y, const nvpl_int_t incY) except* nogil
|
|
64
|
+
cdef void _cblas_dspmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const double alpha, const double* Ap, const double* X, const nvpl_int_t incX, const double beta, double* Y, const nvpl_int_t incY) except* nogil
|
|
65
|
+
cdef void _cblas_dger(const CBLAS_ORDER order, const nvpl_int_t M, const nvpl_int_t N, const double alpha, const double* X, const nvpl_int_t incX, const double* Y, const nvpl_int_t incY, double* A, const nvpl_int_t lda) except* nogil
|
|
66
|
+
cdef void _cblas_dsyr(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const double alpha, const double* X, const nvpl_int_t incX, double* A, const nvpl_int_t lda) except* nogil
|
|
67
|
+
cdef void _cblas_dspr(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const double alpha, const double* X, const nvpl_int_t incX, double* Ap) except* nogil
|
|
68
|
+
cdef void _cblas_dsyr2(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const double alpha, const double* X, const nvpl_int_t incX, const double* Y, const nvpl_int_t incY, double* A, const nvpl_int_t lda) except* nogil
|
|
69
|
+
cdef void _cblas_dspr2(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const double alpha, const double* X, const nvpl_int_t incX, const double* Y, const nvpl_int_t incY, double* A) except* nogil
|
|
70
|
+
cdef void _cblas_chemv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
71
|
+
cdef void _cblas_chbmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
72
|
+
cdef void _cblas_chpmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const void* alpha, const void* Ap, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
73
|
+
cdef void _cblas_cgeru(const CBLAS_ORDER order, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* X, const nvpl_int_t incX, const void* Y, const nvpl_int_t incY, void* A, const nvpl_int_t lda) except* nogil
|
|
74
|
+
cdef void _cblas_cgerc(const CBLAS_ORDER order, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* X, const nvpl_int_t incX, const void* Y, const nvpl_int_t incY, void* A, const nvpl_int_t lda) except* nogil
|
|
75
|
+
cdef void _cblas_cher(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const float alpha, const void* X, const nvpl_int_t incX, void* A, const nvpl_int_t lda) except* nogil
|
|
76
|
+
cdef void _cblas_chpr(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const float alpha, const void* X, const nvpl_int_t incX, void* A) except* nogil
|
|
77
|
+
cdef void _cblas_cher2(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const void* alpha, const void* X, const nvpl_int_t incX, const void* Y, const nvpl_int_t incY, void* A, const nvpl_int_t lda) except* nogil
|
|
78
|
+
cdef void _cblas_chpr2(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const void* alpha, const void* X, const nvpl_int_t incX, const void* Y, const nvpl_int_t incY, void* Ap) except* nogil
|
|
79
|
+
cdef void _cblas_zhemv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
80
|
+
cdef void _cblas_zhbmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
81
|
+
cdef void _cblas_zhpmv(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const void* alpha, const void* Ap, const void* X, const nvpl_int_t incX, const void* beta, void* Y, const nvpl_int_t incY) except* nogil
|
|
82
|
+
cdef void _cblas_zgeru(const CBLAS_ORDER order, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* X, const nvpl_int_t incX, const void* Y, const nvpl_int_t incY, void* A, const nvpl_int_t lda) except* nogil
|
|
83
|
+
cdef void _cblas_zgerc(const CBLAS_ORDER order, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* X, const nvpl_int_t incX, const void* Y, const nvpl_int_t incY, void* A, const nvpl_int_t lda) except* nogil
|
|
84
|
+
cdef void _cblas_zher(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const double alpha, const void* X, const nvpl_int_t incX, void* A, const nvpl_int_t lda) except* nogil
|
|
85
|
+
cdef void _cblas_zhpr(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const double alpha, const void* X, const nvpl_int_t incX, void* A) except* nogil
|
|
86
|
+
cdef void _cblas_zher2(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const void* alpha, const void* X, const nvpl_int_t incX, const void* Y, const nvpl_int_t incY, void* A, const nvpl_int_t lda) except* nogil
|
|
87
|
+
cdef void _cblas_zhpr2(const CBLAS_ORDER order, const CBLAS_UPLO Uplo, const nvpl_int_t N, const void* alpha, const void* X, const nvpl_int_t incX, const void* Y, const nvpl_int_t incY, void* Ap) except* nogil
|
|
88
|
+
cdef void _cblas_sgemm(const CBLAS_ORDER Order, const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t K, const float alpha, const float* A, const nvpl_int_t lda, const float* B, const nvpl_int_t ldb, const float beta, float* C, const nvpl_int_t ldc) except* nogil
|
|
89
|
+
cdef void _cblas_ssymm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const nvpl_int_t M, const nvpl_int_t N, const float alpha, const float* A, const nvpl_int_t lda, const float* B, const nvpl_int_t ldb, const float beta, float* C, const nvpl_int_t ldc) except* nogil
|
|
90
|
+
cdef void _cblas_ssyrk(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const float alpha, const float* A, const nvpl_int_t lda, const float beta, float* C, const nvpl_int_t ldc) except* nogil
|
|
91
|
+
cdef void _cblas_ssyr2k(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const float alpha, const float* A, const nvpl_int_t lda, const float* B, const nvpl_int_t ldb, const float beta, float* C, const nvpl_int_t ldc) except* nogil
|
|
92
|
+
cdef void _cblas_strmm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t M, const nvpl_int_t N, const float alpha, const float* A, const nvpl_int_t lda, float* B, const nvpl_int_t ldb) except* nogil
|
|
93
|
+
cdef void _cblas_strsm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t M, const nvpl_int_t N, const float alpha, const float* A, const nvpl_int_t lda, float* B, const nvpl_int_t ldb) except* nogil
|
|
94
|
+
cdef void _cblas_dgemm(const CBLAS_ORDER Order, const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t K, const double alpha, const double* A, const nvpl_int_t lda, const double* B, const nvpl_int_t ldb, const double beta, double* C, const nvpl_int_t ldc) except* nogil
|
|
95
|
+
cdef void _cblas_dsymm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const nvpl_int_t M, const nvpl_int_t N, const double alpha, const double* A, const nvpl_int_t lda, const double* B, const nvpl_int_t ldb, const double beta, double* C, const nvpl_int_t ldc) except* nogil
|
|
96
|
+
cdef void _cblas_dsyrk(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const double alpha, const double* A, const nvpl_int_t lda, const double beta, double* C, const nvpl_int_t ldc) except* nogil
|
|
97
|
+
cdef void _cblas_dsyr2k(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const double alpha, const double* A, const nvpl_int_t lda, const double* B, const nvpl_int_t ldb, const double beta, double* C, const nvpl_int_t ldc) except* nogil
|
|
98
|
+
cdef void _cblas_dtrmm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t M, const nvpl_int_t N, const double alpha, const double* A, const nvpl_int_t lda, double* B, const nvpl_int_t ldb) except* nogil
|
|
99
|
+
cdef void _cblas_dtrsm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t M, const nvpl_int_t N, const double alpha, const double* A, const nvpl_int_t lda, double* B, const nvpl_int_t ldb) except* nogil
|
|
100
|
+
cdef void _cblas_cgemm(const CBLAS_ORDER Order, const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
101
|
+
cdef void _cblas_csymm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
102
|
+
cdef void _cblas_csyrk(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
103
|
+
cdef void _cblas_csyr2k(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
104
|
+
cdef void _cblas_ctrmm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, void* B, const nvpl_int_t ldb) except* nogil
|
|
105
|
+
cdef void _cblas_ctrsm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, void* B, const nvpl_int_t ldb) except* nogil
|
|
106
|
+
cdef void _cblas_zgemm(const CBLAS_ORDER Order, const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
107
|
+
cdef void _cblas_zsymm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
108
|
+
cdef void _cblas_zsyrk(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
109
|
+
cdef void _cblas_zsyr2k(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
110
|
+
cdef void _cblas_ztrmm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, void* B, const nvpl_int_t ldb) except* nogil
|
|
111
|
+
cdef void _cblas_ztrsm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE TransA, const CBLAS_DIAG Diag, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, void* B, const nvpl_int_t ldb) except* nogil
|
|
112
|
+
cdef void _cblas_chemm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
113
|
+
cdef void _cblas_cherk(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const float alpha, const void* A, const nvpl_int_t lda, const float beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
114
|
+
cdef void _cblas_cher2k(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const float beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
115
|
+
cdef void _cblas_zhemm(const CBLAS_ORDER Order, const CBLAS_SIDE Side, const CBLAS_UPLO Uplo, const nvpl_int_t M, const nvpl_int_t N, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const void* beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
116
|
+
cdef void _cblas_zherk(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const double alpha, const void* A, const nvpl_int_t lda, const double beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
117
|
+
cdef void _cblas_zher2k(const CBLAS_ORDER Order, const CBLAS_UPLO Uplo, const CBLAS_TRANSPOSE Trans, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const void* B, const nvpl_int_t ldb, const double beta, void* C, const nvpl_int_t ldc) except* nogil
|
|
118
|
+
cdef void _cblas_sgemm_batch(CBLAS_ORDER Order, CBLAS_TRANSPOSE* TransA_array, CBLAS_TRANSPOSE* TransB_array, nvpl_int_t* M_array, nvpl_int_t* N_array, nvpl_int_t* K_array, const float* alpha_array, const float** A_array, nvpl_int_t* lda_array, const float** B_array, nvpl_int_t* ldb_array, const float* beta_array, float** C_array, nvpl_int_t* ldc_array, nvpl_int_t group_count, nvpl_int_t* group_size) except* nogil
|
|
119
|
+
cdef void _cblas_dgemm_batch(CBLAS_ORDER Order, CBLAS_TRANSPOSE* TransA_array, CBLAS_TRANSPOSE* TransB_array, nvpl_int_t* M_array, nvpl_int_t* N_array, nvpl_int_t* K_array, const double* alpha_array, const double** A_array, nvpl_int_t* lda_array, const double** B_array, nvpl_int_t* ldb_array, const double* beta_array, double** C_array, nvpl_int_t* ldc_array, nvpl_int_t group_count, nvpl_int_t* group_size) except* nogil
|
|
120
|
+
cdef void _cblas_cgemm_batch(CBLAS_ORDER Order, CBLAS_TRANSPOSE* TransA_array, CBLAS_TRANSPOSE* TransB_array, nvpl_int_t* M_array, nvpl_int_t* N_array, nvpl_int_t* K_array, const void* alpha_array, const void** A_array, nvpl_int_t* lda_array, const void** B_array, nvpl_int_t* ldb_array, const void* beta_array, void** C_array, nvpl_int_t* ldc_array, nvpl_int_t group_count, nvpl_int_t* group_size) except* nogil
|
|
121
|
+
cdef void _cblas_zgemm_batch(CBLAS_ORDER Order, CBLAS_TRANSPOSE* TransA_array, CBLAS_TRANSPOSE* TransB_array, nvpl_int_t* M_array, nvpl_int_t* N_array, nvpl_int_t* K_array, const void* alpha_array, const void** A_array, nvpl_int_t* lda_array, const void** B_array, nvpl_int_t* ldb_array, const void* beta_array, void** C_array, nvpl_int_t* ldc_array, nvpl_int_t group_count, nvpl_int_t* group_size) except* nogil
|
|
122
|
+
cdef void _cblas_sgemm_batch_strided(const CBLAS_ORDER Order, const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t K, const float alpha, const float* A, const nvpl_int_t lda, const nvpl_int_t stridea, const float* B, const nvpl_int_t ldb, const nvpl_int_t strideb, const float beta, float* C, const nvpl_int_t ldc, const nvpl_int_t stridec, const nvpl_int_t batch_size) except* nogil
|
|
123
|
+
cdef void _cblas_dgemm_batch_strided(const CBLAS_ORDER Order, const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t K, const double alpha, const double* A, const nvpl_int_t lda, const nvpl_int_t stridea, const double* B, const nvpl_int_t ldb, const nvpl_int_t strideb, const double beta, double* C, const nvpl_int_t ldc, const nvpl_int_t stridec, const nvpl_int_t batch_size) except* nogil
|
|
124
|
+
cdef void _cblas_cgemm_batch_strided(const CBLAS_ORDER Order, const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const nvpl_int_t stridea, const void* B, const nvpl_int_t ldb, const nvpl_int_t strideb, const void* beta, void* C, const nvpl_int_t ldc, const nvpl_int_t stridec, const nvpl_int_t batch_size) except* nogil
|
|
125
|
+
cdef void _cblas_zgemm_batch_strided(const CBLAS_ORDER Order, const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const nvpl_int_t M, const nvpl_int_t N, const nvpl_int_t K, const void* alpha, const void* A, const nvpl_int_t lda, const nvpl_int_t stridea, const void* B, const nvpl_int_t ldb, const nvpl_int_t strideb, const void* beta, void* C, const nvpl_int_t ldc, const nvpl_int_t stridec, const nvpl_int_t batch_size) except* nogil
|
|
Binary file
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# Copyright (c) 2024-2026, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
|
|
2
|
+
#
|
|
3
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
4
|
+
#
|
|
5
|
+
# This code was automatically generated with version 25.5, generator version 0.3.1.dev1303+g031f1197f. Do not modify it directly.
|
|
6
|
+
|
|
7
|
+
from ..cyfft cimport *
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
###############################################################################
|
|
11
|
+
# Wrapper functions
|
|
12
|
+
###############################################################################
|
|
13
|
+
|
|
14
|
+
cdef int _nvpl_fft_get_version() except?-42 nogil
|
|
15
|
+
cdef fftw_plan _fftw_plan_many_dft(int rank, const int* n, int batch, fftw_complex* in_, const int* inembed, int istride, int idist, fftw_complex* out, const int* onembed, int ostride, int odist, int sign, unsigned flags) except?NULL nogil
|
|
16
|
+
cdef fftw_plan _fftw_plan_many_dft_r2c(int rank, const int* n, int batch, double* in_, const int* inembed, int istride, int idist, fftw_complex* out, const int* onembed, int ostride, int odist, unsigned flags) except?NULL nogil
|
|
17
|
+
cdef fftw_plan _fftw_plan_many_dft_c2r(int rank, const int* n, int batch, fftw_complex* in_, const int* inembed, int istride, int idist, double* out, const int* onembed, int ostride, int odist, unsigned flags) except?NULL nogil
|
|
18
|
+
cdef void _fftw_execute_dft(const fftw_plan plan, fftw_complex* idata, fftw_complex* odata) except* nogil
|
|
19
|
+
cdef void _fftw_execute_dft_r2c(const fftw_plan plan, double* idata, fftw_complex* odata) except* nogil
|
|
20
|
+
cdef void _fftw_execute_dft_c2r(const fftw_plan plan, fftw_complex* idata, double* odata) except* nogil
|
|
21
|
+
cdef fftwf_plan _fftwf_plan_many_dft(int rank, const int* n, int batch, fftwf_complex* in_, const int* inembed, int istride, int idist, fftwf_complex* out, const int* onembed, int ostride, int odist, int sign, unsigned flags) except?NULL nogil
|
|
22
|
+
cdef fftwf_plan _fftwf_plan_many_dft_r2c(int rank, const int* n, int batch, float* in_, const int* inembed, int istride, int idist, fftwf_complex* out, const int* onembed, int ostride, int odist, unsigned flags) except?NULL nogil
|
|
23
|
+
cdef fftwf_plan _fftwf_plan_many_dft_c2r(int rank, const int* n, int batch, fftwf_complex* in_, const int* inembed, int istride, int idist, float* out, const int* onembed, int ostride, int odist, unsigned flags) except?NULL nogil
|
|
24
|
+
cdef void _fftwf_execute_dft(const fftwf_plan plan, fftwf_complex* idata, fftwf_complex* odata) except* nogil
|
|
25
|
+
cdef void _fftwf_execute_dft_r2c(const fftwf_plan plan, float* idata, fftwf_complex* odata) except* nogil
|
|
26
|
+
cdef void _fftwf_execute_dft_c2r(const fftwf_plan plan, fftwf_complex* idata, float* odata) except* nogil
|
|
27
|
+
cdef int _fftw_init_threads() except?-42 nogil
|
|
28
|
+
cdef int _fftwf_init_threads() except?-42 nogil
|
|
29
|
+
cdef void _fftw_plan_with_nthreads(int nthreads) except* nogil
|
|
30
|
+
cdef void _fftwf_plan_with_nthreads(int nthreads) except* nogil
|
|
31
|
+
cdef int _fftw_planner_nthreads() except?-42 nogil
|
|
32
|
+
cdef int _fftwf_planner_nthreads() except?-42 nogil
|
|
33
|
+
cdef void _fftw_cleanup_threads() except* nogil
|
|
34
|
+
cdef void _fftwf_cleanup_threads() except* nogil
|
|
35
|
+
cdef void _fftw_destroy_plan(fftw_plan plan) except* nogil
|
|
36
|
+
cdef void _fftwf_destroy_plan(fftwf_plan plan) except* nogil
|
|
Binary file
|
|
@@ -0,0 +1,85 @@
|
|
|
1
|
+
# Copyright (c) 2024-2026, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
|
|
2
|
+
#
|
|
3
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
4
|
+
#
|
|
5
|
+
# This code was automatically generated with version 25.5, generator version 0.3.1.dev1303+g031f1197f. Do not modify it directly.
|
|
6
|
+
|
|
7
|
+
from libc.stdint cimport intptr_t
|
|
8
|
+
|
|
9
|
+
from .cyblas cimport *
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
###############################################################################
|
|
13
|
+
# Types
|
|
14
|
+
###############################################################################
|
|
15
|
+
|
|
16
|
+
ctypedef nvpl_scomplex_t scomplex
|
|
17
|
+
ctypedef nvpl_dcomplex_t dcomplex
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
###############################################################################
|
|
21
|
+
# Enum
|
|
22
|
+
###############################################################################
|
|
23
|
+
|
|
24
|
+
ctypedef CBLAS_ORDER _ORDER
|
|
25
|
+
ctypedef CBLAS_TRANSPOSE _TRANSPOSE
|
|
26
|
+
ctypedef CBLAS_UPLO _UPLO
|
|
27
|
+
ctypedef CBLAS_DIAG _DIAG
|
|
28
|
+
ctypedef CBLAS_SIDE _SIDE
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
###############################################################################
|
|
32
|
+
# Convenience wrappers/adapters
|
|
33
|
+
###############################################################################
|
|
34
|
+
|
|
35
|
+
|
|
36
|
+
###############################################################################
|
|
37
|
+
# Functions
|
|
38
|
+
###############################################################################
|
|
39
|
+
|
|
40
|
+
cpdef int mkl_set_num_threads_local(int nth) except? -1
|
|
41
|
+
cpdef void mkl_set_num_threads(int nth) except*
|
|
42
|
+
cpdef void openblas_set_num_threads(int num_threads) except*
|
|
43
|
+
cpdef int openblas_set_num_threads_local(int num_threads) except? -1
|
|
44
|
+
cpdef int get_version() except? -1
|
|
45
|
+
cpdef int get_max_threads() except? -1
|
|
46
|
+
cpdef void set_num_threads(int nthr) except*
|
|
47
|
+
cpdef int set_num_threads_local(int nthr_local) except? -1
|
|
48
|
+
cpdef void sgemm(int order, int trans_a, int trans_b, nvpl_int32_t m, nvpl_int32_t n, nvpl_int32_t k, float alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, float beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
49
|
+
cpdef void ssymm(int order, int side, int uplo, nvpl_int32_t m, nvpl_int32_t n, float alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, float beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
50
|
+
cpdef void ssyrk(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, float alpha, intptr_t a, nvpl_int32_t lda, float beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
51
|
+
cpdef void ssyr2k(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, float alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, float beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
52
|
+
cpdef void strmm(int order, int side, int uplo, int trans_a, int diag, nvpl_int32_t m, nvpl_int32_t n, float alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb) except*
|
|
53
|
+
cpdef void strsm(int order, int side, int uplo, int trans_a, int diag, nvpl_int32_t m, nvpl_int32_t n, float alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb) except*
|
|
54
|
+
cpdef void dgemm(int order, int trans_a, int trans_b, nvpl_int32_t m, nvpl_int32_t n, nvpl_int32_t k, double alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, double beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
55
|
+
cpdef void dsymm(int order, int side, int uplo, nvpl_int32_t m, nvpl_int32_t n, double alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, double beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
56
|
+
cpdef void dsyrk(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, double alpha, intptr_t a, nvpl_int32_t lda, double beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
57
|
+
cpdef void dsyr2k(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, double alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, double beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
58
|
+
cpdef void dtrmm(int order, int side, int uplo, int trans_a, int diag, nvpl_int32_t m, nvpl_int32_t n, double alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb) except*
|
|
59
|
+
cpdef void dtrsm(int order, int side, int uplo, int trans_a, int diag, nvpl_int32_t m, nvpl_int32_t n, double alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb) except*
|
|
60
|
+
cpdef void cgemm(int order, int trans_a, int trans_b, nvpl_int32_t m, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
61
|
+
cpdef void csymm(int order, int side, int uplo, nvpl_int32_t m, nvpl_int32_t n, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
62
|
+
cpdef void csyrk(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
63
|
+
cpdef void csyr2k(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
64
|
+
cpdef void ctrmm(int order, int side, int uplo, int trans_a, int diag, nvpl_int32_t m, nvpl_int32_t n, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb) except*
|
|
65
|
+
cpdef void ctrsm(int order, int side, int uplo, int trans_a, int diag, nvpl_int32_t m, nvpl_int32_t n, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb) except*
|
|
66
|
+
cpdef void zgemm(int order, int trans_a, int trans_b, nvpl_int32_t m, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
67
|
+
cpdef void zsymm(int order, int side, int uplo, nvpl_int32_t m, nvpl_int32_t n, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
68
|
+
cpdef void zsyrk(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
69
|
+
cpdef void zsyr2k(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
70
|
+
cpdef void ztrmm(int order, int side, int uplo, int trans_a, int diag, nvpl_int32_t m, nvpl_int32_t n, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb) except*
|
|
71
|
+
cpdef void ztrsm(int order, int side, int uplo, int trans_a, int diag, nvpl_int32_t m, nvpl_int32_t n, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb) except*
|
|
72
|
+
cpdef void chemm(int order, int side, int uplo, nvpl_int32_t m, nvpl_int32_t n, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
73
|
+
cpdef void cherk(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, float alpha, intptr_t a, nvpl_int32_t lda, float beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
74
|
+
cpdef void cher2k(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, float beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
75
|
+
cpdef void zhemm(int order, int side, int uplo, nvpl_int32_t m, nvpl_int32_t n, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, intptr_t beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
76
|
+
cpdef void zherk(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, double alpha, intptr_t a, nvpl_int32_t lda, double beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
77
|
+
cpdef void zher2k(int order, int uplo, int trans, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, intptr_t b, nvpl_int32_t ldb, double beta, intptr_t c, nvpl_int32_t ldc) except*
|
|
78
|
+
cpdef void sgemm_batch(int order, intptr_t trans_a_array, intptr_t trans_b_array, intptr_t m_array, intptr_t n_array, intptr_t k_array, intptr_t alpha_array, intptr_t a_array, intptr_t lda_array, intptr_t b_array, intptr_t ldb_array, intptr_t beta_array, intptr_t c_array, intptr_t ldc_array, nvpl_int32_t group_count, intptr_t group_size) except*
|
|
79
|
+
cpdef void dgemm_batch(int order, intptr_t trans_a_array, intptr_t trans_b_array, intptr_t m_array, intptr_t n_array, intptr_t k_array, intptr_t alpha_array, intptr_t a_array, intptr_t lda_array, intptr_t b_array, intptr_t ldb_array, intptr_t beta_array, intptr_t c_array, intptr_t ldc_array, nvpl_int32_t group_count, intptr_t group_size) except*
|
|
80
|
+
cpdef void cgemm_batch(int order, intptr_t trans_a_array, intptr_t trans_b_array, intptr_t m_array, intptr_t n_array, intptr_t k_array, intptr_t alpha_array, intptr_t a_array, intptr_t lda_array, intptr_t b_array, intptr_t ldb_array, intptr_t beta_array, intptr_t c_array, intptr_t ldc_array, nvpl_int32_t group_count, intptr_t group_size) except*
|
|
81
|
+
cpdef void zgemm_batch(int order, intptr_t trans_a_array, intptr_t trans_b_array, intptr_t m_array, intptr_t n_array, intptr_t k_array, intptr_t alpha_array, intptr_t a_array, intptr_t lda_array, intptr_t b_array, intptr_t ldb_array, intptr_t beta_array, intptr_t c_array, intptr_t ldc_array, nvpl_int32_t group_count, intptr_t group_size) except*
|
|
82
|
+
cpdef void sgemm_batch_strided(int order, int trans_a, int trans_b, nvpl_int32_t m, nvpl_int32_t n, nvpl_int32_t k, float alpha, intptr_t a, nvpl_int32_t lda, nvpl_int32_t stridea, intptr_t b, nvpl_int32_t ldb, nvpl_int32_t strideb, float beta, intptr_t c, nvpl_int32_t ldc, nvpl_int32_t stridec, nvpl_int32_t batch_size) except*
|
|
83
|
+
cpdef void dgemm_batch_strided(int order, int trans_a, int trans_b, nvpl_int32_t m, nvpl_int32_t n, nvpl_int32_t k, double alpha, intptr_t a, nvpl_int32_t lda, nvpl_int32_t stridea, intptr_t b, nvpl_int32_t ldb, nvpl_int32_t strideb, double beta, intptr_t c, nvpl_int32_t ldc, nvpl_int32_t stridec, nvpl_int32_t batch_size) except*
|
|
84
|
+
cpdef void cgemm_batch_strided(int order, int trans_a, int trans_b, nvpl_int32_t m, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, nvpl_int32_t stridea, intptr_t b, nvpl_int32_t ldb, nvpl_int32_t strideb, intptr_t beta, intptr_t c, nvpl_int32_t ldc, nvpl_int32_t stridec, nvpl_int32_t batch_size) except*
|
|
85
|
+
cpdef void zgemm_batch_strided(int order, int trans_a, int trans_b, nvpl_int32_t m, nvpl_int32_t n, nvpl_int32_t k, intptr_t alpha, intptr_t a, nvpl_int32_t lda, nvpl_int32_t stridea, intptr_t b, nvpl_int32_t ldb, nvpl_int32_t strideb, intptr_t beta, intptr_t c, nvpl_int32_t ldc, nvpl_int32_t stridec, nvpl_int32_t batch_size) except*
|
|
@@ -0,0 +1,122 @@
|
|
|
1
|
+
# Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
|
|
2
|
+
#
|
|
3
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
4
|
+
|
|
5
|
+
import _cython_3_2_4
|
|
6
|
+
import enum
|
|
7
|
+
from typing import Callable, ClassVar
|
|
8
|
+
|
|
9
|
+
__pyx_capi__: dict
|
|
10
|
+
__test__: dict
|
|
11
|
+
cgemm: _cython_3_2_4.cython_function_or_method
|
|
12
|
+
cgemm_batch: _cython_3_2_4.cython_function_or_method
|
|
13
|
+
cgemm_batch_strided: _cython_3_2_4.cython_function_or_method
|
|
14
|
+
chemm: _cython_3_2_4.cython_function_or_method
|
|
15
|
+
cher2k: _cython_3_2_4.cython_function_or_method
|
|
16
|
+
cherk: _cython_3_2_4.cython_function_or_method
|
|
17
|
+
csymm: _cython_3_2_4.cython_function_or_method
|
|
18
|
+
csyr2k: _cython_3_2_4.cython_function_or_method
|
|
19
|
+
csyrk: _cython_3_2_4.cython_function_or_method
|
|
20
|
+
ctrmm: _cython_3_2_4.cython_function_or_method
|
|
21
|
+
ctrsm: _cython_3_2_4.cython_function_or_method
|
|
22
|
+
dgemm: _cython_3_2_4.cython_function_or_method
|
|
23
|
+
dgemm_batch: _cython_3_2_4.cython_function_or_method
|
|
24
|
+
dgemm_batch_strided: _cython_3_2_4.cython_function_or_method
|
|
25
|
+
dsymm: _cython_3_2_4.cython_function_or_method
|
|
26
|
+
dsyr2k: _cython_3_2_4.cython_function_or_method
|
|
27
|
+
dsyrk: _cython_3_2_4.cython_function_or_method
|
|
28
|
+
dtrmm: _cython_3_2_4.cython_function_or_method
|
|
29
|
+
dtrsm: _cython_3_2_4.cython_function_or_method
|
|
30
|
+
get_max_threads: _cython_3_2_4.cython_function_or_method
|
|
31
|
+
get_version: _cython_3_2_4.cython_function_or_method
|
|
32
|
+
mkl_set_num_threads: _cython_3_2_4.cython_function_or_method
|
|
33
|
+
mkl_set_num_threads_local: _cython_3_2_4.cython_function_or_method
|
|
34
|
+
openblas_set_num_threads: _cython_3_2_4.cython_function_or_method
|
|
35
|
+
openblas_set_num_threads_local: _cython_3_2_4.cython_function_or_method
|
|
36
|
+
set_num_threads: _cython_3_2_4.cython_function_or_method
|
|
37
|
+
set_num_threads_local: _cython_3_2_4.cython_function_or_method
|
|
38
|
+
sgemm: _cython_3_2_4.cython_function_or_method
|
|
39
|
+
sgemm_batch: _cython_3_2_4.cython_function_or_method
|
|
40
|
+
sgemm_batch_strided: _cython_3_2_4.cython_function_or_method
|
|
41
|
+
ssymm: _cython_3_2_4.cython_function_or_method
|
|
42
|
+
ssyr2k: _cython_3_2_4.cython_function_or_method
|
|
43
|
+
ssyrk: _cython_3_2_4.cython_function_or_method
|
|
44
|
+
strmm: _cython_3_2_4.cython_function_or_method
|
|
45
|
+
strsm: _cython_3_2_4.cython_function_or_method
|
|
46
|
+
zgemm: _cython_3_2_4.cython_function_or_method
|
|
47
|
+
zgemm_batch: _cython_3_2_4.cython_function_or_method
|
|
48
|
+
zgemm_batch_strided: _cython_3_2_4.cython_function_or_method
|
|
49
|
+
zhemm: _cython_3_2_4.cython_function_or_method
|
|
50
|
+
zher2k: _cython_3_2_4.cython_function_or_method
|
|
51
|
+
zherk: _cython_3_2_4.cython_function_or_method
|
|
52
|
+
zsymm: _cython_3_2_4.cython_function_or_method
|
|
53
|
+
zsyr2k: _cython_3_2_4.cython_function_or_method
|
|
54
|
+
zsyrk: _cython_3_2_4.cython_function_or_method
|
|
55
|
+
ztrmm: _cython_3_2_4.cython_function_or_method
|
|
56
|
+
ztrsm: _cython_3_2_4.cython_function_or_method
|
|
57
|
+
|
|
58
|
+
class DIAG(enum.IntEnum):
|
|
59
|
+
"""
|
|
60
|
+
See `CBLAS_DIAG`.
|
|
61
|
+
"""
|
|
62
|
+
__new__: ClassVar[Callable] = ...
|
|
63
|
+
NonUnit: ClassVar[DIAG] = ...
|
|
64
|
+
Unit: ClassVar[DIAG] = ...
|
|
65
|
+
_generate_next_value_: ClassVar[Callable] = ...
|
|
66
|
+
_member_map_: ClassVar[dict] = ...
|
|
67
|
+
_member_names_: ClassVar[list] = ...
|
|
68
|
+
_member_type_: ClassVar[type[int]] = ...
|
|
69
|
+
_value2member_map_: ClassVar[dict] = ...
|
|
70
|
+
|
|
71
|
+
class ORDER(enum.IntEnum):
|
|
72
|
+
"""
|
|
73
|
+
See `CBLAS_ORDER`.
|
|
74
|
+
"""
|
|
75
|
+
__new__: ClassVar[Callable] = ...
|
|
76
|
+
ColMajor: ClassVar[ORDER] = ...
|
|
77
|
+
RowMajor: ClassVar[ORDER] = ...
|
|
78
|
+
_generate_next_value_: ClassVar[Callable] = ...
|
|
79
|
+
_member_map_: ClassVar[dict] = ...
|
|
80
|
+
_member_names_: ClassVar[list] = ...
|
|
81
|
+
_member_type_: ClassVar[type[int]] = ...
|
|
82
|
+
_value2member_map_: ClassVar[dict] = ...
|
|
83
|
+
|
|
84
|
+
class SIDE(enum.IntEnum):
|
|
85
|
+
"""
|
|
86
|
+
See `CBLAS_SIDE`.
|
|
87
|
+
"""
|
|
88
|
+
__new__: ClassVar[Callable] = ...
|
|
89
|
+
Left: ClassVar[SIDE] = ...
|
|
90
|
+
Right: ClassVar[SIDE] = ...
|
|
91
|
+
_generate_next_value_: ClassVar[Callable] = ...
|
|
92
|
+
_member_map_: ClassVar[dict] = ...
|
|
93
|
+
_member_names_: ClassVar[list] = ...
|
|
94
|
+
_member_type_: ClassVar[type[int]] = ...
|
|
95
|
+
_value2member_map_: ClassVar[dict] = ...
|
|
96
|
+
|
|
97
|
+
class TRANSPOSE(enum.IntEnum):
|
|
98
|
+
"""
|
|
99
|
+
See `CBLAS_TRANSPOSE`.
|
|
100
|
+
"""
|
|
101
|
+
__new__: ClassVar[Callable] = ...
|
|
102
|
+
ConjTrans: ClassVar[TRANSPOSE] = ...
|
|
103
|
+
NoTrans: ClassVar[TRANSPOSE] = ...
|
|
104
|
+
Trans: ClassVar[TRANSPOSE] = ...
|
|
105
|
+
_generate_next_value_: ClassVar[Callable] = ...
|
|
106
|
+
_member_map_: ClassVar[dict] = ...
|
|
107
|
+
_member_names_: ClassVar[list] = ...
|
|
108
|
+
_member_type_: ClassVar[type[int]] = ...
|
|
109
|
+
_value2member_map_: ClassVar[dict] = ...
|
|
110
|
+
|
|
111
|
+
class UPLO(enum.IntEnum):
|
|
112
|
+
"""
|
|
113
|
+
See `CBLAS_UPLO`.
|
|
114
|
+
"""
|
|
115
|
+
__new__: ClassVar[Callable] = ...
|
|
116
|
+
Lower: ClassVar[UPLO] = ...
|
|
117
|
+
Upper: ClassVar[UPLO] = ...
|
|
118
|
+
_generate_next_value_: ClassVar[Callable] = ...
|
|
119
|
+
_member_map_: ClassVar[dict] = ...
|
|
120
|
+
_member_names_: ClassVar[list] = ...
|
|
121
|
+
_member_type_: ClassVar[type[int]] = ...
|
|
122
|
+
_value2member_map_: ClassVar[dict] = ...
|
|
Binary file
|