| /aosp_15_r20/external/pytorch/aten/src/ATen/native/cuda/linalg/ |
| H A D | CUDASolver.cpp | 87 …cusolverDnHandle_t handle, int n, int nrhs, double* dA, int lda, int* ipiv, double* ret, int ldb, … in getrs()
94 …cusolverDnHandle_t handle, int n, int nrhs, float* dA, int lda, int* ipiv, float* ret, int ldb, in… in getrs()
105 int lda, in getrs()
130 int lda, in getrs()
282 …cusolverDnHandle_t handle, cusolverEigMode_t jobz, int econ, int m, int n, float *A, int lda, floa… in gesvdj_buffersize()
290 …cusolverDnHandle_t handle, cusolverEigMode_t jobz, int econ, int m, int n, double *A, int lda, dou… in gesvdj_buffersize()
298 … handle, cusolverEigMode_t jobz, int econ, int m, int n, c10::complex<float> *A, int lda, float *S, in gesvdj_buffersize()
313 …andle, cusolverEigMode_t jobz, int econ, int m, int n, c10::complex<double> *A, int lda, double *S, in gesvdj_buffersize()
329 …cusolverDnHandle_t handle, cusolverEigMode_t jobz, int econ, int m, int n, float* A, int lda, floa… in gesvdj()
337 …cusolverDnHandle_t handle, cusolverEigMode_t jobz, int econ, int m, int n, double* A, int lda, dou… in gesvdj()
[all …]
|
| H A D | BatchLinearAlgebraLib.cpp | 264 int lda = std::max<int>(1, m); in apply_svd_cusolver_gesvd() local
381 int lda = A.stride(-1); in apply_svd_cusolver_gesvdj() local
448 int lda = A.stride(-1); in apply_svd_cusolver_gesvdjBatched() local
723 const int64_t lda = std::max<int64_t>(1, n); in apply_cholesky_cusolver_potrf_looped() local
792 const int lda = std::max<int>(1, n); in apply_cholesky_cusolver_potrfBatched() local
828 const int64_t lda = std::max<int64_t>(1, n); in apply_cholesky_cusolver_potrs() local
884 const int64_t lda = std::max<int64_t>(1, n); in apply_cholesky_cusolver_potrsBatched() local
971 int64_t lda = std::max<int64_t>(1, m); in apply_geqrf() local
1092 auto lda = std::max<int>(1, left ? m : n); in apply_ormqr() local
1159 auto lda = std::max<int>(1, m); in apply_orgqr() local
[all …]
|
| H A D | BatchLinearAlgebraLibBlas.cpp | 84 auto lda = std::max<int>(1, m); in apply_geqrf_batched() local
114 auto lda = cuda_int_cast(std::max<int>(1, n), "lda"); in apply_lu_factor_batched_cublas() local
140 auto lda = cuda_int_cast(std::max<int>(1, m), "lda"); in apply_lu_solve_batched_cublas() local
175 auto lda = std::max<int>(1, cuda_int_cast(A.size(-2), "lda")); in apply_triangular_solve() local
205 auto lda = std::max<int>(1, cuda_int_cast(A.size(-2), "lda")); in apply_triangular_solve_batched() local
254 auto lda = std::max<int>(1, m); in apply_gels_batched() local
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/ |
| H A D | BatchLinearAlgebra.cpp | 791 template<> void lapackLu<c10::complex<double>>(int m, int n, c10::complex<double> *a, int lda, int … in lapackLu()
795 template<> void lapackLu<c10::complex<float>>(int m, int n, c10::complex<float> *a, int lda, int *i… in lapackLu()
799 template<> void lapackLu<double>(int m, int n, double *a, int lda, int *ipiv, int *info) { in lapackLu()
803 template<> void lapackLu<float>(int m, int n, float *a, int lda, int *ipiv, int *info) { in lapackLu()
807 …0::complex<double>>(char uplo, int n, int nrhs, c10::complex<double> *a, int lda, c10::complex<dou… in lapackCholeskySolve()
811 …c10::complex<float>>(char uplo, int n, int nrhs, c10::complex<float> *a, int lda, c10::complex<flo… in lapackCholeskySolve()
815 template<> void lapackCholeskySolve<double>(char uplo, int n, int nrhs, double *a, int lda, double … in lapackCholeskySolve()
819 template<> void lapackCholeskySolve<float>(char uplo, int n, int nrhs, float *a, int lda, float *b,… in lapackCholeskySolve()
823 …packCholesky<c10::complex<double>>(char uplo, int n, c10::complex<double> *a, int lda, int *info) { in lapackCholesky()
827 …lapackCholesky<c10::complex<float>>(char uplo, int n, c10::complex<float> *a, int lda, int *info) { in lapackCholesky()
[all …]
|
| H A D | BlasKernel.cpp | 142 C10_UNUSED int64_t lda, in gemv_use_fast_path()
155 … C10_UNUSED const scalar_t *alpha, C10_UNUSED const scalar_t *a, C10_UNUSED const int *lda, in gemv_fast_path()
190 …>(C10_UNUSED char trans, int64_t m, int64_t n, C10_UNUSED float alpha, int64_t lda, int64_t incx, … in gemv_use_fast_path()
197 …(C10_UNUSED char trans, int64_t m, int64_t n, C10_UNUSED double alpha, int64_t lda, int64_t incx, … in gemv_use_fast_path()
202 …s, const int *m, const int *n, const double *alpha, const double *a, const int *lda, const double … in gemv_fast_path()
207 …ans, const int *m, const int *n, const float *alpha, const float *a, const int *lda, const float *… in gemv_fast_path()
232 C10_UNUSED int64_t lda, in gemv_use_fast_path()
246 C10_UNUSED int64_t lda, in gemv_use_fast_path()
347 …6_arith_by_dot_products(const int m, const int n, const float16_t* a, const int lda, const float16… in fp16_gemv_trans_fp16_arith_by_dot_products()
524 …2_arith_by_dot_products(const int m, const int n, const float16_t* a, const int lda, const float16… in fp16_gemv_trans_fp32_arith_by_dot_products()
[all …]
|
| H A D | CPUBlas.cpp | 61 int64_t *lda, int64_t *ldb, int64_t *ldc) { in normalize_last_dims()
89 int64_t lda, int64_t ldb, int64_t ldc) { in use_blas_gemm()
131 const double *a, int64_t lda, in gemm()
174 const float *a, int64_t lda, in gemm()
222 const c10::complex<double> *a, int64_t lda, in gemm()
265 const c10::complex<float> *a, int64_t lda, in gemm()
308 const at::BFloat16 *a, int64_t lda, in gemm()
348 const at::Half *a, int64_t lda, in gemm()
367 const at::BFloat16 *a, int64_t lda, in gemm()
418 const at::Half *a, int64_t lda, in gemm()
[all …]
|
| /aosp_15_r20/external/tensorflow/tensorflow/stream_executor/rocm/ |
| H A D | rocm_blas.cc | 321 int lda, const DeviceMemory<float> &x, int incx, in DoBlasGemv()
332 const DeviceMemory<double> &a, int lda, in DoBlasGemv()
344 const DeviceMemory<std::complex<float>> &a, int lda, in DoBlasGemv()
357 const DeviceMemory<std::complex<double>> &a, int lda, in DoBlasGemv()
370 int lda, const DeviceMemory<float> &x, int incx, in DoBlasSbmv()
380 const DeviceMemory<double> &a, int lda, in DoBlasSbmv()
393 int lda, const DeviceMemoryBase &b, int ldb, in DoBlasGemm()
514 const DeviceMemory<float> &a, int lda, const DeviceMemory<float> &x, in DoBlasGemvWithProfiling()
524 const DeviceMemory<double> &a, int lda, const DeviceMemory<double> &x, in DoBlasGemvWithProfiling()
535 int lda, const DeviceMemory<std::complex<float>> &x, int incx, in DoBlasGemvWithProfiling()
[all …]
|
| /aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/stream_executor/cuda/ |
| H A D | cuda_blas.cc | 538 int lda, const DeviceMemory<float> &x, int incx, in DoBlasInternalImpl()
548 const DeviceMemory<double> &a, int lda, in DoBlasInternalImpl()
559 const DeviceMemory<std::complex<float>> &a, int lda, in DoBlasInternalImpl()
574 const DeviceMemory<std::complex<double>> &a, int lda, in DoBlasInternalImpl()
589 int lda, const DeviceMemory<float> &x, int incx, in DoBlasInternalImpl()
599 const DeviceMemory<double> &a, int lda, in DoBlasInternalImpl()
612 int lda, const DeviceMemoryBase &b, int ldb, in DoBlasInternalImpl()
749 const DeviceMemory<float> &a, int lda, const DeviceMemory<float> &x, in DoBlasInternalImpl()
759 const DeviceMemory<double> &a, int lda, const DeviceMemory<double> &x, in DoBlasInternalImpl()
770 int lda, const DeviceMemory<std::complex<float>> &x, int incx, in DoBlasInternalImpl()
[all …]
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/cpu/ |
| H A D | BlasKernel.cpp | 54 void scale_(int64_t m, int64_t n, opmath_t alpha, scalar_t *a, int64_t lda) { in scale_()
106 int64_t lda, in gemm_notrans_()
142 int64_t lda, in gemm_notrans_()
169 const scalar_t *a, int64_t lda, in gemm_transa_()
200 int64_t lda, in gemm_transb_impl()
233 int64_t lda, in gemm_transb_()
255 int64_t lda, in gemm_transb_()
308 const scalar_t *a, int64_t lda, in gemm_transab_()
337 int64_t lda, in gemm_notrans_()
386 const at::Half *a, int64_t lda, in gemm_transa_()
[all …]
|
| /aosp_15_r20/external/tensorflow/tensorflow/core/util/ |
| H A D | cuda_solvers.cc | 349 const Scalar* A, int lda, in GeamImpl()
381 cublasFillMode_t uplo, int n, Scalar* A, int lda, in PotrfImpl()
414 const Scalar* const host_a_dev_ptrs[], int lda, in PotrfBatchedImpl()
450 int n, Scalar* A, int lda, int* dev_pivots, in GetrfImpl()
483 const Scalar* A, int lda, const int* pivots, in GetrsImpl()
509 int n, Scalar* A, int lda, Scalar* tau, in GeqrfImpl()
543 int lda, const Scalar* dev_tau, Scalar* dev_c, in UnmqrImpl()
586 int n, int k, Scalar* dev_a, int lda, in UngqrImpl()
625 int n, Scalar* dev_A, int lda, in HeevdImpl()
679 int n, Scalar* A, int lda, Scalar* S, Scalar* U, in GesvdImpl()
[all …]
|
| /aosp_15_r20/external/cblas/testing/ |
| H A D | c_cblas2.c | 13 CBLAS_TEST_COMPLEX *a, int *lda, const void *x, int *incx, in F77_cgemv()
42 CBLAS_TEST_COMPLEX *alpha, CBLAS_TEST_COMPLEX *a, int *lda, in F77_cgbmv()
90 CBLAS_TEST_COMPLEX *a, int *lda){ in F77_cgeru()
119 CBLAS_TEST_COMPLEX *a, int *lda) { in F77_cgerc()
146 CBLAS_TEST_COMPLEX *a, int *lda, CBLAS_TEST_COMPLEX *x, in F77_chemv()
176 CBLAS_TEST_COMPLEX *alpha, CBLAS_TEST_COMPLEX *a, int *lda, in F77_chbmv()
296 int *n, int *k, CBLAS_TEST_COMPLEX *a, int *lda, CBLAS_TEST_COMPLEX *x, in F77_ctbmv()
359 int *n, int *k, CBLAS_TEST_COMPLEX *a, int *lda, CBLAS_TEST_COMPLEX *x, in F77_ctbsv()
533 int *n, CBLAS_TEST_COMPLEX *a, int *lda, CBLAS_TEST_COMPLEX *x, in F77_ctrmv()
562 int *n, CBLAS_TEST_COMPLEX *a, int *lda, CBLAS_TEST_COMPLEX *x, in F77_ctrsv()
[all …]
|
| H A D | c_zblas2.c | 13 CBLAS_TEST_ZOMPLEX *a, int *lda, const void *x, int *incx, in F77_zgemv()
42 CBLAS_TEST_ZOMPLEX *alpha, CBLAS_TEST_ZOMPLEX *a, int *lda, in F77_zgbmv()
90 CBLAS_TEST_ZOMPLEX *a, int *lda){ in F77_zgeru()
119 CBLAS_TEST_ZOMPLEX *a, int *lda) { in F77_zgerc()
146 CBLAS_TEST_ZOMPLEX *a, int *lda, CBLAS_TEST_ZOMPLEX *x, in F77_zhemv()
176 CBLAS_TEST_ZOMPLEX *alpha, CBLAS_TEST_ZOMPLEX *a, int *lda, in F77_zhbmv()
296 int *n, int *k, CBLAS_TEST_ZOMPLEX *a, int *lda, CBLAS_TEST_ZOMPLEX *x, in F77_ztbmv()
359 int *n, int *k, CBLAS_TEST_ZOMPLEX *a, int *lda, CBLAS_TEST_ZOMPLEX *x, in F77_ztbsv()
533 int *n, CBLAS_TEST_ZOMPLEX *a, int *lda, CBLAS_TEST_ZOMPLEX *x, in F77_ztrmv()
562 int *n, CBLAS_TEST_ZOMPLEX *a, int *lda, CBLAS_TEST_ZOMPLEX *x, in F77_ztrsv()
[all …]
|
| H A D | c_dblas2.c | 12 double *a, int *lda, double *x, int *incx, double *beta, in F77_dgemv()
39 double *y, int *incy, double *a, int *lda ) { in F77_dger()
64 int *n, double *a, int *lda, double *x, int *incx) { in F77_dtrmv()
92 int *n, double *a, int *lda, double *x, int *incx ) { in F77_dtrsv()
116 int *lda, double *x, int *incx, double *beta, double *y, in F77_dsymv()
140 int *incx, double *a, int *lda) { in F77_dsyr()
164 int *incx, double *y, int *incy, double *a, int *lda) { in F77_dsyr2()
188 double *alpha, double *a, int *lda, double *x, int *incx, in F77_dgbmv()
226 int *n, int *k, double *a, int *lda, double *x, int *incx) { in F77_dtbmv()
272 int *n, int *k, double *a, int *lda, double *x, int *incx) { in F77_dtbsv()
[all …]
|
| H A D | c_sblas2.c | 12 float *a, int *lda, float *x, int *incx, float *beta, in F77_sgemv()
39 float *y, int *incy, float *a, int *lda ) { in F77_sger()
64 int *n, float *a, int *lda, float *x, int *incx) { in F77_strmv()
92 int *n, float *a, int *lda, float *x, int *incx ) { in F77_strsv()
116 int *lda, float *x, int *incx, float *beta, float *y, in F77_ssymv()
140 int *incx, float *a, int *lda) { in F77_ssyr()
164 int *incx, float *y, int *incy, float *a, int *lda) { in F77_ssyr2()
188 float *alpha, float *a, int *lda, float *x, int *incx, in F77_sgbmv()
226 int *n, int *k, float *a, int *lda, float *x, int *incx) { in F77_stbmv()
272 int *n, int *k, float *a, int *lda, float *x, int *incx) { in F77_stbsv()
[all …]
|
| H A D | c_zblas3.c | 15 int *k, CBLAS_TEST_ZOMPLEX *alpha, CBLAS_TEST_ZOMPLEX *a, int *lda, in F77_zgemm()
91 CBLAS_TEST_ZOMPLEX *alpha, CBLAS_TEST_ZOMPLEX *a, int *lda, in F77_zhemm()
155 CBLAS_TEST_ZOMPLEX *alpha, CBLAS_TEST_ZOMPLEX *a, int *lda, in F77_zsymm()
210 double *alpha, CBLAS_TEST_ZOMPLEX *a, int *lda, in F77_zherk()
266 CBLAS_TEST_ZOMPLEX *alpha, CBLAS_TEST_ZOMPLEX *a, int *lda, in F77_zsyrk()
321 CBLAS_TEST_ZOMPLEX *alpha, CBLAS_TEST_ZOMPLEX *a, int *lda, in F77_zher2k()
385 CBLAS_TEST_ZOMPLEX *alpha, CBLAS_TEST_ZOMPLEX *a, int *lda, in F77_zsyr2k()
450 int *lda, CBLAS_TEST_ZOMPLEX *b, int *ldb) { in F77_ztrmm()
509 int *lda, CBLAS_TEST_ZOMPLEX *b, int *ldb) { in F77_ztrsm()
|
| H A D | c_cblas3.c | 15 int *k, CBLAS_TEST_COMPLEX *alpha, CBLAS_TEST_COMPLEX *a, int *lda, in F77_cgemm()
91 CBLAS_TEST_COMPLEX *alpha, CBLAS_TEST_COMPLEX *a, int *lda, in F77_chemm()
155 CBLAS_TEST_COMPLEX *alpha, CBLAS_TEST_COMPLEX *a, int *lda, in F77_csymm()
210 float *alpha, CBLAS_TEST_COMPLEX *a, int *lda, in F77_cherk()
266 CBLAS_TEST_COMPLEX *alpha, CBLAS_TEST_COMPLEX *a, int *lda, in F77_csyrk()
321 CBLAS_TEST_COMPLEX *alpha, CBLAS_TEST_COMPLEX *a, int *lda, in F77_cher2k()
385 CBLAS_TEST_COMPLEX *alpha, CBLAS_TEST_COMPLEX *a, int *lda, in F77_csyr2k()
450 int *lda, CBLAS_TEST_COMPLEX *b, int *ldb) { in F77_ctrmm()
509 int *lda, CBLAS_TEST_COMPLEX *b, int *ldb) { in F77_ctrsm()
|
| H A D | c_sblas3.c | 13 int *k, float *alpha, float *a, int *lda, float *b, int *ldb, in F77_sgemm()
74 float *alpha, float *a, int *lda, float *b, int *ldb, in F77_ssymm()
128 float *alpha, float *a, int *lda, in F77_ssyrk()
176 float *alpha, float *a, int *lda, float *b, int *ldb, in F77_ssyr2k()
231 int *m, int *n, float *alpha, float *a, int *lda, float *b, in F77_strmm()
282 int *m, int *n, float *alpha, float *a, int *lda, float *b, in F77_strsm()
|
| H A D | c_dblas3.c | 15 int *k, double *alpha, double *a, int *lda, double *b, int *ldb, in F77_dgemm()
77 double *alpha, double *a, int *lda, double *b, int *ldb, in F77_dsymm()
131 double *alpha, double *a, int *lda, in F77_dsyrk()
179 double *alpha, double *a, int *lda, double *b, int *ldb, in F77_dsyr2k()
234 int *m, int *n, double *alpha, double *a, int *lda, double *b, in F77_dtrmm()
285 int *m, int *n, double *alpha, double *a, int *lda, double *b, in F77_dtrsm()
|
| /aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/service/gpu/ |
| H A D | cusolver_context.cc | 341 int n, int lda, in PotrfBufferSize()
383 se::DeviceMemory<float> a, int lda, in Potrf()
396 se::DeviceMemory<double> a, int lda, in Potrf()
409 se::DeviceMemory<std::complex<float>> a, int lda, in Potrf()
423 int lda, se::DeviceMemory<int> lapack_info, in Potrf()
435 se::DeviceMemory<float*> as, int lda, in PotrfBatched()
447 se::DeviceMemory<double*> as, int lda, in PotrfBatched()
460 int lda, in PotrfBatched()
473 se::DeviceMemory<std::complex<double>*> as, int lda, in PotrfBatched()
|
| /aosp_15_r20/external/executorch/kernels/optimized/blas/ |
| H A D | BlasKernel.h | 23 void scale_(int64_t m, int64_t n, opmath_t alpha, scalar_t* a, int64_t lda) { in scale_()
74 int64_t lda, in gemm_notrans_()
111 int64_t lda, in gemm_notrans_()
138 const scalar_t *a, int64_t lda, in gemm_transa_()
219 int64_t lda, in gemm_transb_()
256 int64_t lda, in gemm_transb_()
283 const scalar_t *a, int64_t lda, in gemm_transab_()
|
| H A D | CPUBlas.cpp | 51 int64_t *lda, int64_t *ldb, int64_t *ldc) { in normalize_last_dims()
79 const double *a, int64_t lda, in gemm()
119 const float *a, int64_t lda, in gemm()
159 const Half *a, int64_t lda, in gemm()
182 const BFloat16 *a, int64_t lda, in gemm()
|
| /aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/stream_executor/ |
| H A D | stream.cc | 1257 float alpha, const DeviceMemory<float> &a, int lda, in ThenBlasGemv()
1274 int lda, const DeviceMemory<double> &x, int incx, in ThenBlasGemv()
1291 int lda, in ThenBlasGemv()
1311 int lda, in ThenBlasGemv()
1329 float alpha, const DeviceMemory<float> &a, int lda, in ThenBlasSbmv()
1345 int lda, const DeviceMemory<double> &x, int incx, in ThenBlasSbmv()
1378 const DeviceMemory<float> &a, int lda, const DeviceMemory<float> &x, in ThenBlasGemvWithProfiling()
1395 const DeviceMemory<double> &a, int lda, const DeviceMemory<double> &x, in ThenBlasGemvWithProfiling()
1413 const DeviceMemory<std::complex<float>> &a, int lda, in ThenBlasGemvWithProfiling()
1433 const DeviceMemory<std::complex<double>> &a, int lda, in ThenBlasGemvWithProfiling()
[all …]
|
| H A D | stream.h | 756 const DeviceMemory<InputType> &a, int lda, in ThenBlasGemm()
770 const DeviceMemory<InputType> &a, int lda, in ThenBlasGemm()
780 const DeviceMemory<InputType> &a, int lda, in ThenBlasGemm()
818 const DeviceMemory<InputType> &a, int lda, in ThenBlasGemm()
867 uint64_t k, const DeviceMemory<InputType> &a, int lda, in ThenBlasGemmWithAlgorithm()
882 uint64_t k, ConstantType alpha, const DeviceMemory<InputType> &a, int lda, in ThenBlasGemmWithAlgorithm()
920 uint64_t k, ConstantType alpha, const DeviceMemory<InputType> &a, int lda, in ThenBlasGemmStridedBatchedWithAlgorithm()
1035 uint64_t k, ConstantType alpha, const DeviceMemory<InputType> &a, int lda, in ThenBlasGemmStridedBatched()
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/mkl/ |
| H A D | LinearAlgebra.cpp | 13 const float** A, const MKL_INT lda, const float** B, const MKL_INT ldb, const float beta, in mkl_gemm_batched()
21 const double** A, const MKL_INT lda, const double** B, const MKL_INT ldb, const double beta, in mkl_gemm_batched()
29 …const c10::complex<float>** A, const MKL_INT lda, const c10::complex<float>** B, const MKL_INT ldb, in mkl_gemm_batched()
37 …const c10::complex<double>** A, const MKL_INT lda, const c10::complex<double>** B, const MKL_INT l… in mkl_gemm_batched()
45 const c10::BFloat16* A, MKL_INT lda, const c10::BFloat16* B, MKL_INT ldb, in mkl_gemm_bf16bf16f32()
53 const c10::Half* A, int lda, const c10::Half* B, int ldb, in mkl_gemm_f16f16f32()
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/mkldnn/ |
| H A D | Matmul.cpp | 39 const c10::BFloat16 *a, int64_t lda, in mkldnn_bf16_gemm()
50 const c10::Half *a, int64_t lda, in mkldnn_fp16_gemm()
60 const float *a, int64_t lda, in mkldnn_bf32_gemm()
122 const scalar_t *a_data, int64_t lda, in mkldnn_gemm()
198 const c10::BFloat16 *a, int64_t lda, in mkldnn_bf16_gemm()
209 const c10::Half *a, int64_t lda, in mkldnn_fp16_gemm()
220 const float *a, int64_t lda, in mkldnn_bf32_gemm()
468 const int lda = transa == 'T' ? self.stride(1) : self.stride(0); in _mkldnn_gemm_i8i8i32_with_blas() local
|