| /aosp_15_r20/external/pytorch/aten/src/ATen/native/sparse/cuda/ |
| H A D | SparseCUDABlas.cpp | 103 T *b, int64_t ldb, T *beta, T *c, int64_t ldc, in _csrmm2()
205 T *b, int64_t ldb, T beta, T *c, int64_t ldc) in csrmm2()
214 float *b, int64_t ldb, float beta, float *c, int64_t ldc) in csrmm2()
223 double *b, int64_t ldb, double beta, double *c, int64_t ldc) in csrmm2()
232 …c10::complex<float> *b, int64_t ldb, c10::complex<float> beta, c10::complex<float> *c, int64_t ldc) in csrmm2()
249 …c10::complex<double> *b, int64_t ldb, c10::complex<double> beta, c10::complex<double> *c, int64_t … in csrmm2()
264 void adjustLd(char transb, int64_t m, int64_t n, int64_t k, int64_t *ldb, int64_t *ldc) in adjustLd()
283 …onst float *csrvala, int *csrrowptra, int *csrcolinda, const float *b, int64_t ldb, const float *b… in Scsrmm2()
305 …st double *csrvala, int *csrrowptra, int *csrcolinda, const double *b, int64_t ldb, const double *… in Dcsrmm2()
330 …*csrvala, int *csrrowptra, int *csrcolinda, const complex_target_t *b, int64_t ldb, const complex_… in Ccsrmm2()
[all …]
|
| /aosp_15_r20/external/tensorflow/tensorflow/stream_executor/rocm/ |
| H A D | rocm_blas.cc | 393 int lda, const DeviceMemoryBase &b, int ldb, in DoBlasGemm()
557 int lda, const DeviceMemory<Eigen::half> &b, int ldb, float beta, in DoBlasGemmWithProfiling()
568 const DeviceMemory<float> &b, int ldb, float beta, DeviceMemory<float> *c, in DoBlasGemmWithProfiling()
578 const DeviceMemory<double> &b, int ldb, double beta, in DoBlasGemmWithProfiling()
590 const DeviceMemory<std::complex<float>> &b, int ldb, in DoBlasGemmWithProfiling()
602 const DeviceMemory<std::complex<double>> &b, int ldb, in DoBlasGemmWithProfiling()
624 int lda, const DeviceMemory<T> &b, int ldb, const ParamType &beta, in DoBlasGemmWithProfilingImpl()
633 blas::DataType type_b, int ldb, const void *beta, DeviceMemoryBase *c, in DoBlasGemmWithAlgorithm()
644 blas::DataType type_b, int ldb, int64_t stride_b, const void *beta, in DoBlasGemmStridedBatchedWithAlgorithm()
769 const absl::Span<DeviceMemory<T> *const> &b_ptrs_to_wrappers, int ldb, in DoBlasGemmBatchedInternal()
[all …]
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/cpu/ |
| H A D | BlasKernel.cpp | 108 int64_t ldb, in gemm_notrans_()
144 int64_t ldb, in gemm_notrans_()
170 const scalar_t *b, int64_t ldb, in gemm_transa_()
202 int64_t ldb, in gemm_transb_impl()
235 int64_t ldb, in gemm_transb_()
257 int64_t ldb, in gemm_transb_()
309 const scalar_t *b, int64_t ldb, in gemm_transab_()
339 int64_t ldb, in gemm_notrans_()
387 const at::Half *b, int64_t ldb, in gemm_transa_()
419 const at::BFloat16 *b, int64_t ldb, in gemm_transa_()
[all …]
|
| H A D | int8mm_kernel.cpp | 38 int ldb, in tinygemm_kernel()
233 int ldb, in tinygemm_kernel_()
275 int ldb, in tinygemm_kernel()
288 int ldb, in tinygemm_kernel()
301 int ldb, in tinygemm_kernel()
316 int ldb, in tinygemm_kernel()
|
| H A D | int4mm_kernel.cpp | 59 int ldb, in tinygemm_kernel()
209 int ldb, in tinygemm_kernel()
386 int ldb, in tinygemm_kernel_()
434 int ldb, in tinygemm_kernel()
448 int ldb, in tinygemm_kernel()
462 int ldb, in tinygemm_kernel()
520 int ldb, in tinygemm_kernel()
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/ |
| 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()
132 const double *b, int64_t ldb, in gemm()
175 const float *b, int64_t ldb, in gemm()
223 const c10::complex<double> *b, int64_t ldb, in gemm()
266 const c10::complex<float> *b, int64_t ldb, in gemm()
309 const at::BFloat16 *b, int64_t ldb, in gemm()
349 const at::Half *b, int64_t ldb, in gemm()
368 const at::BFloat16 *b, int64_t ldb, in gemm()
419 const at::Half *b, int64_t ldb, in gemm()
[all …]
|
| H A D | BatchLinearAlgebra.cpp | 807 …, int n, int nrhs, c10::complex<double> *a, int lda, c10::complex<double> *b, int ldb, int *info) { in lapackCholeskySolve()
811 …lo, int n, int nrhs, c10::complex<float> *a, int lda, c10::complex<float> *b, int ldb, int *info) { in lapackCholeskySolve()
815 …leskySolve<double>(char uplo, int n, int nrhs, double *a, int lda, double *b, int ldb, int *info) { in lapackCholeskySolve()
819 …CholeskySolve<float>(char uplo, int n, int nrhs, float *a, int lda, float *b, int ldb, int *info) { in lapackCholeskySolve()
1128 int ldb, in lapackLdlSolveSymmetric()
1142 int ldb, in lapackLdlSolveSymmetric()
1156 int ldb, in lapackLdlSolveSymmetric()
1179 int ldb, in lapackLdlSolveSymmetric()
1202 int ldb, in lapackLdlSolveHermitian()
1216 int ldb, in lapackLdlSolveHermitian()
[all …]
|
| H A D | Unfold3d.cpp | 22 void MatCopy(int64_t M, int64_t N, int64_t lda, int64_t ldb, const T* A, T* B) { in MatCopy()
34 int64_t ldb, in MatCopy()
82 int64_t ldb, in MatCopy()
93 int64_t ldb, in MatCopy()
105 int64_t ldb, in MatCopy()
118 int64_t ldb, in MatCopy()
|
| H A D | ConvolutionMM2d.cpp | 252 const int64_t ldb = k; in slow_conv2d_update_output_frame() local
270 const int64_t ldb = k; in slow_conv2d_update_output_frame() local
307 const int64_t ldb = k; in slow_conv2d_backward_update_grad_input_frame() local
325 const int64_t ldb = n; in slow_conv2d_backward_update_grad_input_frame() local
449 const int64_t ldb = n; in slow_conv2d_backward_weight_frame() local
467 const int64_t ldb = k; in slow_conv2d_backward_weight_frame() local
|
| /aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/stream_executor/cuda/ |
| H A D | cuda_blas.cc | 612 int lda, const DeviceMemoryBase &b, int ldb, in DoBlasInternalImpl()
792 int lda, const DeviceMemory<Eigen::half> &b, int ldb, float beta, in DoBlasInternalImpl()
803 const DeviceMemory<float> &b, int ldb, float beta, DeviceMemory<float> *c, in DoBlasInternalImpl()
813 const DeviceMemory<double> &b, int ldb, double beta, in DoBlasInternalImpl()
825 const DeviceMemory<std::complex<float>> &b, int ldb, in DoBlasInternalImpl()
837 const DeviceMemory<std::complex<double>> &b, int ldb, in DoBlasInternalImpl()
881 int lda, const DeviceMemory<T> &b, int ldb, const ParamType &beta, in DoBlasInternalImpl()
1019 blas::DataType type_b, int ldb, const void *beta, DeviceMemoryBase *c, in DoBlasInternalImpl()
1048 blas::DataType type_b, int ldb, int64_t stride_b, const void *beta, in DoBlasInternalImpl()
1191 const DeviceMemorySlice<T> &b_ptrs_to_wrappers, int ldb, Scalar beta, in DoBlasInternalImpl()
[all …]
|
| /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 …nst c10::complex<double>** A, const MKL_INT lda, const c10::complex<double>** B, const MKL_INT ldb, 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/executorch/kernels/optimized/blas/ |
| H A D | BlasKernel.h | 76 int64_t ldb, in gemm_notrans_()
113 int64_t ldb, in gemm_notrans_()
139 const scalar_t *b, int64_t ldb, in gemm_transa_()
221 int64_t ldb, in gemm_transb_()
258 int64_t ldb, in gemm_transb_()
284 const scalar_t *b, int64_t ldb, in gemm_transab_()
|
| H A D | CPUBlas.cpp | 51 int64_t *lda, int64_t *ldb, int64_t *ldc) { in normalize_last_dims()
80 const double *b, int64_t ldb, in gemm()
120 const float *b, int64_t ldb, in gemm()
160 const Half *b, int64_t ldb, in gemm()
183 const BFloat16 *b, int64_t ldb, in gemm()
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/mkldnn/ |
| H A D | Matmul.cpp | 40 const c10::BFloat16 *b, int64_t ldb, in mkldnn_bf16_gemm()
51 const c10::Half *b, int64_t ldb, in mkldnn_fp16_gemm()
61 const float *b, int64_t ldb, in mkldnn_bf32_gemm()
123 const scalar_t *b_data, int64_t ldb, in mkldnn_gemm()
199 const c10::BFloat16 *b, int64_t ldb, in mkldnn_bf16_gemm()
210 const c10::Half *b, int64_t ldb, in mkldnn_fp16_gemm()
221 const float *b, int64_t ldb, in mkldnn_bf32_gemm()
469 const int ldb = transb == 'T' ? mat2.stride(1) : mat2.stride(0); in _mkldnn_gemm_i8i8i32_with_blas() local
|
| /aosp_15_r20/external/cblas/testing/ |
| H A D | c_zblas3.c | 16 CBLAS_TEST_ZOMPLEX *b, int *ldb, CBLAS_TEST_ZOMPLEX *beta, in F77_zgemm()
92 CBLAS_TEST_ZOMPLEX *b, int *ldb, CBLAS_TEST_ZOMPLEX *beta, in F77_zhemm()
156 CBLAS_TEST_ZOMPLEX *b, int *ldb, CBLAS_TEST_ZOMPLEX *beta, in F77_zsymm()
322 CBLAS_TEST_ZOMPLEX *b, int *ldb, double *beta, in F77_zher2k()
386 CBLAS_TEST_ZOMPLEX *b, int *ldb, CBLAS_TEST_ZOMPLEX *beta, 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 | 16 CBLAS_TEST_COMPLEX *b, int *ldb, CBLAS_TEST_COMPLEX *beta, in F77_cgemm()
92 CBLAS_TEST_COMPLEX *b, int *ldb, CBLAS_TEST_COMPLEX *beta, in F77_chemm()
156 CBLAS_TEST_COMPLEX *b, int *ldb, CBLAS_TEST_COMPLEX *beta, in F77_csymm()
322 CBLAS_TEST_COMPLEX *b, int *ldb, float *beta, in F77_cher2k()
386 CBLAS_TEST_COMPLEX *b, int *ldb, CBLAS_TEST_COMPLEX *beta, 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()
176 float *alpha, float *a, int *lda, float *b, int *ldb, in F77_ssyr2k()
232 int *ldb) { in F77_strmm()
283 int *ldb) { 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()
179 double *alpha, double *a, int *lda, double *b, int *ldb, in F77_dsyr2k()
235 int *ldb) { in F77_dtrmm()
286 int *ldb) { in F77_dtrsm()
|
| /aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/stream_executor/ |
| H A D | stream.h | 757 const DeviceMemory<InputType> &b, int ldb, in ThenBlasGemm()
771 const DeviceMemory<InputType> &b, int ldb, in ThenBlasGemm()
781 const DeviceMemory<InputType> &b, int ldb, in ThenBlasGemm()
819 const DeviceMemory<InputType> &b, int ldb, in ThenBlasGemm()
868 const DeviceMemory<InputType> &b, int ldb, DeviceMemory<OutputType> *c, in ThenBlasGemmWithAlgorithm()
883 const DeviceMemory<InputType> &b, int ldb, ConstantType beta, in ThenBlasGemmWithAlgorithm()
921 int64_t stride_a, const DeviceMemory<InputType> &b, int ldb, in ThenBlasGemmStridedBatchedWithAlgorithm()
1036 int64_t stride_a, const DeviceMemory<InputType> &b, int ldb, in ThenBlasGemmStridedBatched()
|
| H A D | stream.cc | 1454 const DeviceMemory<Eigen::half> &b, int ldb, float beta, in ThenBlasGemmWithProfiling()
1474 const DeviceMemory<float> &b, int ldb, float beta, DeviceMemory<float> *c, in ThenBlasGemmWithProfiling()
1493 const DeviceMemory<double> &b, int ldb, double beta, in ThenBlasGemmWithProfiling()
1514 const DeviceMemory<std::complex<float>> &b, int ldb, in ThenBlasGemmWithProfiling()
1536 const DeviceMemory<std::complex<double>> &b, int ldb, in ThenBlasGemmWithProfiling()
1558 DeviceMemory<float> *b, int ldb) { in ThenBlasTrsm()
1574 DeviceMemory<double> *b, int ldb) { in ThenBlasTrsm()
1591 int ldb) { in ThenBlasTrsm()
1609 int ldb) { in ThenBlasTrsm()
1626 DeviceMemory<float *> *bs, int ldb, in ThenBlasTrsmBatched()
[all …]
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/nested/cuda/ |
| H A D | NestedTensorMatmul.cu | 52 const std::vector<int64_t>& ldb, in gemm_grouped_cuda_internal()
184 const std::vector<int64_t>& ldb, in group_gemm_dispatch()
198 const std::vector<int64_t>& ldb, in group_gemm_dispatch()
224 const std::vector<int64_t>& ldb, in group_gemm_dispatch()
349 std::vector<int64_t> ldb(ntensors); in bmm_nested_cuda() local
|
| /aosp_15_r20/external/ComputeLibrary/src/core/NEON/kernels/arm_gemm/ |
| H A D | quantize_wrapper.hpp | 80 void col_sums_pretransposed(const To *B, const int ldb, const int B_multi_stride) { in col_sums_pretransposed()
122 const To *B, const int ldb, const int B_multi_stride, in set_arrays()
182 …void requantize_bias(void *in_buffer, const To *B, const int ldb, const int B_multi_stride) overri… in requantize_bias()
187 …void pretranspose_B_array(void *buffer, const To *B, const int ldb, const int B_multi_stride) over… in pretranspose_B_array()
|
| /aosp_15_r20/external/gemmlowp/eight_bit_int_gemm/ |
| H A D | eight_bit_int_gemm.cc | 71 const std::uint8_t* b, std::int32_t b_offset, int ldb, in EightBitIntGemmImpl()
111 std::int32_t b_offset, int ldb, std::int32_t* c, in EightBitIntGemmInt32Impl()
218 int m, int n, int k, int lda, int ldb, int ldc, in CanHandleMetaFastpath()
304 std::int32_t b_offset, int ldb, std::uint8_t* c, in EightBitIntGemm()
342 std::int32_t ldb, float* c, float c_offset, in EightBitIntGemm()
|
| /aosp_15_r20/external/eigen/bench/ |
| H A D | bench_gemm.cpp | 90 int lda = a.outerStride(); int ldb = b.outerStride(); int ldc = c.rows(); in blas_gemm() local
102 int lda = a.outerStride(); int ldb = b.outerStride(); int ldc = c.rows(); in blas_gemm() local
114 int lda = a.outerStride(); int ldb = b.outerStride(); int ldc = c.rows(); in blas_gemm() local
126 int lda = a.outerStride(); int ldb = b.outerStride(); int ldc = c.rows(); in blas_gemm() local
|
| /aosp_15_r20/frameworks/rs/cpu_ref/ |
| H A D | rsCpuIntrinsicBLAS.cpp | 69 int* ldb, in initABC()
154 int lda = 0, ldb = 0, ldc = 0; in walk_tiled_gemm() local
257 int lda = 0, ldb = 0, ldc = 0; in invokeForEach() local
835 const uint8_t* b, uint8_t b_offset, size_t ldb, in kernelBNNM()
|