g#RddlZddlTd dZd dZd dZddeddddfdZdedfd ZdS) N)*ch|tt|}t}t}t ||D]/\}}||||0t |trt||||St||||S)z builds the C++ vectors for the GPU indices and the resources. Handles the case where the resources are assigned to the list of GPUs ) rangelenGpuResourcesVector Int32Vectorzip push_back isinstance IndexBinary index_binary_cpu_to_gpu_multipleindex_cpu_to_gpu_multiple) resourcesindexcogpusvresvdeviress P/var/www/html/mpstechhub/venv/lib/python3.11/site-packages/faiss/gpu_wrappers.pyindex_cpu_to_gpu_multiple_pyrs |S^^$$   D ==DdI&&3 q s%%%@/dE2FFF(tUB???c,t||d|}|S)N)rrngpu)index_cpu_to_gpus_list)rrr index_gpus rindex_cpu_to_all_gpusr&s&u$TJJJI rc|"|dkrtt}n||dkrt|}d|D}t||||}|S)z Here we can pass list of GPU ids as a parameter or ngpu to use first n GPU's. gpus mut be a list or None. co is a GpuMultipleClonerOptions Nrc*g|]}tS)StandardGpuResources).0_s r z*index_cpu_to_gpus_list..4s 0 0 0a  ! ! 0 0 0r)r get_num_gpusr)rrrrrrs rrr+sh 42::\^^$$ ,TRZZT{{ 0 04 0 0 0C,S%TBBI rFc |j\} } |jjrd} n.|jjr |j}d} nt j|d}d} t|}|jt j krt}n,|jt j krt}ntd|j\}}|| ksJ|jjrd}n.|jjr |j}d}nt j|d}d}t|}|jt j krt}n,|jt j krt}ntd|#t j| |ft j }n&|j| |fksJ|jt j ksJt|}|#t j| |ft j}n|j| |fksJt|}|jt jkrt }n;|j|jcxkrt jkr nnt$}ntdt'}||_||_| |_||_||_||_||_||_| |_||_| |_||_||_ ||_!||_"||_#| d ks| d krtI||| | ntK||||fS) a Compute the k nearest neighbors of a vector on one GPU without constructing an index Parameters ---------- res : StandardGpuResources GPU resources to use during computation xq : array_like Query vectors, shape (nq, d) where d is appropriate for the index. `dtype` must be float32. xb : array_like Database vectors, shape (nb, d) where d is appropriate for the index. `dtype` must be float32. k : int Number of nearest neighbors. D : array_like, optional Output array for distances of the nearest neighbors, shape (nq, k) I : array_like, optional Output array for the nearest neighbors, shape (nq, k) metric : MetricType, optional Distance measure to use (either METRIC_L2 or METRIC_INNER_PRODUCT) device: int, optional Which CUDA device in the system to run the search on. -1 indicates that the current thread-local device state (via cudaGetDevice) should be used (can also be set via torch.cuda.set_device in PyTorch) Otherwise, an integer 0 <= device < numDevices indicates the GPU on which the computation should be run vectorsMemoryLimit: int, optional queriesMemoryLimit: int, optional Memory limits for vectors and queries. If not 0, the GPU will use at most this amount of memory for vectors and queries respectively. Vectors are broken up into chunks of size vectorsMemoryLimit, and queries are broken up into chunks of size queriesMemoryLimit, including the memory required for the results. Returns ------- D : array_like Distances of the nearest neighbors, shape (nq, k) I : array_like Labels of the nearest neighbors, shape (nq, k) TFfloat32dtypezxq must be f32 or f16xb must be float32 or float16NzI must be i64 or i32r)&shapeflags c_contiguous f_contiguousTnpascontiguousarrayswig_ptrr+r)DistanceDataType_F32float16DistanceDataType_F16 TypeErroremptyint64IndicesDataType_I64int32IndicesDataType_I32GpuDistanceParamsmetrickdimsvectorsvectorsRowMajor vectorType numVectorsqueriesqueriesRowMajor queryType numQueries outDistances outIndicesoutIndicesTypedeviceuse_cuvs bfKnn_tilingbfKnn)rxqxbr@DIr?rMrNvectorsMemoryLimitqueriesMemoryLimitnqd xq_row_majorxq_ptrxq_typenbd2 xb_row_majorxb_ptrxb_typeD_ptrI_ptrI_typeargss rknn_gpure;sX HEB x   T  !"I 6 6 6 b\\F x2:& RZ  &/000 XFB 7777 x   T  !"I 6 6 6 b\\F x2:& RZ  &7888y Hb!WBJ / / /w2q'!!!!w"*$$$$ QKKEy Hb!WBH - - -w2q'!!!! QKKEw"($ AG ' ' ' 'rx ' ' ' ' '$.///   DDK DFDIDL'DDODODL'DDNDODDO DDKDMA!3a!7!7S$ 24FGGGG c4 a4Krc8|j\}}|jjrd}n%|jjr |j}d}nt dt |} |jtj krt} n5|jtj krt} ntj |d}d}|j\} } | |ksJ|jjrd} n.|jjr |j}d} ntj |d}d} t |}|jtj krt}n,|jtj krt}nt d|#tj|| ftj }n&|j|| fksJ|jtj ksJt |}t}||_d|_||_||_| |_||_| |_| |_||_| |_||_||_||_t;|||S) ak Compute all pairwise distances between xq and xb on one GPU without constructing an index Parameters ---------- res : StandardGpuResources GPU resources to use during computation xq : array_like Query vectors, shape (nq, d) where d is appropriate for the index. `dtype` must be float32. xb : array_like Database vectors, shape (nb, d) where d is appropriate for the index. `dtype` must be float32. D : array_like, optional Output array for all pairwise distances, shape (nq, nb) metric : MetricType, optional Distance measure to use (either METRIC_L2 or METRIC_INNER_PRODUCT) device: int, optional Which CUDA device in the system to run the search on. -1 indicates that the current thread-local device state (via cudaGetDevice) should be used (can also be set via torch.cuda.set_device in PyTorch) Otherwise, an integer 0 <= device < numDevices indicates the GPU on which the computation should be run Returns ------- D : array_like All pairwise distances, shape (nq, nb) TFz5xq matrix should be row (C) or column-major (Fortran)r)r*r,Nr)r-r.r/r0r1r8r4r+r2r)r5r6r7r3r9r>r?r@rArBrCrDrErFrGrHrIrJrMrP)rrQrRrSr?rMrWrXrYrZr[r\r]r^r_r`rards rpairwise_distance_gpurgs*< HEB xE  E T  CEE Eb\\F x2:& RZ  &  !"I 6 6 6 XFB 7777 x   T  !"I 6 6 6 b\\F x2:& RZ  &7888y Hb"XRZ 0 0 0w2r(""""w"*$$$$ QKKE   DDK DFDIDL'DDODODL'DDNDODDK #t Hr)NN)Nr)NNr) numpyr2 faiss.loaderrrr METRIC_L2rergr"rrrks@@@@"     #d9RRWlmCDCCCCP*.ib b b b b b r