Path	Lines of Code
bench/BenchUtils.h	415
bench/EmbeddingSpMDM8BitBenchmark.cc	282
bench/EmbeddingSpMDMBenchmark.cc	293
bench/EmbeddingSpMDMNBitBenchmark.cc	278
bench/EmbeddingSpMDMNBitRowWiseSparseBenchmark.cc	309
bench/RowwiseAdagradBenchmark.cc	189
bench/RowwiseAdagradFusedBenchmark.cc	162
bench/SparseAdagradBenchmark.cc	190
cmake/modules/FindMKL.cmake	252
fbgemm_gpu/bench/merge_embeddings_benchmark.py	440
fbgemm_gpu/codegen/embedding_backward_split_cpu_approx_template.cpp	191
fbgemm_gpu/codegen/embedding_backward_split_cpu_template.cpp	340
fbgemm_gpu/codegen/embedding_backward_split_indice_weights_template.cu	274
fbgemm_gpu/codegen/embedding_forward_quantized_split_template.cu	917
fbgemm_gpu/codegen/embedding_forward_split_cpu.cpp	526
fbgemm_gpu/fbgemm_gpu/split_embedding_inference_converter.py	145
fbgemm_gpu/fbgemm_gpu/split_table_batched_embeddings_ops.py	1963
fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh	1948
fbgemm_gpu/include/fbgemm_gpu/quantize_ops_utils.h	55
fbgemm_gpu/include/fbgemm_gpu/sparse_ops_utils.h	214
fbgemm_gpu/setup.py	144
fbgemm_gpu/src/cumem_utils.cu	305
fbgemm_gpu/src/cumem_utils_host.cpp	34
fbgemm_gpu/src/jagged_tensor_ops.cu	1150
fbgemm_gpu/src/jagged_tensor_ops_cpu.cpp	967
fbgemm_gpu/src/merge_pooled_embeddings_gpu.cpp	341
fbgemm_gpu/src/permute_pooled_embedding_ops.cu	74
fbgemm_gpu/src/quantize_ops.cu	666
fbgemm_gpu/src/sparse_ops.cu	1953
fbgemm_gpu/src/split_embeddings_cache_cuda.cu	1803
include/fbgemm/Fbgemm.h	804
include/fbgemm/FbgemmEmbedding.h	234
include/fbgemm/QuantUtils.h	224
src/EmbeddingSpMDM.cc	1251
src/EmbeddingSpMDMNBit.cc	1170
src/ExecuteKernelU8S8.cc	486
src/FbgemmI64.cc	409
src/FbgemmI8Depthwise2DAvx2-inl.h	656
src/FbgemmI8Spmdm.cc	296
src/FbgemmSparseDenseVectorInt8Avx512.cc	217
src/GroupwiseConv.cc	938
src/PackAMatrix.cc	153
src/PackAWithIm2Col.cc	645
src/PackAWithRowOffset.cc	201
src/PackWeightMatrixForGConv.cc	189
src/RowWiseSparseAdagradFused.cc	823
src/SparseAdagrad.cc	842
src/Utils.cc	397