|
..
|
|
CMakeLists.txt
|
|
__init__.py
|
|
adagrad.cc
|
|
adagrad.h
|
|
adagrad_avx2.cc
|
|
common.h
|
|
common_avx.cc
|
|
common_avx2.cc
|
|
common_avx512.cc
|
|
cvtsh_ss_bugfix.h
|
|
embedding_lookup.cc
|
|
embedding_lookup.h
|
|
embedding_lookup_avx2.cc
|
|
embedding_lookup_fused_8bit_rowwise_avx2.cc
|
|
embedding_lookup_fused_8bit_rowwise_idx_avx2.cc
|
|
embedding_lookup_idx.cc
|
|
embedding_lookup_idx.h
|
|
embedding_lookup_idx_avx2.cc
|
|
fused_8bit_rowwise_embedding_lookup.cc
|
|
fused_8bit_rowwise_embedding_lookup.h
|
|
fused_8bit_rowwise_embedding_lookup_idx.cc
|
|
fused_8bit_rowwise_embedding_lookup_idx.h
|
|
fused_nbit_rowwise_conversion.cc
|
|
fused_nbit_rowwise_conversion.h
|
|
fused_nbit_rowwise_conversion_avx2.cc
|
|
hp_emblookup_codegen.py
|
|
lstm_unit_cpu-impl.h
|
|
lstm_unit_cpu.h
|
|
lstm_unit_cpu_avx2.cc
|
|
lstm_unit_cpu_common.cc
|
|
lstm_unit_cpu_common.h
|
|
math.h
|
|
math_cpu_avx2.cc
|
|
math_cpu_base.cc
|
|
typed_axpy.cc
|
|
typed_axpy.h
|
|
typed_axpy_avx.cc
|
|
typed_axpy_avx2.cc
|