Home
last modified time | relevance | path

Searched refs:requantize (Results 1 – 6 of 6) sorted by relevance

/external/gemmlowp/meta/generators/
Dtransform_kernels_common.py568 requantize = Requantize(cc_emitter, asm_emitter)
575 requantize.SpecializeTransform1DKernel('int32_t', 'uint8_t', shape[0],
/external/gemmlowp/doc/
Dless-than-8-bit.md22 idea was that to automatically requantize 8bit operands to less-than-8bit during
99 The general idea is that at the packing stage, we requantize input (Lhs/Rhs)
197 stage to requantize input matrix data. See this function in internal/pack.h.
Dpacking.md186 the packing stage we have to requantize inputs accordingly. See
/external/tensorflow/tensorflow/core/graph/
Dmkl_layout_pass.cc319 csinfo_.requantize = "Requantize"; in MklLayoutRewritePass()
505 rinfo_.push_back({csinfo_.requantize, in MklLayoutRewritePass()
506 mkl_op_registry::GetMklOpName(csinfo_.requantize), in MklLayoutRewritePass()
743 string requantize; member
/external/tensorflow/tensorflow/contrib/makefile/
Dtf_op_files.txt206 tensorflow/core/kernels/requantize.cc
/external/tensorflow/tensorflow/core/kernels/
DBUILD5870 "requantize.cc",
6047 "requantize.cc",