Arc sine implementation. \param arg function argument \return function value stored in single-preicision

Hyperbolic area sine implementation. \param arg function argument \return function value stored in single-preicision

Arc tangent implementation. \param arg function argument \return function value stored in single-preicision

Arc tangent implementation. \param x first argument \param y second argument \return function value stored in single-preicision

Hyperbolic area tangent implementation. \param arg function argument \return function value stored in single-preicision

\brief Attach the plugin object to an execution context and grant the plugin the access to some context resource. \param cudnn The cudnn context hand

\brief Get the channel count. \return The channel count.

Cubic root implementation. \param arg function argument \return function value stored in single-preicision

Nearest integer not less than half value. \param arg half to round \return nearest integer not less than \a arg template<typename T> typename enable<h

Ceiling implementation. \param arg value to round \return rounded value

Take sign. \param x value to change sign for \param y value to take sign from \return value equal to \a x in magnitude and to \a y in sign template<ty

Sign implementation \param x first operand \param y second operand \return composed value

Cosine implementation. \param arg function argument \return function value stored in single-preicision

Hyperbolic cosine implementation. \param arg function argument \return function value stored in single-preicision

\brief Create an instance of an IBuilder class. This class is the logging class for the builder. unnamed namespace avoids linkage surprises when lin

\brief Create an instance of an IRefitter class. This class is the logging class for the refitter.

\brief Create an instance of an IRuntime class. This class is the logging class for the runtime.

\brief Define a test for logging \param[in] name The name of the test. This should be a string starting with "TensorRT" and containing dot-separated

deserialize NvInfer Dims from buffer

\brief Deserialize an engine from a stream when plugin factory is not used. \param blob The memory that holds the serialized engine. \param size The

\brief Detach the plugin object from its execution context. This function is called automatically for each plugin when a execution context is destroy

Division implementation. \param x first operand \param y second operand \return Half-precision quotient stored in single-precision

Error function implementation. \param arg function argument \return function value stored in single-preicision

Complementary implementation. \param arg function argument \return function value stored in single-preicision

Exponential implementation. \param arg function argument \return function value stored in single-preicision

Binary exponential implementation. \param arg function argument \return function value stored in single-preicision

Exponential implementation. \param arg function argument \return function value stored in single-preicision

Absolute value implementation. \param arg function argument \return absolute value

Positive difference implementation. \param x first operand \param y second operand \return Positive difference stored in single-precision

Nearest integer not greater than half value. \param arg half to round \return nearest integer not greater than \a arg template<typename T> typename en

Floor implementation. \param arg value to round \return rounded value

Fused multiply-add implementation. \param x first operand \param y second operand \param z third operand \return \a x * \a y + \a z stored in single-p

Maximum implementation. \param x first operand \param y second operand \return maximum value

Minimum implementation. \param x first operand \param y second operand \return minimum value

Modulo implementation. \param x first operand \param y second operand \return Half-precision division remainder stored in single-precision

Classify floating point value. \param arg number to classify \retval FP_ZERO for positive and negative zero \retval FP_SUBNORMAL for subnormal numbers

Classification implementation. \param arg value to classify \retval true if infinite number \retval false else

Decompression implementation. \param arg number to decompress \param exp address to store exponent at \return normalized significant

\brief generate a command line string from the given (argc, argv) values

BERT demo needs a separate engine building path to generate calibration cache. This is because we need to configure SLN and MHA plugins in FP