binary_shift_tile

void ckernel::binary_shift_tile_init()

Please refer to documentation for any_init.

Left Shift

void ckernel::binary_left_shift_tile(uint32_t idst0, uint32_t idst1, uint32_t odst)

Performs an elementwise shift operation to the left on the input at idst0, by input at idst1: y = x0 << x1 Both inputs must be of Int32 data type only. Output overwrites odst in DST.

The DST register buffer must be in acquired state via acquire_dst call. This call is blocking and is only available on the compute engine. A maximum of 4 tiles from each operand can be loaded into DST at once, for a total of 8 tiles, when using 16 bit formats. This gets reduced to 2 tiles from each operand for 32 bit formats.

Return value: None

Argument	Description	Type	Valid Range	Required
idst0	The index of the tile in DST register buffer to use as first operand	uint32_t	Must be less than the size of the DST register buffer	True
idst1	The index of the tile in DST register buffer to use as second operand	uint32_t	Must be less than the size of the DST register buffer	True
odst	The index of the tile in DST register buffer to use as output	uint32_t	Must be less than the size of the DST register buffer	True

template<bool sign_magnitude_format = false>
void ckernel::binary_left_shift_uint32_tile(uint32_t idst0, uint32_t idst1, uint32_t odst)

void ckernel::binary_left_shift_int32_tile(uint32_t idst0, uint32_t idst1, uint32_t odst)

Right Shift

void ckernel::binary_right_shift_tile(uint32_t idst0, uint32_t idst1, uint32_t odst)

Performs an elementwise shift operation to the right on the input at idst0, by input at idst1: y = x0 >> x1 Both inputs must be of Int32 data type only. Output overwrites odst in DST.

The DST register buffer must be in acquired state via acquire_dst call. This call is blocking and is only available on the compute engine. A maximum of 4 tiles from each operand can be loaded into DST at once, for a total of 8 tiles, when using 16 bit formats. This gets reduced to 2 tiles from each operand for 32 bit formats.

Return value: None

Argument	Description	Type	Valid Range	Required
idst0	The index of the tile in DST register buffer to use as first operand	uint32_t	Must be less than the size of the DST register buffer	True
idst1	The index of the tile in DST register buffer to use as second operand	uint32_t	Must be less than the size of the DST register buffer	True
odst	The index of the tile in DST register buffer to use as output	uint32_t	Must be less than the size of the DST register buffer	True

template<bool sign_magnitude_format = false>
void ckernel::binary_right_shift_uint32_tile(uint32_t idst0, uint32_t idst1, uint32_t odst)

void ckernel::binary_right_shift_int32_tile(uint32_t idst0, uint32_t idst1, uint32_t odst)

Logical Right Shift

void ckernel::binary_logical_right_shift_tile(uint32_t idst0, uint32_t idst1, uint32_t odst)

Performs an elementwise logical shift operation to the right on the input at idst0, by input at idst1: y = x0 >> x1 Both inputs must be of Int32 data type only. Output overwrites odst in DST.

The DST register buffer must be in acquired state via acquire_dst call. This call is blocking and is only available on the compute engine. A maximum of 4 tiles from each operand can be loaded into DST at once, for a total of 8 tiles, when using 16 bit formats. This gets reduced to 2 tiles from each operand for 32 bit formats.

Return value: None

Argument	Description	Type	Valid Range	Required
idst0	The index of the tile in DST register buffer to use as first operand	uint32_t	Must be less than the size of the DST register buffer	True
idst1	The index of the tile in DST register buffer to use as second operand	uint32_t	Must be less than the size of the DST register buffer	True
odst	The index of the tile in DST register buffer to use as output	uint32_t	Must be less than the size of the DST register buffer	True

template<bool sign_magnitude_format = false>
void ckernel::binary_logical_right_shift_uint32_tile(uint32_t idst0, uint32_t idst1, uint32_t odst)

void ckernel::binary_logical_right_shift_int32_tile(uint32_t idst0, uint32_t idst1, uint32_t odst)