1.1.5. Half Precision Conversion And Data Movement
[Half Precision Intrinsics]
To use these functions include the header file cuda_fp16.h in your program.
Functions
 __host__ __device__ __half2 __float22half2_rn ( const float2 a )
 Converts both components of float2 number to half precision in roundtonearesteven mode and returns half2 with converted values.
 __host__ __device__ __half __float2half ( const float a )
 Converts float number to half precision in roundtonearesteven mode and returns half with converted value.
 __host__ __device__ __half2 __float2half2_rn ( const float a )
 Converts input to half precision in roundtonearesteven mode and populates both halves of half2 with converted value.
 __host__ __device__ __half __float2half_rd ( const float a )
 Converts float number to half precision in rounddown mode and returns half with converted value.
 __host__ __device__ __half __float2half_rn ( const float a )
 Converts float number to half precision in roundtonearesteven mode and returns half with converted value.
 __host__ __device__ __half __float2half_ru ( const float a )
 Converts float number to half precision in roundup mode and returns half with converted value.
 __host__ __device__ __half __float2half_rz ( const float a )
 Converts float number to half precision in roundtowardszero mode and returns half with converted value.
 __host__ __device__ __half2 __floats2half2_rn ( const float a, const float b )
 Converts both input floats to half precision in roundtonearesteven mode and returns half2 with converted values.
 __host__ __device__ float2 __half22float2 ( const __half2 a )
 Converts both halves of half2 to float2 and returns the result.
 __host__ __device__ float __half2float ( const __half a )
 Converts half number to float.
 __device__ __half2 __half2half2 ( const __half a )
 Returns half2 with both halves equal to the input value.
 __device__ int __half2int_rd ( __half h )
 Convert a half to a signed integer in rounddown mode.
 __device__ int __half2int_rn ( __half h )
 Convert a half to a signed integer in roundtonearesteven mode.
 __device__ int __half2int_ru ( __half h )
 Convert a half to a signed integer in roundup mode.
 __device__ int __half2int_rz ( __half h )
 Convert a half to a signed integer in roundtowardszero mode.
 __device__ long long int __half2ll_rd ( __half h )
 Convert a half to a signed 64bit integer in rounddown mode.
 __device__ long long int __half2ll_rn ( __half h )
 Convert a half to a signed 64bit integer in roundtonearesteven mode.
 __device__ long long int __half2ll_ru ( __half h )
 Convert a half to a signed 64bit integer in roundup mode.
 __device__ long long int __half2ll_rz ( __half h )
 Convert a half to a signed 64bit integer in roundtowardszero mode.
 __device__ short int __half2short_rd ( __half h )
 Convert a half to a signed short integer in rounddown mode.
 __device__ short int __half2short_rn ( __half h )
 Convert a half to a signed short integer in roundtonearesteven mode.
 __device__ short int __half2short_ru ( __half h )
 Convert a half to a signed short integer in roundup mode.
 __device__ short int __half2short_rz ( __half h )
 Convert a half to a signed short integer in roundtowardszero mode.
 __device__ unsigned int __half2uint_rd ( __half h )
 Convert a half to an unsigned integer in rounddown mode.
 __device__ unsigned int __half2uint_rn ( __half h )
 Convert a half to an unsigned integer in roundtonearesteven mode.
 __device__ unsigned int __half2uint_ru ( __half h )
 Convert a half to an unsigned integer in roundup mode.
 __device__ unsigned int __half2uint_rz ( __half h )
 Convert a half to an unsigned integer in roundtowardszero mode.
 __device__ unsigned long long int __half2ull_rd ( __half h )
 Convert a half to an unsigned 64bit integer in rounddown mode.
 __device__ unsigned long long int __half2ull_rn ( __half h )
 Convert a half to an unsigned 64bit integer in roundtonearesteven mode.
 __device__ unsigned long long int __half2ull_ru ( __half h )
 Convert a half to an unsigned 64bit integer in roundup mode.
 __device__ unsigned long long int __half2ull_rz ( __half h )
 Convert a half to an unsigned 64bit integer in roundtowardszero mode.
 __device__ unsigned short int __half2ushort_rd ( __half h )
 Convert a half to an unsigned short integer in rounddown mode.
 __device__ unsigned short int __half2ushort_rn ( __half h )
 Convert a half to an unsigned short integer in roundtonearesteven mode.
 __device__ unsigned short int __half2ushort_ru ( __half h )
 Convert a half to an unsigned short integer in roundup mode.
 __device__ unsigned short int __half2ushort_rz ( __half h )
 Convert a half to an unsigned short integer in roundtowardszero mode.
 __device__ short int __half_as_short ( const __half h )
 Reinterprets bits in a half as a signed short integer.
 __device__ unsigned short int __half_as_ushort ( const __half h )
 Reinterprets bits in a half as an unsigned short integer.
 __device__ __half2 __halves2half2 ( const __half a, const __half b )
 Combines two half numbers into one half2 number.
 __host__ __device__ float __high2float ( const __half2 a )
 Converts high 16 bits of half2 to float and returns the result.
 __device__ __half __high2half ( const __half2 a )
 Returns high 16 bits of half2 input.
 __device__ __half2 __high2half2 ( const __half2 a )
 Extracts high 16 bits from half2 input.
 __device__ __half2 __highs2half2 ( const __half2 a, const __half2 b )
 Extracts high 16 bits from each of the two half2 inputs and combines into one half2 number.
 __device__ __half __int2half_rd ( int i )
 Convert a signed integer to a half in rounddown mode.
 __device__ __half __int2half_rn ( int i )
 Convert a signed integer to a half in roundtonearesteven mode.
 __device__ __half __int2half_ru ( int i )
 Convert a signed integer to a half in roundup mode.
 __device__ __half __int2half_rz ( int i )
 Convert a signed integer to a half in roundtowardszero mode.
 __device__ __half __ll2half_rd ( long long int i )
 Convert a signed 64bit integer to a half in rounddown mode.
 __device__ __half __ll2half_rn ( long long int i )
 Convert a signed 64bit integer to a half in roundtonearesteven mode.
 __device__ __half __ll2half_ru ( long long int i )
 Convert a signed 64bit integer to a half in roundup mode.
 __device__ __half __ll2half_rz ( long long int i )
 Convert a signed 64bit integer to a half in roundtowardszero mode.
 __host__ __device__ float __low2float ( const __half2 a )
 Converts low 16 bits of half2 to float and returns the result.
 __device__ __half __low2half ( const __half2 a )
 Returns low 16 bits of half2 input.
 __device__ __half2 __low2half2 ( const __half2 a )
 Extracts low 16 bits from half2 input.
 __device__ __half2 __lowhigh2highlow ( const __half2 a )
 Swaps both halves of the half2 input.
 __device__ __half2 __lows2half2 ( const __half2 a, const __half2 b )
 Extracts low 16 bits from each of the two half2 inputs and combines into one half2 number.
 __device__ __half __shfl_down_sync ( unsigned mask, __half var, unsigned int delta, int width = warpSize )
 Exchange a variable between threads within a warp. Copy from a thread with higher ID relative to the caller.
 __device__ __half2 __shfl_down_sync ( unsigned mask, __half2 var, unsigned int delta, int width = warpSize )
 Exchange a variable between threads within a warp. Copy from a thread with higher ID relative to the caller.
 __device__ __half __shfl_sync ( unsigned mask, __half var, int delta, int width = warpSize )
 Exchange a variable between threads within a warp. Direct copy from indexed thread.
 __device__ __half2 __shfl_sync ( unsigned mask, __half2 var, int delta, int width = warpSize )
 Exchange a variable between threads within a warp. Direct copy from indexed thread.
 __device__ __half __shfl_up_sync ( unsigned mask, __half var, unsigned int delta, int width = warpSize )
 Exchange a variable between threads within a warp. Copy from a thread with lower ID relative to the caller.
 __device__ __half2 __shfl_up_sync ( unsigned mask, __half2 var, unsigned int delta, int width = warpSize )
 Exchange a variable between threads within a warp. Copy from a thread with lower ID relative to the caller.
 __device__ __half __shfl_xor_sync ( unsigned mask, __half var, int delta, int width = warpSize )
 Exchange a variable between threads within a warp. Copy from a thread based on bitwise XOR of own thread ID.
 __device__ __half2 __shfl_xor_sync ( unsigned mask, __half2 var, int delta, int width = warpSize )
 Exchange a variable between threads within a warp. Copy from a thread based on bitwise XOR of own thread ID.
 __device__ __half __short2half_rd ( short int i )
 Convert a signed short integer to a half in rounddown mode.
 __device__ __half __short2half_rn ( short int i )
 Convert a signed short integer to a half in roundtonearesteven mode.
 __device__ __half __short2half_ru ( short int i )
 Convert a signed short integer to a half in roundup mode.
 __device__ __half __short2half_rz ( short int i )
 Convert a signed short integer to a half in roundtowardszero mode.
 __device__ __half __short_as_half ( const short int i )
 Reinterprets bits in a signed short integer as a half.
 __device__ __half __uint2half_rd ( unsigned int i )
 Convert an unsigned integer to a half in rounddown mode.
 __device__ __half __uint2half_rn ( unsigned int i )
 Convert an unsigned integer to a half in roundtonearesteven mode.
 __device__ __half __uint2half_ru ( unsigned int i )
 Convert an unsigned integer to a half in roundup mode.
 __device__ __half __uint2half_rz ( unsigned int i )
 Convert an unsigned integer to a half in roundtowardszero mode.
 __device__ __half __ull2half_rd ( unsigned long long int i )
 Convert an unsigned 64bit integer to a half in rounddown mode.
 __device__ __half __ull2half_rn ( unsigned long long int i )
 Convert an unsigned 64bit integer to a half in roundtonearesteven mode.
 __device__ __half __ull2half_ru ( unsigned long long int i )
 Convert an unsigned 64bit integer to a half in roundup mode.
 __device__ __half __ull2half_rz ( unsigned long long int i )
 Convert an unsigned 64bit integer to a half in roundtowardszero mode.
 __device__ __half __ushort2half_rd ( unsigned short int i )
 Convert an unsigned short integer to a half in rounddown mode.
 __device__ __half __ushort2half_rn ( unsigned short int i )
 Convert an unsigned short integer to a half in roundtonearesteven mode.
 __device__ __half __ushort2half_ru ( unsigned short int i )
 Convert an unsigned short integer to a half in roundup mode.
 __device__ __half __ushort2half_rz ( unsigned short int i )
 Convert an unsigned short integer to a half in roundtowardszero mode.
 __device__ __half __ushort_as_half ( const unsigned short int i )
 Reinterprets bits in an unsigned short integer as a half.
Functions
 __host__ __device__ __half2 __float22half2_rn ( const float2 a )

Converts both components of float2 number to half precision in roundtonearesteven mode and returns half2 with converted values.
Parameters
 a
  float2
Returns
half2
 The
half2 which has corresponding halves equal to the converted float2 components.
Description
Converts both components of float2 to half precision in roundtonearest mode and combines the results into one half2 number. Low 16 bits of the return value correspond to a.x and high 16 bits of the return value correspond to a.y.
 __host__ __device__ __half __float2half ( const float a )

Converts float number to half precision in roundtonearesteven mode and returns half with converted value.
Parameters
 a
  float
Returns
half
 \p
a converted to half.
Description
Converts float number a to half precision in roundtonearesteven mode.
 __host__ __device__ __half2 __float2half2_rn ( const float a )

Converts input to half precision in roundtonearesteven mode and populates both halves of half2 with converted value.
Parameters
 a
  float
Returns
half2
 The
half2 value with both halves equal to the converted half precision number.
Description
Converts input a to half precision in roundtonearesteven mode and populates both halves of half2 with converted value.
 __host__ __device__ __half __float2half_rd ( const float a )

Converts float number to half precision in rounddown mode and returns half with converted value.
Parameters
 a
  float
Returns
half
 \p
a converted to half.
Description
Converts float number a to half precision in rounddown mode.
 __host__ __device__ __half __float2half_rn ( const float a )

Converts float number to half precision in roundtonearesteven mode and returns half with converted value.
Parameters
 a
  float
Returns
half
 \p
a converted to half.
Description
Converts float number a to half precision in roundtonearesteven mode.
 __host__ __device__ __half __float2half_ru ( const float a )

Converts float number to half precision in roundup mode and returns half with converted value.
Parameters
 a
  float
Returns
half
 \p
a converted to half.
Description
Converts float number a to half precision in roundup mode.
 __host__ __device__ __half __float2half_rz ( const float a )

Converts float number to half precision in roundtowardszero mode and returns half with converted value.
Parameters
 a
  float
Returns
half
 \p
a converted to half.
Description
Converts float number a to half precision in roundtowardszero mode.
 __host__ __device__ __half2 __floats2half2_rn ( const float a, const float b )

Converts both input floats to half precision in roundtonearesteven mode and returns half2 with converted values.
Parameters
 a
  float
 b
  float
Returns
half2
 The
half2 value with corresponding halves equal to the converted input floats.
Description
Converts both input floats to half precision in roundtonearesteven mode and combines the results into one half2 number. Low 16 bits of the return value correspond to the input a, high 16 bits correspond to the input b.
 __host__ __device__ float2 __half22float2 ( const __half2 a )

Converts both halves of half2 to float2 and returns the result.
Parameters
 a
  half2
Returns
float2
 \p
a converted to float2.
Description
Converts both halves of half2 input a to float2 and returns the result.
 __host__ __device__ float __half2float ( const __half a )

Converts half number to float.
Parameters
 a
  half
Returns
float
 \p
a converted to float.
Description
Converts half number a to float.
 __device__ __half2 __half2half2 ( const __half a )

Returns half2 with both halves equal to the input value.
Parameters
 a
  half
Returns
half2
 The
vector which has both its halves equal to the input a.
Description
Returns half2 number with both halves equal to the input ahalf number.
 __device__ int __half2int_rd ( __half h )

Convert a half to a signed integer in rounddown mode.
Parameters
 h
  half
Returns
int
 \p
h converted to a signed integer.
Description
Convert the halfprecision floating point value h to a signed integer in rounddown mode.
 __device__ int __half2int_rn ( __half h )

Convert a half to a signed integer in roundtonearesteven mode.
Parameters
 h
  half
Returns
int
 \p
h converted to a signed integer.
Description
Convert the halfprecision floating point value h to a signed integer in roundtonearesteven mode.
 __device__ int __half2int_ru ( __half h )

Convert a half to a signed integer in roundup mode.
Parameters
 h
  half
Returns
int
 \p
h converted to a signed integer.
Description
Convert the halfprecision floating point value h to a signed integer in roundup mode.
 __device__ int __half2int_rz ( __half h )

Convert a half to a signed integer in roundtowardszero mode.
Parameters
 h
  half
Returns
int
 \p
h converted to a signed integer.
Description
Convert the halfprecision floating point value h to a signed integer in roundtowardszero mode.
 __device__ long long int __half2ll_rd ( __half h )

Convert a half to a signed 64bit integer in rounddown mode.
Parameters
 h
  half
Returns
long long int
 \p
h converted to a signed 64bit integer.
Description
Convert the halfprecision floating point value h to a signed 64bit integer in rounddown mode.
 __device__ long long int __half2ll_rn ( __half h )

Convert a half to a signed 64bit integer in roundtonearesteven mode.
Parameters
 h
  half
Returns
long long int
 \p
h converted to a signed 64bit integer.
Description
Convert the halfprecision floating point value h to a signed 64bit integer in roundtonearesteven mode.
 __device__ long long int __half2ll_ru ( __half h )

Convert a half to a signed 64bit integer in roundup mode.
Parameters
 h
  half
Returns
long long int
 \p
h converted to a signed 64bit integer.
Description
Convert the halfprecision floating point value h to a signed 64bit integer in roundup mode.
 __device__ long long int __half2ll_rz ( __half h )

Convert a half to a signed 64bit integer in roundtowardszero mode.
Parameters
 h
  half
Returns
long long int
 \p
h converted to a signed 64bit integer.
Description
Convert the halfprecision floating point value h to a signed 64bit integer in roundtowardszero mode.
 __device__ short int __half2short_rd ( __half h )

Convert a half to a signed short integer in rounddown mode.
Parameters
 h
  half
Returns
short int
 \p
h converted to a signed short integer.
Description
Convert the halfprecision floating point value h to a signed short integer in rounddown mode.
 __device__ short int __half2short_rn ( __half h )

Convert a half to a signed short integer in roundtonearesteven mode.
Parameters
 h
  half
Returns
short int
 \p
h converted to a signed short integer.
Description
Convert the halfprecision floating point value h to a signed short integer in roundtonearesteven mode.
 __device__ short int __half2short_ru ( __half h )

Convert a half to a signed short integer in roundup mode.
Parameters
 h
  half
Returns
short int
 \p
h converted to a signed short integer.
Description
Convert the halfprecision floating point value h to a signed short integer in roundup mode.
 __device__ short int __half2short_rz ( __half h )

Convert a half to a signed short integer in roundtowardszero mode.
Parameters
 h
  half
Returns
short int
 \p
h converted to a signed short integer.
Description
Convert the halfprecision floating point value h to a signed short integer in roundtowardszero mode.
 __device__ unsigned int __half2uint_rd ( __half h )

Convert a half to an unsigned integer in rounddown mode.
Parameters
 h
  half
Returns
unsigned int
 \p
h converted to an unsigned integer.
Description
Convert the halfprecision floating point value h to an unsigned integer in rounddown mode.
 __device__ unsigned int __half2uint_rn ( __half h )

Convert a half to an unsigned integer in roundtonearesteven mode.
Parameters
 h
  half
Returns
unsigned int
 \p
h converted to an unsigned integer.
Description
Convert the halfprecision floating point value h to an unsigned integer in roundtonearesteven mode.
 __device__ unsigned int __half2uint_ru ( __half h )

Convert a half to an unsigned integer in roundup mode.
Parameters
 h
  half
Returns
unsigned int
 \p
h converted to an unsigned integer.
Description
Convert the halfprecision floating point value h to an unsigned integer in roundup mode.
 __device__ unsigned int __half2uint_rz ( __half h )

Convert a half to an unsigned integer in roundtowardszero mode.
Parameters
 h
  half
Returns
unsigned int
 \p
h converted to an unsigned integer.
Description
Convert the halfprecision floating point value h to an unsigned integer in roundtowardszero mode.
 __device__ unsigned long long int __half2ull_rd ( __half h )

Convert a half to an unsigned 64bit integer in rounddown mode.
Parameters
 h
  half
Returns
unsigned long long int
 \p
h converted to an unsigned 64bit integer.
Description
Convert the halfprecision floating point value h to an unsigned 64bit integer in rounddown mode.
 __device__ unsigned long long int __half2ull_rn ( __half h )

Convert a half to an unsigned 64bit integer in roundtonearesteven mode.
Parameters
 h
  half
Returns
unsigned long long int
 \p
h converted to an unsigned 64bit integer.
Description
Convert the halfprecision floating point value h to an unsigned 64bit integer in roundtonearesteven mode.
 __device__ unsigned long long int __half2ull_ru ( __half h )

Convert a half to an unsigned 64bit integer in roundup mode.
Parameters
 h
  half
Returns
unsigned long long int
 \p
h converted to an unsigned 64bit integer.
Description
Convert the halfprecision floating point value h to an unsigned 64bit integer in roundup mode.
 __device__ unsigned long long int __half2ull_rz ( __half h )

Convert a half to an unsigned 64bit integer in roundtowardszero mode.
Parameters
 h
  half
Returns
unsigned long long int
 \p
h converted to an unsigned 64bit integer.
Description
Convert the halfprecision floating point value h to an unsigned 64bit integer in roundtowardszero mode.
 __device__ unsigned short int __half2ushort_rd ( __half h )

Convert a half to an unsigned short integer in rounddown mode.
Parameters
 h
  half
Returns
unsigned short int
 \p
h converted to an unsigned short integer.
Description
Convert the halfprecision floating point value h to an unsigned short integer in rounddown mode.
 __device__ unsigned short int __half2ushort_rn ( __half h )

Convert a half to an unsigned short integer in roundtonearesteven mode.
Parameters
 h
  half
Returns
unsigned short int
 \p
h converted to an unsigned short integer.
Description
Convert the halfprecision floating point value h to an unsigned short integer in roundtonearesteven mode.
 __device__ unsigned short int __half2ushort_ru ( __half h )

Convert a half to an unsigned short integer in roundup mode.
Parameters
 h
  half
Returns
unsigned short int
 \p
h converted to an an unsigned short integer.
Description
Convert the halfprecision floating point value h to an unsigned short integer in roundup mode.
 __device__ unsigned short int __half2ushort_rz ( __half h )

Convert a half to an unsigned short integer in roundtowardszero mode.
Parameters
 h
  half
Returns
unsigned short int
 \p
h converted to an unsigned short integer.
Description
Convert the halfprecision floating point value h to an unsigned short integer in roundtowardszero mode.
 __device__ short int __half_as_short ( const __half h )

Reinterprets bits in a half as a signed short integer.
Parameters
 h
  half
Returns
short int
 The
reinterpreted value.
Description
Reinterprets the bits in the halfprecision floating point number h as a signed short integer.
 __device__ unsigned short int __half_as_ushort ( const __half h )

Reinterprets bits in a half as an unsigned short integer.
Parameters
 h
  half
Returns
unsigned short int
 The
reinterpreted value.
Description
Reinterprets the bits in the halfprecision floating point h as an unsigned short number.
 __device__ __half2 __halves2half2 ( const __half a, const __half b )

Combines two half numbers into one half2 number.
Parameters
 a
  half
 b
  half
Returns
half2
 The
half2 with one half equal to a and the other to b.
Description
Combines two input half number a and b into one half2 number. Input a is stored in low 16 bits of the return value, input b is stored in high 16 bits of the return value.
 __host__ __device__ float __high2float ( const __half2 a )

Converts high 16 bits of half2 to float and returns the result.
Parameters
 a
  half2
Returns
float
 The
high 16 bits of a converted to float.
Description
Converts high 16 bits of half2 input a to 32 bit floating point number and returns the result.
 __device__ __half __high2half ( const __half2 a )

Returns high 16 bits of half2 input.
Parameters
 a
  half2
Returns
half
 The
high 16 bits of the input.
Description
Returns high 16 bits of half2 input a.
 __device__ __half2 __high2half2 ( const __half2 a )

Extracts high 16 bits from half2 input.
Parameters
 a
  half2
Returns
half2
 The
half2 with both halves equal to the high 16 bits of the input.
Description
Extracts high 16 bits from half2 input a and returns a new half2 number which has both halves equal to the extracted bits.
 __device__ __half2 __highs2half2 ( const __half2 a, const __half2 b )

Extracts high 16 bits from each of the two half2 inputs and combines into one half2 number.
Parameters
 a
  half2
 b
  half2
Returns
half2
 The
high 16 bits of a and of b.
Description
Extracts high 16 bits from each of the two half2 inputs and combines into one half2 number. High 16 bits from input a is stored in low 16 bits of the return value, high 16 bits from input b is stored in high 16 bits of the return value.
 __device__ __half __int2half_rd ( int i )

Convert a signed integer to a half in rounddown mode.
Parameters
 i
  int
Returns
half
 \p
i converted to half.
Description
Convert the signed integer value i to a halfprecision floating point value in rounddown mode.
 __device__ __half __int2half_rn ( int i )

Convert a signed integer to a half in roundtonearesteven mode.
Parameters
 i
  int
Returns
half
 \p
i converted to half.
Description
Convert the signed integer value i to a halfprecision floating point value in roundtonearesteven mode.
 __device__ __half __int2half_ru ( int i )

Convert a signed integer to a half in roundup mode.
Parameters
 i
  int
Returns
half
 \p
i converted to half.
Description
Convert the signed integer value i to a halfprecision floating point value in roundup mode.
 __device__ __half __int2half_rz ( int i )

Convert a signed integer to a half in roundtowardszero mode.
Parameters
 i
  int
Returns
half
 \p
i converted to half.
Description
Convert the signed integer value i to a halfprecision floating point value in roundtowardszero mode.
 __device__ __half __ll2half_rd ( long long int i )

Convert a signed 64bit integer to a half in rounddown mode.
Parameters
 i
  long long int
Returns
half
 \p
i converted to half.
Description
Convert the signed 64bit integer value i to a halfprecision floating point value in rounddown mode.
 __device__ __half __ll2half_rn ( long long int i )

Convert a signed 64bit integer to a half in roundtonearesteven mode.
Parameters
 i
  long long int
Returns
half
 \p
i converted to half.
Description
Convert the signed 64bit integer value i to a halfprecision floating point value in roundtonearesteven mode.
 __device__ __half __ll2half_ru ( long long int i )

Convert a signed 64bit integer to a half in roundup mode.
Parameters
 i
  long long int
Returns
half
 \p
i converted to half.
Description
Convert the signed 64bit integer value i to a halfprecision floating point value in roundup mode.
 __device__ __half __ll2half_rz ( long long int i )

Convert a signed 64bit integer to a half in roundtowardszero mode.
Parameters
 i
  long long int
Returns
half
 \p
i converted to half.
Description
Convert the signed 64bit integer value i to a halfprecision floating point value in roundtowardszero mode.
 __host__ __device__ float __low2float ( const __half2 a )

Converts low 16 bits of half2 to float and returns the result.
Parameters
 a
  half2
Returns
float
 The
low 16 bits of a converted to float.
Description
Converts low 16 bits of half2 input a to 32 bit floating point number and returns the result.
 __device__ __half __low2half ( const __half2 a )

Returns low 16 bits of half2 input.
Parameters
 a
  half2
Returns
half
 Returns
half which contains low 16 bits of the input a.
Description
Returns low 16 bits of half2 input a.
 __device__ __half2 __low2half2 ( const __half2 a )

Extracts low 16 bits from half2 input.
Parameters
 a
  half2
Returns
half2
 The
half2 with both halves equal to the low 16 bits of the input.
Description
Extracts low 16 bits from half2 input a and returns a new half2 number which has both halves equal to the extracted bits.
 __device__ __half2 __lowhigh2highlow ( const __half2 a )

Swaps both halves of the half2 input.
Parameters
 a
  half2
Returns
half2
 \p
a with its halves being swapped.
Description
Swaps both halves of the half2 input and returns a new half2 number with swapped halves.
 __device__ __half2 __lows2half2 ( const __half2 a, const __half2 b )

Extracts low 16 bits from each of the two half2 inputs and combines into one half2 number.
Parameters
 a
  half2
 b
  half2
Returns
half2
 The
low 16 bits of a and of b.
Description
Extracts low 16 bits from each of the two half2 inputs and combines into one half2 number. Low 16 bits from input a is stored in low 16 bits of the return value, low 16 bits from input b is stored in high 16 bits of the return value.
 __device__ __half __shfl_down_sync ( unsigned mask, __half var, unsigned int delta, int width = warpSize )

Exchange a variable between threads within a warp. Copy from a thread with higher ID relative to the caller.
Parameters
 mask
  unsigned int
 var
  half
 delta
  int
 width
  int
Returns
Returns the 2byte word referenced by var from the source thread ID as half. If the source thread ID is out of range or the source thread has exited, the calling thread's own var is returned.
Description
Calculates a source thread ID by adding delta to the caller's thread ID. The value of var held by the resulting thread ID is returned: this has the effect of shifting var down the warp by delta threads. If width is less than warpSize then each subsection of the warp behaves as a separate entity with a starting logical thread ID of 0. As for __shfl_up_sync(), the ID number of the source thread will not wrap around the value of width and so the upper delta threads will remain unchanged.
 __device__ __half2 __shfl_down_sync ( unsigned mask, __half2 var, unsigned int delta, int width = warpSize )

Exchange a variable between threads within a warp. Copy from a thread with higher ID relative to the caller.
Parameters
 mask
  unsigned int
 var
  half2
 delta
  int
 width
  int
Returns
Returns the 4byte word referenced by var from the source thread ID as half2. If the source thread ID is out of range or the source thread has exited, the calling thread's own var is returned.
Description
Calculates a source thread ID by adding delta to the caller's thread ID. The value of var held by the resulting thread ID is returned: this has the effect of shifting var down the warp by delta threads. If width is less than warpSize then each subsection of the warp behaves as a separate entity with a starting logical thread ID of 0. As for __shfl_up_sync(), the ID number of the source thread will not wrap around the value of width and so the upper delta threads will remain unchanged.
 __device__ __half __shfl_sync ( unsigned mask, __half var, int delta, int width = warpSize )

Exchange a variable between threads within a warp. Direct copy from indexed thread.
Parameters
 mask
  unsigned int
 var
  half
 delta
  int
 width
  int
Returns
Returns the 2byte word referenced by var from the source thread ID as half. If the source thread ID is out of range or the source thread has exited, the calling thread's own var is returned.
Description
Returns the value of var held by the thread whose ID is given by delta. If width is less than warpSize then each subsection of the warp behaves as a separate entity with a starting logical thread ID of 0. If delta is outside the range [0:width1], the value returned corresponds to the value of var held by the delta modulo width (i.e. ithin the same subsection). width must have a value which is a power of 2; results are undefined if width is not a power of 2, or is a number greater than warpSize.
 __device__ __half2 __shfl_sync ( unsigned mask, __half2 var, int delta, int width = warpSize )

Exchange a variable between threads within a warp. Direct copy from indexed thread.
Parameters
 mask
  unsigned int
 var
  half2
 delta
  int
 width
  int
Returns
Returns the 4byte word referenced by var from the source thread ID as half2. If the source thread ID is out of range or the source thread has exited, the calling thread's own var is returned.
Description
Returns the value of var held by the thread whose ID is given by delta. If width is less than warpSize then each subsection of the warp behaves as a separate entity with a starting logical thread ID of 0. If delta is outside the range [0:width1], the value returned corresponds to the value of var held by the delta modulo width (i.e. ithin the same subsection). width must have a value which is a power of 2; results are undefined if width is not a power of 2, or is a number greater than warpSize.
 __device__ __half __shfl_up_sync ( unsigned mask, __half var, unsigned int delta, int width = warpSize )

Exchange a variable between threads within a warp. Copy from a thread with lower ID relative to the caller.
Parameters
 mask
  unsigned int
 var
  half
 delta
  int
 width
  int
Returns
Returns the 2byte word referenced by var from the source thread ID as half. If the source thread ID is out of range or the source thread has exited, the calling thread's own var is returned.
Description
Calculates a source thread ID by subtracting delta from the caller's lane ID. The value of var held by the resulting lane ID is returned: in effect, var is shifted up the warp by delta threads. If width is less than warpSize then each subsection of the warp behaves as a separate entity with a starting logical thread ID of 0. The source thread index will not wrap around the value of width, so effectively the lower delta threads will be unchanged. width must have a value which is a power of 2; results are undefined if width is not a power of 2, or is a number greater than warpSize.
 __device__ __half2 __shfl_up_sync ( unsigned mask, __half2 var, unsigned int delta, int width = warpSize )

Exchange a variable between threads within a warp. Copy from a thread with lower ID relative to the caller.
Parameters
 mask
  unsigned int
 var
  half2
 delta
  int
 width
  int
Returns
Returns the 4byte word referenced by var from the source thread ID as half2. If the source thread ID is out of range or the source thread has exited, the calling thread's own var is returned.
Description
Calculates a source thread ID by subtracting delta from the caller's lane ID. The value of var held by the resulting lane ID is returned: in effect, var is shifted up the warp by delta threads. If width is less than warpSize then each subsection of the warp behaves as a separate entity with a starting logical thread ID of 0. The source thread index will not wrap around the value of width, so effectively the lower delta threads will be unchanged. width must have a value which is a power of 2; results are undefined if width is not a power of 2, or is a number greater than warpSize.
 __device__ __half __shfl_xor_sync ( unsigned mask, __half var, int delta, int width = warpSize )

Exchange a variable between threads within a warp. Copy from a thread based on bitwise XOR of own thread ID.
Parameters
 mask
  unsigned int
 var
  half
 delta
  int
 width
  int
Returns
Returns the 2byte word referenced by var from the source thread ID as half. If the source thread ID is out of range or the source thread has exited, the calling thread's own var is returned.
Description
Calculates a source thread ID by performing a bitwise XOR of the caller's thread ID with mask: the value of var held by the resulting thread ID is returned. If width is less than warpSize then each group of width consecutive threads are able to access elements from earlier groups of threads, however if they attempt to access elements from later groups of threads their own value of var will be returned. This mode implements a butterfly addressing pattern such as is used in tree reduction and broadcast.
 __device__ __half2 __shfl_xor_sync ( unsigned mask, __half2 var, int delta, int width = warpSize )

Exchange a variable between threads within a warp. Copy from a thread based on bitwise XOR of own thread ID.
Parameters
 mask
  unsigned int
 var
  half2
 delta
  int
 width
  int
Returns
Returns the 4byte word referenced by var from the source thread ID as half2. If the source thread ID is out of range or the source thread has exited, the calling thread's own var is returned.
Description
Calculates a source thread ID by performing a bitwise XOR of the caller's thread ID with mask: the value of var held by the resulting thread ID is returned. If width is less than warpSize then each group of width consecutive threads are able to access elements from earlier groups of threads, however if they attempt to access elements from later groups of threads their own value of var will be returned. This mode implements a butterfly addressing pattern such as is used in tree reduction and broadcast.
 __device__ __half __short2half_rd ( short int i )

Convert a signed short integer to a half in rounddown mode.
Parameters
 i
  short int
Returns
half
 \p
i converted to half.
Description
Convert the signed short integer value i to a halfprecision floating point value in rounddown mode.
 __device__ __half __short2half_rn ( short int i )

Convert a signed short integer to a half in roundtonearesteven mode.
Parameters
 i
  short int
Returns
half
 \p
i converted to half.
Description
Convert the signed short integer value i to a halfprecision floating point value in roundtonearesteven mode.
 __device__ __half __short2half_ru ( short int i )

Convert a signed short integer to a half in roundup mode.
Parameters
 i
  short int
Returns
half
 \p
i converted to half.
Description
Convert the signed short integer value i to a halfprecision floating point value in roundup mode.
 __device__ __half __short2half_rz ( short int i )

Convert a signed short integer to a half in roundtowardszero mode.
Parameters
 i
  short int
Returns
half
 \p
i converted to half.
Description
Convert the signed short integer value i to a halfprecision floating point value in roundtowardszero mode.
 __device__ __half __short_as_half ( const short int i )

Reinterprets bits in a signed short integer as a half.
Parameters
 i
  short int
Returns
half
 The
reinterpreted value.
Description
Reinterprets the bits in the signed short integer i as a halfprecision floating point number.
 __device__ __half __uint2half_rd ( unsigned int i )

Convert an unsigned integer to a half in rounddown mode.
Parameters
 i
  unsigned int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned integer value i to a halfprecision floating point value in rounddown mode.
 __device__ __half __uint2half_rn ( unsigned int i )

Convert an unsigned integer to a half in roundtonearesteven mode.
Parameters
 i
  unsigned int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned integer value i to a halfprecision floating point value in roundtonearesteven mode.
 __device__ __half __uint2half_ru ( unsigned int i )

Convert an unsigned integer to a half in roundup mode.
Parameters
 i
  unsigned int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned integer value i to a halfprecision floating point value in roundup mode.
 __device__ __half __uint2half_rz ( unsigned int i )

Convert an unsigned integer to a half in roundtowardszero mode.
Parameters
 i
  unsigned int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned integer value i to a halfprecision floating point value in roundtowardszero mode.
 __device__ __half __ull2half_rd ( unsigned long long int i )

Convert an unsigned 64bit integer to a half in rounddown mode.
Parameters
 i
  unsigned long long int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned 64bit integer value i to a halfprecision floating point value in rounddown mode.
 __device__ __half __ull2half_rn ( unsigned long long int i )

Convert an unsigned 64bit integer to a half in roundtonearesteven mode.
Parameters
 i
  unsigned long long int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned 64bit integer value i to a halfprecision floating point value in roundtonearesteven mode.
 __device__ __half __ull2half_ru ( unsigned long long int i )

Convert an unsigned 64bit integer to a half in roundup mode.
Parameters
 i
  unsigned long long int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned 64bit integer value i to a halfprecision floating point value in roundup mode.
 __device__ __half __ull2half_rz ( unsigned long long int i )

Convert an unsigned 64bit integer to a half in roundtowardszero mode.
Parameters
 i
  unsigned long long int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned 64bit integer value i to a halfprecision floating point value in roundtowardszero mode.
 __device__ __half __ushort2half_rd ( unsigned short int i )

Convert an unsigned short integer to a half in rounddown mode.
Parameters
 i
  unsigned short int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned short integer value i to a halfprecision floating point value in rounddown mode.
 __device__ __half __ushort2half_rn ( unsigned short int i )

Convert an unsigned short integer to a half in roundtonearesteven mode.
Parameters
 i
  unsigned short int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned short integer value i to a halfprecision floating point value in roundtonearesteven mode.
 __device__ __half __ushort2half_ru ( unsigned short int i )

Convert an unsigned short integer to a half in roundup mode.
Parameters
 i
  unsigned short int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned short integer value i to a halfprecision floating point value in roundup mode.
 __device__ __half __ushort2half_rz ( unsigned short int i )

Convert an unsigned short integer to a half in roundtowardszero mode.
Parameters
 i
  unsigned short int
Returns
half
 \p
i converted to half.
Description
Convert the unsigned short integer value i to a halfprecision floating point value in roundtowardszero mode.
 __device__ __half __ushort_as_half ( const unsigned short int i )

Reinterprets bits in an unsigned short integer as a half.
Parameters
 i
  unsigned short int
Returns
half
 The
reinterpreted value.
Description
Reinterprets the bits in the unsigned short integer i as a halfprecision floating point number.