3. Functions
- int __nv_abs(int x)
Determine the absolute value of a 32-bit signed integer.
- double __nv_acos(double x)
Calculate the arc cosine of the input argument.
- float __nv_acosf(float x)
Calculate the arc cosine of the input argument.
- double __nv_acosh(double x)
Calculate the nonnegative arc hyperbolic cosine of the input argument.
- float __nv_acoshf(float x)
Calculate the nonnegative arc hyperbolic cosine of the input argument.
- double __nv_asin(double x)
Calculate the arc sine of the input argument.
- float __nv_asinf(float x)
Calculate the arc sine of the input argument.
- double __nv_asinh(double x)
Calculate the arc hyperbolic sine of the input argument.
- float __nv_asinhf(float x)
Calculate the arc hyperbolic sine of the input argument.
- double __nv_atan(double x)
Calculate the arc tangent of the input argument.
- double __nv_atan2(double x, double y)
Calculate the arc tangent of the ratio of first and second input arguments.
- float __nv_atan2f(float x, float y)
Calculate the arc tangent of the ratio of first and second input arguments.
- float __nv_atanf(float x)
Calculate the arc tangent of the input argument.
- double __nv_atanh(double x)
Calculate the arc hyperbolic tangent of the input argument.
- float __nv_atanhf(float x)
Calculate the arc hyperbolic tangent of the input argument.
- unsigned int __nv_brev(unsigned int x)
Reverse the bit order of a 32 bit unsigned integer.
- unsigned long long __nv_brevll(unsigned long long x)
Reverse the bit order of a 64 bit unsigned integer.
- unsigned int __nv_byte_perm(unsigned int x, unsigned int y, unsigned int z)
Return selected bytes from two 32 bit unsigned integers.
- double __nv_cbrt(double x)
Calculate the cube root of the input argument.
- float __nv_cbrtf(float x)
Calculate the cube root of the input argument.
- double __nv_ceil(double x)
Calculate ceiling of the input argument.
- float __nv_ceilf(float x)
Calculate ceiling of the input argument.
- int __nv_clz(int x)
Return the number of consecutive high-order zero bits in a 32 bit integer.
- int __nv_clzll(long long x)
Count the number of consecutive high-order zero bits in a 64 bit integer.
- double __nv_copysign(double x, double y)
Create value with given magnitude, copying sign of second value.
- float __nv_copysignf(float x, float y)
Create value with given magnitude, copying sign of second value.
- double __nv_cos(double x)
Calculate the cosine of the input argument.
- float __nv_cosf(float x)
Calculate the cosine of the input argument.
- double __nv_cosh(double x)
Calculate the hyperbolic cosine of the input argument.
- float __nv_coshf(float x)
Calculate the hyperbolic cosine of the input argument.
- double __nv_cospi(double x)
Calculate the cosine of the input argument \(\times \pi\) .
- float __nv_cospif(float x)
Calculate the cosine of the input argument \(\times \pi\) .
- double __nv_cyl_bessel_i0(double x)
Calculate the value of the regular modified cylindrical Bessel function of order 0 for the input argument.
- float __nv_cyl_bessel_i0f(float x)
Calculate the value of the regular modified cylindrical Bessel function of order 0 for the input argument.
- double __nv_cyl_bessel_i1(double x)
Calculate the value of the regular modified cylindrical Bessel function of order 1 for the input argument.
- float __nv_cyl_bessel_i1f(float x)
Calculate the value of the regular modified cylindrical Bessel function of order 1 for the input argument.
- double __nv_dadd_rd(double x, double y)
Add two floating point values in round-down mode.
- double __nv_dadd_rn(double x, double y)
Add two floating point values in round-to-nearest-even mode.
- double __nv_dadd_ru(double x, double y)
Add two floating point values in round-up mode.
- double __nv_dadd_rz(double x, double y)
Add two floating point values in round-towards-zero mode.
- double __nv_ddiv_rd(double x, double y)
Divide two floating point values in round-down mode.
- double __nv_ddiv_rn(double x, double y)
Divide two floating point values in round-to-nearest-even mode.
- double __nv_ddiv_ru(double x, double y)
Divide two floating point values in round-up mode.
- double __nv_ddiv_rz(double x, double y)
Divide two floating point values in round-towards-zero mode.
- double __nv_dmul_rd(double x, double y)
Multiply two floating point values in round-down mode.
- double __nv_dmul_rn(double x, double y)
Multiply two floating point values in round-to-nearest-even mode.
- double __nv_dmul_ru(double x, double y)
Multiply two floating point values in round-up mode.
- double __nv_dmul_rz(double x, double y)
Multiply two floating point values in round-towards-zero mode.
- float __nv_double2float_rd(double d)
Convert a double to a float in round-down mode.
- float __nv_double2float_rn(double d)
Convert a double to a float in round-to-nearest-even mode.
- float __nv_double2float_ru(double d)
Convert a double to a float in round-up mode.
- float __nv_double2float_rz(double d)
Convert a double to a float in round-towards-zero mode.
- int __nv_double2hiint(double d)
Reinterpret high 32 bits in a double as a signed integer.
- int __nv_double2int_rd(double d)
Convert a double to a signed int in round-down mode.
- int __nv_double2int_rn(double d)
Convert a double to a signed int in round-to-nearest-even mode.
- int __nv_double2int_ru(double d)
Convert a double to a signed int in round-up mode.
- int __nv_double2int_rz(double d)
Convert a double to a signed int in round-towards-zero mode.
- long long __nv_double2ll_rd(double f)
Convert a double to a signed 64-bit int in round-down mode.
- long long __nv_double2ll_rn(double f)
Convert a double to a signed 64-bit int in round-to-nearest-even mode.
- long long __nv_double2ll_ru(double f)
Convert a double to a signed 64-bit int in round-up mode.
- long long __nv_double2ll_rz(double f)
Convert a double to a signed 64-bit int in round-towards-zero mode.
- int __nv_double2loint(double d)
Reinterpret low 32 bits in a double as a signed integer.
- unsigned int __nv_double2uint_rd(double d)
Convert a double to an unsigned int in round-down mode.
- unsigned int __nv_double2uint_rn(double d)
Convert a double to an unsigned int in round-to-nearest-even mode.
- unsigned int __nv_double2uint_ru(double d)
Convert a double to an unsigned int in round-up mode.
- unsigned int __nv_double2uint_rz(double d)
Convert a double to an unsigned int in round-towards-zero mode.
- unsigned long long __nv_double2ull_rd(double f)
Convert a double to an unsigned 64-bit int in round-down mode.
- unsigned long long __nv_double2ull_rn(double f)
Convert a double to an unsigned 64-bit int in round-to-nearest-even mode.
- unsigned long long __nv_double2ull_ru(double f)
Convert a double to an unsigned 64-bit int in round-up mode.
- unsigned long long __nv_double2ull_rz(double f)
Convert a double to an unsigned 64-bit int in round-towards-zero mode.
- long long __nv_double_as_longlong(double x)
Reinterpret bits in a double as a 64-bit signed integer.
- double __nv_drcp_rd(double x)
Compute \(\frac{1}{x}\) in round-down mode.
- double __nv_drcp_rn(double x)
Compute \(\frac{1}{x}\) in round-to-nearest-even mode.
- double __nv_drcp_ru(double x)
Compute \(\frac{1}{x}\) in round-up mode.
- double __nv_drcp_rz(double x)
Compute \(\frac{1}{x}\) in round-towards-zero mode.
- double __nv_dsqrt_rd(double x)
Compute \(\sqrt{x}\) in round-down mode.
- double __nv_dsqrt_rn(double x)
Compute \(\sqrt{x}\) in round-to-nearest-even mode.
- double __nv_dsqrt_ru(double x)
Compute \(\sqrt{x}\) in round-up mode.
- double __nv_dsqrt_rz(double x)
Compute \(\sqrt{x}\) in round-towards-zero mode.
- double __nv_dsub_rd(double a, double b)
- double __nv_dsub_rn(double a, double b)
- double __nv_dsub_ru(double a, double b)
- double __nv_dsub_rz(double a, double b)
- double __nv_erf(double x)
Calculate the error function of the input argument.
- double __nv_erfc(double x)
Calculate the complementary error function of the input argument.
- float __nv_erfcf(float x)
Calculate the complementary error function of the input argument.
- double __nv_erfcinv(double x)
Calculate the inverse complementary error function of the input argument.
- float __nv_erfcinvf(float x)
Calculate the inverse complementary error function of the input argument.
- double __nv_erfcx(double x)
Calculate the scaled complementary error function of the input argument.
- float __nv_erfcxf(float x)
Calculate the scaled complementary error function of the input argument.
- float __nv_erff(float x)
Calculate the error function of the input argument.
- double __nv_erfinv(double x)
Calculate the inverse error function of the input argument.
- float __nv_erfinvf(float x)
Calculate the inverse error function of the input argument.
- double __nv_exp(double x)
Calculate the base \(e\) exponential of the input argument.
- double __nv_exp10(double x)
Calculate the base 10 exponential of the input argument.
- float __nv_exp10f(float x)
Calculate the base 10 exponential of the input argument.
- double __nv_exp2(double x)
Calculate the base 2 exponential of the input argument.
- float __nv_exp2f(float x)
Calculate the base 2 exponential of the input argument.
- float __nv_expf(float x)
Calculate the base \(e\) exponential of the input argument.
- double __nv_expm1(double x)
Calculate the base \(e\) exponential of the input argument, minus 1.
- float __nv_expm1f(float x)
Calculate the base \(e\) exponential of the input argument, minus 1.
- double __nv_fabs(double f)
Calculate the absolute value of the input argument.
- float __nv_fabsf(float f)
Calculate the absolute value of the input argument.
- float __nv_fadd_rd(float x, float y)
Add two floating point values in round-down mode.
- float __nv_fadd_rn(float x, float y)
Add two floating point values in round-to-nearest-even mode.
- float __nv_fadd_ru(float x, float y)
Add two floating point values in round-up mode.
- float __nv_fadd_rz(float x, float y)
Add two floating point values in round-towards-zero mode.
- float __nv_fast_cosf(float x)
Calculate the fast approximate cosine of the input argument.
- float __nv_fast_exp10f(float x)
Calculate the fast approximate base 10 exponential of the input argument.
- float __nv_fast_expf(float x)
Calculate the fast approximate base \(e\) exponential of the input argument.
- float __nv_fast_fdividef(float x, float y)
Calculate the fast approximate division of the input arguments.
- float __nv_fast_log10f(float x)
Calculate the fast approximate base 10 logarithm of the input argument.
- float __nv_fast_log2f(float x)
Calculate the fast approximate base 2 logarithm of the input argument.
- float __nv_fast_logf(float x)
Calculate the fast approximate base \(e\) logarithm of the input argument.
- float __nv_fast_powf(float x, float y)
Calculate the fast approximate of \(x^y\) .
- void __nv_fast_sincosf(float x, float *sptr, float *cptr)
Calculate the fast approximate of sine and cosine of the first input argument.
- float __nv_fast_sinf(float x)
Calculate the fast approximate sine of the input argument.
- float __nv_fast_tanf(float x)
Calculate the fast approximate tangent of the input argument.
- float __nv_fast_tanhf(float x)
Calculate the fast approximate hyperbolic tangent of the input argument.
- double __nv_fdim(double x, double y)
Compute the positive difference between
xandy.- float __nv_fdimf(float x, float y)
Compute the positive difference between
xandy.- float __nv_fdiv_rd(float x, float y)
Divide two floating point values in round-down mode.
- float __nv_fdiv_rn(float x, float y)
Divide two floating point values in round-to-nearest-even mode.
- float __nv_fdiv_ru(float x, float y)
Divide two floating point values in round-up mode.
- float __nv_fdiv_rz(float x, float y)
Divide two floating point values in round-towards-zero mode.
- int __nv_ffs(int x)
Find the position of the least significant bit set to 1 in a 32 bit integer.
- int __nv_ffsll(long long int x)
Find the position of the least significant bit set to 1 in a 64 bit integer.
- int __nv_finitef(float x)
Determine whether argument is finite.
- unsigned short __nv_float2half_rn(float f)
Convert a single-precision float to a half-precision float in round-to-nearest-even mode.
- int __nv_float2int_rd(float in)
Convert a float to a signed integer in round-down mode.
- int __nv_float2int_rn(float in)
Convert a float to a signed integer in round-to-nearest-even mode.
- int __nv_float2int_ru(float in)
Convert a float to a signed integer in round-up mode.
- int __nv_float2int_rz(float in)
Convert a float to a signed integer in round-towards-zero mode.
- long long __nv_float2ll_rd(float f)
Convert a float to a signed 64-bit integer in round-down mode.
- long long __nv_float2ll_rn(float f)
Convert a float to a signed 64-bit integer in round-to-nearest-even mode.
- long long __nv_float2ll_ru(float f)
Convert a float to a signed 64-bit integer in round-up mode.
- long long __nv_float2ll_rz(float f)
Convert a float to a signed 64-bit integer in round-towards-zero mode.
- unsigned int __nv_float2uint_rd(float in)
Convert a float to an unsigned integer in round-down mode.
- unsigned int __nv_float2uint_rn(float in)
Convert a float to an unsigned integer in round-to-nearest-even mode.
- unsigned int __nv_float2uint_ru(float in)
Convert a float to an unsigned integer in round-up mode.
- unsigned int __nv_float2uint_rz(float in)
Convert a float to an unsigned integer in round-towards-zero mode.
- unsigned long long __nv_float2ull_rd(float f)
Convert a float to an unsigned 64-bit integer in round-down mode.
- unsigned long long __nv_float2ull_rn(float f)
Convert a float to an unsigned 64-bit integer in round-to-nearest-even mode.
- unsigned long long __nv_float2ull_ru(float f)
Convert a float to an unsigned 64-bit integer in round-up mode.
- unsigned long long __nv_float2ull_rz(float f)
Convert a float to an unsigned 64-bit integer in round-towards-zero mode.
- int __nv_float_as_int(float x)
Reinterpret bits in a float as a signed integer.
- unsigned int __nv_float_as_uint(float x)
Reinterpret bits in a float as a unsigned integer.
- double __nv_floor(double f)
Calculate the largest integer less than or equal to
x.- float __nv_floorf(float f)
Calculate the largest integer less than or equal to
x.- double __nv_fma(double x, double y, double z)
Compute \(x \times y + z\) as a single operation.
- double __nv_fma_rd(double x, double y, double z)
Compute \(x \times y + z\) as a single operation in round-down mode.
- double __nv_fma_rn(double x, double y, double z)
Compute \(x \times y + z\) as a single operation in round-to-nearest-even mode.
- double __nv_fma_ru(double x, double y, double z)
Compute \(x \times y + z\) as a single operation in round-up mode.
- double __nv_fma_rz(double x, double y, double z)
Compute \(x \times y + z\) as a single operation in round-towards-zero mode.
- float __nv_fmaf(float x, float y, float z)
Compute \(x \times y + z\) as a single operation.
- float __nv_fmaf_ieee_rd(float x, float y, float z)
DOCUMENTATION MISSING.
- float __nv_fmaf_ieee_rn(float x, float y, float z)
DOCUMENTATION MISSING.
- float __nv_fmaf_ieee_ru(float x, float y, float z)
DOCUMENTATION MISSING.
- float __nv_fmaf_ieee_rz(float x, float y, float z)
DOCUMENTATION MISSING.
- float __nv_fmaf_rd(float x, float y, float z)
Compute \(x \times y + z\) as a single operation, in round-down mode.
- float __nv_fmaf_rn(float x, float y, float z)
Compute \(x \times y + z\) as a single operation, in round-to-nearest-even mode.
- float __nv_fmaf_ru(float x, float y, float z)
Compute \(x \times y + z\) as a single operation, in round-up mode.
- float __nv_fmaf_rz(float x, float y, float z)
Compute \(x \times y + z\) as a single operation, in round-towards-zero mode.
- double __nv_fmax(double x, double y)
Determine the maximum numeric value of the arguments.
- float __nv_fmaxf(float x, float y)
Determine the maximum numeric value of the arguments.
- double __nv_fmin(double x, double y)
Determine the minimum numeric value of the arguments.
- float __nv_fminf(float x, float y)
Determine the minimum numeric value of the arguments.
- double __nv_fmod(double x, double y)
Calculate the double-precision floating-point remainder of
x/y.- float __nv_fmodf(float x, float y)
Calculate the floating-point remainder of
x/y.- float __nv_fmul_rd(float x, float y)
Multiply two floating point values in round-down mode.
- float __nv_fmul_rn(float x, float y)
Multiply two floating point values in round-to-nearest-even mode.
- float __nv_fmul_ru(float x, float y)
Multiply two floating point values in round-up mode.
- float __nv_fmul_rz(float x, float y)
Multiply two floating point values in round-towards-zero mode.
- float __nv_frcp_rd(float x)
Compute \(\frac{1}{x}\) in round-down mode.
- float __nv_frcp_rn(float x)
Compute \(\frac{1}{x}\) in round-to-nearest-even mode.
- float __nv_frcp_ru(float x)
Compute \(\frac{1}{x}\) in round-up mode.
- float __nv_frcp_rz(float x)
Compute \(\frac{1}{x}\) in round-towards-zero mode.
- double __nv_frexp(double x, int *b)
Extract mantissa and exponent of a floating-point value.
- float __nv_frexpf(float x, int *b)
Extract mantissa and exponent of a floating-point value.
- float __nv_frsqrt_rn(float x)
Compute \(1/\sqrt{x}\) in round-to-nearest-even mode.
- float __nv_fsqrt_rd(float x)
Compute \(\sqrt{x}\) in round-down mode.
- float __nv_fsqrt_rn(float x)
Compute \(\sqrt{x}\) in round-to-nearest-even mode.
- float __nv_fsqrt_ru(float x)
Compute \(\sqrt{x}\) in round-up mode.
- float __nv_fsqrt_rz(float x)
Compute \(\sqrt{x}\) in round-towards-zero mode.
- float __nv_fsub_rd(float x, float y)
Subtract two floating point values in round-down mode.
- float __nv_fsub_rn(float x, float y)
Subtract two floating point values in round-to-nearest-even mode.
- float __nv_fsub_ru(float x, float y)
Subtract two floating point values in round-up mode.
- float __nv_fsub_rz(float x, float y)
Subtract two floating point values in round-towards-zero mode.
- int __nv_hadd(int x, int y)
Compute average of signed input arguments, avoiding overflow in the intermediate sum.
- float __nv_half2float(unsigned short h)
Convert a half-precision float to a single-precision float in round-to-nearest-even mode.
- double __nv_hiloint2double(int x, int y)
Reinterpret high and low 32-bit integer values as a double.
- double __nv_hypot(double x, double y)
Calculate the square root of the sum of squares of two arguments.
- float __nv_hypotf(float x, float y)
Calculate the square root of the sum of squares of two arguments.
- int __nv_ilogb(double x)
Compute the unbiased integer exponent of the argument.
- int __nv_ilogbf(float x)
Compute the unbiased integer exponent of the argument.
- double __nv_int2double_rn(int i)
Convert a signed int to a double.
- float __nv_int2float_rd(int in)
Convert a signed integer to a float in round-down mode.
- float __nv_int2float_rn(int in)
Convert a signed integer to a float in round-to-nearest-even mode.
- float __nv_int2float_ru(int in)
Convert a signed integer to a float in round-up mode.
- float __nv_int2float_rz(int in)
Convert a signed integer to a float in round-towards-zero mode.
- float __nv_int_as_float(int x)
Reinterpret bits in an integer as a float.
- int __nv_isfinited(double x)
Determine whether argument is finite.
- int __nv_isinfd(double x)
Determine whether argument is infinite.
- int __nv_isinff(float x)
Determine whether argument is infinite.
- int __nv_isnand(double x)
Determine whether argument is a NaN.
- int __nv_isnanf(float x)
Determine whether argument is a NaN.
- double __nv_j0(double x)
Calculate the value of the Bessel function of the first kind of order 0 for the input argument.
- float __nv_j0f(float x)
Calculate the value of the Bessel function of the first kind of order 0 for the input argument.
- double __nv_j1(double x)
Calculate the value of the Bessel function of the first kind of order 1 for the input argument.
- float __nv_j1f(float x)
Calculate the value of the Bessel function of the first kind of order 1 for the input argument.
- double __nv_jn(int n, double x)
Calculate the value of the Bessel function of the first kind of order n for the input argument.
- float __nv_jnf(int n, float x)
Calculate the value of the Bessel function of the first kind of order n for the input argument.
- double __nv_ldexp(double x, int y)
Calculate the value of \(x\cdot 2^{exp}\) .
- float __nv_ldexpf(float x, int y)
Calculate the value of \(x\cdot 2^{exp}\) .
- double __nv_lgamma(double x)
Calculate the natural logarithm of the absolute value of the gamma function of the input argument.
- float __nv_lgammaf(float x)
Calculate the natural logarithm of the absolute value of the gamma function of the input argument.
- double __nv_ll2double_rd(long long l)
Convert a signed 64-bit int to a double in round-down mode.
- double __nv_ll2double_rn(long long l)
Convert a signed 64-bit int to a double in round-to-nearest-even mode.
- double __nv_ll2double_ru(long long l)
Convert a signed 64-bit int to a double in round-up mode.
- double __nv_ll2double_rz(long long l)
Convert a signed 64-bit int to a double in round-towards-zero mode.
- float __nv_ll2float_rd(long long l)
Convert a signed integer to a float in round-down mode.
- float __nv_ll2float_rn(long long l)
Convert a signed 64-bit integer to a float in round-to-nearest-even mode.
- float __nv_ll2float_ru(long long l)
Convert a signed integer to a float in round-up mode.
- float __nv_ll2float_rz(long long l)
Convert a signed integer to a float in round-towards-zero mode.
- long long __nv_llabs(long long x)
Determine the absolute value of a 64-bit signed integer.
- long long __nv_llmax(long long x, long long y)
Determine the maximum value of two 64-bit signed integers.
- long long __nv_llmin(long long x, long long y)
Determine the minimum value of two 64-bit signed integers.
- long long int __nv_llrint(double x)
Round input to nearest integer value.
- long long int __nv_llrintf(float x)
Round input to nearest integer value.
- long long int __nv_llround(double x)
Round to nearest integer value.
- long long int __nv_llroundf(float x)
Round to nearest integer value.
- double __nv_log(double x)
Calculate the base \(e\) logarithm of the input argument.
- double __nv_log10(double x)
Calculate the base 10 logarithm of the input argument.
- float __nv_log10f(float x)
Calculate the base 10 logarithm of the input argument.
- double __nv_log1p(double x)
Calculate the value of \(log_{e}(1+x)\) \(\lfloor x \rfloor\) .
- float __nv_log1pf(float x)
Calculate the value of \(log_{e}(1+x)\) \(\lfloor x \rfloor\) .
- double __nv_log2(double x)
Calculate the base 2 logarithm of the input argument.
- float __nv_log2f(float x)
Calculate the base 2 logarithm of the input argument.
- double __nv_logb(double x)
Calculate the floating point representation of the exponent of the input argument.
- float __nv_logbf(float x)
Calculate the floating point representation of the exponent of the input argument.
- float __nv_logf(float x)
Calculate the base \(e\) logarithm of the input argument.
- double __nv_longlong_as_double(long long x)
Reinterpret bits in a 64-bit signed integer as a double.
- int __nv_max(int x, int y)
Determine the maximum value of two 32-bit signed integers.
- int __nv_min(int x, int y)
Determine the minimum value of two 32-bit signed integers.
- double __nv_modf(double x, double *b)
Break down the input argument into fractional and integral parts.
- float __nv_modff(float x, float *b)
Break down the input argument into fractional and integral parts.
- int __nv_mul24(int x, int y)
Calculate the least significant 32 bits of the product of the least significant 24 bits of two integers.
- long long __nv_mul64hi(long long x, long long y)
Calculate the most significant 64 bits of the product of the two 64 bit integers.
- int __nv_mulhi(int x, int y)
Calculate the most significant 32 bits of the product of the two 32 bit integers.
- double __nv_nan(const signed char *tagp)
Returns "Not a Number" value.
- float __nv_nanf(const signed char *tagp)
Returns "Not a Number" value.
- double __nv_nearbyint(double x)
Round the input argument to the nearest integer.
- float __nv_nearbyintf(float x)
Round the input argument to the nearest integer.
- double __nv_nextafter(double x, double y)
Return next representable double-precision floating-point value after argument.
- float __nv_nextafterf(float x, float y)
Return next representable double-precision floating-point value after argument.
- double __nv_norm(int dim, double const *a)
Calculate the square root of the sum of squares of any number of coordinates.
- double __nv_norm3d(double a, double b, double c)
Calculate the square root of the sum of squares of three coordinates of argument.
- float __nv_norm3df(float a, float b, float c)
Calculate the square root of the sum of squares of three coordinates of argument.
- double __nv_norm4d(double a, double b, double c, double d)
Calculate the square root of the sum of squares of four coordinates of argument.
- float __nv_norm4df(float a, float b, float c, float d)
Calculate the square root of the sum of squares of four coordinates of argument.
- double __nv_normcdf(double x)
Calculate the standard normal cumulative distribution function.
- float __nv_normcdff(float x)
Calculate the standard normal cumulative distribution function.
- double __nv_normcdfinv(double x)
Calculate the inverse of the standard normal cumulative distribution function.
- float __nv_normcdfinvf(float x)
Calculate the inverse of the standard normal cumulative distribution function.
- float __nv_normf(int dim, float const *a)
Calculate the square root of the sum of squares of any number of coordinates.
- int __nv_popc(int x)
Count the number of bits that are set to 1 in a 32 bit integer.
- int __nv_popcll(long long x)
Count the number of bits that are set to 1 in a 64 bit integer.
- double __nv_pow(double x, double y)
Calculate the value of first argument to the power of second argument.
- float __nv_powf(float x, float y)
Calculate the value of first argument to the power of second argument.
- double __nv_powi(double x, int y)
Calculate the value of first argument to the power of second argument.
- float __nv_powif(float x, int y)
Calculate the value of first argument to the power of second argument.
- double __nv_rcbrt(double x)
Calculate reciprocal cube root function.
- float __nv_rcbrtf(float x)
Calculate reciprocal cube root function.
- double __nv_rcp64h(double d)
DOCUMENTATION MISSING.
- double __nv_remainder(double x, double y)
Compute double-precision floating-point remainder.
- float __nv_remainderf(float x, float y)
Compute double-precision floating-point remainder.
- double __nv_remquo(double x, double y, int *c)
Compute double-precision floating-point remainder and part of quotient.
- float __nv_remquof(float x, float y, int *quo)
Compute double-precision floating-point remainder and part of quotient.
- int __nv_rhadd(int x, int y)
Compute rounded average of signed input arguments, avoiding overflow in the intermediate sum.
- double __nv_rhypot(double x, double y)
Calculate the reciprocal square root of the sum of squares of two arguments.
- float __nv_rhypotf(float x, float y)
Calculate the reciprocal square root of the sum of squares of two arguments.
- double __nv_rint(double x)
Round to nearest integer value in floating-point.
- float __nv_rintf(float x)
Round to nearest integer value in floating-point.
- double __nv_rnorm(int dim, double const *a)
Calculate the reciprocal of square root of the sum of squares of any number of coordinates.
- double __nv_rnorm3d(double a, double b, double c)
Calculate the reciprocal square root of the sum of squares of three coordinates of argument.
- float __nv_rnorm3df(float a, float b, float c)
Calculate the reciprocal square root of the sum of squares of three coordinates of argument.
- double __nv_rnorm4d(double a, double b, double c, double d)
Calculate the reciprocal square root of the sum of squares of four coordinates of argument.
- float __nv_rnorm4df(float a, float b, float c, float d)
Calculate the reciprocal square root of the sum of squares of four coordinates of argument.
- float __nv_rnormf(int dim, float const *a)
Calculate the reciprocal of square root of the sum of squares of any number of coordinates.
- double __nv_round(double x)
Round to nearest integer value in floating-point.
- float __nv_roundf(float x)
Round to nearest integer value in floating-point.
- double __nv_rsqrt(double x)
Calculate the reciprocal of the square root of the input argument.
- float __nv_rsqrtf(float x)
Calculate the reciprocal of the square root of the input argument.
- int __nv_sad(int x, int y, int z)
Calculate \(|x - y| + z\) , the sum of absolute difference.
- float __nv_saturatef(float x)
Clamp the input argument to [+0.0, 1.0].
- double __nv_scalbn(double x, int y)
Scale floating-point input by integer power of two.
- float __nv_scalbnf(float x, int y)
Scale floating-point input by integer power of two.
- int __nv_signbitd(double x)
Return the sign bit of the input.
- int __nv_signbitf(float x)
Return the sign bit of the input.
- double __nv_sin(double x)
Calculate the sine of the input argument.
- void __nv_sincos(double x, double *sptr, double *cptr)
Calculate the sine and cosine of the first input argument.
- void __nv_sincosf(float x, float *sptr, float *cptr)
Calculate the sine and cosine of the first input argument.
- void __nv_sincospi(double x, double *sptr, double *cptr)
Calculate the sine and cosine of the first input argument \(\times \pi\) .
- void __nv_sincospif(float x, float *sptr, float *cptr)
Calculate the sine and cosine of the first input argument \(\times \pi\) .
- float __nv_sinf(float x)
Calculate the sine of the input argument.
- double __nv_sinh(double x)
Calculate the hyperbolic sine of the input argument.
- float __nv_sinhf(float x)
Calculate the hyperbolic sine of the input argument.
- double __nv_sinpi(double x)
Calculate the sine of the input argument \(\times \pi\) .
- float __nv_sinpif(float x)
Calculate the sine of the input argument \(\times \pi\) .
- double __nv_sqrt(double x)
Calculate the square root of the input argument.
- float __nv_sqrtf(float x)
Calculate the square root of the input argument.
- double __nv_tan(double x)
Calculate the tangent of the input argument.
- float __nv_tanf(float x)
Calculate the tangent of the input argument.
- double __nv_tanh(double x)
Calculate the hyperbolic tangent of the input argument.
- float __nv_tanhf(float x)
Calculate the hyperbolic tangent of the input argument.
- double __nv_tgamma(double x)
Calculate the gamma function of the input argument.
- float __nv_tgammaf(float x)
Calculate the gamma function of the input argument.
- double __nv_trunc(double x)
Truncate input argument to the integral part.
- float __nv_truncf(float x)
Truncate input argument to the integral part.
- unsigned int __nv_uhadd(unsigned int x, unsigned int y)
Compute average of unsigned input arguments, avoiding overflow in the intermediate sum.
- double __nv_uint2double_rn(unsigned int i)
Convert an unsigned int to a double.
- float __nv_uint2float_rd(unsigned int in)
Convert an unsigned integer to a float in round-down mode.
- float __nv_uint2float_rn(unsigned int in)
Convert an unsigned integer to a float in round-to-nearest-even mode.
- float __nv_uint2float_ru(unsigned int in)
Convert an unsigned integer to a float in round-up mode.
- float __nv_uint2float_rz(unsigned int in)
Convert an unsigned integer to a float in round-towards-zero mode.
- float __nv_uint_as_float(unsigned int x)
Reinterpret bits in an unsigned integer as a float.
- double __nv_ull2double_rd(unsigned long long l)
Convert an unsigned 64-bit int to a double in round-down mode.
- double __nv_ull2double_rn(unsigned long long l)
Convert an unsigned 64-bit int to a double in round-to-nearest-even mode.
- double __nv_ull2double_ru(unsigned long long l)
Convert an unsigned 64-bit int to a double in round-up mode.
- double __nv_ull2double_rz(unsigned long long l)
Convert an unsigned 64-bit int to a double in round-towards-zero mode.
- float __nv_ull2float_rd(unsigned long long l)
Convert an unsigned integer to a float in round-down mode.
- float __nv_ull2float_rn(unsigned long long l)
Convert an unsigned integer to a float in round-to-nearest-even mode.
- float __nv_ull2float_ru(unsigned long long l)
Convert an unsigned integer to a float in round-up mode.
- float __nv_ull2float_rz(unsigned long long l)
Convert an unsigned integer to a float in round-towards-zero mode.
- unsigned long long __nv_ullmax(unsigned long long x, unsigned long long y)
Determine the maximum value of two 64-bit unsigned integers.
- unsigned long long __nv_ullmin(unsigned long long x, unsigned long long y)
Determine the minimum value of two 64-bit unsigned integers.
- unsigned int __nv_umax(unsigned int x, unsigned int y)
Determine the maximum value of two 32-bit unsigned integers.
- unsigned int __nv_umin(unsigned int x, unsigned int y)
Determine the minimum value of two 32-bit unsigned integers.
- unsigned int __nv_umul24(unsigned int x, unsigned int y)
Calculate the least significant 32 bits of the product of the least significant 24 bits of two unsigned integers.
- unsigned long long __nv_umul64hi(unsigned long long x, unsigned long long y)
Calculate the most significant 64 bits of the product of the two 64 unsigned bit integers.
- unsigned int __nv_umulhi(unsigned int x, unsigned int y)
Calculate the most significant 32 bits of the product of the two 32 bit unsigned integers.
- unsigned int __nv_urhadd(unsigned int x, unsigned int y)
Compute rounded average of unsigned input arguments, avoiding overflow in the intermediate sum.
- unsigned int __nv_usad(unsigned int x, unsigned int y, unsigned int z)
Calculate \(|x - y| + z\) , the sum of absolute difference.
- unsigned int __nv_vabs2(unsigned int a)
- unsigned int __nv_vabs4(unsigned int a)
- unsigned int __nv_vabsdiffs2(unsigned int a, unsigned int b)
- unsigned int __nv_vabsdiffs4(unsigned int a, unsigned int b)
- unsigned int __nv_vabsdiffu2(unsigned int a, unsigned int b)
- unsigned int __nv_vabsdiffu4(unsigned int a, unsigned int b)
- unsigned int __nv_vabsss2(unsigned int a)
- unsigned int __nv_vabsss4(unsigned int a)
- unsigned int __nv_vadd2(unsigned int a, unsigned int b)
- unsigned int __nv_vadd4(unsigned int a, unsigned int b)
- unsigned int __nv_vaddss2(unsigned int a, unsigned int b)
- unsigned int __nv_vaddss4(unsigned int a, unsigned int b)
- unsigned int __nv_vaddus2(unsigned int a, unsigned int b)
- unsigned int __nv_vaddus4(unsigned int a, unsigned int b)
- unsigned int __nv_vavgs2(unsigned int a, unsigned int b)
- unsigned int __nv_vavgs4(unsigned int a, unsigned int b)
- unsigned int __nv_vavgu2(unsigned int a, unsigned int b)
- unsigned int __nv_vavgu4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpeq2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpeq4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpges2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpges4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpgeu2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpgeu4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpgts2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpgts4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpgtu2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpgtu4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmples2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmples4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpleu2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpleu4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmplts2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmplts4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpltu2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpltu4(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpne2(unsigned int a, unsigned int b)
- unsigned int __nv_vcmpne4(unsigned int a, unsigned int b)
- unsigned int __nv_vhaddu2(unsigned int a, unsigned int b)
- unsigned int __nv_vhaddu4(unsigned int a, unsigned int b)
- unsigned int __nv_vmaxs2(unsigned int a, unsigned int b)
- unsigned int __nv_vmaxs4(unsigned int a, unsigned int b)
- unsigned int __nv_vmaxu2(unsigned int a, unsigned int b)
- unsigned int __nv_vmaxu4(unsigned int a, unsigned int b)
- unsigned int __nv_vmins2(unsigned int a, unsigned int b)
- unsigned int __nv_vmins4(unsigned int a, unsigned int b)
- unsigned int __nv_vminu2(unsigned int a, unsigned int b)
- unsigned int __nv_vminu4(unsigned int a, unsigned int b)
- unsigned int __nv_vneg2(unsigned int a)
- unsigned int __nv_vneg4(unsigned int a)
- unsigned int __nv_vnegss2(unsigned int a)
- unsigned int __nv_vnegss4(unsigned int a)
- unsigned int __nv_vsads2(unsigned int a, unsigned int b)
- unsigned int __nv_vsads4(unsigned int a, unsigned int b)
- unsigned int __nv_vsadu2(unsigned int a, unsigned int b)
- unsigned int __nv_vsadu4(unsigned int a, unsigned int b)
- unsigned int __nv_vseteq2(unsigned int a, unsigned int b)
- unsigned int __nv_vseteq4(unsigned int a, unsigned int b)
- unsigned int __nv_vsetges2(unsigned int a, unsigned int b)
- unsigned int __nv_vsetges4(unsigned int a, unsigned int b)
- unsigned int __nv_vsetgeu2(unsigned int a, unsigned int b)
- unsigned int __nv_vsetgeu4(unsigned int a, unsigned int b)
- unsigned int __nv_vsetgts2(unsigned int a, unsigned int b)
- unsigned int __nv_vsetgts4(unsigned int a, unsigned int b)
- unsigned int __nv_vsetgtu2(unsigned int a, unsigned int b)
- unsigned int __nv_vsetgtu4(unsigned int a, unsigned int b)
- unsigned int __nv_vsetles2(unsigned int a, unsigned int b)
- unsigned int __nv_vsetles4(unsigned int a, unsigned int b)
- unsigned int __nv_vsetleu2(unsigned int a, unsigned int b)
- unsigned int __nv_vsetleu4(unsigned int a, unsigned int b)
- unsigned int __nv_vsetlts2(unsigned int a, unsigned int b)
- unsigned int __nv_vsetlts4(unsigned int a, unsigned int b)
- unsigned int __nv_vsetltu2(unsigned int a, unsigned int b)
- unsigned int __nv_vsetltu4(unsigned int a, unsigned int b)
- unsigned int __nv_vsetne2(unsigned int a, unsigned int b)
- unsigned int __nv_vsetne4(unsigned int a, unsigned int b)
- unsigned int __nv_vsub2(unsigned int a, unsigned int b)
- unsigned int __nv_vsub4(unsigned int a, unsigned int b)
- unsigned int __nv_vsubss2(unsigned int a, unsigned int b)
- unsigned int __nv_vsubss4(unsigned int a, unsigned int b)
- unsigned int __nv_vsubus2(unsigned int a, unsigned int b)
- unsigned int __nv_vsubus4(unsigned int a, unsigned int b)
- double __nv_y0(double x)
Calculate the value of the Bessel function of the second kind of order 0 for the input argument.
- float __nv_y0f(float x)
Calculate the value of the Bessel function of the second kind of order 0 for the input argument.
- double __nv_y1(double x)
Calculate the value of the Bessel function of the second kind of order 1 for the input argument.
- float __nv_y1f(float x)
Calculate the value of the Bessel function of the second kind of order 1 for the input argument.
- double __nv_yn(int n, double x)
Calculate the value of the Bessel function of the second kind of order n for the input argument.
- float __nv_ynf(int n, float x)
Calculate the value of the Bessel function of the second kind of order n for the input argument.