Single Precision Floating-point Intrinsics#
Functions | |
__DEVICE__ float | __cosf (float __x) |
Returns the fast approximate cosine of x . | |
__DEVICE__ float | __exp10f (float __x) |
Returns the fast approximate for \( 10^x \). | |
__DEVICE__ float | __expf (float __x) |
Returns the fast approximate for \( e^x \). | |
__DEVICE__ float | __fadd_rn (float __x, float __y) |
Add two floating-point values in round-to-nearest-even mode. | |
__DEVICE__ float | __fdiv_rn (float __x, float __y) |
Divide two floating-point values in round-to-nearest-even mode. | |
__DEVICE__ float | __fdividef (float __x, float __y) |
Returns the fast approximate of x / y . | |
__DEVICE__ float | __fmaf_rn (float __x, float __y, float __z) |
Returns \(x \cdot y + z\) as a single operation, in round-to-nearest-even mode. | |
__DEVICE__ float | __fmul_rn (float __x, float __y) |
Multiply two floating-point values in round-to-nearest-even mode. | |
__DEVICE__ float | __frcp_rn (float __x) |
Returns 1 / x in round-to-nearest-even mod. | |
__DEVICE__ float | __frsqrt_rn (float __x) |
Returns \( 1 / \sqrt{x}\) in round-to-nearest-even mode. | |
__DEVICE__ float | __fsqrt_rn (float __x) |
Returns \(\sqrt{x}\) in round-to-nearest-even mode. | |
__DEVICE__ float | __fsub_rn (float __x, float __y) |
Subtract two floating-point values in round-to-nearest-even mode. | |
__DEVICE__ float | __log10f (float __x) |
Returns the fast approximate for base 10 logarithm of x . | |
__DEVICE__ float | __log2f (float __x) |
Returns the fast approximate for base 2 logarithm of x . | |
__DEVICE__ float | __logf (float __x) |
Returns the fast approximate for natural logarithm of x . | |
__DEVICE__ float | __powf (float __x, float __y) |
Returns the fast approximate of \( x^y \). | |
__DEVICE__ float | __saturatef (float __x) |
Clamp x to [+0.0, 1.0]. | |
__DEVICE__ void | __sincosf (float __x, float *__sinptr, float *__cosptr) |
Returns the fast approximate of sine and cosine of x . | |
__DEVICE__ float | __sinf (float __x) |
Returns the fast approximate sine of x . | |
__DEVICE__ float | __tanf (float __x) |
Returns the fast approximate tangent of x . | |
Detailed Description
Single Precision Floating-point Intrinsics
Function Documentation
◆ __cosf()
__DEVICE__ float __cosf | ( | float | __x | ) |
Returns the fast approximate cosine of x
.
◆ __exp10f()
__DEVICE__ float __exp10f | ( | float | __x | ) |
Returns the fast approximate for \( 10^x \).
◆ __expf()
__DEVICE__ float __expf | ( | float | __x | ) |
Returns the fast approximate for \( e^x \).
◆ __fadd_rn()
__DEVICE__ float __fadd_rn | ( | float | __x, |
float | __y | ||
) |
Add two floating-point values in round-to-nearest-even mode.
◆ __fdiv_rn()
__DEVICE__ float __fdiv_rn | ( | float | __x, |
float | __y | ||
) |
Divide two floating-point values in round-to-nearest-even mode.
◆ __fdividef()
__DEVICE__ float __fdividef | ( | float | __x, |
float | __y | ||
) |
Returns the fast approximate of x / y
.
◆ __fmaf_rn()
__DEVICE__ float __fmaf_rn | ( | float | __x, |
float | __y, | ||
float | __z | ||
) |
Returns \(x \cdot y + z\) as a single operation, in round-to-nearest-even mode.
◆ __fmul_rn()
__DEVICE__ float __fmul_rn | ( | float | __x, |
float | __y | ||
) |
Multiply two floating-point values in round-to-nearest-even mode.
◆ __frcp_rn()
__DEVICE__ float __frcp_rn | ( | float | __x | ) |
Returns 1 / x in round-to-nearest-even mod.
◆ __frsqrt_rn()
__DEVICE__ float __frsqrt_rn | ( | float | __x | ) |
Returns \( 1 / \sqrt{x}\) in round-to-nearest-even mode.
◆ __fsqrt_rn()
__DEVICE__ float __fsqrt_rn | ( | float | __x | ) |
Returns \(\sqrt{x}\) in round-to-nearest-even mode.
◆ __fsub_rn()
__DEVICE__ float __fsub_rn | ( | float | __x, |
float | __y | ||
) |
Subtract two floating-point values in round-to-nearest-even mode.
◆ __log10f()
__DEVICE__ float __log10f | ( | float | __x | ) |
Returns the fast approximate for base 10 logarithm of x
.
◆ __log2f()
__DEVICE__ float __log2f | ( | float | __x | ) |
Returns the fast approximate for base 2 logarithm of x
.
◆ __logf()
__DEVICE__ float __logf | ( | float | __x | ) |
Returns the fast approximate for natural logarithm of x
.
◆ __powf()
__DEVICE__ float __powf | ( | float | __x, |
float | __y | ||
) |
Returns the fast approximate of \( x^y \).
◆ __saturatef()
__DEVICE__ float __saturatef | ( | float | __x | ) |
Clamp x
to [+0.0, 1.0].
◆ __sincosf()
__DEVICE__ void __sincosf | ( | float | __x, |
float * | __sinptr, | ||
float * | __cosptr | ||
) |
Returns the fast approximate of sine and cosine of x
.
◆ __sinf()
__DEVICE__ float __sinf | ( | float | __x | ) |
Returns the fast approximate sine of x
.
◆ __tanf()
__DEVICE__ float __tanf | ( | float | __x | ) |
Returns the fast approximate tangent of x
.