Type Definition packed_simd_2::f64x8
source · [−]Expand description
A 512-bit vector with 8 f64
lanes.
Implementations
Creates a new instance with each vector elements initialized with the provided values.
Constructs a new instance with each element initialized to
value
.
Returns a new vector where the value at index
is replaced by new_value
.
Panics
If index >= Self::lanes()
.
Returns a new vector where the value at index
is replaced by new_value
.
Safety
If index >= Self::lanes()
the behavior is undefined.
Horizontal sum of the vector elements.
The intrinsic performs a tree-reduction of the vector elements. That is, for an 8 element vector:
((x0 + x1) + (x2 + x3)) + ((x4 + x5) + (x6 + x7))
If one of the vector element is NaN
the reduction returns
NaN
. The resulting NaN
is not required to be equal to any
of the NaN
s in the vector.
Horizontal product of the vector elements.
The intrinsic performs a tree-reduction of the vector elements. That is, for an 8 element vector:
((x0 * x1) * (x2 * x3)) * ((x4 * x5) * (x6 * x7))
If one of the vector element is NaN
the reduction returns
NaN
. The resulting NaN
is not required to be equal to any
of the NaN
s in the vector.
Largest vector element value.
Smallest vector element value.
Instantiates a new vector with the values of the slice
.
Panics
If slice.len() < Self::lanes()
or &slice[0]
is not aligned
to an align_of::<Self>()
boundary.
Instantiates a new vector with the values of the slice
.
Safety
If slice.len() < Self::lanes()
or &slice[0]
is not aligned
to an align_of::<Self>()
boundary, the behavior is undefined.
Writes the values of the vector to the slice
.
Panics
If slice.len() < Self::lanes()
or &slice[0]
is not
aligned to an align_of::<Self>()
boundary.
Writes the values of the vector to the slice
.
Safety
If slice.len() < Self::lanes()
or &slice[0]
is not
aligned to an align_of::<Self>()
boundary, the behavior is
undefined.
Shuffle vector elements according to indices
.
Smallest positive normal value.
Negative infinity (-∞).
2/sqrt(π)
1/sqrt(2)
Fused multiply add estimate: ~= self * y + z
While fused multiply-add (fma
) has infinite precision,
mul_adde
has at worst the same precision of a multiply followed by an add.
This might be more efficient on architectures that do not have an fma
instruction.
Trait Implementations
Performs the +=
operation. Read more
Performs the +=
operation. Read more
Performs the /=
operation. Read more
Performs the /=
operation. Read more
Performs the *=
operation. Read more
Performs the *=
operation. Read more
Performs the %=
operation. Read more
Performs the %=
operation. Read more
Performs the -=
operation. Read more
Performs the -=
operation. Read more