Type Definition packed_simd_2::mptrx4

pub type mptrx4<T> = Simd<[*mut T; 4]>;

A vector with 4 *mut T lanes

Implementations

impl<T> mptrx4<T>

pub const fn new(x0: *mut T, x1: *mut T, x2: *mut T, x3: *mut T) -> Self

Creates a new instance with each vector elements initialized with the provided values.

pub const fn lanes() -> usize

Returns the number of vector lanes.

pub const fn splat(value: *mut T) -> Self

Constructs a new instance with each element initialized to value.

pub const fn null() -> Self

Constructs a new instance with each element initialized to null.

pub fn is_null(self) -> msizex4

Returns a mask that selects those lanes that contain null pointers.

pub fn extract(self, index: usize) -> *mut T

Extracts the value at index.

Panics

If index >= Self::lanes().

pub unsafe fn extract_unchecked(self, index: usize) -> *mut T

Extracts the value at index.

Safety

If index >= Self::lanes() the behavior is undefined.

pub fn replace(self, index: usize, new_value: *mut T) -> Self

Returns a new vector where the value at index is replaced by new_value.

Panics

If index >= Self::lanes().

pub unsafe fn replace_unchecked(self, index: usize, new_value: *mut T) -> Self

Returns a new vector where the value at index is replaced by new_value.

Safety

If index >= Self::lanes() the behavior is undefined.

impl<T> mptrx4<T>

pub fn eq(self, other: Self) -> msizex4

Lane-wise equality comparison.

pub fn ne(self, other: Self) -> msizex4

Lane-wise inequality comparison.

pub fn lt(self, other: Self) -> msizex4

Lane-wise less-than comparison.

pub fn le(self, other: Self) -> msizex4

Lane-wise less-than-or-equals comparison.

pub fn gt(self, other: Self) -> msizex4

Lane-wise greater-than comparison.

pub fn ge(self, other: Self) -> msizex4

Lane-wise greater-than-or-equals comparison.

impl<T> mptrx4<T>

pub fn from_slice_aligned(slice: &[*mut T]) -> Self

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.

pub fn from_slice_unaligned(slice: &[*mut T]) -> Self

Instantiates a new vector with the values of the slice.

Panics

If slice.len() < Self::lanes().

pub unsafe fn from_slice_aligned_unchecked(slice: &[*mut T]) -> Self

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.

pub unsafe fn from_slice_unaligned_unchecked(slice: &[*mut T]) -> Self

Instantiates a new vector with the values of the slice.

Safety

If slice.len() < Self::lanes() the behavior is undefined.

impl<T> mptrx4<T>

pub fn write_to_slice_aligned(self, slice: &mut [*mut T])

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.

pub fn write_to_slice_unaligned(self, slice: &mut [*mut T])

Writes the values of the vector to the slice.

Panics

If slice.len() < Self::lanes().

pub unsafe fn write_to_slice_aligned_unchecked(self, slice: &mut [*mut T])

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.

pub unsafe fn write_to_slice_unaligned_unchecked(self, slice: &mut [*mut T])

Writes the values of the vector to the slice.

Safety

If slice.len() < Self::lanes() the behavior is undefined.

impl<T> mptrx4<T>

pub unsafe fn offset(self, count: isizex4) -> Self

Calculates the offset from a pointer.

count is in units of T; e.g. a count of 3 represents a pointer offset of 3 * size_of::<T>() bytes.

Safety

If any of the following conditions are violated, the result is Undefined Behavior:

• Both the starting and resulting pointer must be either in bounds or one byte past the end of an allocated object.

• The computed offset, in bytes, cannot overflow an isize.

• The offset being in bounds cannot rely on “wrapping around” the address space. That is, the infinite-precision sum, in bytes must fit in a usize.

The compiler and standard library generally tries to ensure allocations never reach a size where an offset is a concern. For instance, Vec and Box ensure they never allocate more than isize::MAX bytes, so vec.as_ptr().offset(vec.len() as isize) is always safe.

Most platforms fundamentally can’t even construct such an allocation. For instance, no known 64-bit platform can ever serve a request for 263 bytes due to page-table limitations or splitting the address space. However, some 32-bit and 16-bit platforms may successfully serve a request for more than isize::MAX bytes with things like Physical Address Extension. As such, memory acquired directly from allocators or memory mapped files may be too large to handle with this function.

Consider using wrapping_offset instead if these constraints are difficult to satisfy. The only advantage of this method is that it enables more aggressive compiler optimizations.

pub fn wrapping_offset(self, count: isizex4) -> Self

Calculates the offset from a pointer using wrapping arithmetic.

count is in units of T; e.g. a count of 3 represents a pointer offset of 3 * size_of::<T>() bytes.

Safety

The resulting pointer does not need to be in bounds, but it is potentially hazardous to dereference (which requires unsafe).

Always use .offset(count) instead when possible, because offset allows the compiler to optimize better.

pub unsafe fn offset_from(self, origin: Self) -> isizex4

Calculates the distance between two pointers.

The returned value is in units of T: the distance in bytes is divided by mem::size_of::<T>().

This function is the inverse of offset.

Safety

If any of the following conditions are violated, the result is Undefined Behavior:

• Both the starting and other pointer must be either in bounds or one byte past the end of the same allocated object.

• The distance between the pointers, in bytes, cannot overflow an isize.

• The distance between the pointers, in bytes, must be an exact multiple of the size of T.

• The distance being in bounds cannot rely on “wrapping around” the address space.

The compiler and standard library generally try to ensure allocations never reach a size where an offset is a concern. For instance, Vec and Box ensure they never allocate more than isize::MAX bytes, so ptr_into_vec.offset_from(vec.as_ptr()) is always safe.

Most platforms fundamentally can’t even construct such an allocation. For instance, no known 64-bit platform can ever serve a request for 263 bytes due to page-table limitations or splitting the address space. However, some 32-bit and 16-bit platforms may successfully serve a request for more than isize::MAX bytes with things like Physical Address Extension. As such, memory acquired directly from allocators or memory mapped files may be too large to handle with this function.

Consider using wrapping_offset_from instead if these constraints are difficult to satisfy. The only advantage of this method is that it enables more aggressive compiler optimizations.

pub fn wrapping_offset_from(self, origin: Self) -> isizex4

Calculates the distance between two pointers.

The returned value is in units of T: the distance in bytes is divided by mem::size_of::<T>().

If the address different between the two pointers is not a multiple of mem::size_of::<T>() then the result of the division is rounded towards zero.

Though this method is safe for any two pointers, note that its result will be mostly useless if the two pointers aren’t into the same allocated object, for example if they point to two different local variables.

pub unsafe fn add(self, count: usizex4) -> Self

Calculates the offset from a pointer (convenience for .offset(count as isize)).

count is in units of T; e.g. a count of 3 represents a pointer offset of 3 * size_of::<T>() bytes.

Safety

If any of the following conditions are violated, the result is Undefined Behavior:

• Both the starting and resulting pointer must be either in bounds or one byte past the end of an allocated object.

• The computed offset, in bytes, cannot overflow an isize.

• The offset being in bounds cannot rely on “wrapping around” the address space. That is, the infinite-precision sum must fit in a usize.

The compiler and standard library generally tries to ensure allocations never reach a size where an offset is a concern. For instance, Vec and Box ensure they never allocate more than isize::MAX bytes, so vec.as_ptr().add(vec.len()) is always safe.

Most platforms fundamentally can’t even construct such an allocation. For instance, no known 64-bit platform can ever serve a request for 263 bytes due to page-table limitations or splitting the address space. However, some 32-bit and 16-bit platforms may successfully serve a request for more than isize::MAX bytes with things like Physical Address Extension. As such, memory acquired directly from allocators or memory mapped files may be too large to handle with this function.

Consider using wrapping_offset instead if these constraints are difficult to satisfy. The only advantage of this method is that it enables more aggressive compiler optimizations.

pub unsafe fn sub(self, count: usizex4) -> Self

Calculates the offset from a pointer (convenience for .offset((count as isize).wrapping_neg())).

count is in units of T; e.g. a count of 3 represents a pointer offset of 3 * size_of::<T>() bytes.

Safety

If any of the following conditions are violated, the result is Undefined Behavior:

• Both the starting and resulting pointer must be either in bounds or one byte past the end of an allocated object.

• The computed offset cannot exceed isize::MAX bytes.

• The offset being in bounds cannot rely on “wrapping around” the address space. That is, the infinite-precision sum must fit in a usize.

The compiler and standard library generally tries to ensure allocations never reach a size where an offset is a concern. For instance, Vec and Box ensure they never allocate more than isize::MAX bytes, so vec.as_ptr().add(vec.len()).sub(vec.len()) is always safe.

Most platforms fundamentally can’t even construct such an allocation. For instance, no known 64-bit platform can ever serve a request for 2⁶³ bytes due to page-table limitations or splitting the address space. However, some 32-bit and 16-bit platforms may successfully serve a request for more than isize::MAX bytes with things like Physical Address Extension. As such, memory acquired directly from allocators or memory mapped files may be too large to handle with this function.

Consider using wrapping_offset instead if these constraints are difficult to satisfy. The only advantage of this method is that it enables more aggressive compiler optimizations.

pub fn wrapping_add(self, count: usizex4) -> Self

Calculates the offset from a pointer using wrapping arithmetic. (convenience for .wrapping_offset(count as isize))

count is in units of T; e.g. a count of 3 represents a pointer offset of 3 * size_of::<T>() bytes.

Safety

The resulting pointer does not need to be in bounds, but it is potentially hazardous to dereference (which requires unsafe).

Always use .add(count) instead when possible, because add allows the compiler to optimize better.

pub fn wrapping_sub(self, count: usizex4) -> Self

Calculates the offset from a pointer using wrapping arithmetic. (convenience for .wrapping_offset((count as isize).wrapping_sub()))

count is in units of T; e.g. a count of 3 represents a pointer offset of 3 * size_of::<T>() bytes.

Safety

The resulting pointer does not need to be in bounds, but it is potentially hazardous to dereference (which requires unsafe).

Always use .sub(count) instead when possible, because sub allows the compiler to optimize better.

impl<T> mptrx4<T>

pub fn shuffle1_dyn<I>(self, indices: I) -> Self where
    Self: Shuffle1Dyn<Indices = I>, 

Shuffle vector elements according to indices.

impl<T> mptrx4<T> where
    [T; 4]: SimdArray, 

pub unsafe fn read<M>(
    self,
    mask: Simd<[M; 4]>,
    value: Simd<[T; 4]>
) -> Simd<[T; 4]> where
    M: Mask,
    [M; 4]: SimdArray, 

Reads selected vector elements from memory.

Instantiates a new vector by reading the values from self for those lanes whose mask is true, and using the elements of value otherwise.

No memory is accessed for those lanes of self whose mask is false.

Safety

This method is unsafe because it dereferences raw pointers. The pointers must be aligned to mem::align_of::<T>().

impl<T> mptrx4<T> where
    [T; 4]: SimdArray, 

pub unsafe fn write<M>(self, mask: Simd<[M; 4]>, value: Simd<[T; 4]>) where
    M: Mask,
    [M; 4]: SimdArray, 

Writes selected vector elements to memory.

Writes the lanes of values for which the mask is true to their corresponding memory addresses in self.

No memory is accessed for those lanes of self whose mask is false.

Overlapping memory addresses of self are written to in order from the lest-significant to the most-significant element.

Safety

This method is unsafe because it dereferences raw pointers. The pointers must be aligned to mem::align_of::<T>().

Trait Implementations

impl<T> Debug for mptrx4<T>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<T> Default for mptrx4<T>

fn default() -> Self

Returns the “default value” for a type.

impl<T> From<[*mut T; 4]> for mptrx4<T>

fn from(array: [*mut T; 4]) -> Self

Converts to this type from the input type.

impl<T> Hash for mptrx4<T>

fn hash<H: Hasher>(&self, state: &mut H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H) where
    H: Hasher, 

Feeds a slice of this type into the given Hasher.

impl<T> Into<[*mut T; 4]> for mptrx4<T>

fn into(self) -> [*mut T; 4]

Converts this type into the (usually inferred) input type.

impl<T> PartialEq<Simd<[*mut T; 4]>> for mptrx4<T>

fn eq(&self, other: &Self) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Self) -> bool

This method tests for !=.

impl<T> Simd for mptrx4<T>

type Element = *mut T

Element type of the SIMD vector

const LANES: usize = 4usize

The number of elements in the SIMD vector.

type LanesType = [u32; 4]

The type: [u32; Self::N].

impl<T> Eq for mptrx4<T>