Module simd

🔬This is a nightly-only experimental API. (core_intrinsics)

SIMD compiler intrinsics.

In this module, a “vector” is any repr(simd) type.

Functions

• simd_add^⚠Experimental
  Adds two simd vectors elementwise.
• simd_and^⚠Experimental
  “Ands” vectors elementwise.
• simd_arith_offset^⚠Experimental
  Calculates the offset from a pointer vector elementwise, potentially wrapping.
• simd_as^⚠Experimental
  Numerically casts a vector, elementwise.
• simd_bitmask^⚠Experimental
  Truncates an integer vector to a bitmask.
• simd_bitreverse^⚠Experimental
  Reverses bits of each element.
• simd_bswap^⚠Experimental
  Swaps bytes of each element.
• simd_cast^⚠Experimental
  Numerically casts a vector, elementwise.
• simd_cast_ptr^⚠Experimental
  Casts a vector of pointers.
• simd_ceil^⚠Experimental
  Rounds up each element to the next highest integer-valued float.
• simd_ctlz^⚠Experimental
  Counts the leading zeros of each element.
• simd_ctpop^⚠Experimental
  Counts the number of ones in each element.
• simd_cttz^⚠Experimental
  Counts the trailing zeros of each element.
• simd_div^⚠Experimental
  Divides lhs by rhs elementwise.
• simd_eq^⚠Experimental
  Tests elementwise equality of two vectors.
• simd_expose_provenance^⚠Experimental
  Exposes a vector of pointers as a vector of addresses.
• simd_extract^⚠Experimental
  Extracts an element from a vector.
• simd_fabs^⚠Experimental
  Returns absolute value of a vector, elementwise.
• simd_fcos^⚠Experimental
  T must be a vector of floats.
• simd_fexp^⚠Experimental
  T must be a vector of floats.
• simd_fexp2^⚠Experimental
  T must be a vector of floats.
• simd_flog^⚠Experimental
  T must be a vector of floats.
• simd_flog2^⚠Experimental
  T must be a vector of floats.
• simd_flog10^⚠Experimental
  T must be a vector of floats.
• simd_floor^⚠Experimental
  Rounds down each element to the next lowest integer-valued float.
• simd_fma^⚠Experimental
  Computes (x*y) + z for each element, but without any intermediate rounding.
• simd_fmax^⚠Experimental
  Returns the maximum of two vectors, elementwise.
• simd_fmin^⚠Experimental
  Returns the minimum of two vectors, elementwise.
• simd_fsin^⚠Experimental
  T must be a vector of floats.
• simd_fsqrt^⚠Experimental
  Takes the square root of each element.
• simd_gather^⚠Experimental
  Reads a vector of pointers.
• simd_ge^⚠Experimental
  Tests if x is greater than or equal to y, elementwise.
• simd_gt^⚠Experimental
  Tests if x is greater than y, elementwise.
• simd_insert^⚠Experimental
  Inserts an element into a vector, returning the updated vector.
• simd_le^⚠Experimental
  Tests if x is less than or equal to y, elementwise.
• simd_lt^⚠Experimental
  Tests if x is less than y, elementwise.
• simd_masked_load^⚠Experimental
  Reads a vector of pointers.
• simd_masked_store^⚠Experimental
  Writes to a vector of pointers.
• simd_mul^⚠Experimental
  Multiplies two simd vectors elementwise.
• simd_ne^⚠Experimental
  Tests elementwise inequality equality of two vectors.
• simd_neg^⚠Experimental
  Negates a vector elementwise.
• simd_or^⚠Experimental
  “Ors” vectors elementwise.
• simd_reduce_add_ordered^⚠Experimental
  Adds elements within a vector from left to right.
• simd_reduce_add_unordered^⚠Experimental
  Adds elements within a vector in arbitrary order. May also be re-associated with unordered additions on the inputs/outputs.
• simd_reduce_all^⚠Experimental
  Checks if all mask values are true.
• simd_reduce_and^⚠Experimental
  Logical “ands” all elements together.
• simd_reduce_any^⚠Experimental
  Checks if any mask value is true.
• simd_reduce_max^⚠Experimental
  Returns the maximum element of a vector.
• simd_reduce_min^⚠Experimental
  Returns the minimum element of a vector.
• simd_reduce_mul_ordered^⚠Experimental
  Multiplies elements within a vector from left to right.
• simd_reduce_mul_unordered^⚠Experimental
  Multiplies elements within a vector in arbitrary order. May also be re-associated with unordered additions on the inputs/outputs.
• simd_reduce_or^⚠Experimental
  Logical “ors” all elements together.
• simd_reduce_xor^⚠Experimental
  Logical “exclusive ors” all elements together.
• simd_relaxed_fma^⚠Experimental
  Computes (x*y) + z for each element, non-deterministically executing either a fused multiply-add or two operations with rounding of the intermediate result.
• simd_rem^⚠Experimental
  Returns remainder of two vectors elementwise.
• simd_round^⚠Experimental
  Rounds each element to the closest integer-valued float. Ties are resolved by rounding away from 0.
• simd_saturating_add^⚠Experimental
  Adds two simd vectors elementwise, with saturation.
• simd_saturating_sub^⚠Experimental
  Subtracts two simd vectors elementwise, with saturation.
• simd_scatter^⚠Experimental
  Writes to a vector of pointers.
• simd_select^⚠Experimental
  Selects elements from a mask.
• simd_select_bitmask^⚠Experimental
  Selects elements from a bitmask.
• simd_shl^⚠Experimental
  Shifts vector left elementwise, with UB on overflow.
• simd_shr^⚠Experimental
  Shifts vector right elementwise, with UB on overflow.
• simd_shuffle^⚠Experimental
  Shuffles two vectors by const indices.
• simd_sub^⚠Experimental
  Subtracts rhs from lhs elementwise.
• simd_trunc^⚠Experimental
  Returns the integer part of each element as an integer-valued float. In other words, non-integer values are truncated towards zero.
• simd_with_exposed_provenance^⚠Experimental
  Creates a vector of pointers from a vector of addresses.
• simd_xor^⚠Experimental
  “Exclusive ors” vectors elementwise.