Multiply the packed unsigned 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate intege

Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most si

Provides a hint that allows the processor to enter an implementation- dependent optimized state while waiting for a memory write to the monitored addr

Count the number of bits set to 1 in unsigned 32-bit integer a, and return that count in dst. https://www.intel.com/content/www/us/en/docs/intrinsics-

Count the number of bits set to 1 in unsigned 64-bit integer a, and return that count in dst. https://www.intel.com/content/www/us/en/docs/intrinsics-

Compute the absolute differences of packed unsigned 8-bit integers in a and b, then horizontally sum each consecutive 8 differences to produce four un

Broadcast 64-bit integer a to all elements of dst. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm_set1_epi64

Set packed 16-bit integers in dst with the supplied values. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm_set_epi1

Set packed 64-bit integers in dst with the supplied values. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm_set_epi6

Broadcast single-precision (32-bit) floating-point value a to all elements of dst. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index

Set packed 16-bit integers in dst with the supplied values in reverse order. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#

Set packed 32-bit integers in dst with the supplied values in reverse order. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#

Set packed 64-bit integers in dst with the supplied values in reverse order. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#

Set packed 8-bit integers in dst with the supplied values in reverse order. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#t

Set packed double-precision (64-bit) floating-point elements in dst with the supplied values in reverse order. https://www.intel.com/content/www/us/en

Shuffle packed 8-bit integers in a according to shuffle control mask in the corresponding 8-bit element of b, and store the results in dst. https://ww

Negate packed 16-bit integers in a when the corresponding signed 16-bit integer in b is negative, and store the results in dst. Element in dst are zer

Negate packed 32-bit integers in a when the corresponding signed 32-bit integer in b is negative, and store the results in dst. Element in dst are zer

Negate packed 8-bit integers in a when the corresponding signed 8-bit integer in b is negative, and store the results in dst. Element in dst are zeroe

Shift packed 16-bit integers in a left by imm8 while shifting in zeros, and store the results in dst. https://www.intel.com/content/www/us/en/docs/int

Store the lower double-precision (64-bit) floating-point element from a into 2 contiguous elements in memory. mem_addr must be aligned on a 16-byte bo

Store the lower single-precision (32-bit) floating-point element from a into 4 contiguous elements in memory. mem_addr must be aligned on a 16-byte bo

Store the lower double-precision (64-bit) floating-point element from a into memory. mem_addr does not need to be aligned on any particular boundary.

Store the lower single-precision (32-bit) floating-point element from a into memory. mem_addr does not need to be aligned on any particular boundary.

Store the upper double-precision (64-bit) floating-point element from a into memory. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/ind

Store the upper 2 single-precision (32-bit) floating-point elements from a into memory. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/

Store the lower double-precision (64-bit) floating-point element from a into memory. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/ind

Store the lower 2 single-precision (32-bit) floating-point elements from a into memory. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/

Store 2 double-precision (64-bit) floating-point elements from a into memory in reverse order. mem_addr must be aligned on a 16-byte boundary or a gen

Store 4 single-precision (32-bit) floating-point elements from a into memory in reverse order. mem_addr must be aligned on a 16-byte boundary or a gen

Stores 16-bits of integer data a at the address p. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm_storeu_si16

Store 32-bit integer a into memory using a non-temporal hint to minimize cache pollution. If the cache line containing address mem_addr is already in

Store 64-bit integer a into memory using a non-temporal hint to minimize cache pollution. If the cache line containing address mem_addr is already in

Subtract 64-bit integer b from 64-bit integer a, and store the result in dst. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html

Compute the bitwise NOT of a and then AND with a 128-bit vector containing all 1's, and return 1 if the result is zero, otherwise return 0. https://ww

Compute the bitwise AND of 128 bits (representing integer data) in a and mask, and return 1 if the result is zero, otherwise return 0. https://www.int

Compute the bitwise AND of 128 bits (representing integer data) in a and mask, and set ZF to 1 if the result is zero, otherwise set ZF to 0. Compute t

Return vector of type __m128d with undefined elements. Note: MSVC forces zero-initialization while GCC/Clang return truly undefined memory. Use SSE2NE

ARMv7: OR-based reduction - 3 ops vs 4 ops for vpmax cascade */

Compare implemented intrinsics against Intel reference. Returns coverage statistics by instruction set.

Analyze a single intrinsic implementation.

Build the differential test harness for x86.

Verify we're running on x86.

Clear all cached results. Returns count of files removed.

Compare two outputs with optional tolerance */

Compute confidence metrics for an intrinsic's tier classification. Args: analysis: The intrinsic analysis result has_asm: Wh

Count actual NEON intrinsics in function body with context-aware matching. Improvements over simple regex: 1. Removes comments and string lit

Count NEON intrinsics using Clang AST traversal. Returns the count or None if analysis fails. Uses hash-based caching for id

Count vreinterpret casts (don't generate instructions). Uses same context-aware approach as count_neon_intrinsics.

Compile intrinsic and count SIMD instructions in generated assembly. Returns instruction count or None if compilation fails.

Helper to create directory if it doesn't exist */

Extract specific function content from header file.

Extract the complete function body from starting line.

Parse sse2neon.h and extract all implemented intrinsic names. Returns a set of intrinsic function names.

Find a suitable C++ compiler.

Run the differential harness to generate golden data.

Generate golden data for a single intrinsic */

Generate summary statistics.

Return (cache_hits, cache_misses) statistics.

Check if AST node represents a NEON intrinsic call.

Check if a float is a quiet NaN (MSB of mantissa = 1) */

Negative double qNaN */

Double precision sNaN */

Parse sse2neon.h and analyze all intrinsics. Args: filepath: Path to sse2neon.h use_unifdef: If True, preprocess with unifde

Preprocess sse2neon.h with unifdef to get AArch64-specific code paths. Returns the preprocessed content as a string, or None if unifdef is n

Print analysis as JSON.

Print analysis as markdown report.

Print coverage report to stdout.

Print validation report to stderr.

Print detailed verbose report. Args: results: List of intrinsic analyses show_confidence: If True, compute and display confidence

Level 3: Apply assembly generation analysis to specified tier intrinsics. Most accurate method - compiles intrinsics and counts actual SIMD

Apply Clang AST analysis to specified tier intrinsics for more precise NEON count. Args: results: List of intrinsic analyses