quantize to 4 bits, expand to 8 bits

This version doesn't truncate and is simpler

Add packed 16-bit integers in a and b, and store the results in dst. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm

Compute the bitwise NOT of 128 bits (representing integer data) in a and then AND with b, and store the result in dst. https://www.intel.com/content/w

Perform a carry-less multiplication of two 64-bit integers, selected from a and b according to imm8, and store the results in dst. https://www.intel.c

Copy the lower 64-bit integer in a to dst. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm_cvtsi128_si64

Vertically multiply each unsigned 8-bit integer from a with the corresponding signed 8-bit integer from b, producing intermediate signed 16-bit intege

Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst. dst does not follow the IEEE Stan

Create mask from the most significant bit of each 8-bit element in a, and store the result in dst. https://www.intel.com/content/www/us/en/docs/intrin

Multiply the packed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the low 16 bits of the intermediate integers in dst.

Compute the bitwise OR of packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst. https://www.intel.com/con

Compute the bitwise OR of 128 bits (representing integer data) in a and b, and store the result in dst. https://www.intel.com/content/www/us/en/docs/i

Convert packed signed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation, and store the results in dst. https://www.inte

Broadcast 32-bit integer a to all elements of dst. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm_set1_epi32

Set packed 32-bit integers in dst with the supplied values. https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#text=_mm_set_epi3

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

Compute the bitwise XOR of 128 bits (representing integer data) in a and b, and store the result in dst. https://www.intel.com/content/www/us/en/docs/

ARMv7 polyfill ARMv7/some A64 lacks vmull_p64, but it has vmull_p8. vmull_p8 calculates 8 8-bit->16-bit polynomial multiplies, but we need a 64-bit->

ARMv7 polyfill ARMv7/some A64 lacks vmull_p64, but it has vmull_p8. vmull_p8 calculates 8 8-bit->16-bit polynomial multiplies, but we need a 64-bit->

The allocate_padded_buffer function is a low-level function to allocate memory with padding so we can read past the "length" bytes safely. It is used

The allocate_padded_buffer function is a low-level function to allocate memory with padding so we can read past the "length" bytes safely. It is used

* @brief Generate a prefix-sum array using the Brent-Kung algorithm. * * This will take an input array of the form: * v0, v1, v2, ... * ... an

can_allocate Returns true if there are any free links.

given a code point cp, writes to c the utf-8 code, outputting the length in bytes, if the length is zero, the code point is invalid This can possibly

given a code point cp, writes to c the utf-8 code, outputting the length in bytes, if the length is zero, the code point is invalid This can possibly

* @brief SP float round down and convert to integer. * * @param v The value to round. * * @return The rounded value. */

handle a unicode codepoint write appropriate values into dest src will advance 6 bytes or 12 bytes dest will advance a variable amount (return via poi

handle a unicode codepoint write appropriate values into dest src will advance 6 bytes or 12 bytes dest will advance a variable amount (return via poi

inverse

for KTX2 files, the mips can be compressed using various encoders

True if address a has acceptable alignment