Mercurial > vec

comparison README @ 0:02a517e4c492

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
*: initial commit
author Paper <paper@paper.us.eu.org>
date Tue, 22 Oct 2024 01:22:41 -0400
parents
children f12b5dd4e18c
comparison
equal deleted inserted replaced
-1:000000000000 0:02a517e4c492
1 vec - a tiny SIMD vector header-only library written in C99
2
3 it comes with an extremely basic (and somewhat lacking) API,
4 where there are eight supported vector types, all 128-bit:
5
6 vint8x16 - 16 signed 8-bit integers
7 vint16x8 - 8 signed 16-bit integers
8 vint32x4 - 4 signed 32-bit integers
9 vint64x2 - 2 signed 64-bit integers
10 vuint8x16 - 16 unsigned 8-bit integers
11 vuint16x8 - 8 unsigned 16-bit integers
12 vuint32x4 - 4 unsigned 32-bit integers
13 vuint32x4 - 2 unsigned 64-bit integers
14
15 all of these have many operations that are prefixed with the
16 name of the type and an underscore, for example:
17
18 vint8x16 vint8x16_splat(uint8_t x)
19 - creates a vint8x16 where all of the values are filled
20 with the value of `x'
21
22 the current supported operations are:
23
24 v[u]intAxB splat([u]intA_t x)
25 creates a vector with all of the values are filled with
26 the value of `x'
27
28 v[u]intAxB load(const [u]intA_t x[B])
29 copies the values from the memory address stored at `x';
30 the address is NOT required to be aligned
31
32 void store(v[u]intAxB vec, [u]intA_t x[B])
33 copies the values from the vector into the memory address
34 stored at `x'
35
36 like with load(), this does not require address alignment
37
38 v[u]intAxB add(v[u]intAxB vec1, v[u]intAxB vec2)
39 adds the value of `vec1' and `vec2' and returns it
40
41 v[u]intAxB sub(v[u]intAxB vec1, v[u]intAxB vec2)
42 subtracts the value of `vec2' from `vec1' and returns it
43
44 v[u]intAxB mul(v[u]intAxB vec1, v[u]intAxB vec2)
45 multiplies the values of `vec1' and `vec2' together and
46 returns it