File: int8_simd.h

package info (click to toggle)
pytorch 1.13.1%2Bdfsg-4
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 139,252 kB
  • sloc: cpp: 1,100,274; python: 706,454; ansic: 83,052; asm: 7,618; java: 3,273; sh: 2,841; javascript: 612; makefile: 323; xml: 269; ruby: 185; yacc: 144; objc: 68; lex: 44
file content (23 lines) | stat: -rw-r--r-- 722 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
#pragma once

// We want to allow 128-bit wide SIMD if either NEON is available (as
// detected by GEMMLOWP_NEON), or whether SSE4.2 and Clang is
// available (in which case we will use the neon_sse.h library to
// share source between the two implementations). We use SSE4.2 to
// ensure we can use the full neon2sse library, and we use Clang as
// GCC has issues correctly compiling some parts of the neon2sse
// library.

// Otherwise, the INT8_NEON_SIMD variable will be undefined.

#include "gemmlowp/fixedpoint/fixedpoint.h"
#include "gemmlowp/public/gemmlowp.h"

#ifdef GEMMLOWP_NEON
#define INT8_NEON_SIMD
#endif

#if defined(__SSE4_2__) && defined(__clang__)
#include "NEON_2_SSE.h"
#define INT8_NEON_SIMD
#endif