armv7(float): Optimize encode usecase using NE10 library

Optimize opus encode (float only) usecase using ARM NE10
library. Mainly effects opus_fft and ctl_mdct_forward
and related functions.

This optimization can be used for ARM CPUs that have NEON
VFP unit. This patch only enables optimizations for ARMv7.

Official ARM NE10 library page available at
http://projectne10.github.io/Ne10/

To enable this optimization, use
--enable-intrinsics --with-NE10=<install_prefix>
or
--enable-intrinsics --with-NE10-libraries=<NE10_lib_dir> --with-NE10-includes=<NE10_includes_dir>

Compile time checks made during configure process to make sure
optimization option available only when compiler supports NEON
instrinsics.

Runtime checks made to make sure optimized functions only called
on appropriate hardware.

Signed-off-by: Timothy B. Terriberry <tterribe@xiph.org>
This commit is contained in:
Viswanath Puttagunta 2015-05-15 12:42:19 -05:00 committed by Jean-Marc Valin
parent 0fe5143525
commit f48abe8308
31 changed files with 1492 additions and 143 deletions

View file

@ -37,6 +37,7 @@
#include "os_support.h"
#include "stack_alloc.h"
#include "quant_bands.h"
#include "cpu_support.h"
static const opus_int16 eband5ms[] = {
/*0 200 400 600 800 1k 1.2 1.4 1.6 2k 2.4 2.8 3.2 4k 4.8 5.6 6.8 8k 9.6 12k 15.6 */
@ -229,6 +230,7 @@ CELTMode *opus_custom_mode_create(opus_int32 Fs, int frame_size, int *error)
opus_val16 *window;
opus_int16 *logN;
int LM;
int arch = opus_select_arch();
ALLOC_STACK;
#if !defined(VAR_ARRAYS) && !defined(USE_ALLOCA)
if (global_stack==NULL)
@ -389,7 +391,7 @@ CELTMode *opus_custom_mode_create(opus_int32 Fs, int frame_size, int *error)
compute_pulse_cache(mode, mode->maxLM);
if (clt_mdct_init(&mode->mdct, 2*mode->shortMdctSize*mode->nbShortMdcts,
mode->maxLM) == 0)
mode->maxLM, arch) == 0)
goto failure;
if (error)
@ -408,6 +410,8 @@ failure:
#ifdef CUSTOM_MODES
void opus_custom_mode_destroy(CELTMode *mode)
{
int arch = opus_select_arch();
if (mode == NULL)
return;
#ifndef CUSTOM_MODES_ONLY
@ -431,7 +435,7 @@ void opus_custom_mode_destroy(CELTMode *mode)
opus_free((opus_int16*)mode->cache.index);
opus_free((unsigned char*)mode->cache.bits);
opus_free((unsigned char*)mode->cache.caps);
clt_mdct_clear(&mode->mdct);
clt_mdct_clear(&mode->mdct, arch);
opus_free((CELTMode *)mode);
}