commit f48abe8308ba7a67e443ad0911e06d62fd47ba91
author Viswanath Puttagunta <viswanath.puttagunta@linaro.org> Fri May 15 12:42:19 2015 -0500
committer Jean-Marc Valin <jmvalin@jmvalin.ca> Wed Oct 07 18:09:20 2015 -0400
tree a231446a0bc212ae891524881580f9b5ffd90798
parent 0fe514352568530d4bd18a6686e6878417e6cf41

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>

celt/static_modes_float.h

diff --git a/celt/static_modes_float.h b/celt/static_modes_float.h
index 2fadb62..e102a38 100644
--- a/celt/static_modes_float.h
+++ b/celt/static_modes_float.h
@@ -4,6 +4,11 @@
 #include "modes.h"
 #include "rate.h"
 
+#ifdef HAVE_ARM_NE10
+#define OVERRIDE_FFT 1
+#include "static_modes_float_arm_ne10.h"
+#endif
+
 #ifndef DEF_WINDOW120
 #define DEF_WINDOW120
 static const opus_val16 window120[120] = {
@@ -431,6 +436,11 @@
 {5, 96, 3, 32, 4, 8, 2, 4, 4, 1, 0, 0, 0, 0, 0, 0, },   /* factors */
 fft_bitrev480,  /* bitrev */
 fft_twiddles48000_960,  /* bitrev */
+#ifdef OVERRIDE_FFT
+(arch_fft_state *)&cfg_arch_480,
+#else
+NULL,
+#endif
 };
 #endif
 
@@ -443,6 +453,11 @@
 {5, 48, 3, 16, 4, 4, 4, 1, 0, 0, 0, 0, 0, 0, 0, 0, },    /* factors */
 fft_bitrev240,  /* bitrev */
 fft_twiddles48000_960,  /* bitrev */
+#ifdef OVERRIDE_FFT
+(arch_fft_state *)&cfg_arch_240,
+#else
+NULL,
+#endif
 };
 #endif
 
@@ -455,6 +470,11 @@
 {5, 24, 3, 8, 2, 4, 4, 1, 0, 0, 0, 0, 0, 0, 0, 0, },    /* factors */
 fft_bitrev120,  /* bitrev */
 fft_twiddles48000_960,  /* bitrev */
+#ifdef OVERRIDE_FFT
+(arch_fft_state *)&cfg_arch_120,
+#else
+NULL,
+#endif
 };
 #endif
 
@@ -467,6 +487,11 @@
 {5, 12, 3, 4, 4, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },    /* factors */
 fft_bitrev60,   /* bitrev */
 fft_twiddles48000_960,  /* bitrev */
+#ifdef OVERRIDE_FFT
+(arch_fft_state *)&cfg_arch_60,
+#else
+NULL,
+#endif
 };
 #endif