diff options
author | Linfeng Zhang <linfengz@google.com> | 2016-07-14 02:40:48 +0300 |
---|---|---|
committer | Jean-Marc Valin <jmvalin@jmvalin.ca> | 2017-04-14 01:30:27 +0300 |
commit | 8e19536baa5064a89abe93570fcc99412b6c68a1 (patch) | |
tree | 95eb80319a5cc30193dfe78726ca070f4365a7c8 /silk_headers.mk | |
parent | c43633d1a9d3747f96fc30a32f6fdaa322195aed (diff) |
Optimize silk_warped_autocorrelation_FIX() for ARM NEON
The optimization is bit exact with C function.
This optimization speeds up fixed-point SILK encoder on NEON about
5% to 8%. (Tested on Acer Chromebook, ARMv7 Processor rev 3 (v7l).)
Change-Id: I582f6f3585b7946149e16a2ad3084ebc0ae79a4f
Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>
Diffstat (limited to 'silk_headers.mk')
-rw-r--r-- | silk_headers.mk | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/silk_headers.mk b/silk_headers.mk index cb104919..278500b5 100644 --- a/silk_headers.mk +++ b/silk_headers.mk @@ -32,6 +32,7 @@ silk/arm/NSQ_del_dec_arm.h \ silk/arm/NSQ_neon.h \ silk/fixed/main_FIX.h \ silk/fixed/structs_FIX.h \ +silk/fixed/arm/warped_autocorrelation_FIX_arm.h \ silk/fixed/mips/noise_shape_analysis_FIX_mipsr1.h \ silk/fixed/mips/warped_autocorrelation_FIX_mipsr1.h \ silk/float/main_FLP.h \ |