diff options
| author | Linfeng Zhang <linfengz@google.com> | 2016-08-25 18:12:54 -0700 |
|---|---|---|
| committer | Jean-Marc Valin <jmvalin@jmvalin.ca> | 2017-01-30 16:00:03 -0500 |
| commit | cfdaf365b928755d04442af5bddb1e41726466b0 (patch) | |
| tree | 257a72990e9cd53cd19e3a9247100019da6862ff /silk_sources.mk | |
| parent | 68afa490ccc2fad1e3492f32119a381b9befc279 (diff) | |
| download | opus-cfdaf365b928755d04442af5bddb1e41726466b0.tar.gz | |
Optimize silk_NSQ_del_dec() for ARM NEON
The optimization is bit exact with C function.
This optimization speeds up SILK encoder on NEON as following.
Fixed-point:
Complexity 0-5: 0%
Complexity 6-7: 6%
Complexity 8-9: 10%
Complexity 10: 8%
Got similar results on floating-point.
Signed-off-by: Jean-Marc Valin <jmvalin@jmvalin.ca>
Diffstat (limited to 'silk_sources.mk')
| -rw-r--r-- | silk_sources.mk | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/silk_sources.mk b/silk_sources.mk index de8b14d9..e6b33721 100644 --- a/silk_sources.mk +++ b/silk_sources.mk @@ -85,6 +85,7 @@ silk/x86/VQ_WMat_EC_sse.c SILK_SOURCES_ARM_NEON_INTR = \ silk/arm/arm_silk_map.c \ +silk/arm/NSQ_del_dec_neon_intr.c \ silk/arm/NSQ_neon.c SILK_SOURCES_FIXED = \ |