Add SSE optimization of FIR float filter

Adds x86 SSE optimization of the FIR filter, float version only.
Used ARM implementation as template. Improves performance by a
factor of 2-2.5 on Silvermont architecture.

Change-Id: I503ce2bf4cbf10355f5eec3e9d73b364fa701241
Signed-off-by: Henrik Smiding <henrik.smiding@intel.com>
diff --git a/services/audioflinger/AudioResamplerDyn.cpp b/services/audioflinger/AudioResamplerDyn.cpp
index 6481b85..f137ed9 100644
--- a/services/audioflinger/AudioResamplerDyn.cpp
+++ b/services/audioflinger/AudioResamplerDyn.cpp
@@ -29,9 +29,10 @@
 #include <utils/Log.h>
 #include <audio_utils/primitives.h>
 
-#include "AudioResamplerFirOps.h" // USE_NEON and USE_INLINE_ASSEMBLY defined here
+#include "AudioResamplerFirOps.h" // USE_NEON, USE_SSE and USE_INLINE_ASSEMBLY defined here
 #include "AudioResamplerFirProcess.h"
 #include "AudioResamplerFirProcessNeon.h"
+#include "AudioResamplerFirProcessSSE.h"
 #include "AudioResamplerFirGen.h" // requires math.h
 #include "AudioResamplerDyn.h"