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/AudioResamplerFirOps.h b/services/audioflinger/AudioResamplerFirOps.h
index 658285d..7a60186 100644
--- a/services/audioflinger/AudioResamplerFirOps.h
+++ b/services/audioflinger/AudioResamplerFirOps.h
@@ -32,6 +32,13 @@
 #define USE_NEON (false)
 #endif
 
+#if defined(__SSSE3__)  // Should be supported in x86 ABI for both 32 & 64-bit.
+#define USE_SSE (true)
+#include <tmmintrin.h>
+#else
+#define USE_SSE (false)
+#endif
+
 template<typename T, typename U>
 struct is_same
 {