Experiment with AVX optimizations for FMAC, FMUL operations.

media/base/sinc_resampler.h

 // Copyright (c) 2012 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #ifndef MEDIA_BASE_SINC_RESAMPLER_H_
 #define MEDIA_BASE_SINC_RESAMPLER_H_
 
 #include <memory>
 
 #include "base/callback.h"
 #include "base/gtest_prod_util.h"
 #include "base/macros.h"
 #include "base/memory/aligned_memory.h"
 #include "build/build_config.h"
 #include "media/base/media_export.h"
+#include "media/base/vector_math.h"
 
 namespace media {
 
 // SincResampler is a high-quality single-channel sample-rate converter.
 class MEDIA_EXPORT SincResampler {
  public:
   enum {
     // The kernel size can be adjusted for quality (higher is better) at the
-    // expense of performance.  Must be a multiple of 32.
-    // TODO(dalecurtis): Test performance to see if we can jack this up to 64+.
-    kKernelSize = 32,
+    // expense of performance.  For performance we use the same kernel size
+    // as the SIMD optimized Convolve() operation.
+    kKernelSize = vector_math::kKernelSize,
 
     // Default request size.  Affects how often and for how much SincResampler
     // calls back for input.  Must be greater than kKernelSize.
     kDefaultRequestSize = 512,
 
     // The kernel offset count is used for interpolation and is the number of
     // sub-sample kernel shifts.  Can be adjusted for quality (higher is better)
     // at the expense of allocating more memory.
     kKernelOffsetCount = 32,
     kKernelStorageSize = kKernelSize * (kKernelOffsetCount + 1),
@@ skipping 40 matching lines @@
   void SetRatio(double io_sample_rate_ratio);
 
   float* get_kernel_for_testing() { return kernel_storage_.get(); }
 
   // Return number of input frames consumed by a callback but not yet processed.
   // Since input/output ratio can be fractional, so can this value.
   // Zero before first call to Resample().
   double BufferedFrames() const;
 
  private:
-  FRIEND_TEST_ALL_PREFIXES(SincResamplerTest, Convolve);
-  FRIEND_TEST_ALL_PREFIXES(SincResamplerPerfTest, Convolve);
-
   void InitializeKernel();
   void UpdateRegions(bool second_load);
 
-  // Compute convolution of |k1| and |k2| over |input_ptr|, resultant sums are
-  // linearly interpolated using |kernel_interpolation_factor|.  On x86, the
-  // underlying implementation is chosen at run time based on SSE support.  On
-  // ARM, NEON support is chosen at compile time based on compilation flags.
-  static float Convolve_C(const float* input_ptr, const float* k1,
-                          const float* k2, double kernel_interpolation_factor);
-#if defined(ARCH_CPU_X86_FAMILY)
-  static float Convolve_SSE(const float* input_ptr, const float* k1,
-                            const float* k2,
-                            double kernel_interpolation_factor);
-#elif defined(ARCH_CPU_ARM_FAMILY) && defined(USE_NEON)
-  static float Convolve_NEON(const float* input_ptr, const float* k1,
-                             const float* k2,
-                             double kernel_interpolation_factor);
-#endif
-
   // The ratio of input / output sample rates.
   double io_sample_rate_ratio_;
 
   // An index on the source input buffer with sub-sample precision.  It must be
   // double precision to avoid drift.
   double virtual_source_idx_;
 
   // The buffer is primed once at the very beginning of processing.
   bool buffer_primed_;
 
@@ skipping 30 matching lines @@
   float* const r2_;
   float* r3_;
   float* r4_;
 
   DISALLOW_COPY_AND_ASSIGN(SincResampler);
 };
 
 }  // namespace media
 
 #endif  // MEDIA_BASE_SINC_RESAMPLER_H_