Add SincResampler ported from WebKit.

media/base/sinc_resampler.cc

Index: media/base/sinc_resampler.cc
diff --git a/media/base/sinc_resampler.cc b/media/base/sinc_resampler.cc
new file mode 100644
index 0000000000000000000000000000000000000000..ba0f129baf05d83ce8843cbe211e83dd69e22831
--- /dev/null
+++ b/media/base/sinc_resampler.cc
@@ -0,0 +1,199 @@
+// 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.
+//
+// Input buffer layout, dividing the total buffer into regions (r0 - r5):
+//
+// |----------------|-----------------------------------------|----------------|
+//
+//                                   kBlockSize + kKernelSize / 2
+//                   <--------------------------------------------------------->
+//                                               r0
+//
+//  kKernelSize / 2   kKernelSize / 2         kKernelSize / 2   kKernelSize / 2
+// <---------------> <--------------->       <---------------> <--------------->
+//         r1                r2                      r3                r4
+//
+//                                                     kBlockSize
+//                                     <--------------------------------------->
+//                                                         r5
+//
+// The algorithm:
+//
+// 1) Consume input frames into r0 (r1 is zero-initialized).
+// 2) Position kernel centered at start of r0 (r2) and generate output frames
+//    until kernel is centered at start of r4 or we've finished generating all
+//    the output frames.
+// 3) Copy r3 to r1 and r4 to r2.
+// 4) Consume input frames into r5 (zero-pad if we run out of input).
+// 5) Goto (2) until all of input is consumed.
+//
+// Note: we're glossing over how the sub-sample handling works with
+// |virtual_source_index_|, etc.
+// MSVC++ requires this to be set before any other includes to get M_PI.
+#define _USE_MATH_DEFINES

[Chris Rogers, 2012/07/02 20:38:14]

Not sure if there's any cleaner way to do this?

In WebKit we have a header called <wtf/MathExtras.h> which handles this for
us...

[DaleCurtis, 2012/07/03 00:36:34]

Not that I've found, this is what I used in my other CL too and I see it around
the Chrome code base.

+
+#include "media/base/sinc_resampler.h"
+
+#include <cmath>
+
+#include "base/logging.h"
+
+namespace media {
+
+// The kernel size can be adjusted for quality (higher is better).
+static const int kKernelSize = 32;

[Chris Rogers, 2012/07/02 20:38:14]

32 should be fine for now, but you could add a TODO here about testing the
performance to see if we can afford to jack this up to 64.

[DaleCurtis, 2012/07/03 00:36:34]

Done.

+// The kernel offset count is used for interpolation and is the number of
+// sub-sample kernel shifts.
+static const int kKernelOffsetCount = 32;
+
+const int SincResampler::kBlockSize = 512;
+const int SincResampler::kBufferSize = kBlockSize + kKernelSize;
+COMPILE_ASSERT(kKernelSize % 2 == 0, kKernelSize_must_be_even);
+COMPILE_ASSERT(
+    SincResampler::kBlockSize > kKernelSize, kBlockSize_must_be_gt_kKernelSize);
+
+SincResampler::SincResampler(AudioSourceProvider* provider, double scale_factor)
+    : scale_factor_(scale_factor),
+      virtual_source_idx_(0),
+      buffer_primed_(false),
+      provider_(provider),
+      // TODO(dalecurtis): When we switch to AVX/SSE optimization, we'll need to
+      // allocate with 32-byte alignment and ensure they're sized % 32 bytes.
+      kernel_storage_(new float[kKernelSize * (kKernelOffsetCount + 1)]),
+      input_buffer_(new float[kBufferSize]) {
+  memset(kernel_storage_, 0,
+         sizeof(*kernel_storage_) * kKernelSize * (kKernelOffsetCount + 1));
+  memset(input_buffer_, 0, sizeof(*kernel_storage_) * kBufferSize);
+
+  InitializeKernel();
+}
+
+SincResampler::~SincResampler() {
+  delete[] kernel_storage_;
+  delete[] input_buffer_;
+}
+
+void SincResampler::InitializeKernel() {
+  // Blackman window parameters.
+  double alpha = 0.16;
+  double a0 = 0.5 * (1.0 - alpha);
+  double a1 = 0.5;
+  double a2 = 0.5 * alpha;
+
+  // |sinc_scale_factor| is basically the normalized cutoff frequency of the
+  // low-pass filter.
+  double sinc_scale_factor = scale_factor_ > 1.0 ? 1.0 / scale_factor_ : 1.0;
+
+  // The sinc function is an idealized brick-wall filter, but since we're
+  // windowing it the transition from pass to stop does not happen right away.
+  // So we should adjust the lowpass filter cutoff slightly downward to avoid
+  // some aliasing at the very high-end.
+  // TODO(crogers): this value is empirical and to be more exact should vary
+  // depending on kKernelSize.
+  sinc_scale_factor *= 0.9;
+
+  // Generates a set of windowed sinc() kernels.
+  // We generate a range of sub-sample offsets from 0.0 to 1.0.
+  for (int offset_idx = 0; offset_idx <= kKernelOffsetCount; ++offset_idx) {
+    double subsample_offset =
+        static_cast<double>(offset_idx) / kKernelOffsetCount;
+
+    for (int i = 0; i < kKernelSize; ++i) {
+      // Compute the sinc with offset.
+      // TODO(dalecurtis): Is M_PI precise enough here? It was using piDouble.

[Chris Rogers, 2012/07/02 20:38:14]

I think it should be fine -- in any case the unit test should tell us

[DaleCurtis, 2012/07/03 00:36:34]

Done.

+      double s =
+          sinc_scale_factor * M_PI * (i - kKernelSize / 2 - subsample_offset);
+      double sinc = (!s ? 1.0 : sin(s) / s) * sinc_scale_factor;
+
+      // Compute Blackman window, matching the offset of the sinc().
+      double x = (i - subsample_offset) / kKernelSize;
+      double window = a0 - a1 * cos(2.0 * M_PI * x) + a2 * cos(4.0 * M_PI * x);
+
+      // Window the sinc() function and store at the correct offset.
+      kernel_storage_[i + offset_idx * kKernelSize] = sinc * window;
+    }
+  }
+}
+
+void SincResampler::Resample(float* destination, int number_of_frames) {
+  int remaining_frames = number_of_frames;
+
+  // Setup various region pointers in the buffer (see diagram above).
+  float* r0 = input_buffer_ + kKernelSize / 2;
+  float* r1 = input_buffer_;
+  float* r2 = r0;
+  float* r3 = r0 + kBlockSize - kKernelSize / 2;
+  float* r4 = r0 + kBlockSize;
+  float* r5 = r0 + kKernelSize / 2;
+
+  // Step (1) -- Prime the input buffer at the start of the input stream.
+  if (!buffer_primed_) {
+    provider_->ProvideInput(r0, kBlockSize + kKernelSize / 2);
+    buffer_primed_ = true;
+  }
+
+  // Step (2) -- Resample!
+  while (remaining_frames) {
+    while (virtual_source_idx_ < kBlockSize) {
+      // |virtual_source_idx_| lies in between two kernel offsets so figure out
+      // what they are.
+      int source_idx = static_cast<int>(virtual_source_idx_);
+      double subsample_remainder = virtual_source_idx_ - source_idx;
+
+      double virtual_offset_idx = subsample_remainder * kKernelOffsetCount;
+      int offset_idx = static_cast<int>(virtual_offset_idx);
+
+      float* k1 = kernel_storage_ + offset_idx * kKernelSize;
+      float* k2 = k1 + kKernelSize;
+
+      // Initialize input pointer based on quantized |virtual_source_idx_|.
+      float* input_ptr = r1 + source_idx;
+
+      // We'll compute "convolutions" for the two kernels which straddle
+      // |virtual_source_idx_|.
+      float sum1 = 0;
+      float sum2 = 0;
+
+      // Figure out how much to weight each kernel's "convolution".
+      double kernel_interpolation_factor = virtual_offset_idx - offset_idx;
+
+      // Generate a single output sample.
+      int n = kKernelSize;
+      float input;
+      // TODO(dalecurtis): For initial commit, I've ripped out all the SSE
+      // optimizations, these definitely need to go back in before release.
+      while (n--) {
+        input = *input_ptr++;
+        sum1 += input * *k1++;
+        sum2 += input * *k2++;
+      }
+
+      // Linearly interpolate the two "convolutions".
+      double result = (1.0 - kernel_interpolation_factor) * sum1
+          + kernel_interpolation_factor * sum2;
+
+      *destination++ = result;
+
+      // Advance the virtual index.
+      virtual_source_idx_ += scale_factor_;
+
+      if (!--remaining_frames)
+        return;
+    }
+
+    // Wrap back around to the start.
+    virtual_source_idx_ -= kBlockSize;
+
+    // Step (3) Copy r3 to r1 and r4 to r2.
+    // This wraps the last input frames back to the start of the buffer.
+    memcpy(r1, r3, sizeof(*input_buffer_) * (kKernelSize / 2));
+    memcpy(r2, r4, sizeof(*input_buffer_) * (kKernelSize / 2));
+
+    // Step (4)
+    // Refresh the buffer with more input.
+    provider_->ProvideInput(r5, kBlockSize);
+  }
+}
+
+}  // namespace media