SIMD implementation of Convolver for Lanczos filter etc.

skia/ext/image_operations.cc

 // Copyright (c) 2011 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.
 
 #define _USE_MATH_DEFINES
 #include <algorithm>
 #include <cmath>
 #include <limits>
 
 #include "skia/ext/image_operations.h"
@@ skipping 298 matching lines @@
     // arbitrarily add this to the center of the filter array (this won't always
     // be the center of the filter function since it could get clipped on the
     // edges, but it doesn't matter enough to worry about that case).
     int16 leftovers = output->FloatToFixed(1.0f) - fixed_sum;
     fixed_filter_values[fixed_filter_values->size() / 2] += leftovers;
 
     // Now it's ready to go.
     output->AddFilter(src_begin, &fixed_filter_values[0],
                       static_cast<int>(fixed_filter_values->size()));
   }
+
+  output->PaddingForSIMD(8);

[evannier, 2011/02/14 23:45:13]

At the API layer, this seems wrong to be visible from the outside.
For example one could conceive that an optimization (that I discussed in my
comments) that the layer below would be responsible for detecting cycles in the
values, at which point, when you push the values in 'AddFilter' you have no
guarantee that any value was actually added.

[fbarchard, 2011/02/15 23:16:45]

should be 16?

[jiesun, 2011/02/17 20:17:58]

I agree this is ugly, but there is no "finalizefilters". padding only happened
at the end of all filters.  filter_values is also private. ...

[jiesun, 2011/02/17 20:17:58]

16 byte = 8 coefficient because Fixed is short(2bytes)

 }
 
 ImageOperations::ResizeMethod ResizeMethodToAlgorithmMethod(
     ImageOperations::ResizeMethod method) {
   // Convert any "Quality Method" into an "Algorithm Method"
   if (method >= ImageOperations::RESIZE_FIRST_ALGORITHM_METHOD &&
       method <= ImageOperations::RESIZE_LAST_ALGORITHM_METHOD) {
     return method;
   }
   // The call to ImageOperationsGtv::Resize() above took care of
@@ skipping 125 matching lines @@
     src_row += h * row_words;
     dst_row += result.rowBytes() / 4;
   }
   result.setIsOpaque(img.isOpaque());
   return result;
 #else
   return SkBitmap();
 #endif  // OS_POSIX && !OS_MACOSX
 }
 
+#ifdef ARCH_CPU_X86_FAMILY
+#ifdef _MSC_VER
+#include <intrin.h>
+#endif
+#endif
+
+bool ImageOperations::hasSSE2() {
+#ifdef ARCH_CPU_X86_FAMILY
+#ifdef _MSC_VER
+  int cpu_info[4] = {-1};
+  __cpuid(cpu_info, 0);
+  int num_ids = cpu_info[0];

[fbarchard, 2011/02/15 23:16:45]

is this necessary?  i thought everyone that supports cpuid at all, support
function 1?

[jiesun, 2011/02/17 20:17:58]

Done.

+  if (num_ids > 0) {
+    __cpuid(cpu_info, 1);
+    return (cpu_info[3] & (1<<26)) != 0;
+  }
+  return false;
+#else
+  // TODO(jiesun): This has to be resolved. We could not use skia implementation.
+  return true;
+#endif
+#else
+  return false;
+#endif
+}
+
 // static
 SkBitmap ImageOperations::ResizeBasic(const SkBitmap& source,
                                       ResizeMethod method,
                                       int dest_width, int dest_height,
                                       const SkIRect& dest_subset) {
   // Ensure that the ResizeMethod enumeration is sound.
   SkASSERT(((RESIZE_FIRST_QUALITY_METHOD <= method) &&
             (method <= RESIZE_LAST_QUALITY_METHOD)) ||
            ((RESIZE_FIRST_ALGORITHM_METHOD <= method) &&
             (method <= RESIZE_LAST_ALGORITHM_METHOD)));
@@ skipping 28 matching lines @@
       reinterpret_cast<const uint8*>(source.getPixels());
 
   // Convolve into the result.
   SkBitmap result;
   result.setConfig(SkBitmap::kARGB_8888_Config,
                    dest_subset.width(), dest_subset.height());
   result.allocPixels();
   BGRAConvolve2D(source_subset, static_cast<int>(source.rowBytes()),
                  !source.isOpaque(), filter.x_filter(), filter.y_filter(),
                  static_cast<int>(result.rowBytes()),
-                 static_cast<unsigned char*>(result.getPixels()));
+                 static_cast<unsigned char*>(result.getPixels()), hasSSE2());
 
   // Preserve the "opaque" flag for use as an optimization later.
   result.setIsOpaque(source.isOpaque());
 
   base::TimeDelta delta = base::TimeTicks::Now() - resize_start;
   UMA_HISTOGRAM_TIMES("Image.ResampleMS", delta);
 
   return result;
 }
 
 // static
 SkBitmap ImageOperations::Resize(const SkBitmap& source,
                                  ResizeMethod method,
                                  int dest_width, int dest_height) {
   SkIRect dest_subset = { 0, 0, dest_width, dest_height };
   return Resize(source, method, dest_width, dest_height, dest_subset);
 }
 
 }  // namespace skia