Files
vpx/vpx_dsp/sum_squares.c
Geza Lore abd00505d1 Add optimized vpx_sum_squares_2d_i16 for vp10.
Using this we can eliminate large numbers of calls to predict intra,
and is also faster than most of the variance functions it replaces.
This is an equivalence transform so coding performance is unaffected.

Encoder speedup is approx 7% when var_tx, super_tx and ext_tx are all
enabled.

Change-Id: I0d4c83afc4a97a1826f3abd864bd68e41bb504fb
2016-02-15 16:54:52 +00:00

30 lines
773 B
C

/*
* Copyright (c) 2015 The WebM project authors. All Rights Reserved.
*
* Use of this source code is governed by a BSD-style license
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
* in the file PATENTS. All contributing project authors may
* be found in the AUTHORS file in the root of the source tree.
*/
#include <assert.h>
#include "./vpx_dsp_rtcd.h"
uint64_t vpx_sum_squares_2d_i16_c(const int16_t *src, int src_stride,
int size) {
int r, c;
uint64_t ss = 0;
for (r = 0; r < size; r++) {
for (c = 0; c < size; c++) {
const int16_t v = src[c];
ss += v*v;
}
src += src_stride;
}
return ss;
}