a61785b6a1
Optimized fdct4x4 (8x4) for ARMv6 instruction set. - No interlocks in Cortex-A8 pipeline - One interlock cycle in ARM11 pipeline - About 2.16 times faster than current C-code compiled with -O3 Change-Id: I60484ecd144365da45bb68a960d30196b59952b8
25 lines
695 B
C
25 lines
695 B
C
/*
|
|
* Copyright (c) 2011 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 "vpx_config.h"
|
|
#include "vp8/encoder/dct.h"
|
|
|
|
#if HAVE_ARMV6
|
|
|
|
void vp8_fast_fdct8x4_armv6(short *input, short *output, int pitch)
|
|
{
|
|
vp8_fast_fdct4x4_armv6(input, output, pitch);
|
|
vp8_fast_fdct4x4_armv6(input + 4, output + 16, pitch);
|
|
}
|
|
|
|
#endif /* HAVE_ARMV6 */
|
|
|
|
|