mirror of
https://chromium.googlesource.com/libyuv/libyuv
synced 2025-12-08 09:47:45 +08:00
5790a765b9
I422ToUYVYRow_AVX2 optimized from 7 cycles per 32 pixels to 4.6 cycles. Instead of 2 vpermq and vpunpcklbw: vmovdqu (%1),%%xmm2 vmovdqu 0x00(%1,%2,1),%%xmm3 vpermq $0xd8,%%ymm2,%%ymm2 vpermq $0xd8,%%ymm3,%%ymm3 vpunpcklbw %%ymm3,%%ymm2,%%ymm2 ..use vpmovzxbd to expand the bytes to shorts, then vpslld and vpor vpmovzxbd (%1),%%ymm2 vpmovzxbd 0x00(%1,%2,1),%%ymm3 vpslld $0x10,%%ymm3,%%ymm3 vpor %%ymm3,%%ymm2,%%ymm2 which reduces the port 5 bottleneck by 1 cycle. Bug: libyuv:556 Test: out/Release/libyuv_unittest --gtest_filter=*I42?To*UY*Opt Change-Id: I53799e53cc6b090a1a695c839094c193be3eecaf Reviewed-on: https://chromium-review.googlesource.com/899873 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: richard winterton <rrwinterton@gmail.com> Reviewed-by: Cheng Wang <wangcheng@google.com>
17 lines
544 B
C
17 lines
544 B
C
/*
|
|
* Copyright 2012 The LibYuv 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.
|
|
*/
|
|
|
|
#ifndef INCLUDE_LIBYUV_VERSION_H_
|
|
#define INCLUDE_LIBYUV_VERSION_H_
|
|
|
|
#define LIBYUV_VERSION 1696
|
|
|
|
#endif // INCLUDE_LIBYUV_VERSION_H_
|