Skip to content

L
libyuv
Commit ee99b851 authored by Frank Barchard's avatar Frank Barchard
Browse files
Options

Port ARGBToRGB565 from aarch64 neon to 32 bit 

The 64 bit version of ARGBToRGB565 to 32 bit. 64 bit is using sri which shifts and inserts, saving some masking.  The instruction is available for neon 32 bit as well.

R=magjed@chromium.org, harryjin@google.com
BUG=libyuv:571

Review URL: https://codereview.chromium.org/1724393002 .
parent ab0dfdd4
Hide whitespace changes
Inline Side-by-side
Showing with 16 additions and 27 deletions
README.chromium
View file @ ee99b851
Name: libyuv
URL: http://code.google.com/p/libyuv/
Version: 1578
Version: 1579
License: BSD
License File: LICENSE
......
include/libyuv/version.h
View file @ ee99b851
......@@ -11,6 +11,6 @@
#ifndef INCLUDE_LIBYUV_VERSION_H_ // NOLINT
#define INCLUDE_LIBYUV_VERSION_H_
#define LIBYUV_VERSION 1578
#define LIBYUV_VERSION 1579
#endif // INCLUDE_LIBYUV_VERSION_H_ NOLINT
source/row_neon.cc
View file @ ee99b851
......@@ -317,16 +317,11 @@ void I422ToRGB24Row_NEON(const uint8* src_y,
}
#define ARGBTORGB565 \
"vshr.u8 d20, d20, #3 \n" /* B */ \
"vshr.u8 d21, d21, #2 \n" /* G */ \
"vshr.u8 d22, d22, #3 \n" /* R */ \
"vmovl.u8 q8, d20 \n" /* B */ \
"vmovl.u8 q9, d21 \n" /* G */ \
"vmovl.u8 q10, d22 \n" /* R */ \
"vshl.u16 q9, q9, #5 \n" /* G */ \
"vshl.u16 q10, q10, #11 \n" /* R */ \
"vorr q0, q8, q9 \n" /* BG */ \
"vorr q0, q0, q10 \n" /* BGR */
"vshll.u8 q0, d22, #8 \n" /* R */ \
"vshll.u8 q8, d21, #8 \n" /* G */ \
"vshll.u8 q9, d20, #8 \n" /* B */ \
"vsri.16 q0, q8, #5 \n" /* RG */ \
"vsri.16 q0, q9, #11 \n" /* RGB */
void I422ToRGB565Row_NEON(const uint8* src_y,
const uint8* src_u,
......@@ -359,19 +354,13 @@ void I422ToRGB565Row_NEON(const uint8* src_y,
}
#define ARGBTOARGB1555 \
"vshr.u8 q10, q10, #3 \n" /* B */ \
"vshr.u8 d22, d22, #3 \n" /* R */ \
"vshr.u8 d23, d23, #7 \n" /* A */ \
"vmovl.u8 q8, d20 \n" /* B */ \
"vmovl.u8 q9, d21 \n" /* G */ \
"vmovl.u8 q10, d22 \n" /* R */ \
"vmovl.u8 q11, d23 \n" /* A */ \
"vshl.u16 q9, q9, #5 \n" /* G */ \
"vshl.u16 q10, q10, #10 \n" /* R */ \
"vshl.u16 q11, q11, #15 \n" /* A */ \
"vorr q0, q8, q9 \n" /* BG */ \
"vorr q1, q10, q11 \n" /* RA */ \
"vorr q0, q0, q1 \n" /* BGRA */
"vshll.u8 q0, d23, #8 \n" /* A */ \
"vshll.u8 q8, d22, #8 \n" /* R */ \
"vshll.u8 q9, d21, #8 \n" /* G */ \
"vshll.u8 q10, d20, #8 \n" /* B */ \
"vsri.16 q0, q8, #1 \n" /* AR */ \
"vsri.16 q0, q9, #6 \n" /* ARG */ \
"vsri.16 q0, q10, #11 \n" /* ARGB */
void I422ToARGB1555Row_NEON(const uint8* src_y,
const uint8* src_u,
......
source/row_neon64.cc
View file @ ee99b851
......@@ -323,8 +323,8 @@ void I422ToRGB24Row_NEON(const uint8* src_y,
#define ARGBTORGB565 \
"shll v0.8h, v22.8b, #8 \n" /* R */ \
"shll v20.8h, v20.8b, #8 \n" /* B */ \
"shll v21.8h, v21.8b, #8 \n" /* G */ \
"shll v20.8h, v20.8b, #8 \n" /* B */ \
"sri v0.8h, v21.8h, #5 \n" /* RG */ \
"sri v0.8h, v20.8h, #11 \n" /* RGB */
......@@ -363,8 +363,8 @@ void I422ToRGB565Row_NEON(const uint8* src_y,
#define ARGBTOARGB1555 \
"shll v0.8h, v23.8b, #8 \n" /* A */ \
"shll v22.8h, v22.8b, #8 \n" /* R */ \
"shll v20.8h, v20.8b, #8 \n" /* B */ \
"shll v21.8h, v21.8b, #8 \n" /* G */ \
"shll v20.8h, v20.8b, #8 \n" /* B */ \
"sri v0.8h, v22.8h, #1 \n" /* AR */ \
"sri v0.8h, v21.8h, #6 \n" /* ARG */ \
"sri v0.8h, v20.8h, #11 \n" /* ARGB */
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment