aboutsummaryrefslogtreecommitdiff
path: root/source/row_neon.cc
diff options
context:
space:
mode:
authorFrank Barchard <fbarchard@google.com>2022-09-19 18:44:41 -0700
committerlibyuv LUCI CQ <libyuv-scoped@luci-project-accounts.iam.gserviceaccount.com>2022-09-20 02:00:52 +0000
commit248172e2ba2d3f09e4d3258e396e8f53ff594157 (patch)
tree63996424d51074f4781bed42fcc00be9bb93893f /source/row_neon.cc
parentbe50557db77cac055507470f46482e74156deb78 (diff)
downloadlibyuv-248172e2ba2d3f09e4d3258e396e8f53ff594157.tar.gz
I422ToRGB24, I422ToRAW, I422ToRGB24MatrixFilter conversion functions added.
- YUV to RGB use linear for first and last row. - add assert(yuvconstants) - rename pointers to match row functions. - use macros that match row functions. - use 12 bit upsampler for conversions of 10 and 12 bits Cortex A53 AArch32 I420ToRGB24_Opt (3627 ms) I422ToRGB24_Opt (4099 ms) I444ToRGB24_Opt (4186 ms) I420ToRGB24Filter_Opt (5451 ms) I422ToRGB24Filter_Opt (5430 ms) AVX2 Was I420ToRGB24Filter_Opt (583 ms) Now I420ToRGB24Filter_Opt (560 ms) Neon Cortex A7 Was I420ToRGB24Filter_Opt (5447 ms) Now I420ToRGB24Filter_Opt (5439 ms) Bug: libyuv:938 Change-Id: I1731f2dd591073ae11a756f06574103ba0f803c7 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3906082 Reviewed-by: Justin Green <greenjustin@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
Diffstat (limited to 'source/row_neon.cc')
-rw-r--r--source/row_neon.cc23
1 files changed, 23 insertions, 0 deletions
diff --git a/source/row_neon.cc b/source/row_neon.cc
index 3f5c5de1..36185e8c 100644
--- a/source/row_neon.cc
+++ b/source/row_neon.cc
@@ -156,6 +156,29 @@ void I444ToARGBRow_NEON(const uint8_t* src_y,
: "cc", "memory", YUVTORGB_REGS, "d6");
}
+void I444ToRGB24Row_NEON(const uint8_t* src_y,
+ const uint8_t* src_u,
+ const uint8_t* src_v,
+ uint8_t* dst_rgb24,
+ const struct YuvConstants* yuvconstants,
+ int width) {
+ asm volatile(
+ YUVTORGB_SETUP
+ "1: \n" READYUV444 YUVTORGB
+ RGBTORGB8
+ "subs %[width], %[width], #8 \n"
+ "vst3.8 {d0, d2, d4}, [%[dst_rgb24]]! \n"
+ "bgt 1b \n"
+ : [src_y] "+r"(src_y), // %[src_y]
+ [src_u] "+r"(src_u), // %[src_u]
+ [src_v] "+r"(src_v), // %[src_v]
+ [dst_rgb24] "+r"(dst_rgb24), // %[dst_argb]
+ [width] "+r"(width) // %[width]
+ : [kUVCoeff] "r"(&yuvconstants->kUVCoeff), // %[kUVCoeff]
+ [kRGBCoeffBias] "r"(&yuvconstants->kRGBCoeffBias) // %[kRGBCoeffBias]
+ : "cc", "memory", YUVTORGB_REGS);
+}
+
void I422ToARGBRow_NEON(const uint8_t* src_y,
const uint8_t* src_u,
const uint8_t* src_v,