mirror of
https://chromium.googlesource.com/libyuv/libyuv
synced 2026-01-01 03:12:16 +08:00
void HalfFloat1Row_NEON(const uint16* src, uint16* dst, float, int width) {
asm volatile (
"1: \n"
MEMACCESS(0)
"ld1 {v1.16b}, [%0], #16 \n" // load 8 shorts
"subs %w2, %w2, #8 \n" // 8 pixels per loop
"uxtl v2.4s, v1.4h \n" // 8 int's
"uxtl2 v1.4s, v1.8h \n"
"scvtf v2.4s, v2.4s \n" // 8 floats
"scvtf v1.4s, v1.4s \n"
"fcvtn v4.4h, v2.4s \n" // 8 floatsgit
"fcvtn2 v4.8h, v1.4s \n"
MEMACCESS(1)
"st1 {v4.16b}, [%1], #16 \n" // store 8 shorts
"b.gt 1b \n"
: "+r"(src), // %0
"+r"(dst), // %1
"+r"(width) // %2
:
: "cc", "memory", "v1", "v2", "v4"
);
}
void HalfFloatRow_NEON(const uint16* src, uint16* dst, float scale, int width) {
asm volatile (
"1: \n"
MEMACCESS(0)
"ld1 {v1.16b}, [%0], #16 \n" // load 8 shorts
"subs %w2, %w2, #8 \n" // 8 pixels per loop
"uxtl v2.4s, v1.4h \n" // 8 int's
"uxtl2 v1.4s, v1.8h \n"
"scvtf v2.4s, v2.4s \n" // 8 floats
"scvtf v1.4s, v1.4s \n"
"fmul v2.4s, v2.4s, %3.s[0] \n" // adjust exponent
"fmul v1.4s, v1.4s, %3.s[0] \n"
"uqshrn v4.4h, v2.4s, #13 \n" // isolate halffloat
"uqshrn2 v4.8h, v1.4s, #13 \n"
MEMACCESS(1)
"st1 {v4.16b}, [%1], #16 \n" // store 8 shorts
"b.gt 1b \n"
: "+r"(src), // %0
"+r"(dst), // %1
"+r"(width) // %2
: "w"(scale * 1.9259299444e-34f) // %3
: "cc", "memory", "v1", "v2", "v4"
);
}
TEST=LibYUVPlanarTest.TestHalfFloatPlane_One
BUG=libyuv:560
R=hubbe@chromium.org
Review URL: https://codereview.chromium.org/2430313008 .
|
||
|---|---|---|
| .. | ||
| compare_common.cc | ||
| compare_gcc.cc | ||
| compare_neon64.cc | ||
| compare_neon.cc | ||
| compare_win.cc | ||
| compare.cc | ||
| convert_argb.cc | ||
| convert_from_argb.cc | ||
| convert_from.cc | ||
| convert_jpeg.cc | ||
| convert_to_argb.cc | ||
| convert_to_i420.cc | ||
| convert.cc | ||
| cpu_id.cc | ||
| mjpeg_decoder.cc | ||
| mjpeg_validate.cc | ||
| planar_functions.cc | ||
| rotate_any.cc | ||
| rotate_argb.cc | ||
| rotate_common.cc | ||
| rotate_gcc.cc | ||
| rotate_mips.cc | ||
| rotate_neon64.cc | ||
| rotate_neon.cc | ||
| rotate_win.cc | ||
| rotate.cc | ||
| row_any.cc | ||
| row_common.cc | ||
| row_gcc.cc | ||
| row_mips.cc | ||
| row_msa.cc | ||
| row_neon64.cc | ||
| row_neon.cc | ||
| row_win.cc | ||
| scale_any.cc | ||
| scale_argb.cc | ||
| scale_common.cc | ||
| scale_gcc.cc | ||
| scale_mips.cc | ||
| scale_neon64.cc | ||
| scale_neon.cc | ||
| scale_win.cc | ||
| scale.cc | ||
| video_common.cc | ||