claude-noether
e3c28495ae
mc10 (¼-H), mc30 (¾-H), mc01 (¼-V), mc03 (¾-V). Each is the
corresponding half-pel filter (mc20 or mc02) with one extra L2
rounded-average step against an integer-source pixel at the tail:
mc10[r,c] = avg(clip255(mc20(s)), s[r, c ])
mc30[r,c] = avg(clip255(mc20(s)), s[r, c+1])
mc01[r,c] = avg(clip255(mc02(s)), s[r, c ])
mc03[r,c] = avg(clip255(mc02(s)), s[r+1, c ])
Each shader is ~45 lines (mc20-/mc02-pattern + 1 L2 line).
CMake foreach loop generates the 4 SPV compile rules. Dispatch
helper `dispatch_h264_qpel_axis_qpu` shares plumbing across all 4
(axis flag selects src_max bounds: H reads cols -2..+10, V reads
rows -2..+10). DEFINE_QPEL_AXIS_QPU + DEFINE_QPEL_DISPATCH_QPU
macros collapse ~200 LOC of boilerplate.
Recipe table flips DAEDALUS_KERNEL_H264_QPEL_MC{10,30,01,03} from
CPU to QPU.
Verified on hertz:
$ ./build/test_api_h264 | grep "qpel mc[01230]"
H.264 qpel mc10: 2048/2048 bytes bit-exact (100.0000%)
H.264 qpel mc30: 2048/2048 bytes bit-exact (100.0000%)
H.264 qpel mc01: 2048/2048 bytes bit-exact (100.0000%)
H.264 qpel mc03: 2048/2048 bytes bit-exact (100.0000%)
(+ mc20/mc02/mc22 anchors from previous PRs)
Qpel QPU coverage:
put_ mc20 ✓ mc02 ✓ mc22 ✓ (3 anchors)
mc10 ✓ mc30 ✓ mc01 ✓ mc03 ✓ (4 quarter-axis, THIS PR)
mc11/12/13/21/23/31/32/33 — CPU NEON (8 diagonals)
avg_ all 15 positions — CPU NEON
7 of 15 useful put_ positions now on QPU. The 8 diagonals each
compose two half-pel results via L2; can land via dedicated kernels
or by chaining existing anchor dispatches (the latter would need
the L2 step as a fourth dispatch — probably cheaper to write
dedicated 8x diagonal shaders).
45 lines
1.6 KiB
Plaintext
45 lines
1.6 KiB
Plaintext
// daedalus-fourier — H.264 luma qpel mc03 (8x8, ¾-pel vertical),
|
|
// V3D 7.1. Per H.264 §8.4.2.2.1 "n" position:
|
|
//
|
|
// dst[r,c] = ((clip255(mc02(s)[r,c]) + s[r+1, c] + 1) >> 1)
|
|
//
|
|
// Same as mc01 but L2-averages with src[r+1, c] instead of src[r, c].
|
|
//
|
|
// License: BSD-2-Clause.
|
|
|
|
#version 450
|
|
#extension GL_EXT_shader_8bit_storage : require
|
|
#extension GL_EXT_shader_explicit_arithmetic_types : require
|
|
|
|
layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
|
|
layout(binding = 0) readonly buffer Src { uint8_t src[]; } u_src;
|
|
layout(binding = 1) buffer Dst { uint8_t dst[]; } u_dst;
|
|
layout(binding = 2) readonly buffer Meta { uvec4 meta[]; } u_meta;
|
|
layout(push_constant) uniform PC { uint n_blocks, stride_u8, _p0, _p1; } pc;
|
|
|
|
void main()
|
|
{
|
|
uint block_idx = gl_WorkGroupID.x;
|
|
if (block_idx >= pc.n_blocks) return;
|
|
|
|
uint lane = gl_LocalInvocationID.x;
|
|
uint r = lane >> 3, c = lane & 7u;
|
|
|
|
uint dst_off = u_meta.meta[block_idx].x;
|
|
uint src_off = u_meta.meta[block_idx].y;
|
|
uint stride = pc.stride_u8;
|
|
uint col_base = src_off + c;
|
|
|
|
int s_m2 = int(u_src.src[col_base + (r - 2u) * stride]);
|
|
int s_m1 = int(u_src.src[col_base + (r - 1u) * stride]);
|
|
int s_0 = int(u_src.src[col_base + r * stride]);
|
|
int s_p1 = int(u_src.src[col_base + (r + 1u) * stride]);
|
|
int s_p2 = int(u_src.src[col_base + (r + 2u) * stride]);
|
|
int s_p3 = int(u_src.src[col_base + (r + 3u) * stride]);
|
|
int v = s_m2 - 5 * s_m1 + 20 * s_0 + 20 * s_p1 - 5 * s_p2 + s_p3 + 16;
|
|
int vp = clamp(v >> 5, 0, 255);
|
|
|
|
int avg = (vp + s_p1 + 1) >> 1; // L2 with src[r+1, c]
|
|
u_dst.dst[dst_off + r * stride + c] = uint8_t(avg);
|
|
}
|