More

src/gpu/shaders/thumbnail.wgsl

@@ -0,0 +1,36 @@
+// Stage-1 companion kernel: build a tiny grayscale luma thumbnail on the GPU.
+//
+// One thread per thumbnail pixel. Each thread nearest-samples a source pixel
+// and writes its luma (0..255) into `thumb[ty * tw + tx]`. This lets the motion
+// (parallax) proxy be computed on the GPU instead of the CPU reading the full
+// RGBA frame, so extraction leans on the GPU rather than the CPU.
+
+struct Params {
+    w: u32,
+    h: u32,
+    tw: u32,
+    th: u32,
+    pad0: u32,
+}
+
+@group(0) @binding(0) var<uniform> params: Params;
+@group(0) @binding(1) var src_tex: texture_2d<f32>;
+@group(0) @binding(2) var<storage, read_write> thumb: array<f32>;
+
+fn luma(c: vec4<f32>) -> f32 {
+    return 0.299 * c.r + 0.587 * c.g + 0.114 * c.b;
+}
+
+@compute @workgroup_size(256, 1, 1)
+fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
+    let i = gid.x;
+    if (i >= params.tw * params.th) {
+        return;
+    }
+    let tx = i % params.tw;
+    let ty = i / params.tw;
+    let sx = i32(tx * params.w / params.tw);
+    let sy = i32(ty * params.h / params.th);
+    // Scale to 0..255 to match the CPU thumbnail / motion-diff convention.
+    thumb[i] = luma(textureLoad(src_tex, vec2<i32>(sx, sy), 0)) * 255.0;
+}