#version 460
// d4r engine, presets E and F: NGX's cuda_copy_exposure_kernel. After each frame the frame's exposure (the game's
// 1x1 texture or the AutoExposure measurement) goes into a 1x1 half surface, which the next frame's input kernel
// samples as the previous exposure (its texture 352; on a reset frame NGX binds the current exposure there instead,
// so the engine copies before the input kernel too). The formatted half store truncates toward zero, like the
// auto-exposure copy (engine/exposure_k.comp).
layout(local_size_x = 32) in;   // one full wave32 subgroup; invocation 0 stores
layout(set = 0, binding = 0) uniform sampler2D source;
layout(set = 0, binding = 1, r16f) uniform writeonly image2D previous;
float truncatedHalf(float v)
{
    uint bits = packHalf2x16(vec2(v, 0.0)) & 65535u;
    if (unpackHalf2x16(bits).x > v) --bits;
    return unpackHalf2x16(bits).x;
}
void main()
{
    if (gl_LocalInvocationID.x == 0u)
        imageStore(previous, ivec2(0), vec4(truncatedHalf(texelFetch(source, ivec2(0), 0).r)));
}