#version 450 // Write-back merge of a VRAM mirror (vk_memory.c, wb_merge_record): copies a 32-bit word of what the GPU left in the // mirror into the pool's imported buffer (guest memory) only where it differs from the snapshot taken before the // submission's GPU work, so words the GPU did not change keep what the CPU wrote meanwhile. // One invocation per word of the listed ranges; ranges are sorted by their first invocation (x: word offset in the // mirror and imported bindings, y: word offset in the snapshot binding, z: words, w: first invocation). // With track set (shadow storage) a word that changed also marks its 4 KiB page of guest memory in Pages: page0 is the // bindings' start within its page, so the CPU's write-back at the fence reads only the marked pages of the shadow // (vk_memory.c, shadow_wb_cb). layout(local_size_x = 64) in; layout(std430, set = 0, binding = 0) readonly buffer Post { uint post[]; }; layout(std430, set = 0, binding = 1) readonly buffer Pre { uint pre[]; }; layout(std430, set = 0, binding = 2) buffer Dst { uint dst[]; }; layout(std430, set = 0, binding = 3) readonly buffer Ranges { uvec4 rng[]; }; layout(std430, set = 0, binding = 4) writeonly buffer Pages { uint pages[]; }; layout(push_constant) uniform Push { uint nranges, total, page0, track; } pc; void main() { uint i = gl_GlobalInvocationID.x; if (i >= pc.total) return; uint lo = 0, hi = pc.nranges; while (hi - lo > 1) { uint m = (lo + hi) >> 1; if (rng[m].w <= i) lo = m; else hi = m; } uvec4 r = rng[lo]; uint k = i - r.w; uint v = post[r.x + k]; if (v != pre[r.y + k]) { dst[r.x + k] = v; if (pc.track != 0u) pages[(pc.page0 + (r.x + k) * 4u) >> 12] = 1u; } }