Another approach

This commit is contained in:
MaranBr 2026-05-28 17:05:23 -04:00
parent b69fab0350
commit 630dca7afd

View file

@ -1619,27 +1619,38 @@ void BufferCache<P>::TouchBuffer(Buffer& buffer, BufferId buffer_id) noexcept {
template <class P>
bool BufferCache<P>::SynchronizeBuffer(Buffer& buffer, DAddr device_addr, u32 size) {
upload_copies.clear();
u64 total_size_bytes = 0;
u64 staging_offset = 0;
u64 largest_copy = 0;
DAddr buffer_start = buffer.cpu_addr_cached;
memory_tracker.ForEachUploadRange(device_addr, size, [&](u64 device_addr_out, u64 range_size) {
if (IsRegionGpuModified(device_addr_out, range_size)) {
return;
}
upload_copies.push_back(BufferCopy{
.src_offset = total_size_bytes,
.dst_offset = device_addr_out - buffer_start,
.size = range_size,
DAddr buffer_start = buffer.CpuAddr();
auto push = [&](u64 start, u64 end) {
if (start >= end) {
return;
}
u64 sz = end - start;
copies.push_back({
.src_offset = staging_offset,
.dst_offset = start - buffer_start,
.size = sz
});
total_size_bytes += range_size;
largest_copy = (std::max)(largest_copy, range_size);
staging_offset += sz;
largest_copy = std::max(largest_copy, sz);
};
memory_tracker.ForEachUploadRange(device_addr, size, [&](u64 addr, u64 range_size) {
u64 start = addr;
u64 end = addr + range_size;
gpu_modified_ranges.ForEachInRange(start, range_size, [&](u64 gstart, u64 gsize) {
u64 gend = gstart + gsize;
push(start, gstart);
start = std::max(start, gend);
});
push(start, end);
ClearDownload(addr, range_size);
gpu_modified_ranges.Subtract(addr, range_size);
});
if (total_size_bytes == 0) {
return true;
}
std::span<BufferCopy> copies_span(upload_copies.data(), upload_copies.size());
UploadMemory(buffer, total_size_bytes, largest_copy, copies_span);
any_buffer_uploaded = true;
if (copies.empty()) {
return true;
}
UploadMemory(buffer, staging_offset, largest_copy, std::span(copies));
return false;
}