mirror of
https://github.com/MobileGL-Dev/MobileGL
synced 2026-11-16 14:33:24 +09:00
[Fix] (Magma): a frame's recording is submitted every 16384 draws/dispatches and continues on a fresh command buffer, with at most frames-in-flight + 1 submissions outstanding - rd12's 981k-draw loading frame no longer grows one command buffer until Adreno's 16 KiB driver mappings exhaust vm.max_map_count (MOBILEGL_MAGMA_MAX_DRAWS_PER_COMMAND_BUFFER, 0 = unbounded)
This commit is contained in:
@@ -6381,6 +6381,8 @@ void main() {
|
||||
Bool VulkanRenderer::SetupDraw(FrameContext::FrameData& frame, GLenum mode, Flags<DrawSetupAspect> aspects,
|
||||
const DrawCmdParam& drawParams,
|
||||
const IndexBufferView* pIndexBufferView) {
|
||||
// First, before anything of this draw is recorded or resolved.
|
||||
SplitOversizedRecording();
|
||||
// Sync each sampled texture at most once across this whole draw: the layout
|
||||
// probe loop, the post-transition loop, and ResolveSamplerDescriptor would
|
||||
// otherwise each re-run the full SyncTexture path on the same textures.
|
||||
@@ -6981,6 +6983,7 @@ void main() {
|
||||
}
|
||||
|
||||
void VulkanRenderer::DispatchCompute(GLuint numGroupsX, GLuint numGroupsY, GLuint numGroupsZ) {
|
||||
SplitOversizedRecording();
|
||||
m_textureManager->CollectGarbage();
|
||||
auto& frame = m_frameContext.GetCurrent();
|
||||
// The DISPATCH accessor: with a pipeline bound this is its compute stage program
|
||||
@@ -7034,6 +7037,7 @@ void main() {
|
||||
}
|
||||
|
||||
void VulkanRenderer::DispatchComputeIndirect(GLintptr indirect) {
|
||||
SplitOversizedRecording();
|
||||
m_textureManager->CollectGarbage();
|
||||
auto& frame = m_frameContext.GetCurrent();
|
||||
// See DispatchCompute: the dispatch accessor, not the draw one.
|
||||
@@ -12669,6 +12673,54 @@ void main() {
|
||||
return FlushPendingCommands();
|
||||
}
|
||||
|
||||
void VulkanRenderer::SplitOversizedRecording() {
|
||||
const Uint32 maxDraws = MG_Config::Features.MagmaMaxDrawsPerCommandBuffer;
|
||||
if (maxDraws == 0) {
|
||||
return;
|
||||
}
|
||||
// Counted before the check, so a buffer carries at most maxDraws calls before the one
|
||||
// that splits it. OnFrameCommandRecordingBegan resets the count on every new recording.
|
||||
if (++m_drawsInRecording <= maxDraws || !HasPendingRecordedWork()) {
|
||||
return;
|
||||
}
|
||||
// Nothing of the current call is recorded yet, so the split falls between two GL calls,
|
||||
// exactly where a glFlush would put it: the render pass ends with STORE, the next draw
|
||||
// re-begins it with LOAD, and queries and transform feedback are bracketed per draw.
|
||||
if (!FlushPendingCommands()) {
|
||||
return;
|
||||
}
|
||||
// Fresh command buffer: the same reset every other mid-frame flush site applies.
|
||||
m_lastSampledSetValid = false;
|
||||
++m_oversizedRecordingSplits;
|
||||
MGLOG_I_ONCE("DirectVulkan: a frame recorded more than %u draws into one command buffer; submitting it and "
|
||||
"continuing on a fresh one (MOBILEGL_MAGMA_MAX_DRAWS_PER_COMMAND_BUFFER, 0 = unbounded)",
|
||||
maxDraws);
|
||||
MGLOG_D("DirectVulkan: split an oversized recording (%llu so far, submit index %llu)",
|
||||
static_cast<unsigned long long>(m_oversizedRecordingSplits),
|
||||
static_cast<unsigned long long>(m_submitCounter));
|
||||
|
||||
// Splitting only bounds the driver's command memory if the submitted buffers are freed
|
||||
// as fast as they are produced. A GPU that falls behind would park them all on the
|
||||
// retired list, which is the same growth spread over more buffers - so hold the queue
|
||||
// to frames-in-flight + 1 outstanding submissions, the steady state of a pipelined
|
||||
// frame plus this split. Wait on the fence directly rather than through
|
||||
// WaitForSubmitIndex: its opportunistic TryDrainFrameTransients may rewind the transient
|
||||
// arena, and this runs at the start of a draw whose caller may already hold slices of it.
|
||||
const SizeT maxOutstanding = static_cast<SizeT>(m_frameContext.GetFrameCount()) + 1;
|
||||
while (m_inFlightSubmits.size() > maxOutstanding) {
|
||||
const SubmitRecord oldest = m_inFlightSubmits.front();
|
||||
if (oldest.fence == VK_NULL_HANDLE) {
|
||||
break;
|
||||
}
|
||||
const VkResult waitResult = vkWaitForFences(m_device, 1, &oldest.fence, VK_TRUE, UINT64_MAX);
|
||||
if (waitResult != VK_SUCCESS) {
|
||||
MGLOG_E_ONCE("SplitOversizedRecording: vkWaitForFences returned %d", waitResult);
|
||||
break;
|
||||
}
|
||||
OnSubmitsCompletedUpTo(oldest.submitIndex);
|
||||
}
|
||||
}
|
||||
|
||||
Bool VulkanRenderer::WaitForSubmitIndex(Uint64 submitIndex, Uint64 timeoutNs, Bool flushIfPending) {
|
||||
if (IsSubmitIndexComplete(submitIndex)) {
|
||||
return true;
|
||||
@@ -12707,6 +12759,7 @@ void main() {
|
||||
}
|
||||
|
||||
void VulkanRenderer::OnFrameCommandRecordingBegan(VkCommandBuffer commandBuffer) {
|
||||
m_drawsInRecording = 0;
|
||||
// Dynamic state does not survive a command-buffer boundary.
|
||||
ResetDynamicStateShadow();
|
||||
InvalidateSetupDrawSnapshots();
|
||||
|
||||
Reference in New Issue
Block a user