d3d11: Use multiple staging buffers
Using multiple staging buffers and tracking their 'mLastUsageSerial' can
best avoid buffer map stalls in Buffer::WriteInternal.
Bug: dawn:2357
Change-Id: I7bda152640d329608702d9af7639c39bf1bd1c6a
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/170920
Commit-Queue: Jie A Chen <jie.a.chen@intel.com>
Reviewed-by: Austin Eng <enga@chromium.org>
Reviewed-by: Peng Huang <penghuang@chromium.org>
diff --git a/src/dawn/native/Buffer.cpp b/src/dawn/native/Buffer.cpp
index d7a4a41..e508ce2 100644
--- a/src/dawn/native/Buffer.cpp
+++ b/src/dawn/native/Buffer.cpp
@@ -877,6 +877,10 @@
mLastUsageSerial = serial;
}
+ExecutionSerial BufferBase::GetLastUsageSerial() const {
+ return mLastUsageSerial;
+}
+
void BufferBase::SetHasAccess(bool hasAccess) {
mState = hasAccess ? BufferState::Unmapped : BufferState::SharedMemoryNoAccess;
}
diff --git a/src/dawn/native/Buffer.h b/src/dawn/native/Buffer.h
index 20b13ea..5db99ce 100644
--- a/src/dawn/native/Buffer.h
+++ b/src/dawn/native/Buffer.h
@@ -86,6 +86,7 @@
uint64_t GetSize() const;
uint64_t GetAllocatedSize() const;
+ ExecutionSerial GetLastUsageSerial() const;
// |GetUsageExternalOnly| returns the usage with which the buffer was created using the
// base WebGPU API. Additional usages may be added for internal state tracking. |GetUsage|
diff --git a/src/dawn/native/d3d11/BufferD3D11.cpp b/src/dawn/native/d3d11/BufferD3D11.cpp
index 9f463f4..a571a37 100644
--- a/src/dawn/native/d3d11/BufferD3D11.cpp
+++ b/src/dawn/native/d3d11/BufferD3D11.cpp
@@ -630,11 +630,14 @@
// mD3d11ConstantBuffer.
Ref<BufferBase> stagingBuffer;
DAWN_TRY_ASSIGN(stagingBuffer, ToBackend(GetDevice())->GetStagingBuffer(commandContext, size));
-
+ stagingBuffer->MarkUsedInPendingCommands();
DAWN_TRY(ToBackend(stagingBuffer)->WriteInternal(commandContext, 0, data, size));
+ DAWN_TRY(Buffer::CopyInternal(commandContext, ToBackend(stagingBuffer.Get()),
+ /*sourceOffset=*/0,
+ /*size=*/size, this, offset));
+ ToBackend(GetDevice())->ReturnStagingBuffer(std::move(stagingBuffer));
- return Buffer::CopyInternal(commandContext, ToBackend(stagingBuffer.Get()), /*sourceOffset=*/0,
- /*size=*/size, this, offset);
+ return {};
}
// static
diff --git a/src/dawn/native/d3d11/DeviceD3D11.cpp b/src/dawn/native/d3d11/DeviceD3D11.cpp
index e42ad64..e194452 100644
--- a/src/dawn/native/d3d11/DeviceD3D11.cpp
+++ b/src/dawn/native/d3d11/DeviceD3D11.cpp
@@ -378,7 +378,7 @@
DAWN_ASSERT(GetState() == State::Disconnected);
mImplicitPixelLocalStorageAttachmentTextureViews = {};
- mStagingBuffer = nullptr;
+ mStagingBuffers.clear();
Base::DestroyImpl();
}
@@ -550,27 +550,58 @@
ResultOrError<Ref<BufferBase>> Device::GetStagingBuffer(
const ScopedCommandRecordingContext* commandContext,
uint64_t size) {
- constexpr uint64_t kMinSize = 4 * 1024;
- constexpr uint64_t kMaxSize = 16 * 1024 * 1024;
- uint64_t bufferSize = mStagingBuffer.Get() ? mStagingBuffer->GetSize() : 0;
- if (size > bufferSize) {
- bufferSize = Align(size, kMinSize);
- BufferDescriptor descriptor;
- descriptor.usage = wgpu::BufferUsage::MapWrite | wgpu::BufferUsage::CopySrc;
- descriptor.size = bufferSize;
- descriptor.mappedAtCreation = false;
- descriptor.label = "DawnDeviceStagingBuffer";
- Ref<BufferBase> buffer;
+ constexpr uint64_t kMinStagingBufferSize = 4 * 1024;
+ uint64_t bufferSize = Align(size, kMinStagingBufferSize);
+ BufferDescriptor descriptor;
+ descriptor.usage = wgpu::BufferUsage::MapWrite | wgpu::BufferUsage::CopySrc;
+ descriptor.size = bufferSize;
+ descriptor.mappedAtCreation = false;
+ descriptor.label = "DawnDeviceStagingBuffer";
+ Ref<BufferBase> buffer;
+ // We don't cache the buffer if it's too large.
+ if (bufferSize > kMaxStagingBufferSize) {
DAWN_TRY_ASSIGN(buffer, Buffer::Create(this, Unpack(&descriptor), commandContext));
- // We don't cache the buffer if it's too large.
- if (bufferSize > kMaxSize) {
+ return buffer;
+ }
+
+ ExecutionSerial completedSerial = GetQueue()->GetCompletedCommandSerial();
+ for (auto it = mStagingBuffers.begin(); it != mStagingBuffers.end(); ++it) {
+ if ((*it)->GetLastUsageSerial() > completedSerial) {
+ // This buffer, and none after it are ready. Advance to the end and stop the search.
+ break;
+ }
+
+ if ((*it)->GetSize() >= bufferSize) {
+ // this buffer is large enough. Stop searching and remove.
+ buffer = *it;
+ mStagingBuffers.erase(it);
return buffer;
}
- mStagingBuffer = buffer;
}
- // Ensure there is no more than 1 active usage of the staging buffer.
- DAWN_ASSERT(mStagingBuffer->GetRefCountForTesting() <= 1);
- return mStagingBuffer;
+
+ // Create a new staging buffer as no existing one can be re-used.
+ DAWN_TRY_ASSIGN(buffer, Buffer::Create(this, Unpack(&descriptor), commandContext));
+ mTotalStagingBufferSize += bufferSize;
+
+ // Purge the old staging buffers if the total size is too large.
+ constexpr uint64_t kMaxTotalSize = 16 * 1024 * 1024;
+ for (auto it = mStagingBuffers.begin(); it != mStagingBuffers.end() &&
+ mTotalStagingBufferSize > kMaxTotalSize &&
+ (*it)->GetLastUsageSerial() <= completedSerial;) {
+ mTotalStagingBufferSize -= (*it)->GetSize();
+ it = mStagingBuffers.erase(it);
+ }
+
+ return buffer;
+}
+
+void Device::ReturnStagingBuffer(Ref<BufferBase>&& buffer) {
+ DAWN_ASSERT(mStagingBuffers.empty() ||
+ mStagingBuffers.back()->GetLastUsageSerial() <= buffer->GetLastUsageSerial());
+ // Only the cached buffers can be re-used.
+ if (buffer->GetSize() <= kMaxStagingBufferSize) {
+ mStagingBuffers.push_back(std::move(buffer));
+ }
}
} // namespace dawn::native::d3d11
diff --git a/src/dawn/native/d3d11/DeviceD3D11.h b/src/dawn/native/d3d11/DeviceD3D11.h
index 7d34cb1..21aca83 100644
--- a/src/dawn/native/d3d11/DeviceD3D11.h
+++ b/src/dawn/native/d3d11/DeviceD3D11.h
@@ -99,15 +99,16 @@
uint32_t implicitAttachmentIndex);
// Grab a staging buffer, the size of which is no less than 'size'.
- // Note: We assume only 1 staging buffer is active, so the client should release it as soon as
- // possbile once the buffer usage is done.
+ // The buffer must be returned before the advancing of the current pending serial.
ResultOrError<Ref<BufferBase>> GetStagingBuffer(
const ScopedCommandRecordingContext* commandContext,
uint64_t size);
+ void ReturnStagingBuffer(Ref<BufferBase>&& buffer);
private:
using Base = d3d::Device;
using Base::Base;
+ static constexpr uint64_t kMaxStagingBufferSize = 512 * 1024;
ResultOrError<Ref<BindGroupBase>> CreateBindGroupImpl(
const BindGroupDescriptor* descriptor) override;
@@ -162,8 +163,9 @@
// TODO(dawn:1704): decide when to clear the cached implicit pixel local storage attachments.
std::array<Ref<TextureViewBase>, kMaxPLSSlots> mImplicitPixelLocalStorageAttachmentTextureViews;
- // The cached staging buffer.
- Ref<BufferBase> mStagingBuffer;
+ // The cached staging buffers.
+ std::vector<Ref<BufferBase>> mStagingBuffers;
+ uint64_t mTotalStagingBufferSize = 0;
};
} // namespace dawn::native::d3d11
