Files
MobileGL/MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.h
T
BZLZHH 8f2b766b56 [Perf] (MG_Backend): let DirectVulkan trust across frames what it proved once
The draw fast path still paid for its own proofs: the hottest single
load (20% of TrySetupDrawFastPath) was chasing the cold
VertexInputStateFactory heap entry just to answer "same vertex-input
layout?". That answer now comes from the frontend VAO's config-guarded
aux memo (layout hash + attribute masks), and a VAO-cycling stream with
a stable layout skips the pre-flight AND pipeline re-resolution
entirely. The VkProgramObject* is memoized on the snapshot behind a new
ProgramFactory cache-structure epoch (bumped on every insert/erase; use
is re-stamped so the idle sweep can never evict a live entry). A
render-state version move no longer forces the full path: the pipeline
value hash is refreshed in place and the 8-entry memo probed directly
(the GL_BLEND-toggle case).

The resolved-vertex-bindings memo now revalidates all-resident unmapped
entries ACROSS frames via per-binding slice epochs - minted from a
process-lifetime counter so a recycled address can never revalidate,
with every mutation path funnelled through BumpSliceEpoch - while
stamping each resource's GPU-use serial exactly as the skipped acquire
would, preserving the busy-tracking that glBufferSubData's
host-write-vs-staged-copy choice depends on. Resident index buffers get
the same treatment through an EBO slice memo.

The six-part dynamic-state tail (viewport/scissor/blend constants/depth
bias/line width/stencil) is gated behind one render-state-parameters
version + pass-geometry compare per command buffer. GetSlice is inlined;
SampledBindingsUnchanged walks only the program's declared bindings.

Quiet-box 6-round order-alternating A/B (on top of the frontend
VAO-bind commit): vanilla_draw -20.8% (790 -> 626 ns/op, 3.4x native to
2.5x), sampler_churn -28.2%, ubo_range -8.4%, state_toggle -3.8%;
tex_param's matrix flag (+10%) was adjudicated by an isolated
alternating re-run at +1.0% - position bias, not regression. Unit tests
421/421.
2026-08-06 13:18:38 -04:00

77 lines
3.3 KiB
C++

// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.h
// Copyright (c) 2025-2026 MobileGL-Dev
// Licensed under the GNU Lesser General Public License v3.0:
// https://www.gnu.org/licenses/gpl-3.0.txt
// https://www.gnu.org/licenses/lgpl-3.0.txt
// SPDX-License-Identifier: LGPL-3.0-only
// End of Source File Header
#pragma once
#include "BufferSlice.h"
#include "../VkIncludes.h"
#include <Includes.h>
#include <vk_mem_alloc.h>
namespace MobileGL::MG_Backend::DirectVulkan {
struct VkBufferObjectDesc {
VmaAllocator allocator = nullptr;
VkDeviceSize size = 0;
VkBufferUsageFlags usage = 0;
VmaMemoryUsage memoryUsage = VMA_MEMORY_USAGE_AUTO;
VmaAllocationCreateFlags allocationFlags = 0;
// Memory property bits the allocation MUST satisfy (e.g. HOST_VISIBLE|HOST_COHERENT
// for a persistently-mapped buffer the app writes into without explicit flushes).
VkMemoryPropertyFlags requiredFlags = 0;
};
class VkBufferObject {
public:
VkBufferObject() = default;
~VkBufferObject();
VkBufferObject(const VkBufferObject&) = delete;
VkBufferObject& operator=(const VkBufferObject&) = delete;
VkBufferObject(VkBufferObject&& other) noexcept;
VkBufferObject& operator=(VkBufferObject&& other) noexcept;
Bool Create(const VkBufferObjectDesc& desc);
Bool Create(VmaAllocator allocator, VkDeviceSize size, VkBufferUsageFlags usage,
VmaMemoryUsage memoryUsage, VmaAllocationCreateFlags allocationFlags = 0,
VkMemoryPropertyFlags requiredFlags = 0);
void Destroy();
void* Map();
void Unmap();
Bool Upload(const void* data, VkDeviceSize size, VkDeviceSize offset = 0);
Bool Invalidate(VkDeviceSize size = VK_WHOLE_SIZE, VkDeviceSize offset = 0);
VkBuffer GetHandle() const { return m_buffer; }
VkDeviceSize GetSize() const { return m_size; }
// Inline: runs on the per-draw acquire path (a resident buffer bind is a
// GetSlice per binding), where an out-of-line call was measurable.
BufferSlice GetSlice(VkDeviceSize offset = 0, VkDeviceSize size = VK_WHOLE_SIZE) const {
MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::GetSlice offset out of range");
const VkDeviceSize resolvedSize = (size == VK_WHOLE_SIZE) ? (m_size - offset) : size;
MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::GetSlice range out of bounds");
BufferSlice slice{};
slice.buffer = m_buffer;
slice.offset = offset;
slice.size = resolvedSize;
slice.mapped = (m_mappedData != nullptr) ? static_cast<Uint8*>(m_mappedData) + offset : nullptr;
return slice;
}
void* GetMappedData() const { return m_mappedData; }
Bool IsMapped() const { return m_mappedData != nullptr; }
Bool IsValid() const { return m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr; }
private:
VmaAllocator m_allocator = nullptr;
VkBuffer m_buffer = VK_NULL_HANDLE;
VmaAllocation m_allocation = nullptr;
void* m_mappedData = nullptr;
VkDeviceSize m_size = 0;
};
} // namespace MobileGL::MG_Backend::DirectVulkan