Files
MobileGL/MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.cpp
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

180 lines
6.3 KiB
C++

// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.cpp
// 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
#include "VkBufferObject.h"
namespace MobileGL::MG_Backend::DirectVulkan {
VkBufferObject::VkBufferObject(VkBufferObject&& other) noexcept {
m_allocator = other.m_allocator;
m_buffer = other.m_buffer;
m_allocation = other.m_allocation;
m_mappedData = other.m_mappedData;
m_size = other.m_size;
other.m_allocator = nullptr;
other.m_buffer = VK_NULL_HANDLE;
other.m_allocation = nullptr;
other.m_mappedData = nullptr;
other.m_size = 0;
}
VkBufferObject& VkBufferObject::operator=(VkBufferObject&& other) noexcept {
if (this == &other) {
return *this;
}
Destroy();
m_allocator = other.m_allocator;
m_buffer = other.m_buffer;
m_allocation = other.m_allocation;
m_mappedData = other.m_mappedData;
m_size = other.m_size;
other.m_allocator = nullptr;
other.m_buffer = VK_NULL_HANDLE;
other.m_allocation = nullptr;
other.m_mappedData = nullptr;
other.m_size = 0;
return *this;
}
VkBufferObject::~VkBufferObject() {
Destroy();
}
Bool VkBufferObject::Create(const VkBufferObjectDesc& desc) {
return Create(desc.allocator, desc.size, desc.usage, desc.memoryUsage, desc.allocationFlags,
desc.requiredFlags);
}
Bool VkBufferObject::Create(VmaAllocator allocator, VkDeviceSize size, VkBufferUsageFlags usage,
VmaMemoryUsage memoryUsage, VmaAllocationCreateFlags allocationFlags,
VkMemoryPropertyFlags requiredFlags) {
MOBILEGL_ASSERT(allocator != nullptr, "VkBufferObject::Create requires valid VMA allocator");
MOBILEGL_ASSERT(size > 0, "VkBufferObject::Create requires non-zero size");
Destroy();
m_allocator = allocator;
VkBufferCreateInfo bufferInfo{};
bufferInfo.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO;
bufferInfo.size = size;
bufferInfo.usage = usage;
bufferInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
VmaAllocationCreateInfo allocationInfo{};
allocationInfo.usage = memoryUsage;
allocationInfo.flags = allocationFlags;
allocationInfo.requiredFlags = requiredFlags;
const VkResult result =
vmaCreateBuffer(m_allocator, &bufferInfo, &allocationInfo, &m_buffer, &m_allocation, nullptr);
if (result != VK_SUCCESS) {
MGLOG_E("VkBufferObject::Create failed: vmaCreateBuffer returned %d", result);
m_allocator = nullptr;
m_buffer = VK_NULL_HANDLE;
m_allocation = nullptr;
m_size = 0;
return false;
}
m_size = size;
return true;
}
void VkBufferObject::Destroy() {
Unmap();
if (m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr) {
vmaDestroyBuffer(m_allocator, m_buffer, m_allocation);
}
m_buffer = VK_NULL_HANDLE;
m_allocation = nullptr;
m_allocator = nullptr;
m_size = 0;
}
void* VkBufferObject::Map() {
MOBILEGL_ASSERT(IsValid(), "VkBufferObject::Map called on invalid buffer");
if (m_mappedData != nullptr) {
return m_mappedData;
}
const VkResult mapResult = vmaMapMemory(m_allocator, m_allocation, &m_mappedData);
if (mapResult != VK_SUCCESS || m_mappedData == nullptr) {
MGLOG_E("VkBufferObject::Map failed: vmaMapMemory returned %d", mapResult);
m_mappedData = nullptr;
return nullptr;
}
return m_mappedData;
}
void VkBufferObject::Unmap() {
if (!IsValid() || m_mappedData == nullptr) {
m_mappedData = nullptr;
return;
}
vmaUnmapMemory(m_allocator, m_allocation);
m_mappedData = nullptr;
}
Bool VkBufferObject::Upload(const void* data, VkDeviceSize size, VkDeviceSize offset) {
MOBILEGL_ASSERT(IsValid(), "VkBufferObject::Upload called on invalid buffer");
MOBILEGL_ASSERT(data != nullptr || size == 0, "VkBufferObject::Upload data pointer is null");
MOBILEGL_ASSERT(offset + size <= m_size, "VkBufferObject::Upload out of range");
if (size == 0) {
return true;
}
const Bool wasMapped = IsMapped();
void* mapped = wasMapped ? m_mappedData : Map();
if (mapped == nullptr) {
MGLOG_E("VkBufferObject::Upload failed: unable to map buffer");
return false;
}
Memcpy(static_cast<Uint8*>(mapped) + offset, data, static_cast<SizeT>(size));
const VkResult flushResult = vmaFlushAllocation(m_allocator, m_allocation, offset, size);
if (flushResult != VK_SUCCESS) {
MGLOG_E("VkBufferObject::Upload failed: vmaFlushAllocation returned %d", flushResult);
if (!wasMapped) {
Unmap();
}
return false;
}
if (!wasMapped) {
Unmap();
}
return true;
}
Bool VkBufferObject::Invalidate(VkDeviceSize size, VkDeviceSize offset) {
MOBILEGL_ASSERT(IsValid(), "VkBufferObject::Invalidate called on invalid buffer");
MOBILEGL_ASSERT(IsMapped(), "VkBufferObject::Invalidate requires mapped memory");
MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::Invalidate offset out of range");
const VkDeviceSize resolvedSize = size == VK_WHOLE_SIZE ? m_size - offset : size;
MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::Invalidate range out of bounds");
if (resolvedSize == 0) {
return true;
}
const VkResult result = vmaInvalidateAllocation(m_allocator, m_allocation, offset, resolvedSize);
if (result != VK_SUCCESS) {
MGLOG_E("VkBufferObject::Invalidate failed: vmaInvalidateAllocation returned %d", result);
return false;
}
return true;
}
} // namespace MobileGL::MG_Backend::DirectVulkan