diff options
Diffstat (limited to 'src/video_core/renderer_vulkan')
24 files changed, 215 insertions, 266 deletions
diff --git a/src/video_core/renderer_vulkan/blit_image.cpp b/src/video_core/renderer_vulkan/blit_image.cpp index cf2964a3f..28d4b15a0 100644 --- a/src/video_core/renderer_vulkan/blit_image.cpp +++ b/src/video_core/renderer_vulkan/blit_image.cpp @@ -495,6 +495,9 @@ void BlitImageHelper::BlitDepthStencil(const Framebuffer* dst_framebuffer, const Region2D& dst_region, const Region2D& src_region, Tegra::Engines::Fermi2D::Filter filter, Tegra::Engines::Fermi2D::Operation operation) { + if (!device.IsExtShaderStencilExportSupported()) { + return; + } ASSERT(filter == Tegra::Engines::Fermi2D::Filter::Point); ASSERT(operation == Tegra::Engines::Fermi2D::Operation::SrcCopy); const BlitImagePipelineKey key{ diff --git a/src/video_core/renderer_vulkan/maxwell_to_vk.cpp b/src/video_core/renderer_vulkan/maxwell_to_vk.cpp index 9a0b10568..a8540339d 100644 --- a/src/video_core/renderer_vulkan/maxwell_to_vk.cpp +++ b/src/video_core/renderer_vulkan/maxwell_to_vk.cpp @@ -259,6 +259,26 @@ FormatInfo SurfaceFormat(const Device& device, FormatType format_type, bool with break; } } + // Transcode on hardware that doesn't support BCn natively + if (!device.IsOptimalBcnSupported() && VideoCore::Surface::IsPixelFormatBCn(pixel_format)) { + const bool is_srgb = with_srgb && VideoCore::Surface::IsPixelFormatSRGB(pixel_format); + if (pixel_format == PixelFormat::BC4_SNORM) { + tuple.format = VK_FORMAT_R8_SNORM; + } else if (pixel_format == PixelFormat::BC4_UNORM) { + tuple.format = VK_FORMAT_R8_UNORM; + } else if (pixel_format == PixelFormat::BC5_SNORM) { + tuple.format = VK_FORMAT_R8G8_SNORM; + } else if (pixel_format == PixelFormat::BC5_UNORM) { + tuple.format = VK_FORMAT_R8G8_UNORM; + } else if (pixel_format == PixelFormat::BC6H_SFLOAT || + pixel_format == PixelFormat::BC6H_UFLOAT) { + tuple.format = VK_FORMAT_R16G16B16A16_SFLOAT; + } else if (is_srgb) { + tuple.format = VK_FORMAT_A8B8G8R8_SRGB_PACK32; + } else { + tuple.format = VK_FORMAT_A8B8G8R8_UNORM_PACK32; + } + } const bool attachable = (tuple.usage & Attachable) != 0; const bool storage = (tuple.usage & Storage) != 0; diff --git a/src/video_core/renderer_vulkan/renderer_vulkan.cpp b/src/video_core/renderer_vulkan/renderer_vulkan.cpp index 77128c6e2..454bb66a4 100644 --- a/src/video_core/renderer_vulkan/renderer_vulkan.cpp +++ b/src/video_core/renderer_vulkan/renderer_vulkan.cpp @@ -12,6 +12,7 @@ #include <fmt/format.h> #include "common/logging/log.h" +#include "common/polyfill_ranges.h" #include "common/scope_exit.h" #include "common/settings.h" #include "common/telemetry.h" @@ -65,6 +66,21 @@ std::string BuildCommaSeparatedExtensions( return fmt::format("{}", fmt::join(available_extensions, ",")); } +DebugCallback MakeDebugCallback(const vk::Instance& instance, const vk::InstanceDispatch& dld) { + if (!Settings::values.renderer_debug) { + return DebugCallback{}; + } + const std::optional properties = vk::EnumerateInstanceExtensionProperties(dld); + const auto it = std::ranges::find_if(*properties, [](const auto& prop) { + return std::strcmp(VK_EXT_DEBUG_UTILS_EXTENSION_NAME, prop.extensionName) == 0; + }); + if (it != properties->end()) { + return CreateDebugUtilsCallback(instance); + } else { + return CreateDebugReportCallback(instance); + } +} + } // Anonymous namespace Device CreateDevice(const vk::Instance& instance, const vk::InstanceDispatch& dld, @@ -87,10 +103,10 @@ RendererVulkan::RendererVulkan(Core::TelemetrySession& telemetry_session_, cpu_memory(cpu_memory_), gpu(gpu_), library(OpenLibrary(context.get())), instance(CreateInstance(*library, dld, VK_API_VERSION_1_1, render_window.GetWindowInfo().type, Settings::values.renderer_debug.GetValue())), - debug_callback(Settings::values.renderer_debug ? CreateDebugCallback(instance) : nullptr), + debug_callback(MakeDebugCallback(instance, dld)), surface(CreateSurface(instance, render_window.GetWindowInfo())), - device(CreateDevice(instance, dld, *surface)), memory_allocator(device, false), - state_tracker(), scheduler(device, state_tracker), + device(CreateDevice(instance, dld, *surface)), memory_allocator(device), state_tracker(), + scheduler(device, state_tracker), swapchain(*surface, device, scheduler, render_window.GetFramebufferLayout().width, render_window.GetFramebufferLayout().height, false), present_manager(instance, render_window, device, memory_allocator, scheduler, swapchain, @@ -173,7 +189,7 @@ void Vulkan::RendererVulkan::RenderScreenshot(const Tegra::FramebufferConfig& fr return; } const Layout::FramebufferLayout layout{renderer_settings.screenshot_framebuffer_layout}; - vk::Image staging_image = device.GetLogical().CreateImage(VkImageCreateInfo{ + vk::Image staging_image = memory_allocator.CreateImage(VkImageCreateInfo{ .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO, .pNext = nullptr, .flags = VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT, @@ -196,7 +212,6 @@ void Vulkan::RendererVulkan::RenderScreenshot(const Tegra::FramebufferConfig& fr .pQueueFamilyIndices = nullptr, .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED, }); - const auto image_commit = memory_allocator.Commit(staging_image, MemoryUsage::DeviceLocal); const vk::ImageView dst_view = device.GetLogical().CreateImageView(VkImageViewCreateInfo{ .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO, @@ -234,8 +249,8 @@ void Vulkan::RendererVulkan::RenderScreenshot(const Tegra::FramebufferConfig& fr .queueFamilyIndexCount = 0, .pQueueFamilyIndices = nullptr, }; - const vk::Buffer dst_buffer = device.GetLogical().CreateBuffer(dst_buffer_info); - MemoryCommit dst_buffer_memory = memory_allocator.Commit(dst_buffer, MemoryUsage::Download); + const vk::Buffer dst_buffer = + memory_allocator.CreateBuffer(dst_buffer_info, MemoryUsage::Download); scheduler.RequestOutsideRenderPassOperationContext(); scheduler.Record([&](vk::CommandBuffer cmdbuf) { @@ -309,8 +324,9 @@ void Vulkan::RendererVulkan::RenderScreenshot(const Tegra::FramebufferConfig& fr scheduler.Finish(); // Copy backing image data to the QImage screenshot buffer - const auto dst_memory_map = dst_buffer_memory.Map(); - std::memcpy(renderer_settings.screenshot_bits, dst_memory_map.data(), dst_memory_map.size()); + dst_buffer.Invalidate(); + std::memcpy(renderer_settings.screenshot_bits, dst_buffer.Mapped().data(), + dst_buffer.Mapped().size()); renderer_settings.screenshot_complete_callback(false); renderer_settings.screenshot_requested = false; } diff --git a/src/video_core/renderer_vulkan/renderer_vulkan.h b/src/video_core/renderer_vulkan/renderer_vulkan.h index b2e8cbd1b..ca22c0baa 100644 --- a/src/video_core/renderer_vulkan/renderer_vulkan.h +++ b/src/video_core/renderer_vulkan/renderer_vulkan.h @@ -5,6 +5,7 @@ #include <memory> #include <string> +#include <variant> #include "common/dynamic_library.h" #include "video_core/renderer_base.h" @@ -33,6 +34,8 @@ class GPU; namespace Vulkan { +using DebugCallback = std::variant<vk::DebugUtilsMessenger, vk::DebugReportCallback>; + Device CreateDevice(const vk::Instance& instance, const vk::InstanceDispatch& dld, VkSurfaceKHR surface); @@ -71,7 +74,7 @@ private: vk::InstanceDispatch dld; vk::Instance instance; - vk::DebugUtilsMessenger debug_callback; + DebugCallback debug_callback; vk::SurfaceKHR surface; ScreenInfo screen_info; diff --git a/src/video_core/renderer_vulkan/vk_blit_screen.cpp b/src/video_core/renderer_vulkan/vk_blit_screen.cpp index acb143fc7..ad3b29f0e 100644 --- a/src/video_core/renderer_vulkan/vk_blit_screen.cpp +++ b/src/video_core/renderer_vulkan/vk_blit_screen.cpp @@ -162,7 +162,7 @@ void BlitScreen::Draw(const Tegra::FramebufferConfig& framebuffer, SetUniformData(data, layout); SetVertexData(data, framebuffer, layout); - const std::span<u8> mapped_span = buffer_commit.Map(); + const std::span<u8> mapped_span = buffer.Mapped(); std::memcpy(mapped_span.data(), &data, sizeof(data)); if (!use_accelerated) { @@ -1071,14 +1071,9 @@ void BlitScreen::ReleaseRawImages() { scheduler.Wait(tick); } raw_images.clear(); - raw_buffer_commits.clear(); - aa_image_view.reset(); aa_image.reset(); - aa_commit = MemoryCommit{}; - buffer.reset(); - buffer_commit = MemoryCommit{}; } void BlitScreen::CreateStagingBuffer(const Tegra::FramebufferConfig& framebuffer) { @@ -1094,20 +1089,18 @@ void BlitScreen::CreateStagingBuffer(const Tegra::FramebufferConfig& framebuffer .pQueueFamilyIndices = nullptr, }; - buffer = device.GetLogical().CreateBuffer(ci); - buffer_commit = memory_allocator.Commit(buffer, MemoryUsage::Upload); + buffer = memory_allocator.CreateBuffer(ci, MemoryUsage::Upload); } void BlitScreen::CreateRawImages(const Tegra::FramebufferConfig& framebuffer) { raw_images.resize(image_count); raw_image_views.resize(image_count); - raw_buffer_commits.resize(image_count); const auto create_image = [&](bool used_on_framebuffer = false, u32 up_scale = 1, u32 down_shift = 0) { u32 extra_usages = used_on_framebuffer ? VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT : VK_IMAGE_USAGE_TRANSFER_DST_BIT; - return device.GetLogical().CreateImage(VkImageCreateInfo{ + return memory_allocator.CreateImage(VkImageCreateInfo{ .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO, .pNext = nullptr, .flags = 0, @@ -1130,9 +1123,6 @@ void BlitScreen::CreateRawImages(const Tegra::FramebufferConfig& framebuffer) { .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED, }); }; - const auto create_commit = [&](vk::Image& image) { - return memory_allocator.Commit(image, MemoryUsage::DeviceLocal); - }; const auto create_image_view = [&](vk::Image& image, bool used_on_framebuffer = false) { return device.GetLogical().CreateImageView(VkImageViewCreateInfo{ .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO, @@ -1161,7 +1151,6 @@ void BlitScreen::CreateRawImages(const Tegra::FramebufferConfig& framebuffer) { for (size_t i = 0; i < image_count; ++i) { raw_images[i] = create_image(); - raw_buffer_commits[i] = create_commit(raw_images[i]); raw_image_views[i] = create_image_view(raw_images[i]); } @@ -1169,7 +1158,6 @@ void BlitScreen::CreateRawImages(const Tegra::FramebufferConfig& framebuffer) { const u32 up_scale = Settings::values.resolution_info.up_scale; const u32 down_shift = Settings::values.resolution_info.down_shift; aa_image = create_image(true, up_scale, down_shift); - aa_commit = create_commit(aa_image); aa_image_view = create_image_view(aa_image, true); VkExtent2D size{ .width = (up_scale * framebuffer.width) >> down_shift, diff --git a/src/video_core/renderer_vulkan/vk_blit_screen.h b/src/video_core/renderer_vulkan/vk_blit_screen.h index 68ec20253..8365b5668 100644 --- a/src/video_core/renderer_vulkan/vk_blit_screen.h +++ b/src/video_core/renderer_vulkan/vk_blit_screen.h @@ -142,13 +142,11 @@ private: vk::Sampler sampler; vk::Buffer buffer; - MemoryCommit buffer_commit; std::vector<u64> resource_ticks; std::vector<vk::Image> raw_images; std::vector<vk::ImageView> raw_image_views; - std::vector<MemoryCommit> raw_buffer_commits; vk::DescriptorPool aa_descriptor_pool; vk::DescriptorSetLayout aa_descriptor_set_layout; @@ -159,7 +157,6 @@ private: vk::DescriptorSets aa_descriptor_sets; vk::Image aa_image; vk::ImageView aa_image_view; - MemoryCommit aa_commit; u32 raw_width = 0; u32 raw_height = 0; diff --git a/src/video_core/renderer_vulkan/vk_buffer_cache.cpp b/src/video_core/renderer_vulkan/vk_buffer_cache.cpp index e30fcb1ed..b72f95235 100644 --- a/src/video_core/renderer_vulkan/vk_buffer_cache.cpp +++ b/src/video_core/renderer_vulkan/vk_buffer_cache.cpp @@ -50,7 +50,7 @@ size_t BytesPerIndex(VkIndexType index_type) { } } -vk::Buffer CreateBuffer(const Device& device, u64 size) { +vk::Buffer CreateBuffer(const Device& device, const MemoryAllocator& memory_allocator, u64 size) { VkBufferUsageFlags flags = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_UNIFORM_TEXEL_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_TEXEL_BUFFER_BIT | @@ -60,7 +60,7 @@ vk::Buffer CreateBuffer(const Device& device, u64 size) { if (device.IsExtTransformFeedbackSupported()) { flags |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT; } - return device.GetLogical().CreateBuffer({ + const VkBufferCreateInfo buffer_ci = { .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .pNext = nullptr, .flags = 0, @@ -69,7 +69,8 @@ vk::Buffer CreateBuffer(const Device& device, u64 size) { .sharingMode = VK_SHARING_MODE_EXCLUSIVE, .queueFamilyIndexCount = 0, .pQueueFamilyIndices = nullptr, - }); + }; + return memory_allocator.CreateBuffer(buffer_ci, MemoryUsage::DeviceLocal); } } // Anonymous namespace @@ -79,8 +80,8 @@ Buffer::Buffer(BufferCacheRuntime&, VideoCommon::NullBufferParams null_params) Buffer::Buffer(BufferCacheRuntime& runtime, VideoCore::RasterizerInterface& rasterizer_, VAddr cpu_addr_, u64 size_bytes_) : VideoCommon::BufferBase<VideoCore::RasterizerInterface>(rasterizer_, cpu_addr_, size_bytes_), - device{&runtime.device}, buffer{CreateBuffer(*device, SizeBytes())}, - commit{runtime.memory_allocator.Commit(buffer, MemoryUsage::DeviceLocal)} { + device{&runtime.device}, buffer{ + CreateBuffer(*device, runtime.memory_allocator, SizeBytes())} { if (runtime.device.HasDebuggingToolAttached()) { buffer.SetObjectNameEXT(fmt::format("Buffer 0x{:x}", CpuAddr()).c_str()); } @@ -138,7 +139,7 @@ public: const u32 num_first_offset_copies = 4; const size_t bytes_per_index = BytesPerIndex(index_type); const size_t size_bytes = num_triangle_indices * bytes_per_index * num_first_offset_copies; - buffer = device.GetLogical().CreateBuffer(VkBufferCreateInfo{ + const VkBufferCreateInfo buffer_ci = { .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .pNext = nullptr, .flags = 0, @@ -147,14 +148,21 @@ public: .sharingMode = VK_SHARING_MODE_EXCLUSIVE, .queueFamilyIndexCount = 0, .pQueueFamilyIndices = nullptr, - }); + }; + buffer = memory_allocator.CreateBuffer(buffer_ci, MemoryUsage::DeviceLocal); if (device.HasDebuggingToolAttached()) { buffer.SetObjectNameEXT("Quad LUT"); } - memory_commit = memory_allocator.Commit(buffer, MemoryUsage::DeviceLocal); - const StagingBufferRef staging = staging_pool.Request(size_bytes, MemoryUsage::Upload); - u8* staging_data = staging.mapped_span.data(); + const bool host_visible = buffer.IsHostVisible(); + const StagingBufferRef staging = [&] { + if (host_visible) { + return StagingBufferRef{}; + } + return staging_pool.Request(size_bytes, MemoryUsage::Upload); + }(); + + u8* staging_data = host_visible ? buffer.Mapped().data() : staging.mapped_span.data(); const size_t quad_size = bytes_per_index * 6; for (u32 first = 0; first < num_first_offset_copies; ++first) { @@ -164,29 +172,33 @@ public: } } - scheduler.RequestOutsideRenderPassOperationContext(); - scheduler.Record([src_buffer = staging.buffer, src_offset = staging.offset, - dst_buffer = *buffer, size_bytes](vk::CommandBuffer cmdbuf) { - const VkBufferCopy copy{ - .srcOffset = src_offset, - .dstOffset = 0, - .size = size_bytes, - }; - const VkBufferMemoryBarrier write_barrier{ - .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER, - .pNext = nullptr, - .srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT, - .dstAccessMask = VK_ACCESS_INDEX_READ_BIT, - .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED, - .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED, - .buffer = dst_buffer, - .offset = 0, - .size = size_bytes, - }; - cmdbuf.CopyBuffer(src_buffer, dst_buffer, copy); - cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_TRANSFER_BIT, - VK_PIPELINE_STAGE_VERTEX_INPUT_BIT, 0, write_barrier); - }); + if (!host_visible) { + scheduler.RequestOutsideRenderPassOperationContext(); + scheduler.Record([src_buffer = staging.buffer, src_offset = staging.offset, + dst_buffer = *buffer, size_bytes](vk::CommandBuffer cmdbuf) { + const VkBufferCopy copy{ + .srcOffset = src_offset, + .dstOffset = 0, + .size = size_bytes, + }; + const VkBufferMemoryBarrier write_barrier{ + .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER, + .pNext = nullptr, + .srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT, + .dstAccessMask = VK_ACCESS_INDEX_READ_BIT, + .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED, + .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED, + .buffer = dst_buffer, + .offset = 0, + .size = size_bytes, + }; + cmdbuf.CopyBuffer(src_buffer, dst_buffer, copy); + cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_TRANSFER_BIT, + VK_PIPELINE_STAGE_VERTEX_INPUT_BIT, 0, write_barrier); + }); + } else { + buffer.Flush(); + } } void BindBuffer(u32 first) { @@ -361,7 +373,7 @@ void BufferCacheRuntime::CopyBuffer(VkBuffer dst_buffer, VkBuffer src_buffer, .dstAccessMask = VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT, }; // Measuring a popular game, this number never exceeds the specified size once data is warmed up - boost::container::small_vector<VkBufferCopy, 3> vk_copies(copies.size()); + boost::container::small_vector<VkBufferCopy, 8> vk_copies(copies.size()); std::ranges::transform(copies, vk_copies.begin(), MakeBufferCopy); scheduler.RequestOutsideRenderPassOperationContext(); scheduler.Record([src_buffer, dst_buffer, vk_copies, barrier](vk::CommandBuffer cmdbuf) { @@ -578,7 +590,8 @@ void BufferCacheRuntime::ReserveNullBuffer() { .pNext = nullptr, .flags = 0, .size = 4, - .usage = VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT, + .usage = VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_INDEX_BUFFER_BIT | + VK_BUFFER_USAGE_TRANSFER_DST_BIT, .sharingMode = VK_SHARING_MODE_EXCLUSIVE, .queueFamilyIndexCount = 0, .pQueueFamilyIndices = nullptr, @@ -587,11 +600,10 @@ void BufferCacheRuntime::ReserveNullBuffer() { create_info.usage |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT; } create_info.usage |= VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT; - null_buffer = device.GetLogical().CreateBuffer(create_info); + null_buffer = memory_allocator.CreateBuffer(create_info, MemoryUsage::DeviceLocal); if (device.HasDebuggingToolAttached()) { null_buffer.SetObjectNameEXT("Null buffer"); } - null_buffer_commit = memory_allocator.Commit(null_buffer, MemoryUsage::DeviceLocal); scheduler.RequestOutsideRenderPassOperationContext(); scheduler.Record([buffer = *null_buffer](vk::CommandBuffer cmdbuf) { diff --git a/src/video_core/renderer_vulkan/vk_buffer_cache.h b/src/video_core/renderer_vulkan/vk_buffer_cache.h index cdeef8846..95446c732 100644 --- a/src/video_core/renderer_vulkan/vk_buffer_cache.h +++ b/src/video_core/renderer_vulkan/vk_buffer_cache.h @@ -48,7 +48,6 @@ private: const Device* device{}; vk::Buffer buffer; - MemoryCommit commit; std::vector<BufferView> views; }; @@ -142,7 +141,6 @@ private: std::shared_ptr<QuadStripIndexBuffer> quad_strip_index_buffer; vk::Buffer null_buffer; - MemoryCommit null_buffer_commit; std::unique_ptr<Uint8Pass> uint8_pass; QuadIndexedPass quad_index_pass; diff --git a/src/video_core/renderer_vulkan/vk_fsr.cpp b/src/video_core/renderer_vulkan/vk_fsr.cpp index df972cd54..9bcdca2fb 100644 --- a/src/video_core/renderer_vulkan/vk_fsr.cpp +++ b/src/video_core/renderer_vulkan/vk_fsr.cpp @@ -205,10 +205,9 @@ void FSR::CreateDescriptorSets() { void FSR::CreateImages() { images.resize(image_count * 2); image_views.resize(image_count * 2); - buffer_commits.resize(image_count * 2); for (size_t i = 0; i < image_count * 2; ++i) { - images[i] = device.GetLogical().CreateImage(VkImageCreateInfo{ + images[i] = memory_allocator.CreateImage(VkImageCreateInfo{ .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO, .pNext = nullptr, .flags = 0, @@ -231,7 +230,6 @@ void FSR::CreateImages() { .pQueueFamilyIndices = nullptr, .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED, }); - buffer_commits[i] = memory_allocator.Commit(images[i], MemoryUsage::DeviceLocal); image_views[i] = device.GetLogical().CreateImageView(VkImageViewCreateInfo{ .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO, .pNext = nullptr, diff --git a/src/video_core/renderer_vulkan/vk_fsr.h b/src/video_core/renderer_vulkan/vk_fsr.h index 5d872861f..8bb9fc23a 100644 --- a/src/video_core/renderer_vulkan/vk_fsr.h +++ b/src/video_core/renderer_vulkan/vk_fsr.h @@ -47,7 +47,6 @@ private: vk::Sampler sampler; std::vector<vk::Image> images; std::vector<vk::ImageView> image_views; - std::vector<MemoryCommit> buffer_commits; }; } // namespace Vulkan diff --git a/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp b/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp index c1595642e..ad35cacac 100644 --- a/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp +++ b/src/video_core/renderer_vulkan/vk_graphics_pipeline.cpp @@ -652,13 +652,14 @@ void GraphicsPipeline::MakePipeline(VkRenderPass render_pass) { .pNext = nullptr, .negativeOneToOne = key.state.ndc_minus_one_to_one.Value() != 0 ? VK_TRUE : VK_FALSE, }; + const u32 num_viewports = std::min<u32>(device.GetMaxViewports(), Maxwell::NumViewports); VkPipelineViewportStateCreateInfo viewport_ci{ .sType = VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO, .pNext = nullptr, .flags = 0, - .viewportCount = Maxwell::NumViewports, + .viewportCount = num_viewports, .pViewports = nullptr, - .scissorCount = Maxwell::NumViewports, + .scissorCount = num_viewports, .pScissors = nullptr, }; if (device.IsNvViewportSwizzleSupported()) { diff --git a/src/video_core/renderer_vulkan/vk_master_semaphore.cpp b/src/video_core/renderer_vulkan/vk_master_semaphore.cpp index 5eeda08d2..6b288b994 100644 --- a/src/video_core/renderer_vulkan/vk_master_semaphore.cpp +++ b/src/video_core/renderer_vulkan/vk_master_semaphore.cpp @@ -75,15 +75,9 @@ void MasterSemaphore::Refresh() { void MasterSemaphore::Wait(u64 tick) { if (!semaphore) { - // If we don't support timeline semaphores, use an atomic wait - while (true) { - u64 current_value = gpu_tick.load(std::memory_order_relaxed); - if (current_value >= tick) { - return; - } - gpu_tick.wait(current_value); - } - + // If we don't support timeline semaphores, wait for the value normally + std::unique_lock lk{free_mutex}; + free_cv.wait(lk, [&] { return gpu_tick.load(std::memory_order_relaxed) >= tick; }); return; } @@ -198,11 +192,13 @@ void MasterSemaphore::WaitThread(std::stop_token token) { fence.Wait(); fence.Reset(); - gpu_tick.store(host_tick); - gpu_tick.notify_all(); - std::scoped_lock lock{free_mutex}; - free_queue.push_front(std::move(fence)); + { + std::scoped_lock lock{free_mutex}; + free_queue.push_front(std::move(fence)); + gpu_tick.store(host_tick); + } + free_cv.notify_one(); } } diff --git a/src/video_core/renderer_vulkan/vk_master_semaphore.h b/src/video_core/renderer_vulkan/vk_master_semaphore.h index 1e7c90215..3f599d7bd 100644 --- a/src/video_core/renderer_vulkan/vk_master_semaphore.h +++ b/src/video_core/renderer_vulkan/vk_master_semaphore.h @@ -72,6 +72,7 @@ private: std::atomic<u64> current_tick{1}; ///< Current logical tick. std::mutex wait_mutex; std::mutex free_mutex; + std::condition_variable free_cv; std::condition_variable_any wait_cv; std::queue<Waitable> wait_queue; ///< Queue for the fences to be waited on by the wait thread. std::deque<vk::Fence> free_queue; ///< Holds available fences for submission. diff --git a/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp b/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp index 18e040a1b..d600c4e61 100644 --- a/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp +++ b/src/video_core/renderer_vulkan/vk_pipeline_cache.cpp @@ -167,7 +167,10 @@ Shader::RuntimeInfo MakeRuntimeInfo(std::span<const Shader::IR::Program> program info.fixed_state_point_size = point_size; } if (key.state.xfb_enabled) { - info.xfb_varyings = VideoCommon::MakeTransformFeedbackVaryings(key.state.xfb_state); + auto [varyings, count] = + VideoCommon::MakeTransformFeedbackVaryings(key.state.xfb_state); + info.xfb_varyings = varyings; + info.xfb_count = count; } info.convert_depth_mode = gl_ndc; } @@ -214,7 +217,10 @@ Shader::RuntimeInfo MakeRuntimeInfo(std::span<const Shader::IR::Program> program info.fixed_state_point_size = point_size; } if (key.state.xfb_enabled != 0) { - info.xfb_varyings = VideoCommon::MakeTransformFeedbackVaryings(key.state.xfb_state); + auto [varyings, count] = + VideoCommon::MakeTransformFeedbackVaryings(key.state.xfb_state); + info.xfb_varyings = varyings; + info.xfb_count = count; } info.convert_depth_mode = gl_ndc; break; @@ -303,7 +309,7 @@ PipelineCache::PipelineCache(RasterizerVulkan& rasterizer_, const Device& device .support_int16 = device.IsShaderInt16Supported(), .support_int64 = device.IsShaderInt64Supported(), .support_vertex_instance_id = false, - .support_float_controls = true, + .support_float_controls = device.IsKhrShaderFloatControlsSupported(), .support_separate_denorm_behavior = float_control.denormBehaviorIndependence == VK_SHADER_FLOAT_CONTROLS_INDEPENDENCE_ALL, .support_separate_rounding_mode = @@ -319,12 +325,13 @@ PipelineCache::PipelineCache(RasterizerVulkan& rasterizer_, const Device& device .support_fp64_signed_zero_nan_preserve = float_control.shaderSignedZeroInfNanPreserveFloat64 != VK_FALSE, .support_explicit_workgroup_layout = device.IsKhrWorkgroupMemoryExplicitLayoutSupported(), - .support_vote = true, + .support_vote = device.IsSubgroupFeatureSupported(VK_SUBGROUP_FEATURE_VOTE_BIT), .support_viewport_index_layer_non_geometry = device.IsExtShaderViewportIndexLayerSupported(), .support_viewport_mask = device.IsNvViewportArray2Supported(), .support_typeless_image_loads = device.IsFormatlessImageLoadSupported(), - .support_demote_to_helper_invocation = true, + .support_demote_to_helper_invocation = + device.IsExtShaderDemoteToHelperInvocationSupported(), .support_int64_atomics = device.IsExtShaderAtomicInt64Supported(), .support_derivative_control = true, .support_geometry_shader_passthrough = device.IsNvGeometryShaderPassthroughSupported(), @@ -705,10 +712,7 @@ std::unique_ptr<ComputePipeline> PipelineCache::CreateComputePipeline( std::unique_ptr<ComputePipeline> PipelineCache::CreateComputePipeline( ShaderPools& pools, const ComputePipelineCacheKey& key, Shader::Environment& env, PipelineStatistics* statistics, bool build_in_parallel) try { - // TODO: Remove this when Intel fixes their shader compiler. - // https://github.com/IGCIT/Intel-GPU-Community-Issue-Tracker-IGCIT/issues/159 - if (device.GetDriverID() == VK_DRIVER_ID_INTEL_PROPRIETARY_WINDOWS && - !Settings::values.enable_compute_pipelines.GetValue()) { + if (device.HasBrokenCompute()) { LOG_ERROR(Render_Vulkan, "Skipping 0x{:016x}", key.Hash()); return nullptr; } diff --git a/src/video_core/renderer_vulkan/vk_present_manager.cpp b/src/video_core/renderer_vulkan/vk_present_manager.cpp index 10ace0420..d681bd22a 100644 --- a/src/video_core/renderer_vulkan/vk_present_manager.cpp +++ b/src/video_core/renderer_vulkan/vk_present_manager.cpp @@ -181,7 +181,7 @@ void PresentManager::RecreateFrame(Frame* frame, u32 width, u32 height, bool is_ frame->height = height; frame->is_srgb = is_srgb; - frame->image = dld.CreateImage({ + frame->image = memory_allocator.CreateImage({ .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO, .pNext = nullptr, .flags = VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT, @@ -204,8 +204,6 @@ void PresentManager::RecreateFrame(Frame* frame, u32 width, u32 height, bool is_ .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED, }); - frame->image_commit = memory_allocator.Commit(frame->image, MemoryUsage::DeviceLocal); - frame->image_view = dld.CreateImageView({ .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO, .pNext = nullptr, diff --git a/src/video_core/renderer_vulkan/vk_present_manager.h b/src/video_core/renderer_vulkan/vk_present_manager.h index 4ac2e2395..83e859416 100644 --- a/src/video_core/renderer_vulkan/vk_present_manager.h +++ b/src/video_core/renderer_vulkan/vk_present_manager.h @@ -29,7 +29,6 @@ struct Frame { vk::Image image; vk::ImageView image_view; vk::Framebuffer framebuffer; - MemoryCommit image_commit; vk::CommandBuffer cmdbuf; vk::Semaphore render_ready; vk::Fence present_done; diff --git a/src/video_core/renderer_vulkan/vk_rasterizer.cpp b/src/video_core/renderer_vulkan/vk_rasterizer.cpp index 84e3a30cc..f7c0d939a 100644 --- a/src/video_core/renderer_vulkan/vk_rasterizer.cpp +++ b/src/video_core/renderer_vulkan/vk_rasterizer.cpp @@ -315,7 +315,14 @@ void RasterizerVulkan::Clear(u32 layer_count) { FlushWork(); gpu_memory->FlushCaching(); +#if ANDROID + if (Settings::IsGPULevelHigh()) { + // This is problematic on Android, disable on GPU Normal. + query_cache.UpdateCounters(); + } +#else query_cache.UpdateCounters(); +#endif auto& regs = maxwell3d->regs; const bool use_color = regs.clear_surface.R || regs.clear_surface.G || regs.clear_surface.B || @@ -925,7 +932,7 @@ void RasterizerVulkan::UpdateViewportsState(Tegra::Engines::Maxwell3D::Regs& reg } const bool is_rescaling{texture_cache.IsRescaling()}; const float scale = is_rescaling ? Settings::values.resolution_info.up_factor : 1.0f; - const std::array viewports{ + const std::array viewport_list{ GetViewportState(device, regs, 0, scale), GetViewportState(device, regs, 1, scale), GetViewportState(device, regs, 2, scale), GetViewportState(device, regs, 3, scale), GetViewportState(device, regs, 4, scale), GetViewportState(device, regs, 5, scale), @@ -935,7 +942,11 @@ void RasterizerVulkan::UpdateViewportsState(Tegra::Engines::Maxwell3D::Regs& reg GetViewportState(device, regs, 12, scale), GetViewportState(device, regs, 13, scale), GetViewportState(device, regs, 14, scale), GetViewportState(device, regs, 15, scale), }; - scheduler.Record([viewports](vk::CommandBuffer cmdbuf) { cmdbuf.SetViewport(0, viewports); }); + scheduler.Record([this, viewport_list](vk::CommandBuffer cmdbuf) { + const u32 num_viewports = std::min<u32>(device.GetMaxViewports(), Maxwell::NumViewports); + const vk::Span<VkViewport> viewports(viewport_list.data(), num_viewports); + cmdbuf.SetViewport(0, viewports); + }); } void RasterizerVulkan::UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs) { @@ -948,7 +959,7 @@ void RasterizerVulkan::UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs up_scale = Settings::values.resolution_info.up_scale; down_shift = Settings::values.resolution_info.down_shift; } - const std::array scissors{ + const std::array scissor_list{ GetScissorState(regs, 0, up_scale, down_shift), GetScissorState(regs, 1, up_scale, down_shift), GetScissorState(regs, 2, up_scale, down_shift), @@ -966,7 +977,11 @@ void RasterizerVulkan::UpdateScissorsState(Tegra::Engines::Maxwell3D::Regs& regs GetScissorState(regs, 14, up_scale, down_shift), GetScissorState(regs, 15, up_scale, down_shift), }; - scheduler.Record([scissors](vk::CommandBuffer cmdbuf) { cmdbuf.SetScissor(0, scissors); }); + scheduler.Record([this, scissor_list](vk::CommandBuffer cmdbuf) { + const u32 num_scissors = std::min<u32>(device.GetMaxViewports(), Maxwell::NumViewports); + const vk::Span<VkRect2D> scissors(scissor_list.data(), num_scissors); + cmdbuf.SetScissor(0, scissors); + }); } void RasterizerVulkan::UpdateDepthBias(Tegra::Engines::Maxwell3D::Regs& regs) { diff --git a/src/video_core/renderer_vulkan/vk_smaa.cpp b/src/video_core/renderer_vulkan/vk_smaa.cpp index f8735189d..5efd7d66e 100644 --- a/src/video_core/renderer_vulkan/vk_smaa.cpp +++ b/src/video_core/renderer_vulkan/vk_smaa.cpp @@ -25,9 +25,7 @@ namespace { #define ARRAY_TO_SPAN(a) std::span(a, (sizeof(a) / sizeof(a[0]))) -std::pair<vk::Image, MemoryCommit> CreateWrappedImage(const Device& device, - MemoryAllocator& allocator, - VkExtent2D dimensions, VkFormat format) { +vk::Image CreateWrappedImage(MemoryAllocator& allocator, VkExtent2D dimensions, VkFormat format) { const VkImageCreateInfo image_ci{ .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO, .pNext = nullptr, @@ -46,11 +44,7 @@ std::pair<vk::Image, MemoryCommit> CreateWrappedImage(const Device& device, .pQueueFamilyIndices = nullptr, .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED, }; - - auto image = device.GetLogical().CreateImage(image_ci); - auto commit = allocator.Commit(image, Vulkan::MemoryUsage::DeviceLocal); - - return std::make_pair(std::move(image), std::move(commit)); + return allocator.CreateImage(image_ci); } void TransitionImageLayout(vk::CommandBuffer& cmdbuf, VkImage image, VkImageLayout target_layout, @@ -82,7 +76,7 @@ void TransitionImageLayout(vk::CommandBuffer& cmdbuf, VkImage image, VkImageLayo void UploadImage(const Device& device, MemoryAllocator& allocator, Scheduler& scheduler, vk::Image& image, VkExtent2D dimensions, VkFormat format, std::span<const u8> initial_contents = {}) { - auto upload_buffer = device.GetLogical().CreateBuffer(VkBufferCreateInfo{ + const VkBufferCreateInfo upload_ci = { .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .pNext = nullptr, .flags = 0, @@ -91,9 +85,10 @@ void UploadImage(const Device& device, MemoryAllocator& allocator, Scheduler& sc .sharingMode = VK_SHARING_MODE_EXCLUSIVE, .queueFamilyIndexCount = 0, .pQueueFamilyIndices = nullptr, - }); - auto upload_commit = allocator.Commit(upload_buffer, MemoryUsage::Upload); - std::ranges::copy(initial_contents, upload_commit.Map().begin()); + }; + auto upload_buffer = allocator.CreateBuffer(upload_ci, MemoryUsage::Upload); + std::ranges::copy(initial_contents, upload_buffer.Mapped().begin()); + upload_buffer.Flush(); const std::array<VkBufferImageCopy, 1> regions{{{ .bufferOffset = 0, @@ -117,9 +112,6 @@ void UploadImage(const Device& device, MemoryAllocator& allocator, Scheduler& sc VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL); }); scheduler.Finish(); - - // This should go out of scope before the commit - auto upload_buffer2 = std::move(upload_buffer); } vk::ImageView CreateWrappedImageView(const Device& device, vk::Image& image, VkFormat format) { @@ -531,10 +523,8 @@ void SMAA::CreateImages() { static constexpr VkExtent2D area_extent{AREATEX_WIDTH, AREATEX_HEIGHT}; static constexpr VkExtent2D search_extent{SEARCHTEX_WIDTH, SEARCHTEX_HEIGHT}; - std::tie(m_static_images[Area], m_static_buffer_commits[Area]) = - CreateWrappedImage(m_device, m_allocator, area_extent, VK_FORMAT_R8G8_UNORM); - std::tie(m_static_images[Search], m_static_buffer_commits[Search]) = - CreateWrappedImage(m_device, m_allocator, search_extent, VK_FORMAT_R8_UNORM); + m_static_images[Area] = CreateWrappedImage(m_allocator, area_extent, VK_FORMAT_R8G8_UNORM); + m_static_images[Search] = CreateWrappedImage(m_allocator, search_extent, VK_FORMAT_R8_UNORM); m_static_image_views[Area] = CreateWrappedImageView(m_device, m_static_images[Area], VK_FORMAT_R8G8_UNORM); @@ -544,12 +534,11 @@ void SMAA::CreateImages() { for (u32 i = 0; i < m_image_count; i++) { Images& images = m_dynamic_images.emplace_back(); - std::tie(images.images[Blend], images.buffer_commits[Blend]) = - CreateWrappedImage(m_device, m_allocator, m_extent, VK_FORMAT_R16G16B16A16_SFLOAT); - std::tie(images.images[Edges], images.buffer_commits[Edges]) = - CreateWrappedImage(m_device, m_allocator, m_extent, VK_FORMAT_R16G16_SFLOAT); - std::tie(images.images[Output], images.buffer_commits[Output]) = - CreateWrappedImage(m_device, m_allocator, m_extent, VK_FORMAT_R16G16B16A16_SFLOAT); + images.images[Blend] = + CreateWrappedImage(m_allocator, m_extent, VK_FORMAT_R16G16B16A16_SFLOAT); + images.images[Edges] = CreateWrappedImage(m_allocator, m_extent, VK_FORMAT_R16G16_SFLOAT); + images.images[Output] = + CreateWrappedImage(m_allocator, m_extent, VK_FORMAT_R16G16B16A16_SFLOAT); images.image_views[Blend] = CreateWrappedImageView(m_device, images.images[Blend], VK_FORMAT_R16G16B16A16_SFLOAT); diff --git a/src/video_core/renderer_vulkan/vk_smaa.h b/src/video_core/renderer_vulkan/vk_smaa.h index 99a369148..0e214258a 100644 --- a/src/video_core/renderer_vulkan/vk_smaa.h +++ b/src/video_core/renderer_vulkan/vk_smaa.h @@ -66,13 +66,11 @@ private: std::array<vk::Pipeline, MaxSMAAStage> m_pipelines{}; std::array<vk::RenderPass, MaxSMAAStage> m_renderpasses{}; - std::array<MemoryCommit, MaxStaticImage> m_static_buffer_commits; std::array<vk::Image, MaxStaticImage> m_static_images{}; std::array<vk::ImageView, MaxStaticImage> m_static_image_views{}; struct Images { vk::DescriptorSets descriptor_sets{}; - std::array<MemoryCommit, MaxDynamicImage> buffer_commits; std::array<vk::Image, MaxDynamicImage> images{}; std::array<vk::ImageView, MaxDynamicImage> image_views{}; std::array<vk::Framebuffer, MaxSMAAStage> framebuffers{}; diff --git a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp index 74ca77216..ce92f66ab 100644 --- a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp +++ b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.cpp @@ -30,55 +30,6 @@ constexpr VkDeviceSize MAX_STREAM_BUFFER_REQUEST_SIZE = 8_MiB; constexpr VkDeviceSize STREAM_BUFFER_SIZE = 128_MiB; constexpr VkDeviceSize REGION_SIZE = STREAM_BUFFER_SIZE / StagingBufferPool::NUM_SYNCS; -constexpr VkMemoryPropertyFlags HOST_FLAGS = - VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT; -constexpr VkMemoryPropertyFlags STREAM_FLAGS = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT | HOST_FLAGS; - -bool IsStreamHeap(VkMemoryHeap heap) noexcept { - return STREAM_BUFFER_SIZE < (heap.size * 2) / 3; -} - -std::optional<u32> FindMemoryTypeIndex(const VkPhysicalDeviceMemoryProperties& props, u32 type_mask, - VkMemoryPropertyFlags flags) noexcept { - for (u32 type_index = 0; type_index < props.memoryTypeCount; ++type_index) { - if (((type_mask >> type_index) & 1) == 0) { - // Memory type is incompatible - continue; - } - const VkMemoryType& memory_type = props.memoryTypes[type_index]; - if ((memory_type.propertyFlags & flags) != flags) { - // Memory type doesn't have the flags we want - continue; - } - if (!IsStreamHeap(props.memoryHeaps[memory_type.heapIndex])) { - // Memory heap is not suitable for streaming - continue; - } - // Success! - return type_index; - } - return std::nullopt; -} - -u32 FindMemoryTypeIndex(const VkPhysicalDeviceMemoryProperties& props, u32 type_mask, - bool try_device_local) { - std::optional<u32> type; - if (try_device_local) { - // Try to find a DEVICE_LOCAL_BIT type, Nvidia and AMD have a dedicated heap for this - type = FindMemoryTypeIndex(props, type_mask, STREAM_FLAGS); - if (type) { - return *type; - } - } - // Otherwise try without the DEVICE_LOCAL_BIT - type = FindMemoryTypeIndex(props, type_mask, HOST_FLAGS); - if (type) { - return *type; - } - // This should never happen, and in case it does, signal it as an out of memory situation - throw vk::Exception(VK_ERROR_OUT_OF_DEVICE_MEMORY); -} - size_t Region(size_t iterator) noexcept { return iterator / REGION_SIZE; } @@ -87,58 +38,26 @@ size_t Region(size_t iterator) noexcept { StagingBufferPool::StagingBufferPool(const Device& device_, MemoryAllocator& memory_allocator_, Scheduler& scheduler_) : device{device_}, memory_allocator{memory_allocator_}, scheduler{scheduler_} { - const vk::Device& dev = device.GetLogical(); - stream_buffer = dev.CreateBuffer(VkBufferCreateInfo{ + VkBufferCreateInfo stream_ci = { .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .pNext = nullptr, .flags = 0, .size = STREAM_BUFFER_SIZE, .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT | - VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT | - VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT, + VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT, .sharingMode = VK_SHARING_MODE_EXCLUSIVE, .queueFamilyIndexCount = 0, .pQueueFamilyIndices = nullptr, - }); - if (device.HasDebuggingToolAttached()) { - stream_buffer.SetObjectNameEXT("Stream Buffer"); - } - VkMemoryDedicatedRequirements dedicated_reqs{ - .sType = VK_STRUCTURE_TYPE_MEMORY_DEDICATED_REQUIREMENTS, - .pNext = nullptr, - .prefersDedicatedAllocation = VK_FALSE, - .requiresDedicatedAllocation = VK_FALSE, - }; - const auto requirements = dev.GetBufferMemoryRequirements(*stream_buffer, &dedicated_reqs); - const bool make_dedicated = dedicated_reqs.prefersDedicatedAllocation == VK_TRUE || - dedicated_reqs.requiresDedicatedAllocation == VK_TRUE; - const VkMemoryDedicatedAllocateInfo dedicated_info{ - .sType = VK_STRUCTURE_TYPE_MEMORY_DEDICATED_ALLOCATE_INFO, - .pNext = nullptr, - .image = nullptr, - .buffer = *stream_buffer, }; - const auto memory_properties = device.GetPhysical().GetMemoryProperties().memoryProperties; - VkMemoryAllocateInfo stream_memory_info{ - .sType = VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO, - .pNext = make_dedicated ? &dedicated_info : nullptr, - .allocationSize = requirements.size, - .memoryTypeIndex = - FindMemoryTypeIndex(memory_properties, requirements.memoryTypeBits, true), - }; - stream_memory = dev.TryAllocateMemory(stream_memory_info); - if (!stream_memory) { - LOG_INFO(Render_Vulkan, "Dynamic memory allocation failed, trying with system memory"); - stream_memory_info.memoryTypeIndex = - FindMemoryTypeIndex(memory_properties, requirements.memoryTypeBits, false); - stream_memory = dev.AllocateMemory(stream_memory_info); + if (device.IsExtTransformFeedbackSupported()) { + stream_ci.usage |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT; } - + stream_buffer = memory_allocator.CreateBuffer(stream_ci, MemoryUsage::Stream); if (device.HasDebuggingToolAttached()) { - stream_memory.SetObjectNameEXT("Stream Buffer Memory"); + stream_buffer.SetObjectNameEXT("Stream Buffer"); } - stream_buffer.BindMemory(*stream_memory, 0); - stream_pointer = stream_memory.Map(0, STREAM_BUFFER_SIZE); + stream_pointer = stream_buffer.Mapped(); + ASSERT_MSG(!stream_pointer.empty(), "Stream buffer must be host visible!"); } StagingBufferPool::~StagingBufferPool() = default; @@ -199,7 +118,7 @@ StagingBufferRef StagingBufferPool::GetStreamBuffer(size_t size) { return StagingBufferRef{ .buffer = *stream_buffer, .offset = static_cast<VkDeviceSize>(offset), - .mapped_span = std::span<u8>(stream_pointer + offset, size), + .mapped_span = stream_pointer.subspan(offset, size), .usage{}, .log2_level{}, .index{}, @@ -247,29 +166,29 @@ std::optional<StagingBufferRef> StagingBufferPool::TryGetReservedBuffer(size_t s StagingBufferRef StagingBufferPool::CreateStagingBuffer(size_t size, MemoryUsage usage, bool deferred) { const u32 log2 = Common::Log2Ceil64(size); - vk::Buffer buffer = device.GetLogical().CreateBuffer({ + VkBufferCreateInfo buffer_ci = { .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .pNext = nullptr, .flags = 0, .size = 1ULL << log2, .usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT | - VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | - VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT, + VK_BUFFER_USAGE_INDEX_BUFFER_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT, .sharingMode = VK_SHARING_MODE_EXCLUSIVE, .queueFamilyIndexCount = 0, .pQueueFamilyIndices = nullptr, - }); + }; + if (device.IsExtTransformFeedbackSupported()) { + buffer_ci.usage |= VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT; + } + vk::Buffer buffer = memory_allocator.CreateBuffer(buffer_ci, usage); if (device.HasDebuggingToolAttached()) { ++buffer_index; buffer.SetObjectNameEXT(fmt::format("Staging Buffer {}", buffer_index).c_str()); } - MemoryCommit commit = memory_allocator.Commit(buffer, usage); - const std::span<u8> mapped_span = IsHostVisible(usage) ? commit.Map() : std::span<u8>{}; - + const std::span<u8> mapped_span = buffer.Mapped(); StagingBuffer& entry = GetCache(usage)[log2].entries.emplace_back(StagingBuffer{ .buffer = std::move(buffer), - .commit = std::move(commit), .mapped_span = mapped_span, .usage = usage, .log2_level = log2, diff --git a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.h b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.h index 4fd15f11a..5f69f08b1 100644 --- a/src/video_core/renderer_vulkan/vk_staging_buffer_pool.h +++ b/src/video_core/renderer_vulkan/vk_staging_buffer_pool.h @@ -46,7 +46,6 @@ private: struct StagingBuffer { vk::Buffer buffer; - MemoryCommit commit; std::span<u8> mapped_span; MemoryUsage usage; u32 log2_level; @@ -97,8 +96,7 @@ private: Scheduler& scheduler; vk::Buffer stream_buffer; - vk::DeviceMemory stream_memory; - u8* stream_pointer = nullptr; + std::span<u8> stream_pointer; size_t iterator = 0; size_t used_iterator = 0; diff --git a/src/video_core/renderer_vulkan/vk_texture_cache.cpp b/src/video_core/renderer_vulkan/vk_texture_cache.cpp index f025f618b..8385b5509 100644 --- a/src/video_core/renderer_vulkan/vk_texture_cache.cpp +++ b/src/video_core/renderer_vulkan/vk_texture_cache.cpp @@ -15,7 +15,6 @@ #include "video_core/renderer_vulkan/blit_image.h" #include "video_core/renderer_vulkan/maxwell_to_vk.h" #include "video_core/renderer_vulkan/vk_compute_pass.h" -#include "video_core/renderer_vulkan/vk_rasterizer.h" #include "video_core/renderer_vulkan/vk_render_pass_cache.h" #include "video_core/renderer_vulkan/vk_scheduler.h" #include "video_core/renderer_vulkan/vk_staging_buffer_pool.h" @@ -163,11 +162,12 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) { }; } -[[nodiscard]] vk::Image MakeImage(const Device& device, const ImageInfo& info) { +[[nodiscard]] vk::Image MakeImage(const Device& device, const MemoryAllocator& allocator, + const ImageInfo& info) { if (info.type == ImageType::Buffer) { return vk::Image{}; } - return device.GetLogical().CreateImage(MakeImageCreateInfo(device, info)); + return allocator.CreateImage(MakeImageCreateInfo(device, info)); } [[nodiscard]] VkImageAspectFlags ImageAspectMask(PixelFormat format) { @@ -330,9 +330,9 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) { }; } -[[maybe_unused]] [[nodiscard]] std::vector<VkBufferCopy> TransformBufferCopies( - std::span<const VideoCommon::BufferCopy> copies, size_t buffer_offset) { - std::vector<VkBufferCopy> result(copies.size()); +[[maybe_unused]] [[nodiscard]] boost::container::small_vector<VkBufferCopy, 16> +TransformBufferCopies(std::span<const VideoCommon::BufferCopy> copies, size_t buffer_offset) { + boost::container::small_vector<VkBufferCopy, 16> result(copies.size()); std::ranges::transform( copies, result.begin(), [buffer_offset](const VideoCommon::BufferCopy& copy) { return VkBufferCopy{ @@ -344,7 +344,7 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) { return result; } -[[nodiscard]] std::vector<VkBufferImageCopy> TransformBufferImageCopies( +[[nodiscard]] boost::container::small_vector<VkBufferImageCopy, 16> TransformBufferImageCopies( std::span<const BufferImageCopy> copies, size_t buffer_offset, VkImageAspectFlags aspect_mask) { struct Maker { VkBufferImageCopy operator()(const BufferImageCopy& copy) const { @@ -377,14 +377,14 @@ constexpr VkBorderColor ConvertBorderColor(const std::array<float, 4>& color) { VkImageAspectFlags aspect_mask; }; if (aspect_mask == (VK_IMAGE_ASPECT_DEPTH_BIT | VK_IMAGE_ASPECT_STENCIL_BIT)) { - std::vector<VkBufferImageCopy> result(copies.size() * 2); + boost::container::small_vector<VkBufferImageCopy, 16> result(copies.size() * 2); std::ranges::transform(copies, result.begin(), Maker{buffer_offset, VK_IMAGE_ASPECT_DEPTH_BIT}); std::ranges::transform(copies, result.begin() + copies.size(), Maker{buffer_offset, VK_IMAGE_ASPECT_STENCIL_BIT}); return result; } else { - std::vector<VkBufferImageCopy> result(copies.size()); + boost::container::small_vector<VkBufferImageCopy, 16> result(copies.size()); std::ranges::transform(copies, result.begin(), Maker{buffer_offset, aspect_mask}); return result; } @@ -839,14 +839,14 @@ bool TextureCacheRuntime::ShouldReinterpret(Image& dst, Image& src) { VkBuffer TextureCacheRuntime::GetTemporaryBuffer(size_t needed_size) { const auto level = (8 * sizeof(size_t)) - std::countl_zero(needed_size - 1ULL); - if (buffer_commits[level]) { + if (buffers[level]) { return *buffers[level]; } const auto new_size = Common::NextPow2(needed_size); static constexpr VkBufferUsageFlags flags = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_UNIFORM_TEXEL_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_TEXEL_BUFFER_BIT; - buffers[level] = device.GetLogical().CreateBuffer({ + const VkBufferCreateInfo temp_ci = { .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .pNext = nullptr, .flags = 0, @@ -855,9 +855,8 @@ VkBuffer TextureCacheRuntime::GetTemporaryBuffer(size_t needed_size) { .sharingMode = VK_SHARING_MODE_EXCLUSIVE, .queueFamilyIndexCount = 0, .pQueueFamilyIndices = nullptr, - }); - buffer_commits[level] = std::make_unique<MemoryCommit>( - memory_allocator.Commit(buffers[level], MemoryUsage::DeviceLocal)); + }; + buffers[level] = memory_allocator.CreateBuffer(temp_ci, MemoryUsage::DeviceLocal); return *buffers[level]; } @@ -867,8 +866,8 @@ void TextureCacheRuntime::BarrierFeedbackLoop() { void TextureCacheRuntime::ReinterpretImage(Image& dst, Image& src, std::span<const VideoCommon::ImageCopy> copies) { - std::vector<VkBufferImageCopy> vk_in_copies(copies.size()); - std::vector<VkBufferImageCopy> vk_out_copies(copies.size()); + boost::container::small_vector<VkBufferImageCopy, 16> vk_in_copies(copies.size()); + boost::container::small_vector<VkBufferImageCopy, 16> vk_out_copies(copies.size()); const VkImageAspectFlags src_aspect_mask = src.AspectMask(); const VkImageAspectFlags dst_aspect_mask = dst.AspectMask(); @@ -1157,7 +1156,7 @@ void TextureCacheRuntime::ConvertImage(Framebuffer* dst, ImageView& dst_view, Im void TextureCacheRuntime::CopyImage(Image& dst, Image& src, std::span<const VideoCommon::ImageCopy> copies) { - std::vector<VkImageCopy> vk_copies(copies.size()); + boost::container::small_vector<VkImageCopy, 16> vk_copies(copies.size()); const VkImageAspectFlags aspect_mask = dst.AspectMask(); ASSERT(aspect_mask == src.AspectMask()); @@ -1266,8 +1265,8 @@ void TextureCacheRuntime::TickFrame() {} Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu_addr_, VAddr cpu_addr_) : VideoCommon::ImageBase(info_, gpu_addr_, cpu_addr_), scheduler{&runtime_.scheduler}, - runtime{&runtime_}, original_image(MakeImage(runtime_.device, info)), - commit(runtime_.memory_allocator.Commit(original_image, MemoryUsage::DeviceLocal)), + runtime{&runtime_}, + original_image(MakeImage(runtime_.device, runtime_.memory_allocator, info)), aspect_mask(ImageAspectMask(info.format)) { if (IsPixelFormatASTC(info.format) && !runtime->device.IsOptimalAstcSupported()) { if (Settings::values.async_astc.GetValue()) { @@ -1280,6 +1279,10 @@ Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu flags |= VideoCommon::ImageFlagBits::Converted; flags |= VideoCommon::ImageFlagBits::CostlyLoad; } + if (IsPixelFormatBCn(info.format) && !runtime->device.IsOptimalBcnSupported()) { + flags |= VideoCommon::ImageFlagBits::Converted; + flags |= VideoCommon::ImageFlagBits::CostlyLoad; + } if (runtime->device.HasDebuggingToolAttached()) { original_image.SetObjectNameEXT(VideoCommon::Name(*this).c_str()); } @@ -1332,7 +1335,7 @@ void Image::UploadMemory(VkBuffer buffer, VkDeviceSize offset, ScaleDown(true); } scheduler->RequestOutsideRenderPassOperationContext(); - std::vector vk_copies = TransformBufferImageCopies(copies, offset, aspect_mask); + auto vk_copies = TransformBufferImageCopies(copies, offset, aspect_mask); const VkBuffer src_buffer = buffer; const VkImage vk_image = *original_image; const VkImageAspectFlags vk_aspect_mask = aspect_mask; @@ -1367,8 +1370,9 @@ void Image::DownloadMemory(std::span<VkBuffer> buffers_span, std::span<VkDeviceS if (is_rescaled) { ScaleDown(); } - boost::container::small_vector<VkBuffer, 1> buffers_vector{}; - boost::container::small_vector<std::vector<VkBufferImageCopy>, 1> vk_copies; + boost::container::small_vector<VkBuffer, 8> buffers_vector{}; + boost::container::small_vector<boost::container::small_vector<VkBufferImageCopy, 16>, 8> + vk_copies; for (size_t index = 0; index < buffers_span.size(); index++) { buffers_vector.emplace_back(buffers_span[index]); vk_copies.emplace_back( @@ -1467,9 +1471,7 @@ bool Image::ScaleUp(bool ignore) { auto scaled_info = info; scaled_info.size.width = scaled_width; scaled_info.size.height = scaled_height; - scaled_image = MakeImage(runtime->device, scaled_info); - auto& allocator = runtime->memory_allocator; - scaled_commit = MemoryCommit(allocator.Commit(scaled_image, MemoryUsage::DeviceLocal)); + scaled_image = MakeImage(runtime->device, runtime->memory_allocator, scaled_info); ignore = false; } current_image = *scaled_image; @@ -1858,7 +1860,7 @@ Framebuffer::~Framebuffer() = default; void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime, std::span<ImageView*, NUM_RT> color_buffers, ImageView* depth_buffer, bool is_rescaled) { - std::vector<VkImageView> attachments; + boost::container::small_vector<VkImageView, NUM_RT + 1> attachments; RenderPassKey renderpass_key{}; s32 num_layers = 1; diff --git a/src/video_core/renderer_vulkan/vk_texture_cache.h b/src/video_core/renderer_vulkan/vk_texture_cache.h index f14525dcb..220943116 100644 --- a/src/video_core/renderer_vulkan/vk_texture_cache.h +++ b/src/video_core/renderer_vulkan/vk_texture_cache.h @@ -116,7 +116,6 @@ public: static constexpr size_t indexing_slots = 8 * sizeof(size_t); std::array<vk::Buffer, indexing_slots> buffers{}; - std::array<std::unique_ptr<MemoryCommit>, indexing_slots> buffer_commits{}; }; class Image : public VideoCommon::ImageBase { @@ -180,12 +179,10 @@ private: TextureCacheRuntime* runtime{}; vk::Image original_image; - MemoryCommit commit; std::vector<vk::ImageView> storage_image_views; VkImageAspectFlags aspect_mask = 0; bool initialized = false; vk::Image scaled_image{}; - MemoryCommit scaled_commit{}; VkImage current_image{}; std::unique_ptr<Framebuffer> scale_framebuffer; diff --git a/src/video_core/renderer_vulkan/vk_turbo_mode.cpp b/src/video_core/renderer_vulkan/vk_turbo_mode.cpp index a802d3c49..460d8d59d 100644 --- a/src/video_core/renderer_vulkan/vk_turbo_mode.cpp +++ b/src/video_core/renderer_vulkan/vk_turbo_mode.cpp @@ -18,7 +18,7 @@ using namespace Common::Literals; TurboMode::TurboMode(const vk::Instance& instance, const vk::InstanceDispatch& dld) #ifndef ANDROID - : m_device{CreateDevice(instance, dld, VK_NULL_HANDLE)}, m_allocator{m_device, false} + : m_device{CreateDevice(instance, dld, VK_NULL_HANDLE)}, m_allocator{m_device} #endif { { @@ -41,7 +41,7 @@ void TurboMode::Run(std::stop_token stop_token) { auto& dld = m_device.GetLogical(); // Allocate buffer. 2MiB should be sufficient. - auto buffer = dld.CreateBuffer(VkBufferCreateInfo{ + const VkBufferCreateInfo buffer_ci = { .sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO, .pNext = nullptr, .flags = 0, @@ -50,10 +50,8 @@ void TurboMode::Run(std::stop_token stop_token) { .sharingMode = VK_SHARING_MODE_EXCLUSIVE, .queueFamilyIndexCount = 0, .pQueueFamilyIndices = nullptr, - }); - - // Commit some device local memory for the buffer. - auto commit = m_allocator.Commit(buffer, MemoryUsage::DeviceLocal); + }; + vk::Buffer buffer = m_allocator.CreateBuffer(buffer_ci, MemoryUsage::DeviceLocal); // Create the descriptor pool to contain our descriptor. static constexpr VkDescriptorPoolSize pool_size{ |