Fixed Civilization VII - added TIR mixed samples support

src/video_core/renderer_vulkan/fixed_pipeline_state.cpp

@@ -129,7 +129,13 @@ void FixedPipelineState::Refresh(Tegra::Engines::Maxwell3D& maxwell3d, DynamicFe
     topology.Assign(can_collapse_topology_class
                         ? TOPOLOGY_CLASS_REPRESENTATIVE_LUT[static_cast<size_t>(topology_)]
                         : topology_);
-    msaa_mode.Assign(regs.anti_alias_samples_mode);
+    // Target-independent rasterization rasterizes (and depth tests) at the raster sample count
+    if (regs.tir_mode == Maxwell::TIRMode::RasterNTargetM &&
+        regs.anti_alias_raster != Maxwell::AntiAliasRaster::Mode1x1) {
+        msaa_mode.Assign(static_cast<Tegra::Texture::MsaaMode>(regs.anti_alias_raster));
+    } else {
+        msaa_mode.Assign(regs.anti_alias_samples_mode);
+    }
     attachment0_dual_source_blend.Assign(ComputeAttachment0DualSourceBlend(regs) ? 1 : 0);
 
     raw2 = 0;

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -1089,6 +1089,58 @@ VkImageView TextureCacheRuntime::GetOrCreateResolveShadow(VkImage msaa_image, Vk
     return *shadow.view;
 }
 
+VkImageView TextureCacheRuntime::GetOrCreateTirColorScratch(VkImage color_image, VkFormat format,
+                                                            VkExtent2D extent, u32 layers,
+                                                            VkSampleCountFlagBits samples) {
+    TirColorScratch& scratch = tir_color_scratch[color_image];
+    if (scratch.image && scratch.format == format && scratch.extent.width == extent.width &&
+        scratch.extent.height == extent.height && scratch.layers == layers &&
+        scratch.samples == samples) {
+        return *scratch.view;
+    }
+    if (scratch.image) {
+        scheduler.Finish();
+    }
+    scratch.image = memory_allocator.CreateImage(VkImageCreateInfo{
+        .sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO,
+        .pNext = nullptr,
+        .flags = 0,
+        .imageType = VK_IMAGE_TYPE_2D,
+        .format = format,
+        .extent = {extent.width, extent.height, 1},
+        .mipLevels = 1,
+        .arrayLayers = layers,
+        .samples = samples,
+        .tiling = VK_IMAGE_TILING_OPTIMAL,
+        .usage = VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT | VK_IMAGE_USAGE_TRANSFER_SRC_BIT,
+        .sharingMode = VK_SHARING_MODE_EXCLUSIVE,
+        .queueFamilyIndexCount = 0,
+        .pQueueFamilyIndices = nullptr,
+        .initialLayout = VK_IMAGE_LAYOUT_UNDEFINED,
+    });
+    scratch.view = device.GetLogical().CreateImageView(VkImageViewCreateInfo{
+        .sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO,
+        .pNext = nullptr,
+        .flags = 0,
+        .image = *scratch.image,
+        .viewType = layers > 1 ? VK_IMAGE_VIEW_TYPE_2D_ARRAY : VK_IMAGE_VIEW_TYPE_2D,
+        .format = format,
+        .components{},
+        .subresourceRange{
+            .aspectMask = VK_IMAGE_ASPECT_COLOR_BIT,
+            .baseMipLevel = 0,
+            .levelCount = 1,
+            .baseArrayLayer = 0,
+            .layerCount = layers,
+        },
+    });
+    scratch.format = format;
+    scratch.extent = extent;
+    scratch.layers = layers;
+    scratch.samples = samples;
+    return *scratch.view;
+}
+
 const TextureCacheRuntime::ResolveShadow* TextureCacheRuntime::GetValidResolveShadow(
     VkImage msaa_image) const {
     const auto it = resolve_shadows.find(msaa_image);
@@ -2970,6 +3022,26 @@ Framebuffer::Framebuffer(TextureCacheRuntime& runtime, ImageView* color_buffer,
 
 Framebuffer::~Framebuffer() = default;
 
+/// Single-sampled color targets with a multisampled depth buffer, as used by target-independent
+/// rasterization. Vulkan requires matching sample counts for these attachments.
+static bool IsMixedSamplesTarget(std::span<ImageView*, NUM_RT> color_buffers,
+                                 const ImageView* depth_buffer) {
+    if (depth_buffer == nullptr || depth_buffer->Samples() == VK_SAMPLE_COUNT_1_BIT) {
+        return false;
+    }
+    bool has_color = false;
+    for (const ImageView* const color_buffer : color_buffers) {
+        if (color_buffer == nullptr) {
+            continue;
+        }
+        if (color_buffer->Samples() != VK_SAMPLE_COUNT_1_BIT) {
+            return false;
+        }
+        has_color = true;
+    }
+    return has_color;
+}
+
 void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
                                     std::span<ImageView*, NUM_RT> color_buffers,
                                     ImageView* depth_buffer, bool is_rescaled_) {
@@ -3024,6 +3096,13 @@ void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
     } else {
         renderpass_key.depth_format = PixelFormat::Invalid;
     }
+    if (IsMixedSamplesTarget(color_buffers, depth_buffer)) {
+        const VkExtent2D extent{(std::min)(render_area.width, width),
+                                (std::min)(render_area.height, height)};
+        CreateMixedSamplesFramebuffer(runtime, color_buffers, attachments, renderpass_key,
+                                      static_cast<u32>((std::max)(num_layers, 1)), extent);
+        return;
+    }
     renderpass_key.samples = samples;
     const bool do_resolve_color = ENABLE_MSAA_TILER_RESOLVE &&
         samples != VK_SAMPLE_COUNT_1_BIT && num_colors > 0 && runtime.device.IsTiler();
@@ -3040,10 +3119,7 @@ void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
     discard_msaa_depth_stencil = ENABLE_MSAA_RESOLVE_CONSUME &&
                                  ENABLE_MSAA_DEPTH_STENCIL_DISCARD && do_resolve_depth_stencil;
 
-    renderpass = runtime.render_pass_cache.Get(renderpass_key);
-    render_pass_key = renderpass_key;
-    render_pass_cache = &runtime.render_pass_cache;
-    runtime_ptr = &runtime;
+    UseRenderPass(runtime, renderpass_key);
     render_area.width = (std::min)(render_area.width, width);
     render_area.height = (std::min)(render_area.height, height);
 
@@ -3075,6 +3151,53 @@ void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
     }
 
     num_color_buffers = static_cast<u32>(num_colors);
+    CreateVkFramebuffer(runtime, attachments, static_cast<u32>((std::max)(num_layers, 1)));
+}
+
+void Framebuffer::CreateMixedSamplesFramebuffer(TextureCacheRuntime& runtime,
+                                                std::span<ImageView*, NUM_RT> color_buffers,
+                                                std::span<const VkImageView> attachments,
+                                                RenderPassKey renderpass_key, u32 layers,
+                                                VkExtent2D extent) {
+    // attachments holds the real color targets followed by the depth buffer
+    const size_t num_colors = attachments.size() - 1;
+    boost::container::small_vector<VkImageView, NUM_RT * 2 + 2> mixed_attachments;
+    for (const ImageView* const color_buffer : color_buffers) {
+        if (!color_buffer) {
+            continue;
+        }
+        const VkFormat vk_format = MaxwellToVK::SurfaceFormat(runtime.device, FormatType::Optimal,
+                                                              true, color_buffer->format)
+                                       .format;
+        mixed_attachments.push_back(runtime.GetOrCreateTirColorScratch(
+            color_buffer->ImageHandle(), vk_format, extent, layers, samples));
+    }
+    mixed_attachments.push_back(attachments[num_colors]);
+    for (size_t index = 0; index < num_colors; ++index) {
+        mixed_attachments.push_back(attachments[index]);
+    }
+    // Multisampled scratch color + depth, resolving color into the real single-sampled targets
+    renderpass_key.samples = samples;
+    renderpass_key.resolve_color = true;
+    renderpass_key.resolve_depth_stencil = false;
+    discard_msaa_color = false;
+    discard_msaa_depth_stencil = false;
+    UseRenderPass(runtime, renderpass_key);
+    render_area = extent;
+    num_color_buffers = static_cast<u32>(num_colors);
+    CreateVkFramebuffer(runtime, mixed_attachments, layers);
+}
+
+void Framebuffer::UseRenderPass(TextureCacheRuntime& runtime,
+                                const RenderPassKey& renderpass_key) {
+    renderpass = runtime.render_pass_cache.Get(renderpass_key);
+    render_pass_key = renderpass_key;
+    render_pass_cache = &runtime.render_pass_cache;
+    runtime_ptr = &runtime;
+}
+
+void Framebuffer::CreateVkFramebuffer(TextureCacheRuntime& runtime,
+                                      std::span<const VkImageView> attachments, u32 layers) {
     framebuffer = runtime.device.GetLogical().CreateFramebuffer({
         .sType = VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO,
         .pNext = nullptr,
@@ -3084,7 +3207,7 @@ void Framebuffer::CreateFramebuffer(TextureCacheRuntime& runtime,
         .pAttachments = attachments.data(),
         .width = render_area.width,
         .height = render_area.height,
-        .layers = static_cast<u32>((std::max)(num_layers, 1)),
+        .layers = layers,
     });
 }
 

src/video_core/renderer_vulkan/vk_texture_cache.h

@@ -133,6 +133,11 @@ public:
 
     [[nodiscard]] const ResolveShadow* GetValidResolveShadow(VkImage msaa_image) const;
 
+    /// Multisampled stand-in for a single-sampled color target rendered with a TIR depth buffer
+    [[nodiscard]] VkImageView GetOrCreateTirColorScratch(VkImage color_image, VkFormat format,
+                                                         VkExtent2D extent, u32 layers,
+                                                         VkSampleCountFlagBits samples);
+
     void InvalidateResolveShadow(VkImage msaa_image);
 
     void MarkResolveShadowUpToDate(VkImage msaa_image);
@@ -187,6 +192,15 @@ public:
 
     std::vector<MsaaScratchImage> msaa_scratch_images;
     ::Common::unordered_map<VkImage, ResolveShadow> resolve_shadows;
+    struct TirColorScratch {
+        vk::Image image;
+        vk::ImageView view;
+        VkFormat format = VK_FORMAT_UNDEFINED;
+        VkExtent2D extent{};
+        u32 layers = 0;
+        VkSampleCountFlagBits samples = VK_SAMPLE_COUNT_1_BIT;
+    };
+    ::Common::unordered_map<VkImage, TirColorScratch> tir_color_scratch;
     std::vector<std::pair<u64, ResolveShadow>> pending_resolve_shadows;
 };
 
@@ -279,6 +293,22 @@ public:
     void MarkResolveShadowsUpToDate() const;
 
 private:
+    /// Builds a framebuffer for single-sampled color targets drawn with a multisampled depth
+    /// buffer (target-independent rasterization). Color is rendered into multisampled scratch
+    /// images that resolve into the real targets at the end of the pass.
+    void CreateMixedSamplesFramebuffer(TextureCacheRuntime& runtime,
+                                       std::span<ImageView*, NUM_RT> color_buffers,
+                                       std::span<const VkImageView> attachments,
+                                       RenderPassKey renderpass_key, u32 layers,
+                                       VkExtent2D extent);
+
+    /// Fetches the render pass for the key from the cache and remembers it for variants.
+    void UseRenderPass(TextureCacheRuntime& runtime, const RenderPassKey& renderpass_key);
+
+    /// Creates the Vulkan framebuffer for the current render pass and render area.
+    void CreateVkFramebuffer(TextureCacheRuntime& runtime,
+                             std::span<const VkImageView> attachments, u32 layers);
+
     static constexpr size_t NUM_MEMOIZED_RENDER_PASS_VARIANTS = 8;
 
     vk::Framebuffer framebuffer;

src/video_core/texture_cache/texture_cache.h

@@ -1928,7 +1928,26 @@ ImageViewId TextureCache<P>::FindDepthBuffer() {
     if (gpu_addr == 0) {
         return ImageViewId{};
     }
-    const ImageInfo info(regs.zeta, regs.zeta_size, regs.anti_alias_samples_mode);
+    // Target-independent rasterization: the depth buffer keeps the raster sample count while
+    // the color targets use anti_alias_samples_mode.
+    Tegra::Texture::MsaaMode zeta_msaa_mode = regs.anti_alias_samples_mode;
+    if (regs.anti_alias_raster != Tegra::Engines::Maxwell3D::Regs::AntiAliasRaster::Mode1x1) {
+        const auto raster_mode = static_cast<Tegra::Texture::MsaaMode>(regs.anti_alias_raster);
+        bool use_raster = regs.tir_mode == Tegra::Engines::Maxwell3D::Regs::TIRMode::RasterNTargetM;
+        if (!use_raster && regs.anti_alias_samples_mode == Tegra::Texture::MsaaMode::Msaa1x1) {
+            // Clears can be issued before tir_mode is enabled. Only a depth buffer sized for the
+            // raster samples relative to the color target is treated as multisampled, otherwise
+            // it ping-pongs between a 1x and a multisampled image every frame.
+            const auto& rt0 = regs.rt[0];
+            use_raster = rt0.Address() != 0 && rt0.format != Tegra::RenderTargetFormat::NONE &&
+                         regs.zeta_size.width == rt0.width * NumSamplesX(raster_mode) &&
+                         regs.zeta_size.height == rt0.height * NumSamplesY(raster_mode);
+        }
+        if (use_raster) {
+            zeta_msaa_mode = raster_mode;
+        }
+    }
+    const ImageInfo info(regs.zeta, regs.zeta_size, zeta_msaa_mode);
     return FindRenderTargetView(info, gpu_addr);
 }