[vk, qcom] Memory, Samplers, BindingBuffers and UniformBufferAlignment set by hardware capabilities for QCOM. (#3280)

This PR adjust resources usage of Eden based on driver specification, improving stability and smarter resources usage, extends the amount of TotalPipelineWorkers on Android.

Co-authored-by: Caio Oliveira <caiooliveirafarias0@gmail.com>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/3280
Reviewed-by: Lizzie <lizzie@eden-emu.dev>
Reviewed-by: DraVee <dravee@eden-emu.dev>
Co-authored-by: CamilleLaVey <camillelavey99@gmail.com>
Co-committed-by: CamilleLaVey <camillelavey99@gmail.com>

src/video_core/buffer_cache/buffer_cache.h

@@ -407,6 +407,12 @@ void BufferCache<P>::SetComputeUniformBufferState(u32 mask,
 
 template <class P>
 void BufferCache<P>::UnbindGraphicsStorageBuffers(size_t stage) {
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers()) {
+            channel_state->total_graphics_storage_buffers -=
+                static_cast<u32>(std::popcount(channel_state->enabled_storage_buffers[stage]));
+        }
+    }
     channel_state->enabled_storage_buffers[stage] = 0;
     channel_state->written_storage_buffers[stage] = 0;
 }
@@ -414,8 +420,26 @@ void BufferCache<P>::UnbindGraphicsStorageBuffers(size_t stage) {
 template <class P>
 bool BufferCache<P>::BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index, u32 cbuf_index,
                                                u32 cbuf_offset, bool is_written) {
+    const bool already_enabled =
+        ((channel_state->enabled_storage_buffers[stage] >> ssbo_index) & 1U) != 0;
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers() && !already_enabled) {
+            const u32 max_bindings = runtime.GetMaxDynamicStorageBuffers();
+            if (channel_state->total_graphics_storage_buffers >= max_bindings) {
+                LOG_WARNING(HW_GPU,
+                            "Skipping graphics storage buffer {} due to driver limit {}",
+                            ssbo_index, max_bindings);
+                return false;
+            }
+        }
+    }
     channel_state->enabled_storage_buffers[stage] |= 1U << ssbo_index;
     channel_state->written_storage_buffers[stage] |= (is_written ? 1U : 0U) << ssbo_index;
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers() && !already_enabled) {
+            ++channel_state->total_graphics_storage_buffers;
+        }
+    }
 
     const auto& cbufs = maxwell3d->state.shader_stages[stage];
     const GPUVAddr ssbo_addr = cbufs.const_buffers[cbuf_index].address + cbuf_offset;
@@ -446,6 +470,12 @@ void BufferCache<P>::BindGraphicsTextureBuffer(size_t stage, size_t tbo_index, G
 
 template <class P>
 void BufferCache<P>::UnbindComputeStorageBuffers() {
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers()) {
+            channel_state->total_compute_storage_buffers -=
+                static_cast<u32>(std::popcount(channel_state->enabled_compute_storage_buffers));
+        }
+    }
     channel_state->enabled_compute_storage_buffers = 0;
     channel_state->written_compute_storage_buffers = 0;
     channel_state->image_compute_texture_buffers = 0;
@@ -459,8 +489,26 @@ void BufferCache<P>::BindComputeStorageBuffer(size_t ssbo_index, u32 cbuf_index,
                   ssbo_index);
         return;
     }
+    const bool already_enabled =
+        ((channel_state->enabled_compute_storage_buffers >> ssbo_index) & 1U) != 0;
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers() && !already_enabled) {
+            const u32 max_bindings = runtime.GetMaxDynamicStorageBuffers();
+            if (channel_state->total_compute_storage_buffers >= max_bindings) {
+                LOG_WARNING(HW_GPU,
+                            "Skipping compute storage buffer {} due to driver limit {}",
+                            ssbo_index, max_bindings);
+                return;
+            }
+        }
+    }
     channel_state->enabled_compute_storage_buffers |= 1U << ssbo_index;
     channel_state->written_compute_storage_buffers |= (is_written ? 1U : 0U) << ssbo_index;
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers() && !already_enabled) {
+            ++channel_state->total_compute_storage_buffers;
+        }
+    }
 
     const auto& launch_desc = kepler_compute->launch_description;
     if (((launch_desc.const_buffer_enable_mask >> cbuf_index) & 1) == 0) {
@@ -793,9 +841,23 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
     const u32 size = (std::min)(binding.size, (*channel_state->uniform_buffer_sizes)[stage][index]);
     Buffer& buffer = slot_buffers[binding.buffer_id];
     TouchBuffer(buffer, binding.buffer_id);
-    const bool use_fast_buffer = binding.buffer_id != NULL_BUFFER_ID &&
-                                 size <= channel_state->uniform_buffer_skip_cache_size &&
-                                 !memory_tracker.IsRegionGpuModified(device_addr, size);
+    const bool has_host_buffer = binding.buffer_id != NULL_BUFFER_ID;
+    const u32 offset = has_host_buffer ? buffer.Offset(device_addr) : 0;
+    const bool needs_alignment_stream = [&]() {
+        if constexpr (IS_OPENGL) {
+            return false;
+        } else {
+            if (!has_host_buffer) {
+                return false;
+            }
+            const u32 alignment = runtime.GetUniformBufferAlignment();
+            return alignment > 1 && (offset % alignment) != 0;
+        }
+    }();
+    const bool use_fast_buffer = needs_alignment_stream ||
+                                 (has_host_buffer &&
+                                  size <= channel_state->uniform_buffer_skip_cache_size &&
+                                  !memory_tracker.IsRegionGpuModified(device_addr, size));
     if (use_fast_buffer) {
         if constexpr (IS_OPENGL) {
             if (runtime.HasFastBufferSubData()) {
@@ -834,7 +896,6 @@ void BufferCache<P>::BindHostGraphicsUniformBuffer(size_t stage, u32 index, u32
     if (!needs_bind) {
         return;
     }
-    const u32 offset = buffer.Offset(device_addr);
     if constexpr (IS_OPENGL) {
         // Mark the index as dirty if offset doesn't match
         const bool is_copy_bind = offset != 0 && !runtime.SupportsNonZeroUniformOffset();
@@ -951,9 +1012,30 @@ void BufferCache<P>::BindHostComputeUniformBuffers() {
         TouchBuffer(buffer, binding.buffer_id);
         const u32 size =
             (std::min)(binding.size, (*channel_state->compute_uniform_buffer_sizes)[index]);
+        const bool has_host_buffer = binding.buffer_id != NULL_BUFFER_ID;
+        const u32 offset = has_host_buffer ? buffer.Offset(binding.device_addr) : 0;
+        const bool needs_alignment_stream = [&]() {
+            if constexpr (IS_OPENGL) {
+                return false;
+            } else {
+                if (!has_host_buffer) {
+                    return false;
+                }
+                const u32 alignment = runtime.GetUniformBufferAlignment();
+                return alignment > 1 && (offset % alignment) != 0;
+            }
+        }();
+        if constexpr (!IS_OPENGL) {
+            if (needs_alignment_stream) {
+                const std::span<u8> span =
+                    runtime.BindMappedUniformBuffer(0, binding_index, size);
+                device_memory.ReadBlockUnsafe(binding.device_addr, span.data(), size);
+                return;
+            }
+        }
+
         SynchronizeBuffer(buffer, binding.device_addr, size);
 
-        const u32 offset = buffer.Offset(binding.device_addr);
         buffer.MarkUsage(offset, size);
         if constexpr (NEEDS_BIND_UNIFORM_INDEX) {
             runtime.BindComputeUniformBuffer(binding_index, buffer, offset, size);

src/video_core/buffer_cache/buffer_cache_base.h

@@ -8,6 +8,7 @@
 
 #include <algorithm>
 #include <array>
+#include <bit>
 #include <functional>
 #include <memory>
 #include <mutex>
@@ -132,6 +133,9 @@ public:
     u32 enabled_compute_storage_buffers = 0;
     u32 written_compute_storage_buffers = 0;
 
+    u32 total_graphics_storage_buffers = 0;
+    u32 total_compute_storage_buffers = 0;
+
     std::array<u32, NUM_STAGES> enabled_texture_buffers{};
     std::array<u32, NUM_STAGES> written_texture_buffers{};
     std::array<u32, NUM_STAGES> image_texture_buffers{};

src/video_core/renderer_opengl/gl_buffer_cache.h

@@ -198,6 +198,10 @@ public:
         return device.CanReportMemoryUsage();
     }
 
+    u32 GetUniformBufferAlignment() const {
+        return static_cast<u32>(device.GetUniformBufferAlignment());
+    }
+
     u32 GetStorageBufferAlignment() const {
         return static_cast<u32>(device.GetShaderStorageBufferAlignment());
     }

src/video_core/renderer_vulkan/vk_buffer_cache.cpp

@@ -333,6 +333,13 @@ BufferCacheRuntime::BufferCacheRuntime(const Device& device_, MemoryAllocator& m
       staging_pool{staging_pool_}, guest_descriptor_queue{guest_descriptor_queue_},
       quad_index_pass(device, scheduler, descriptor_pool, staging_pool,
                       compute_pass_descriptor_queue) {
+    const VkDriverIdKHR driver_id = device.GetDriverID();
+    limit_dynamic_storage_buffers = driver_id == VK_DRIVER_ID_QUALCOMM_PROPRIETARY ||
+                                    driver_id == VK_DRIVER_ID_MESA_TURNIP ||
+                                    driver_id == VK_DRIVER_ID_ARM_PROPRIETARY;
+    if (limit_dynamic_storage_buffers) {
+        max_dynamic_storage_buffers = device.GetMaxDescriptorSetStorageBuffersDynamic();
+    }
     if (device.GetDriverID() != VK_DRIVER_ID_QUALCOMM_PROPRIETARY) {
         // TODO: FixMe: Uint8Pass compute shader does not build on some Qualcomm drivers.
         uint8_pass = std::make_unique<Uint8Pass>(device, scheduler, descriptor_pool, staging_pool,
@@ -368,6 +375,10 @@ bool BufferCacheRuntime::CanReportMemoryUsage() const {
     return device.CanReportMemoryUsage();
 }
 
+u32 BufferCacheRuntime::GetUniformBufferAlignment() const {
+    return static_cast<u32>(device.GetUniformBufferAlignment());
+}
+
 u32 BufferCacheRuntime::GetStorageBufferAlignment() const {
     return static_cast<u32>(device.GetStorageBufferAlignment());
 }

src/video_core/renderer_vulkan/vk_buffer_cache.h

@@ -6,6 +6,8 @@
 
 #pragma once
 
+#include <limits>
+
 #include "video_core/buffer_cache/buffer_cache_base.h"
 #include "video_core/buffer_cache/memory_tracker_base.h"
 #include "video_core/buffer_cache/usage_tracker.h"
@@ -94,6 +96,8 @@ public:
 
     bool CanReportMemoryUsage() const;
 
+    u32 GetUniformBufferAlignment() const;
+
     u32 GetStorageBufferAlignment() const;
 
     [[nodiscard]] StagingBufferRef UploadStagingBuffer(size_t size);
@@ -149,6 +153,14 @@ public:
         guest_descriptor_queue.AddTexelBuffer(buffer.View(offset, size, format));
     }
 
+    bool ShouldLimitDynamicStorageBuffers() const {
+        return limit_dynamic_storage_buffers;
+    }
+
+    u32 GetMaxDynamicStorageBuffers() const {
+        return max_dynamic_storage_buffers;
+    }
+
 private:
     void BindBuffer(VkBuffer buffer, u32 offset, u32 size) {
         guest_descriptor_queue.AddBuffer(buffer, offset, size);
@@ -170,6 +182,9 @@ private:
 
     std::unique_ptr<Uint8Pass> uint8_pass;
     QuadIndexedPass quad_index_pass;
+
+    bool limit_dynamic_storage_buffers = false;
+    u32 max_dynamic_storage_buffers = std::numeric_limits<u32>::max();
 };
 
 struct BufferCacheParams {

src/video_core/renderer_vulkan/vk_pipeline_cache.cpp

@@ -278,8 +278,9 @@ size_t GetTotalPipelineWorkers() {
     const size_t max_core_threads =
         std::max<size_t>(static_cast<size_t>(std::thread::hardware_concurrency()), 2ULL) - 1ULL;
 #ifdef ANDROID
-    // Leave at least a few cores free in android
-    constexpr size_t free_cores = 3ULL;
+    // Leave at least one core free on Android. Previously we reserved two, but
+    // shipping builds benefit from one extra compilation worker.
+    constexpr size_t free_cores = 1ULL;
     if (max_core_threads <= free_cores) {
         return 1ULL;
     }
@@ -797,6 +798,19 @@ std::unique_ptr<ComputePipeline> PipelineCache::CreateComputePipeline(
     }
 
     auto program{TranslateProgram(pools.inst, pools.block, env, cfg, host_info)};
+    const VkDriverIdKHR driver_id = device.GetDriverID();
+    const bool needs_shared_mem_clamp =
+        driver_id == VK_DRIVER_ID_QUALCOMM_PROPRIETARY ||
+        driver_id == VK_DRIVER_ID_ARM_PROPRIETARY;
+    const u32 max_shared_memory = device.GetMaxComputeSharedMemorySize();
+    if (needs_shared_mem_clamp && program.shared_memory_size > max_shared_memory) {
+        LOG_WARNING(Render_Vulkan,
+                    "Compute shader 0x{:016x} requests {}KB shared memory but device max is {}KB - clamping",
+                    key.unique_hash,
+                    program.shared_memory_size / 1024,
+                    max_shared_memory / 1024);
+        program.shared_memory_size = max_shared_memory;
+    }
     const std::vector<u32> code{EmitSPIRV(profile, program, this->optimize_spirv_output)};
     device.SaveShader(code);
     vk::ShaderModule spv_module{BuildShader(device, code)};

src/video_core/renderer_vulkan/vk_texture_cache.cpp

@@ -1527,6 +1527,10 @@ bool TextureCacheRuntime::CanReportMemoryUsage() const {
     return device.CanReportMemoryUsage();
 }
 
+std::optional<size_t> TextureCacheRuntime::GetSamplerHeapBudget() const {
+    return device.GetSamplerHeapBudget();
+}
+
 void TextureCacheRuntime::TickFrame() {}
 
 Image::Image(TextureCacheRuntime& runtime_, const ImageInfo& info_, GPUVAddr gpu_addr_,

src/video_core/renderer_vulkan/vk_texture_cache.h

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2019 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
@@ -62,6 +65,8 @@ public:
 
     bool CanReportMemoryUsage() const;
 
+    std::optional<size_t> GetSamplerHeapBudget() const;
+
     void BlitImage(Framebuffer* dst_framebuffer, ImageView& dst, ImageView& src,
                    const Region2D& dst_region, const Region2D& src_region,
                    Tegra::Engines::Fermi2D::Filter filter,

src/video_core/texture_cache/texture_cache.h

@@ -6,6 +6,8 @@
 
 #pragma once
 
+#include <limits>
+#include <optional>
 #include <unordered_set>
 #include <boost/container/small_vector.hpp>
 
@@ -1736,11 +1738,89 @@ SamplerId TextureCache<P>::FindSampler(const TSCEntry& config) {
     }
     const auto [pair, is_new] = channel_state->samplers.try_emplace(config);
     if (is_new) {
+        EnforceSamplerBudget();
         pair->second = slot_samplers.insert(runtime, config);
     }
     return pair->second;
 }
 
+template <class P>
+std::optional<size_t> TextureCache<P>::QuerySamplerBudget() const {
+    if constexpr (requires { runtime.GetSamplerHeapBudget(); }) {
+        return runtime.GetSamplerHeapBudget();
+    } else {
+        return std::nullopt;
+    }
+}
+
+template <class P>
+void TextureCache<P>::EnforceSamplerBudget() {
+    const auto budget = QuerySamplerBudget();
+    if (!budget) {
+        return;
+    }
+    if (slot_samplers.size() < *budget) {
+        return;
+    }
+    if (!channel_state) {
+        return;
+    }
+    if (last_sampler_gc_frame == frame_tick) {
+        return;
+    }
+    last_sampler_gc_frame = frame_tick;
+    TrimInactiveSamplers(*budget);
+}
+
+template <class P>
+void TextureCache<P>::TrimInactiveSamplers(size_t budget) {
+    if (channel_state->samplers.empty()) {
+        return;
+    }
+    static constexpr size_t SAMPLER_GC_SLACK = 1024;
+    auto mark_active = [](auto& set, SamplerId id) {
+        if (!id || id == CORRUPT_ID || id == NULL_SAMPLER_ID) {
+            return;
+        }
+        set.insert(id);
+    };
+    std::unordered_set<SamplerId> active;
+    active.reserve(channel_state->graphics_sampler_ids.size() +
+                   channel_state->compute_sampler_ids.size());
+    for (const SamplerId id : channel_state->graphics_sampler_ids) {
+        mark_active(active, id);
+    }
+    for (const SamplerId id : channel_state->compute_sampler_ids) {
+        mark_active(active, id);
+    }
+
+    size_t removed = 0;
+    auto& sampler_map = channel_state->samplers;
+    for (auto it = sampler_map.begin(); it != sampler_map.end();) {
+        const SamplerId sampler_id = it->second;
+        if (!sampler_id || sampler_id == CORRUPT_ID) {
+            it = sampler_map.erase(it);
+            continue;
+        }
+        if (active.find(sampler_id) != active.end()) {
+            ++it;
+            continue;
+        }
+        slot_samplers.erase(sampler_id);
+        it = sampler_map.erase(it);
+        ++removed;
+        if (slot_samplers.size() + SAMPLER_GC_SLACK <= budget) {
+            break;
+        }
+    }
+
+    if (removed != 0) {
+        LOG_WARNING(HW_GPU,
+                    "Sampler cache exceeded {} entries on this driver; reclaimed {} inactive samplers",
+                    budget, removed);
+    }
+}
+
 template <class P>
 ImageViewId TextureCache<P>::FindColorBuffer(size_t index) {
     const auto& regs = maxwell3d->regs;

src/video_core/texture_cache/texture_cache_base.h

@@ -429,6 +429,9 @@ private:
 
     void QueueAsyncDecode(Image& image, ImageId image_id);
     void TickAsyncDecode();
+    void EnforceSamplerBudget();
+    void TrimInactiveSamplers(size_t budget);
+    std::optional<size_t> QuerySamplerBudget() const;
 
     Runtime& runtime;
 
@@ -500,6 +503,7 @@ private:
 
     u64 modification_tick = 0;
     u64 frame_tick = 0;
+    u64 last_sampler_gc_frame = (std::numeric_limits<u64>::max)();
 
     Common::ThreadWorker texture_decode_worker{1, "TextureDecoder"};
     std::vector<std::unique_ptr<AsyncDecodeContext>> async_decodes;

src/video_core/vulkan_common/vulkan_device.cpp

@@ -605,6 +605,18 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
         if (version < VK_MAKE_API_VERSION(0, 255, 615, 512)) {
             has_broken_parallel_compiling = true;
         }
+        const size_t sampler_limit = properties.properties.limits.maxSamplerAllocationCount;
+        if (sampler_limit > 0) {
+            constexpr size_t MIN_SAMPLER_BUDGET = 1024U;
+            const size_t reserved = sampler_limit / 4U;
+            const size_t derived_budget =
+                (std::max)(MIN_SAMPLER_BUDGET, sampler_limit - reserved);
+            sampler_heap_budget = derived_budget;
+            LOG_WARNING(Render_Vulkan,
+                        "Qualcomm driver reports max {} samplers; reserving {} (25%) and "
+                        "allowing Eden to use {} (75%) to avoid heap exhaustion",
+                        sampler_limit, reserved, sampler_heap_budget);
+        }
     }
 
     if (extensions.sampler_filter_minmax && is_amd) {
@@ -1529,6 +1541,13 @@ void Device::SetupFamilies(VkSurfaceKHR surface) {
     }
 }
 
+std::optional<size_t> Device::GetSamplerHeapBudget() const {
+    if (sampler_heap_budget == 0) {
+        return std::nullopt;
+    }
+    return sampler_heap_budget;
+}
+
 u64 Device::GetDeviceMemoryUsage() const {
     VkPhysicalDeviceMemoryBudgetPropertiesEXT budget;
     budget.sType = VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_MEMORY_BUDGET_PROPERTIES_EXT;

src/video_core/vulkan_common/vulkan_device.h

@@ -6,6 +6,7 @@
 
 #pragma once
 
+#include <optional>
 #include <set>
 #include <span>
 #include <string>
@@ -326,6 +327,16 @@ public:
         return properties.properties.limits.maxComputeSharedMemorySize;
     }
 
+    /// Returns the maximum number of dynamic storage buffer descriptors per set.
+    u32 GetMaxDescriptorSetStorageBuffersDynamic() const {
+        return properties.properties.limits.maxDescriptorSetStorageBuffersDynamic;
+    }
+
+    /// Returns the maximum number of dynamic uniform buffer descriptors per set.
+    u32 GetMaxDescriptorSetUniformBuffersDynamic() const {
+        return properties.properties.limits.maxDescriptorSetUniformBuffersDynamic;
+    }
+
     /// Returns float control properties of the device.
     const VkPhysicalDeviceFloatControlsPropertiesKHR& FloatControlProperties() const {
         return properties.float_controls;
@@ -744,6 +755,8 @@ public:
         return has_broken_parallel_compiling;
     }
 
+    std::optional<size_t> GetSamplerHeapBudget() const;
+
     /// Returns the vendor name reported from Vulkan.
     std::string_view GetVendorName() const {
         return properties.driver.driverName;
@@ -1040,6 +1053,7 @@ private:
     bool dynamic_state3_alpha_to_coverage{};
     bool dynamic_state3_alpha_to_one{};
     bool supports_conditional_barriers{};      ///< Allows barriers in conditional control flow.
+    size_t sampler_heap_budget{};              ///< Sampler budget for buggy drivers (0 = unlimited).
     u64 device_access_memory{};                ///< Total size of device local memory in bytes.
     u32 sets_per_pool{};                       ///< Sets per Description Pool
     NvidiaArchitecture nvidia_arch{NvidiaArchitecture::Arch_AmpereOrNewer};