[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/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,