early-access version 3500

src/video_core/renderer_opengl/gl_device.cpp

@@ -169,6 +169,7 @@ Device::Device(Core::Frontend::EmuWindow& emu_window) {
     has_draw_texture = GLAD_GL_NV_draw_texture;
     warp_size_potentially_larger_than_guest = !is_nvidia && !is_intel;
     need_fastmath_off = is_nvidia;
+    need_gather_subpixel_offset = is_amd;
     can_report_memory = GLAD_GL_NVX_gpu_memory_info;
 
     // At the moment of writing this, only Nvidia's driver optimizes BufferSubData on exclusive

src/video_core/renderer_opengl/gl_device.h

@@ -160,6 +160,10 @@ public:
         return need_fastmath_off;
     }
 
+    bool NeedsGatherSubpixelOffset() const {
+        return need_gather_subpixel_offset;
+    }
+
     bool HasCbufFtouBug() const {
         return has_cbuf_ftou_bug;
     }
@@ -225,6 +229,7 @@ private:
     bool has_draw_texture{};
     bool warp_size_potentially_larger_than_guest{};
     bool need_fastmath_off{};
+    bool need_gather_subpixel_offset{};
     bool has_cbuf_ftou_bug{};
     bool has_bool_ref_bug{};
     bool can_report_memory{};

src/video_core/renderer_opengl/gl_shader_cache.cpp

@@ -218,6 +218,7 @@ ShaderCache::ShaderCache(RasterizerOpenGL& rasterizer_, Core::Frontend::EmuWindo
           .lower_left_origin_mode = true,
           .need_declared_frag_colors = true,
           .need_fastmath_off = device.NeedsFastmathOff(),
+          .need_gather_subpixel_offset = device.NeedsGatherSubpixelOffset(),
 
           .has_broken_spirv_clamp = true,
           .has_broken_unsigned_image_offsets = true,

src/video_core/renderer_vulkan/vk_pipeline_cache.cpp

@@ -329,6 +329,7 @@ PipelineCache::PipelineCache(RasterizerVulkan& rasterizer_, const Device& device
 
         .lower_left_origin_mode = false,
         .need_declared_frag_colors = false,
+        .need_gather_subpixel_offset = device.NeedsGatherSubpixelOffset(),
 
         .has_broken_spirv_clamp = driver_id == VK_DRIVER_ID_INTEL_PROPRIETARY_WINDOWS,
         .has_broken_spirv_position_input = driver_id == VK_DRIVER_ID_QUALCOMM_PROPRIETARY,

src/video_core/vulkan_common/vulkan_device.cpp

@@ -431,6 +431,7 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
                         "AMD GCN4 and earlier have broken VK_IMAGE_CREATE_CUBE_COMPATIBLE_BIT");
             has_broken_cube_compatibility = true;
         }
+        need_gather_subpixel_offset = true;
     }
     if (extensions.sampler_filter_minmax && is_amd) {
         // Disable ext_sampler_filter_minmax on AMD GCN4 and lower as it is broken.

src/video_core/vulkan_common/vulkan_device.h

@@ -554,6 +554,10 @@ public:
         return features.robustness2.nullDescriptor;
     }
 
+    bool NeedsGatherSubpixelOffset() const {
+        return need_gather_subpixel_offset;
+    }
+
     u32 GetMaxVertexInputAttributes() const {
         return properties.properties.limits.maxVertexInputAttributes;
     }
@@ -664,6 +668,7 @@ private:
     bool must_emulate_bgr565{};             ///< Emulates BGR565 by swizzling RGB565 format.
     bool dynamic_state3_blending{};         ///< Has all blending features of dynamic_state3.
     bool dynamic_state3_enables{};          ///< Has all enables features of dynamic_state3.
+    bool need_gather_subpixel_offset{};     ///< Needs offset at ImageGather for correct rounding.
     u64 device_access_memory{};             ///< Total size of device local memory in bytes.
     u32 sets_per_pool{};                    ///< Sets per Description Pool