From 780240e6979b198e7bd10feaad5399b8b4b63762 Mon Sep 17 00:00:00 2001 From: Wollnashorn Date: Wed, 5 Apr 2023 01:29:46 +0200 Subject: shader_recompiler: Add subpixel offset for correct rounding at `ImageGather` On AMD a subpixel offset of 1/512 of the texel size is applied to the texture coordinates at a ImageGather call to ensure the rounding at the texel centers is done the same way as in Maxwell or other Nvidia architectures. See https://www.reedbeta.com/blog/texture-gathers-and-coordinate-precision/ for more details why this might be necessary. This should fix shadow artifacts at object edges in Zelda: Breath of the Wild (#9957, #6956). --- src/video_core/renderer_opengl/gl_device.cpp | 1 + src/video_core/renderer_opengl/gl_device.h | 5 +++++ src/video_core/renderer_opengl/gl_shader_cache.cpp | 1 + 3 files changed, 7 insertions(+) (limited to 'src/video_core/renderer_opengl') diff --git a/src/video_core/renderer_opengl/gl_device.cpp b/src/video_core/renderer_opengl/gl_device.cpp index 22ed16ebf..d36a0a7a1 100644 --- a/src/video_core/renderer_opengl/gl_device.cpp +++ b/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 diff --git a/src/video_core/renderer_opengl/gl_device.h b/src/video_core/renderer_opengl/gl_device.h index 3ff8cad83..e8104c4de 100644 --- a/src/video_core/renderer_opengl/gl_device.h +++ b/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{}; diff --git a/src/video_core/renderer_opengl/gl_shader_cache.cpp b/src/video_core/renderer_opengl/gl_shader_cache.cpp index 479bb8ba3..b40aa6f5e 100644 --- a/src/video_core/renderer_opengl/gl_shader_cache.cpp +++ b/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, -- cgit v1.2.3