diff --git a/src/video_core/renderer_opengl/gl_device.cpp b/src/video_core/renderer_opengl/gl_device.cpp index c65b24c695..b30d5be749 100644 --- a/src/video_core/renderer_opengl/gl_device.cpp +++ b/src/video_core/renderer_opengl/gl_device.cpp @@ -62,6 +62,7 @@ Device::Device() { max_varyings = GetInteger(GL_MAX_VARYING_VECTORS); has_warp_intrinsics = GLAD_GL_NV_gpu_shader5 && GLAD_GL_NV_shader_thread_group && GLAD_GL_NV_shader_thread_shuffle; + has_shader_ballot = GLAD_GL_ARB_shader_ballot; has_vertex_viewport_layer = GLAD_GL_ARB_shader_viewport_layer_array; has_image_load_formatted = HasExtension(extensions, "GL_EXT_shader_image_load_formatted"); has_variable_aoffi = TestVariableAoffi(); @@ -79,6 +80,7 @@ Device::Device(std::nullptr_t) { max_vertex_attributes = 16; max_varyings = 15; has_warp_intrinsics = true; + has_shader_ballot = true; has_vertex_viewport_layer = true; has_image_load_formatted = true; has_variable_aoffi = true; diff --git a/src/video_core/renderer_opengl/gl_device.h b/src/video_core/renderer_opengl/gl_device.h index bf35bd0b65..6c86fe207c 100644 --- a/src/video_core/renderer_opengl/gl_device.h +++ b/src/video_core/renderer_opengl/gl_device.h @@ -34,6 +34,10 @@ public: return has_warp_intrinsics; } + bool HasShaderBallot() const { + return has_shader_ballot; + } + bool HasVertexViewportLayer() const { return has_vertex_viewport_layer; } @@ -68,6 +72,7 @@ private: u32 max_vertex_attributes{}; u32 max_varyings{}; bool has_warp_intrinsics{}; + bool has_shader_ballot{}; bool has_vertex_viewport_layer{}; bool has_image_load_formatted{}; bool has_variable_aoffi{}; diff --git a/src/video_core/renderer_opengl/gl_shader_decompiler.cpp b/src/video_core/renderer_opengl/gl_shader_decompiler.cpp index 21c137ec5c..5d2c38a5e6 100644 --- a/src/video_core/renderer_opengl/gl_shader_decompiler.cpp +++ b/src/video_core/renderer_opengl/gl_shader_decompiler.cpp @@ -1382,13 +1382,19 @@ private: Expression FSwizzleAdd(Operation operation) { const std::string op_a = VisitOperand(operation, 0).AsFloat(); const std::string op_b = VisitOperand(operation, 1).AsFloat(); + + if (!device.HasShaderBallot()) { + LOG_ERROR(Render_OpenGL, "Shader ballot is unavailable but required by the shader"); + return {fmt::format("{} + {}", op_a, op_b), Type::Float}; + } + const std::string instr_mask = VisitOperand(operation, 2).AsUint(); - const std::string mask = code.GenerateTemporary(); - code.AddLine("uint {} = {} >> ((gl_SubGroupInvocationARB & 3) << 1);", mask, instr_mask); + code.AddLine("uint {} = ({} >> ((gl_SubGroupInvocationARB & 3) << 1)) & 3;", mask, + instr_mask); - const std::string modifier_a = fmt::format("fswzadd_modifiers_a[{} & 3]", mask); - const std::string modifier_b = fmt::format("fswzadd_modifiers_b[{} & 3]", mask); + const std::string modifier_a = fmt::format("fswzadd_modifiers_a[{}]", mask); + const std::string modifier_b = fmt::format("fswzadd_modifiers_b[{}]", mask); return {fmt::format("(({} * {}) + ({} * {}))", op_a, modifier_a, op_b, modifier_b), Type::Float}; } @@ -1957,11 +1963,21 @@ private: } Expression ThreadId(Operation operation) { + if (!device.HasShaderBallot()) { + LOG_ERROR(Render_OpenGL, "Shader ballot is unavailable but required by the shader"); + return {"0U", Type::Uint}; + } return {"gl_SubGroupInvocationARB", Type::Uint}; } Expression ShuffleIndexed(Operation operation) { - const std::string value = VisitOperand(operation, 0).AsFloat(); + std::string value = VisitOperand(operation, 0).AsFloat(); + + if (!device.HasShaderBallot()) { + LOG_ERROR(Render_OpenGL, "Shader ballot is unavailable but required by the shader"); + return {std::move(value), Type::Float}; + } + const std::string index = VisitOperand(operation, 1).AsUint(); return {fmt::format("readInvocationARB({}, {})", value, index), Type::Float}; }