From 8af6bfb8b09f70552f2775db4a029a94968c6db4 Mon Sep 17 00:00:00 2001 From: Lioncash Date: Tue, 3 Dec 2019 04:17:23 -0500 Subject: [PATCH 1/2] VideoCommon/ShaderGenCommon: Add function for writing fmt-based strings Begins the conversion of the shader generators over to using fmt formatting specifiers. This also has a benefit over the older StringFromFormat-based API in that all formatted data is appended to the existing buffer rather than creating a completely separate string and then appending it to the internal string buffer. --- Source/Core/VideoCommon/ShaderGenCommon.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/Source/Core/VideoCommon/ShaderGenCommon.h b/Source/Core/VideoCommon/ShaderGenCommon.h index 12fa76fb72..889a446df8 100644 --- a/Source/Core/VideoCommon/ShaderGenCommon.h +++ b/Source/Core/VideoCommon/ShaderGenCommon.h @@ -6,11 +6,14 @@ #include #include +#include #include #include #include #include +#include + #include "Common/CommonTypes.h" #include "Common/StringUtil.h" #include "VideoCommon/VideoCommon.h" @@ -101,6 +104,8 @@ class ShaderCode : public ShaderGeneratorInterface public: ShaderCode() { m_buffer.reserve(16384); } const std::string& GetBuffer() const { return m_buffer; } + + // Deprecated: Writes format strings using traditional printf format strings. void Write(const char* fmt, ...) #ifdef __GNUC__ __attribute__((format(printf, 2, 3))) @@ -112,6 +117,13 @@ public: va_end(arglist); } + // Writes format strings using fmtlib format strings. + template + void WriteFmt(std::string_view format, Args&&... args) + { + fmt::format_to(std::back_inserter(m_buffer), format, std::forward(args)...); + } + protected: std::string m_buffer; }; From 0f28f4049ba1df95ba038419f00ef8f75c5260f9 Mon Sep 17 00:00:00 2001 From: Lioncash Date: Tue, 3 Dec 2019 04:28:33 -0500 Subject: [PATCH 2/2] VideoCommon/TextureConverterShaderGen: Convert over to fmt Easily the most straightforward to convert over, given the lack of significant formatting arguments. --- .../VideoCommon/TextureConverterShaderGen.cpp | 208 +++++++++--------- 1 file changed, 104 insertions(+), 104 deletions(-) diff --git a/Source/Core/VideoCommon/TextureConverterShaderGen.cpp b/Source/Core/VideoCommon/TextureConverterShaderGen.cpp index c1935c64b5..47919fb1ab 100644 --- a/Source/Core/VideoCommon/TextureConverterShaderGen.cpp +++ b/Source/Core/VideoCommon/TextureConverterShaderGen.cpp @@ -32,23 +32,23 @@ static void WriteHeader(APIType api_type, ShaderCode& out) { if (api_type == APIType::D3D) { - out.Write("cbuffer PSBlock : register(b0) {\n" - " float2 src_offset, src_size;\n" - " float3 filter_coefficients;\n" - " float gamma_rcp;\n" - " float2 clamp_tb;\n" - " float pixel_height;\n" - "};\n\n"); + out.WriteFmt("cbuffer PSBlock : register(b0) {{\n" + " float2 src_offset, src_size;\n" + " float3 filter_coefficients;\n" + " float gamma_rcp;\n" + " float2 clamp_tb;\n" + " float pixel_height;\n" + "}};\n\n"); } else if (api_type == APIType::OpenGL || api_type == APIType::Vulkan) { - out.Write("UBO_BINDING(std140, 1) uniform PSBlock {\n" - " float2 src_offset, src_size;\n" - " float3 filter_coefficients;\n" - " float gamma_rcp;\n" - " float2 clamp_tb;\n" - " float pixel_height;\n" - "};\n"); + out.WriteFmt("UBO_BINDING(std140, 1) uniform PSBlock {{\n" + " float2 src_offset, src_size;\n" + " float3 filter_coefficients;\n" + " float gamma_rcp;\n" + " float2 clamp_tb;\n" + " float pixel_height;\n" + "}};\n"); } } @@ -59,35 +59,35 @@ ShaderCode GenerateVertexShader(APIType api_type) if (api_type == APIType::D3D) { - out.Write("void main(in uint id : SV_VertexID, out float3 v_tex0 : TEXCOORD0,\n" - " out float4 opos : SV_Position) {\n"); + out.WriteFmt("void main(in uint id : SV_VertexID, out float3 v_tex0 : TEXCOORD0,\n" + " out float4 opos : SV_Position) {{\n"); } else if (api_type == APIType::OpenGL || api_type == APIType::Vulkan) { if (g_ActiveConfig.backend_info.bSupportsGeometryShaders) { - out.Write("VARYING_LOCATION(0) out VertexData {\n"); - out.Write(" float3 v_tex0;\n"); - out.Write("};\n"); + out.WriteFmt("VARYING_LOCATION(0) out VertexData {{\n" + " float3 v_tex0;\n" + "}};\n"); } else { - out.Write("VARYING_LOCATION(0) out float3 v_tex0;\n"); + out.WriteFmt("VARYING_LOCATION(0) out float3 v_tex0;\n"); } - out.Write("#define id gl_VertexID\n" - "#define opos gl_Position\n" - "void main() {\n"); + out.WriteFmt("#define id gl_VertexID\n" + "#define opos gl_Position\n" + "void main() {{\n"); } - out.Write(" v_tex0 = float3(float((id << 1) & 2), float(id & 2), 0.0f);\n"); - out.Write( + out.WriteFmt(" v_tex0 = float3(float((id << 1) & 2), float(id & 2), 0.0f);\n"); + out.WriteFmt( " opos = float4(v_tex0.xy * float2(2.0f, -2.0f) + float2(-1.0f, 1.0f), 0.0f, 1.0f);\n"); - out.Write(" v_tex0 = float3(src_offset + (src_size * v_tex0.xy), 0.0f);\n"); + out.WriteFmt(" v_tex0 = float3(src_offset + (src_size * v_tex0.xy), 0.0f);\n"); // NDC space is flipped in Vulkan if (api_type == APIType::Vulkan) - out.Write(" opos.y = -opos.y;\n"); + out.WriteFmt(" opos.y = -opos.y;\n"); - out.Write("}\n"); + out.WriteFmt("}}\n"); return out; } @@ -101,52 +101,52 @@ ShaderCode GeneratePixelShader(APIType api_type, const UidData* uid_data) if (api_type == APIType::D3D) { - out.Write("Texture2DArray tex0 : register(t0);\n" - "SamplerState samp0 : register(s0);\n" - "float4 SampleEFB(float3 uv, float y_offset) {\n" - " return tex0.Sample(samp0, float3(uv.x, clamp(uv.y + (y_offset * pixel_height), " - "clamp_tb.x, clamp_tb.y), %s));\n" - "}\n\n", - mono_depth ? "0.0" : "uv.z"); - out.Write("void main(in float3 v_tex0 : TEXCOORD0, out float4 ocol0 : SV_Target)\n{\n"); + out.WriteFmt("Texture2DArray tex0 : register(t0);\n" + "SamplerState samp0 : register(s0);\n" + "float4 SampleEFB(float3 uv, float y_offset) {{\n" + " return tex0.Sample(samp0, float3(uv.x, clamp(uv.y + (y_offset * pixel_height), " + "clamp_tb.x, clamp_tb.y), {}));\n" + "}}\n\n", + mono_depth ? "0.0" : "uv.z"); + out.WriteFmt("void main(in float3 v_tex0 : TEXCOORD0, out float4 ocol0 : SV_Target)\n{{\n"); } else if (api_type == APIType::OpenGL || api_type == APIType::Vulkan) { - out.Write("SAMPLER_BINDING(0) uniform sampler2DArray samp0;\n"); - out.Write("float4 SampleEFB(float3 uv, float y_offset) {\n" - " return texture(samp0, float3(uv.x, clamp(uv.y + (y_offset * pixel_height), " - "clamp_tb.x, clamp_tb.y), %s));\n" - "}\n", - mono_depth ? "0.0" : "uv.z"); + out.WriteFmt("SAMPLER_BINDING(0) uniform sampler2DArray samp0;\n"); + out.WriteFmt("float4 SampleEFB(float3 uv, float y_offset) {{\n" + " return texture(samp0, float3(uv.x, clamp(uv.y + (y_offset * pixel_height), " + "clamp_tb.x, clamp_tb.y), {}));\n" + "}}\n", + mono_depth ? "0.0" : "uv.z"); if (g_ActiveConfig.backend_info.bSupportsGeometryShaders) { - out.Write("VARYING_LOCATION(0) in VertexData {\n"); - out.Write(" float3 v_tex0;\n"); - out.Write("};\n"); + out.WriteFmt("VARYING_LOCATION(0) in VertexData {{\n" + " float3 v_tex0;\n" + "}};\n"); } else { - out.Write("VARYING_LOCATION(0) in vec3 v_tex0;\n"); + out.WriteFmt("VARYING_LOCATION(0) in vec3 v_tex0;\n"); } - out.Write("FRAGMENT_OUTPUT_LOCATION(0) out vec4 ocol0;" - "void main()\n{\n"); + out.WriteFmt("FRAGMENT_OUTPUT_LOCATION(0) out vec4 ocol0;" + "void main()\n{{\n"); } // The copy filter applies to both color and depth copies. This has been verified on hardware. // The filter is only applied to the RGB channels, the alpha channel is left intact. if (uid_data->copy_filter) { - out.Write(" float4 prev_row = SampleEFB(v_tex0, -1.0f);\n" - " float4 current_row = SampleEFB(v_tex0, 0.0f);\n" - " float4 next_row = SampleEFB(v_tex0, 1.0f);\n" - " float4 texcol = float4(min(prev_row.rgb * filter_coefficients[0] +\n" - " current_row.rgb * filter_coefficients[1] +\n" - " next_row.rgb * filter_coefficients[2], \n" - " float3(1, 1, 1)), current_row.a);\n"); + out.WriteFmt(" float4 prev_row = SampleEFB(v_tex0, -1.0f);\n" + " float4 current_row = SampleEFB(v_tex0, 0.0f);\n" + " float4 next_row = SampleEFB(v_tex0, 1.0f);\n" + " float4 texcol = float4(min(prev_row.rgb * filter_coefficients[0] +\n" + " current_row.rgb * filter_coefficients[1] +\n" + " next_row.rgb * filter_coefficients[2], \n" + " float3(1, 1, 1)), current_row.a);\n"); } else { - out.Write( + out.WriteFmt( " float4 current_row = SampleEFB(v_tex0, 0.0f);\n" " float4 texcol = float4(min(current_row.rgb * filter_coefficients[1], float3(1, 1, 1)),\n" " current_row.a);\n"); @@ -155,62 +155,62 @@ ShaderCode GeneratePixelShader(APIType api_type, const UidData* uid_data) if (uid_data->is_depth_copy) { if (!g_ActiveConfig.backend_info.bSupportsReversedDepthRange) - out.Write("texcol.x = 1.0 - texcol.x;\n"); + out.WriteFmt("texcol.x = 1.0 - texcol.x;\n"); - out.Write(" int depth = int(texcol.x * 16777216.0);\n" + out.WriteFmt(" int depth = int(texcol.x * 16777216.0);\n" - // Convert to Z24 format - " int4 workspace;\n" - " workspace.r = (depth >> 16) & 255;\n" - " workspace.g = (depth >> 8) & 255;\n" - " workspace.b = depth & 255;\n" + // Convert to Z24 format + " int4 workspace;\n" + " workspace.r = (depth >> 16) & 255;\n" + " workspace.g = (depth >> 8) & 255;\n" + " workspace.b = depth & 255;\n" - // Convert to Z4 format - " workspace.a = (depth >> 16) & 0xF0;\n" + // Convert to Z4 format + " workspace.a = (depth >> 16) & 0xF0;\n" - // Normalize components to [0.0..1.0] - " texcol = float4(workspace) / 255.0;\n"); + // Normalize components to [0.0..1.0] + " texcol = float4(workspace) / 255.0;\n"); switch (uid_data->dst_format) { case EFBCopyFormat::R4: // Z4 - out.Write(" ocol0 = texcol.aaaa;\n"); + out.WriteFmt(" ocol0 = texcol.aaaa;\n"); break; case EFBCopyFormat::R8_0x1: // Z8 case EFBCopyFormat::R8: // Z8H - out.Write(" ocol0 = texcol.rrrr;\n"); + out.WriteFmt(" ocol0 = texcol.rrrr;\n"); break; case EFBCopyFormat::RA8: // Z16 - out.Write(" ocol0 = texcol.gggr;\n"); + out.WriteFmt(" ocol0 = texcol.gggr;\n"); break; case EFBCopyFormat::RG8: // Z16 (reverse order) - out.Write(" ocol0 = texcol.rrrg;\n"); + out.WriteFmt(" ocol0 = texcol.rrrg;\n"); break; case EFBCopyFormat::RGBA8: // Z24X8 - out.Write(" ocol0 = float4(texcol.rgb, 1.0);\n"); + out.WriteFmt(" ocol0 = float4(texcol.rgb, 1.0);\n"); break; case EFBCopyFormat::G8: // Z8M - out.Write(" ocol0 = texcol.gggg;\n"); + out.WriteFmt(" ocol0 = texcol.gggg;\n"); break; case EFBCopyFormat::B8: // Z8L - out.Write(" ocol0 = texcol.bbbb;\n"); + out.WriteFmt(" ocol0 = texcol.bbbb;\n"); break; case EFBCopyFormat::GB8: // Z16L - copy lower 16 depth bits // expected to be used as an IA8 texture (upper 8 bits stored as intensity, lower 8 bits // stored as alpha) // Used e.g. in Zelda: Skyward Sword - out.Write(" ocol0 = texcol.gggb;\n"); + out.WriteFmt(" ocol0 = texcol.gggb;\n"); break; default: ERROR_LOG(VIDEO, "Unknown copy zbuf format: 0x%X", static_cast(uid_data->dst_format)); - out.Write(" ocol0 = float4(texcol.bgr, 0.0);\n"); + out.WriteFmt(" ocol0 = float4(texcol.bgr, 0.0);\n"); break; } } @@ -229,99 +229,99 @@ ShaderCode GeneratePixelShader(APIType api_type, const UidData* uid_data) case EFBCopyFormat::RA4: // IA4 case EFBCopyFormat::RA8: // IA8 if (has_four_bits) - out.Write(" texcol = float4(int4(texcol * 255.0) & 0xF0) * (1.0 / 240.0);\n"); + out.WriteFmt(" texcol = float4(int4(texcol * 255.0) & 0xF0) * (1.0 / 240.0);\n"); // TODO - verify these coefficients - out.Write(" const float3 coefficients = float3(0.257, 0.504, 0.098);\n" - " float intensity = dot(texcol.rgb, coefficients) + 16.0 / 255.0;\n" - " ocol0 = float4(intensity, intensity, intensity, %s);\n", - has_alpha ? "texcol.a" : "intensity"); + out.WriteFmt(" const float3 coefficients = float3(0.257, 0.504, 0.098);\n" + " float intensity = dot(texcol.rgb, coefficients) + 16.0 / 255.0;\n" + " ocol0 = float4(intensity, intensity, intensity, {});\n", + has_alpha ? "texcol.a" : "intensity"); break; default: ERROR_LOG(VIDEO, "Unknown copy intensity format: 0x%X", static_cast(uid_data->dst_format)); - out.Write(" ocol0 = texcol;\n"); + out.WriteFmt(" ocol0 = texcol;\n"); break; } } else { if (!uid_data->efb_has_alpha) - out.Write(" texcol.a = 1.0;\n"); + out.WriteFmt(" texcol.a = 1.0;\n"); switch (uid_data->dst_format) { case EFBCopyFormat::R4: // R4 - out.Write(" float red = float(int(texcol.r * 255.0) & 0xF0) * (1.0 / 240.0);\n" - " ocol0 = float4(red, red, red, red);\n"); + out.WriteFmt(" float red = float(int(texcol.r * 255.0) & 0xF0) * (1.0 / 240.0);\n" + " ocol0 = float4(red, red, red, red);\n"); break; case EFBCopyFormat::R8_0x1: // R8 case EFBCopyFormat::R8: // R8 - out.Write(" ocol0 = texcol.rrrr;\n"); + out.WriteFmt(" ocol0 = texcol.rrrr;\n"); break; case EFBCopyFormat::RA4: // RA4 - out.Write(" float2 red_alpha = float2(int2(texcol.ra * 255.0) & 0xF0) * (1.0 / 240.0);\n" - " ocol0 = red_alpha.rrrg;\n"); + out.WriteFmt(" float2 red_alpha = float2(int2(texcol.ra * 255.0) & 0xF0) * (1.0 / 240.0);\n" + " ocol0 = red_alpha.rrrg;\n"); break; case EFBCopyFormat::RA8: // RA8 - out.Write(" ocol0 = texcol.rrra;\n"); + out.WriteFmt(" ocol0 = texcol.rrra;\n"); break; case EFBCopyFormat::A8: // A8 - out.Write(" ocol0 = texcol.aaaa;\n"); + out.WriteFmt(" ocol0 = texcol.aaaa;\n"); break; case EFBCopyFormat::G8: // G8 - out.Write(" ocol0 = texcol.gggg;\n"); + out.WriteFmt(" ocol0 = texcol.gggg;\n"); break; case EFBCopyFormat::B8: // B8 - out.Write(" ocol0 = texcol.bbbb;\n"); + out.WriteFmt(" ocol0 = texcol.bbbb;\n"); break; case EFBCopyFormat::RG8: // RG8 - out.Write(" ocol0 = texcol.rrrg;\n"); + out.WriteFmt(" ocol0 = texcol.rrrg;\n"); break; case EFBCopyFormat::GB8: // GB8 - out.Write(" ocol0 = texcol.gggb;\n"); + out.WriteFmt(" ocol0 = texcol.gggb;\n"); break; case EFBCopyFormat::RGB565: // RGB565 - out.Write(" float2 red_blue = float2(int2(texcol.rb * 255.0) & 0xF8) * (1.0 / 248.0);\n" - " float green = float(int(texcol.g * 255.0) & 0xFC) * (1.0 / 252.0);\n" - " ocol0 = float4(red_blue.r, green, red_blue.g, 1.0);\n"); + out.WriteFmt(" float2 red_blue = float2(int2(texcol.rb * 255.0) & 0xF8) * (1.0 / 248.0);\n" + " float green = float(int(texcol.g * 255.0) & 0xFC) * (1.0 / 252.0);\n" + " ocol0 = float4(red_blue.r, green, red_blue.g, 1.0);\n"); break; case EFBCopyFormat::RGB5A3: // RGB5A3 // TODO: The MSB controls whether we have RGB5 or RGB4A3, this selection // will need to be implemented once we move away from floats. - out.Write(" float3 color = float3(int3(texcol.rgb * 255.0) & 0xF8) * (1.0 / 248.0);\n" - " float alpha = float(int(texcol.a * 255.0) & 0xE0) * (1.0 / 224.0);\n" - " ocol0 = float4(color, alpha);\n"); + out.WriteFmt(" float3 color = float3(int3(texcol.rgb * 255.0) & 0xF8) * (1.0 / 248.0);\n" + " float alpha = float(int(texcol.a * 255.0) & 0xE0) * (1.0 / 224.0);\n" + " ocol0 = float4(color, alpha);\n"); break; case EFBCopyFormat::RGBA8: // RGBA8 - out.Write(" ocol0 = texcol;\n"); + out.WriteFmt(" ocol0 = texcol;\n"); break; case EFBCopyFormat::XFB: - out.Write( + out.WriteFmt( " ocol0 = float4(pow(texcol.rgb, float3(gamma_rcp, gamma_rcp, gamma_rcp)), 1.0f);\n"); break; default: ERROR_LOG(VIDEO, "Unknown copy color format: 0x%X", static_cast(uid_data->dst_format)); - out.Write(" ocol0 = texcol;\n"); + out.WriteFmt(" ocol0 = texcol;\n"); break; } } - out.Write("}\n"); + out.WriteFmt("}}\n"); return out; }