Compare commits

...

7 Commits

Author SHA1 Message Date
lizzie eba63c51c8 use shell wrapper 2026-07-03 17:42:10 +00:00
lizzie 4e8372be13 openssl update? 2026-07-03 17:41:37 +00:00
lizzie 024a66fc1e better patches 2026-07-03 17:39:29 +00:00
lizzie 558175adf9 [cmake] update OpenSSL, FFmpeg, vkhdr; remove stale ssl patches
Signed-off-by: lizzie <lizzie@eden-emu.dev>
2026-07-03 17:39:14 +00:00
lizzie 4c65780f11 Revert "[common/dynamic_library] fix AUR build error (#4156)" (#4157)
This reverts commit a9c4c8aefd.

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4157
Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
2026-07-02 22:07:37 +02:00
lizzie a9c4c8aefd [common/dynamic_library] fix AUR build error (#4156)
not gonna question why there was an ifdef there

Signed-off-by: lizzie <lizzie@eden-emu.dev>

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4156
Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
2026-07-02 19:49:19 +02:00
lizzie a769505a45 [vk, ogl] Remove dedicated precomputed swizzle table; use shorter inline table in block_linear swizzle shaders (#4146)
old table = 64 * 8 * sizeof(u32) = 512 * 4 = 4096 bytes
new table = 8 * sizeof(u32) = 8 * 4 = 32 bytes

the expression
```glsl
    return ((pos & 0x0180) >> 1)
         | ((pos & 0x0040) >> 2)
         | ((pos & 0x0020) << 3)
         | ((pos & 0x0010) << 1)
         | ((pos & 0x000f) << 0);
```
is equivalent for generating the table but idk if we'd want that

Signed-off-by: lizzie <lizzie@eden-emu.dev>

Co-authored-by: CamilleLaVey <camillelavey99@gmail.com>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4146
Reviewed-by: CamilleLaVey <camillelavey99@gmail.com>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
2026-07-02 19:24:07 +02:00
14 changed files with 125 additions and 347 deletions
@@ -15,16 +15,6 @@ diff --git a/CMakeLists.txt b/CMakeLists.txt
index 5420ecc..9ffd5a0 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -19,9 +19,7 @@ include(FetchContent)
include(ProcessorCount)
include(cmake/ConfigureOpenSSL.cmake)
include(cmake/DetectTargetPlatform.cmake)
-include(cmake/FetchOpenSSL.cmake)
include(cmake/FindVcvarsall.cmake)
-include(cmake/GetCPM.cmake)
# Custom options
option(OPENSSL_BUILD_VERBOSE "Enable verbose output from build" OFF)
@@ -47,9 +45,6 @@ if("${OPENSSL_TARGET_PLATFORM}" STREQUAL "")
detect_target_platform(OPENSSL_TARGET_PLATFORM)
endif()
@@ -128,87 +118,3 @@ index 5420ecc..9ffd5a0 100644
)"
)
endif()
diff --git a/cmake/FetchOpenSSL.cmake b/cmake/FetchOpenSSL.cmake
deleted file mode 100644
index a43505d..0000000
--- a/cmake/FetchOpenSSL.cmake
+++ /dev/null
@@ -1,64 +0,0 @@
-function(fetch_openssl)
- if(EXISTS "${OPENSSL_SOURCE}" AND IS_DIRECTORY "${OPENSSL_SOURCE}")
- # Fetch the local OpenSSL source
- if(NOT IS_ABSOLUTE "${OPENSSL_SOURCE}")
- string(PREPEND OPENSSL_SOURCE ${CMAKE_SOURCE_DIR}/)
- endif()
-
- string(REPLACE "\\" "/" openssl-source_SOURCE_DIR "${OPENSSL_SOURCE}")
- set(openssl-source_BINARY_DIR ${CMAKE_CURRENT_BINARY_DIR}/openssl-source-build)
- else()
- set(CPM_OPTIONS
- NAME openssl-source
- DOWNLOAD_ONLY ON
- )
-
- if(NOT OPENSSL_CONFIGURE_VERBOSE)
- list(APPEND CPM_OPTIONS QUIET)
- endif()
-
- if("${OPENSSL_SOURCE}" MATCHES "^http")
- # Download OpenSSL source from the internet
- list(APPEND CPM_OPTIONS URL ${OPENSSL_SOURCE})
- else()
- # Download OpenSSL source from the official website
- if("${OPENSSL_TARGET_VERSION}" STREQUAL "")
- set(OPENSSL_TARGET_VERSION ${PROJECT_VERSION})
- endif()
-
- if(OPENSSL_TARGET_VERSION VERSION_EQUAL PROJECT_VERSION)
- list(APPEND CPM_OPTIONS URL_HASH SHA256=aaf51a1fe064384f811daeaeb4ec4dce7340ec8bd893027eee676af31e83a04f)
- endif()
-
- if(OPENSSL_TARGET_VERSION MATCHES "^1\.1\.1[a-w]$")
- string(REPLACE "." "_" OPENSSL_TAGGED_VERSION ${OPENSSL_TARGET_VERSION})
- list(APPEND CPM_OPTIONS URL https://github.com/openssl/openssl/releases/download/OpenSSL_${OPENSSL_TAGGED_VERSION}/openssl-${OPENSSL_TARGET_VERSION}.tar.gz)
- else()
- list(APPEND CPM_OPTIONS URL https://github.com/openssl/openssl/releases/download/openssl-${OPENSSL_TARGET_VERSION}/openssl-${OPENSSL_TARGET_VERSION}.tar.gz)
- endif()
- endif()
-
- CPMAddPackage(${CPM_OPTIONS})
- endif()
-
- # Clean build directory if source directory has changed
- if(DEFINED CACHE{openssl-source_SOURCE_DIR_OLD} AND NOT openssl-source_SOURCE_DIR STREQUAL openssl-source_SOURCE_DIR_OLD)
- set(openssl-source_SOURCE_DIR_OLD ${openssl-source_SOURCE_DIR} CACHE INTERNAL "Previously fetched OpenSSL source")
-
- if(IS_DIRECTORY ${openssl-source_BINARY_DIR})
- file(REMOVE_RECURSE ${openssl-source_BINARY_DIR})
- file(MAKE_DIRECTORY ${openssl-source_BINARY_DIR})
- endif()
- endif()
-
- # Override the FindOpenSSL module
- FetchContent_Declare(
- OpenSSL
- SOURCE_DIR ${openssl-source_SOURCE_DIR}
- BINARY_DIR ${openssl-source_BINARY_DIR}
- OVERRIDE_FIND_PACKAGE
- )
- FetchContent_MakeAvailable(OpenSSL)
-
- return(PROPAGATE openssl_SOURCE_DIR openssl_BINARY_DIR)
-endfunction()
diff --git a/cmake/GetCPM.cmake b/cmake/GetCPM.cmake
deleted file mode 100644
index bfc50f5..0000000
--- a/cmake/GetCPM.cmake
+++ /dev/null
@@ -1,5 +0,0 @@
-file(
- DOWNLOAD https://github.com/cpm-cmake/CPM.cmake/releases/latest/download/get_cpm.cmake
- ${CMAKE_CURRENT_BINARY_DIR}/get_cpm.cmake
-)
-include(${CMAKE_CURRENT_BINARY_DIR}/get_cpm.cmake)
--
2.54.0
+11 -21
View File
@@ -9,23 +9,23 @@ Subject: [PATCH] use ccache
2 files changed, 3 insertions(+), 10 deletions(-)
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 9ffd5a0..9ff14c8 100644
index d6c998c..d943c59 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -28,7 +28,6 @@ option(OPENSSL_ENABLE_PARALLEL "Build and test in parallel if possible" ON)
option(OPENSSL_INSTALL "Install OpenSSL components to the <prefix> directory" OFF)
option(OPENSSL_INSTALL_CERT "Install cert.pem to the <openssldir> directory" OFF)
option(OPENSSL_TEST "Enable testing and build OpenSSL self tests" OFF)
-option(OPENSSL_USE_CCACHE "Use ccache if available" ON)
@@ -20,7 +20,6 @@ include(ProcessorCount)
include(cmake/CheckBuildMismatches.cmake)
include(cmake/ConfigureOpenSSL.cmake)
include(cmake/DetectTargetPlatform.cmake)
-include(cmake/FetchOpenSSL.cmake)
include(cmake/FindVcvarsall.cmake)
if("${OPENSSL_BUILD_TARGET}" STREQUAL "")
# Makefile target for build
# Custom options
diff --git a/cmake/ConfigureOpenSSL.cmake b/cmake/ConfigureOpenSSL.cmake
index 211c18b..3d8cbed 100644
index be8d651..c186c16 100644
--- a/cmake/ConfigureOpenSSL.cmake
+++ b/cmake/ConfigureOpenSSL.cmake
@@ -69,15 +69,9 @@ function(apply_ccache FILE)
message(FATAL_ERROR "Couldn't find Makefile")
@@ -77,15 +77,9 @@ function(apply_ccache FILE)
)
endif()
- if(OPENSSL_USE_CCACHE)
@@ -42,13 +42,3 @@ index 211c18b..3d8cbed 100644
if(MSVC)
string(REPLACE "/Zi /Fdossl_static.pdb " "" MAKEFILE "${MAKEFILE}")
@@ -171,4 +165,4 @@ function(configure_openssl)
string(REPLACE "/W3" "/W0" MAKEFILE "${MAKEFILE}")
file(WRITE ${OPENSSL_MAKEFILE} "${MAKEFILE}")
endif()
-endfunction()
\ No newline at end of file
+endfunction()
--
2.54.0
@@ -8,10 +8,10 @@ Subject: [PATCH 2/2] use cmake compiler flags
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/cmake/ConfigureOpenSSL.cmake b/cmake/ConfigureOpenSSL.cmake
index 3d8cbed..3012e05 100644
index c186c16..222e9c2 100644
--- a/cmake/ConfigureOpenSSL.cmake
+++ b/cmake/ConfigureOpenSSL.cmake
@@ -135,7 +135,10 @@ function(configure_openssl)
@@ -147,7 +147,10 @@ function(configure_openssl)
endif()
execute_process(
@@ -23,6 +23,3 @@ index 3d8cbed..3012e05 100644
WORKING_DIRECTORY ${CONFIGURE_BUILD_DIR}
${VERBOSE_OPTION}
COMMAND_ERROR_IS_FATAL ANY
--
2.54.0
@@ -1,39 +0,0 @@
--- a/CMakeLists.txt 2026-06-01 23:53:16.498043856 -0400
+++ b/CMakeLists.txt 2026-06-01 23:53:23.910543615 -0400
@@ -312,13 +312,29 @@
${OPENSSL_SHARED_CRYPTO_LIBRARY}
${OPENSSL_SHARED_SSL_LIBRARY}
)
-add_custom_command(
- OUTPUT ${OPENSSL_BUILD_OUTPUT}
- COMMAND ${OPENSSL_BUILD_COMMAND}
- DEPENDS ${OPENSSL_SOURCES}
- WORKING_DIRECTORY ${OpenSSL_BINARY_DIR}
- VERBATIM
-)
+if (WIN32)
+ add_custom_command(
+ OUTPUT ${OPENSSL_BUILD_OUTPUT}
+ COMMAND ${OPENSSL_BUILD_COMMAND}
+ DEPENDS ${OPENSSL_SOURCES}
+ WORKING_DIRECTORY ${OpenSSL_BINARY_DIR}
+ VERBATIM)
+else()
+ set(_openssl_build_script "${CMAKE_CURRENT_BINARY_DIR}/BuildOpenSSL.cmake")
+ file(WRITE ${_openssl_build_script}
+ "execute_process(\n"
+ " COMMAND ${OPENSSL_BUILD_COMMAND}\n"
+ " WORKING_DIRECTORY ${OpenSSL_BINARY_DIR}\n"
+ " RESULT_VARIABLE _r)\n"
+ "if(_r)\n"
+ " message(FATAL_ERROR \"OpenSSL build failed: \${_r}\")\n"
+ "endif()\n")
+ add_custom_command(
+ OUTPUT ${OPENSSL_BUILD_OUTPUT}
+ COMMAND ${CMAKE_COMMAND} -P ${_openssl_build_script}
+ DEPENDS ${OPENSSL_SOURCES}
+ VERBATIM)
+endif()
if(PROJECT_IS_TOP_LEVEL)
add_custom_target(openssl-build ALL DEPENDS ${OPENSSL_BUILD_OUTPUT})
+7 -8
View File
@@ -203,7 +203,7 @@
"version": "1.10.0"
},
"openssl": {
"hash": "29002ce50cb95a4f4f1d0e9d3f684401fbd4eac34203dc2eef3b6334af5d44aa46bf788b63a6f5c139c383eafb7269ae87a58a9a3ad5912903b9773e545ccc0a",
"hash": "2405891660b67e4cc01c7868e100f2766e1c6290120213ae62f775ef3d9610c3527bdc43d4c831260417450c74353b0693ae3e24cca3e99b02e4daa548b93904",
"min_version": "3.0.0",
"package": "OpenSSL",
"patches": [
@@ -211,7 +211,7 @@
],
"repo": "openssl/openssl",
"tag": "openssl-%VERSION%",
"version": "3.6.2"
"version": "4.0.1"
},
"openssl-ci": {
"ci": true,
@@ -223,19 +223,18 @@
},
"openssl-cmake": {
"bundled": true,
"hash": "2cc185c924fd70e7d886257ca0caa42b3b8f7f712f2052b4f94dde74759e27022de76178460e18c9bdfc57c366583999e198fbb6052d4e7d91c099d15a0ca63e",
"hash": "bc73a6c035f299711bb90e20b16fa3521e8ffdab32d8d17f9e7f5cde1ff5def37ec6f9e03de25c3466d18885815c0874331f56e592b8a2f7deeb484c69c5c621",
"options": [
"OPENSSL_CONFIGURE_OPTIONS threads"
],
"patches": [
"0001-cpmutil-compat.patch",
"0002-use-ccache.patch",
"0003-use-cmake-compiler-flags.patch",
"0004-use-shell-wrapper.patch"
"0003-use-cmake-compiler-flags.patch"
],
"repo": "jimmy-park/openssl-cmake",
"tag": "%VERSION%",
"version": "3.6.2"
"version": "4.0.1"
},
"opus": {
"find_args": "MODULE",
@@ -371,11 +370,11 @@
"version": "1.4.341.0"
},
"xbyak": {
"hash": "b6475276b2faaeb315734ea8f4f8bd87ededcee768961b39679bee547e7f3e98884d8b7851e176d861dab30a80a76e6ea302f8c111483607dde969b4797ea95a",
"hash": "03d870f63741ff8c00501329bf9947bdf58e7cc4c3884e3de9b827f31942438887555f601a5f80d405946854eb54ab907b4e2a3ad955ca4ad890a243917dd4ae",
"package": "xbyak",
"repo": "herumi/xbyak",
"tag": "v%VERSION%",
"version": "7.35.2"
"version": "7.37.3"
},
"zlib": {
"hash": "16fea4df307a68cf0035858abe2fd550250618a97590e202037acd18a666f57afc10f8836cbbd472d54a0e76539d0e558cb26f059d53de52ff90634bbf4f47d4",
@@ -11,9 +11,8 @@
#define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
#define END_PUSH_CONSTANTS };
#define UNIFORM(n)
#define BINDING_SWIZZLE_BUFFER 0
#define BINDING_INPUT_BUFFER 1
#define BINDING_OUTPUT_IMAGE 2
#define BINDING_INPUT_BUFFER 0
#define BINDING_OUTPUT_IMAGE 1
#else // ^^^ Vulkan ^^^ // vvv OpenGL vvv
@@ -26,8 +25,7 @@
#define BEGIN_PUSH_CONSTANTS
#define END_PUSH_CONSTANTS
#define UNIFORM(n) layout (location = n) uniform
#define BINDING_SWIZZLE_BUFFER 0
#define BINDING_INPUT_BUFFER 1
#define BINDING_INPUT_BUFFER 0
#define BINDING_OUTPUT_IMAGE 0
#endif
@@ -43,10 +41,6 @@ UNIFORM(6) uint block_height;
UNIFORM(7) uint block_height_mask;
END_PUSH_CONSTANTS
layout(binding = BINDING_SWIZZLE_BUFFER, std430) readonly buffer SwizzleTable {
uint swizzle_table[];
};
#if HAS_EXTENDED_TYPES
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU8 { uint8_t u8data[]; };
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU16 { uint16_t u16data[]; };
@@ -71,9 +65,19 @@ const uint GOB_SIZE_SHIFT = GOB_SIZE_X_SHIFT + GOB_SIZE_Y_SHIFT + GOB_SIZE_Z_SHI
const uvec2 SWIZZLE_MASK = uvec2(GOB_SIZE_X - 1, GOB_SIZE_Y - 1);
uint SwizzleTable(uint pos) {
const uint t[8] = uint[](
0x12100200, 0x13110301, 0x16140604, 0x17150705,
0x1a180a08, 0x1b190b09, 0x1e1c0e0c, 0x1f1d0f0d
);
const uint i = pos >> 4;
const uint h = (t[i / 4] >> ((i % 4) * 8)) & 0xff;
return (h << 4) | (pos & 0xf);
}
uint SwizzleOffset(uvec2 pos) {
pos = pos & SWIZZLE_MASK;
return swizzle_table[pos.y * 64 + pos.x];
return SwizzleTable(pos.y * 64 + pos.x);
}
uvec4 ReadTexel(uint offset) {
@@ -11,9 +11,8 @@
#define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
#define END_PUSH_CONSTANTS };
#define UNIFORM(n)
#define BINDING_SWIZZLE_BUFFER 0
#define BINDING_INPUT_BUFFER 1
#define BINDING_OUTPUT_IMAGE 2
#define BINDING_INPUT_BUFFER 0
#define BINDING_OUTPUT_IMAGE 1
#else // ^^^ Vulkan ^^^ // vvv OpenGL vvv
@@ -26,8 +25,7 @@
#define BEGIN_PUSH_CONSTANTS
#define END_PUSH_CONSTANTS
#define UNIFORM(n) layout (location = n) uniform
#define BINDING_SWIZZLE_BUFFER 0
#define BINDING_INPUT_BUFFER 1
#define BINDING_INPUT_BUFFER 0
#define BINDING_OUTPUT_IMAGE 0
#endif
@@ -45,10 +43,6 @@ UNIFORM(8) uint block_depth;
UNIFORM(9) uint block_depth_mask;
END_PUSH_CONSTANTS
layout(binding = BINDING_SWIZZLE_BUFFER, std430) readonly buffer SwizzleTable {
uint swizzle_table[];
};
#if HAS_EXTENDED_TYPES
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU8 { uint8_t u8data[]; };
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU16 { uint16_t u16data[]; };
@@ -73,9 +67,19 @@ const uint GOB_SIZE_SHIFT = GOB_SIZE_X_SHIFT + GOB_SIZE_Y_SHIFT + GOB_SIZE_Z_SHI
const uvec2 SWIZZLE_MASK = uvec2(GOB_SIZE_X - 1, GOB_SIZE_Y - 1);
uint SwizzleTable(uint pos) {
const uint t[8] = uint[](
0x12100200, 0x13110301, 0x16140604, 0x17150705,
0x1a180a08, 0x1b190b09, 0x1e1c0e0c, 0x1f1d0f0d
);
const uint i = pos >> 4;
const uint h = (t[i / 4] >> ((i % 4) * 8)) & 0xff;
return (h << 4) | (pos & 0xf);
}
uint SwizzleOffset(uvec2 pos) {
pos = pos & SWIZZLE_MASK;
return swizzle_table[pos.y * 64 + pos.x];
return SwizzleTable(pos.y * 64 + pos.x);
}
uvec4 ReadTexel(uint offset) {
@@ -10,9 +10,8 @@
#define BEGIN_PUSH_CONSTANTS layout(push_constant) uniform PushConstants {
#define END_PUSH_CONSTANTS };
#define UNIFORM(n)
#define BINDING_SWIZZLE_BUFFER 0
#define BINDING_INPUT_BUFFER 1
#define BINDING_OUTPUT_BUFFER 2
#define BINDING_INPUT_BUFFER 0
#define BINDING_OUTPUT_BUFFER 1
#else
#extension GL_NV_gpu_shader5 : enable
#ifdef GL_NV_gpu_shader5
@@ -23,7 +22,6 @@
#define BEGIN_PUSH_CONSTANTS
#define END_PUSH_CONSTANTS
#define UNIFORM(n) layout(location = n) uniform
#define BINDING_SWIZZLE_BUFFER 0
#define BINDING_INPUT_BUFFER 1
#define BINDING_OUTPUT_BUFFER 0
#endif
@@ -66,13 +64,9 @@ END_PUSH_CONSTANTS
#endif
// --- Buffers ---
layout(binding = BINDING_SWIZZLE_BUFFER, std430) readonly buffer SwizzleTable {
uint swizzle_table[];
};
#if HAS_EXTENDED_TYPES
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU8 { uint8_t u8data[]; };
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU16 { uint16_t u16data[]; };
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU8 { uint8_t u8data[]; };
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU16 { uint16_t u16data[]; };
#endif
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU32 { uint u32data[]; };
layout(binding = BINDING_INPUT_BUFFER, std430) buffer InputBufferU64 { uvec2 u64data[]; };
@@ -96,10 +90,20 @@ const uint GOB_SIZE_Z_SHIFT = 0;
const uint GOB_SIZE_SHIFT = GOB_SIZE_X_SHIFT + GOB_SIZE_Y_SHIFT + GOB_SIZE_Z_SHIFT;
const uvec2 SWIZZLE_MASK = uvec2(GOB_SIZE_X - 1u, GOB_SIZE_Y - 1u);
uint SwizzleTable(uint pos) {
const uint t[8] = uint[](
0x12100200, 0x13110301, 0x16140604, 0x17150705,
0x1a180a08, 0x1b190b09, 0x1e1c0e0c, 0x1f1d0f0d
);
const uint i = pos >> 4;
const uint h = (t[i / 4] >> ((i % 4) * 8)) & 0xff;
return (h << 4) | (pos & 0xf);
}
// --- Helpers ---
uint SwizzleOffset(uvec2 pos) {
pos &= SWIZZLE_MASK;
return swizzle_table[pos.y * 64u + pos.x];
return SwizzleTable(pos.y * 64u + pos.x);
}
uvec4 ReadTexel(uint offset) {
@@ -1,3 +1,6 @@
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
@@ -56,10 +59,8 @@ UtilShaders::UtilShaders(ProgramManager& program_manager_)
copy_bc4_program(MakeProgram(OPENGL_COPY_BC4_COMP)),
convert_s8d24_program(MakeProgram(OPENGL_CONVERT_S8D24_COMP)),
convert_ms_to_nonms_program(MakeProgram(CONVERT_MSAA_TO_NON_MSAA_COMP)),
convert_nonms_to_ms_program(MakeProgram(CONVERT_NON_MSAA_TO_MSAA_COMP)) {
const auto swizzle_table = Tegra::Texture::MakeSwizzleTable();
swizzle_table_buffer.Create();
glNamedBufferStorage(swizzle_table_buffer.handle, sizeof(swizzle_table), &swizzle_table, 0);
convert_nonms_to_ms_program(MakeProgram(CONVERT_NON_MSAA_TO_MSAA_COMP))
{
}
UtilShaders::~UtilShaders() = default;
@@ -116,13 +117,11 @@ void UtilShaders::ASTCDecode(Image& image, const StagingBufferMap& map,
void UtilShaders::BlockLinearUpload2D(Image& image, const StagingBufferMap& map,
std::span<const SwizzleParameters> swizzles) {
static constexpr Extent3D WORKGROUP_SIZE{32, 32, 1};
static constexpr GLuint BINDING_SWIZZLE_BUFFER = 0;
static constexpr GLuint BINDING_INPUT_BUFFER = 1;
static constexpr GLuint BINDING_INPUT_BUFFER = 0;
static constexpr GLuint BINDING_OUTPUT_IMAGE = 0;
program_manager.BindComputeProgram(block_linear_unswizzle_2d_program.handle);
glFlushMappedNamedBufferRange(map.buffer, map.offset, image.guest_size_bytes);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, BINDING_SWIZZLE_BUFFER, swizzle_table_buffer.handle);
const GLenum store_format = StoreFormat(BytesPerBlock(image.info.format));
for (const SwizzleParameters& swizzle : swizzles) {
@@ -153,14 +152,11 @@ void UtilShaders::BlockLinearUpload2D(Image& image, const StagingBufferMap& map,
void UtilShaders::BlockLinearUpload3D(Image& image, const StagingBufferMap& map,
std::span<const SwizzleParameters> swizzles) {
static constexpr Extent3D WORKGROUP_SIZE{16, 8, 8};
static constexpr GLuint BINDING_SWIZZLE_BUFFER = 0;
static constexpr GLuint BINDING_INPUT_BUFFER = 1;
static constexpr GLuint BINDING_INPUT_BUFFER = 0;
static constexpr GLuint BINDING_OUTPUT_IMAGE = 0;
glFlushMappedNamedBufferRange(map.buffer, map.offset, image.guest_size_bytes);
program_manager.BindComputeProgram(block_linear_unswizzle_3d_program.handle);
glBindBufferBase(GL_SHADER_STORAGE_BUFFER, BINDING_SWIZZLE_BUFFER, swizzle_table_buffer.handle);
const GLenum store_format = StoreFormat(BytesPerBlock(image.info.format));
for (const SwizzleParameters& swizzle : swizzles) {
@@ -1,3 +1,6 @@
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
@@ -45,9 +48,6 @@ public:
private:
ProgramManager& program_manager;
OGLBuffer swizzle_table_buffer;
OGLProgram astc_decoder_program;
OGLProgram block_linear_unswizzle_2d_program;
OGLProgram block_linear_unswizzle_3d_program;
@@ -653,71 +653,8 @@ void ASTCDecoderPass::Assemble(Image& image, const StagingBufferRef& map,
scheduler.Finish();
}
constexpr u32 BL3D_BINDING_SWIZZLE_TABLE = 0;
constexpr u32 BL3D_BINDING_INPUT_BUFFER = 1;
constexpr u32 BL3D_BINDING_OUTPUT_BUFFER = 2;
constexpr std::array<VkDescriptorSetLayoutBinding, 3> BL3D_DESCRIPTOR_SET_BINDINGS{{
{
.binding = BL3D_BINDING_SWIZZLE_TABLE,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, // swizzle_table[]
.descriptorCount = 1,
.stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
.pImmutableSamplers = nullptr,
},
{
.binding = BL3D_BINDING_INPUT_BUFFER,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, // block-linear input
.descriptorCount = 1,
.stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
.pImmutableSamplers = nullptr,
},
{
.binding = BL3D_BINDING_OUTPUT_BUFFER,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
.descriptorCount = 1,
.stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
.pImmutableSamplers = nullptr,
},
}};
constexpr DescriptorBankInfo BL3D_BANK_INFO{
.uniform_buffers = 0,
.storage_buffers = 3,
.texture_buffers = 0,
.image_buffers = 0,
.textures = 0,
.images = 0,
.score = 3,
};
constexpr std::array<VkDescriptorUpdateTemplateEntry, 3>
BL3D_DESCRIPTOR_UPDATE_TEMPLATE_ENTRY{{
{
.dstBinding = BL3D_BINDING_SWIZZLE_TABLE,
.dstArrayElement = 0,
.descriptorCount = 1,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
.offset = BL3D_BINDING_SWIZZLE_TABLE * sizeof(DescriptorUpdateEntry),
.stride = sizeof(DescriptorUpdateEntry),
},
{
.dstBinding = BL3D_BINDING_INPUT_BUFFER,
.dstArrayElement = 0,
.descriptorCount = 1,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
.offset = BL3D_BINDING_INPUT_BUFFER * sizeof(DescriptorUpdateEntry),
.stride = sizeof(DescriptorUpdateEntry),
},
{
.dstBinding = BL3D_BINDING_OUTPUT_BUFFER,
.dstArrayElement = 0,
.descriptorCount = 1,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
.offset = BL3D_BINDING_OUTPUT_BUFFER * sizeof(DescriptorUpdateEntry),
.stride = sizeof(DescriptorUpdateEntry),
}
}};
constexpr u32 BL3D_BINDING_INPUT_BUFFER = 0;
constexpr u32 BL3D_BINDING_OUTPUT_BUFFER = 1;
struct alignas(16) BlockLinearUnswizzle3DPushConstants {
u32 blocks_dim[3]; // Offset 0
@@ -745,11 +682,50 @@ BlockLinearUnswizzle3DPass::BlockLinearUnswizzle3DPass(
DescriptorPool& descriptor_pool_,
StagingBufferPool& staging_buffer_pool_,
ComputePassDescriptorQueue& compute_pass_descriptor_queue_)
: ComputePass(
device_, scheduler_, descriptor_pool_,
BL3D_DESCRIPTOR_SET_BINDINGS,
BL3D_DESCRIPTOR_UPDATE_TEMPLATE_ENTRY,
BL3D_BANK_INFO,
: ComputePass(device_, scheduler_, descriptor_pool_,
std::array<VkDescriptorSetLayoutBinding, 2>{{
{
.binding = BL3D_BINDING_INPUT_BUFFER,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER, // block-linear input
.descriptorCount = 1,
.stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
.pImmutableSamplers = nullptr,
},
{
.binding = BL3D_BINDING_OUTPUT_BUFFER,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
.descriptorCount = 1,
.stageFlags = VK_SHADER_STAGE_COMPUTE_BIT,
.pImmutableSamplers = nullptr,
},
}},
std::array<VkDescriptorUpdateTemplateEntry, 2>{{
{
.dstBinding = BL3D_BINDING_INPUT_BUFFER,
.dstArrayElement = 0,
.descriptorCount = 1,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
.offset = BL3D_BINDING_INPUT_BUFFER * sizeof(DescriptorUpdateEntry),
.stride = sizeof(DescriptorUpdateEntry),
},
{
.dstBinding = BL3D_BINDING_OUTPUT_BUFFER,
.dstArrayElement = 0,
.descriptorCount = 1,
.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER,
.offset = BL3D_BINDING_OUTPUT_BUFFER * sizeof(DescriptorUpdateEntry),
.stride = sizeof(DescriptorUpdateEntry),
}
}},
DescriptorBankInfo{
.uniform_buffers = 0,
.storage_buffers = 2,
.texture_buffers = 0,
.image_buffers = 0,
.textures = 0,
.images = 0,
.score = 2,
},
COMPUTE_PUSH_CONSTANT_RANGE<sizeof(BlockLinearUnswizzle3DPushConstants)>,
BLOCK_LINEAR_UNSWIZZLE_3D_BCN_COMP_SPV),
scheduler{scheduler_},
@@ -822,8 +798,6 @@ void BlockLinearUnswizzle3DPass::UnswizzleChunk(
pc.blocks_dim[2] = z_count; // Only process the count
compute_pass_descriptor_queue.Acquire(scheduler, 3);
compute_pass_descriptor_queue.AddBuffer(*image.runtime->swizzle_table_buffer, 0,
image.runtime->swizzle_table_size);
compute_pass_descriptor_queue.AddBuffer(swizzled.buffer,
sw.buffer_offset + swizzled.offset,
image.guest_size_bytes - sw.buffer_offset);
@@ -909,40 +909,6 @@ TextureCacheRuntime::TextureCacheRuntime(const Device& device_, Scheduler& sched
bl3d_unswizzle_pass.emplace(device, scheduler, descriptor_pool,
staging_buffer_pool, compute_pass_descriptor_queue);
}
// --- Create swizzle table buffer ---
{
auto table = Tegra::Texture::MakeSwizzleTable();
swizzle_table_size = static_cast<VkDeviceSize>(table.size() * sizeof(table[0]));
auto staging = staging_buffer_pool.Request(swizzle_table_size, MemoryUsage::Upload);
std::memcpy(staging.mapped_span.data(), table.data(), static_cast<size_t>(swizzle_table_size));
VkBufferCreateInfo ci{
.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO,
.size = swizzle_table_size,
.usage = VK_BUFFER_USAGE_STORAGE_BUFFER_BIT |
VK_BUFFER_USAGE_TRANSFER_DST_BIT |
VK_BUFFER_USAGE_TRANSFER_SRC_BIT,
.sharingMode = VK_SHARING_MODE_EXCLUSIVE,
};
swizzle_table_buffer = memory_allocator.CreateBuffer(ci, MemoryUsage::DeviceLocal);
scheduler.RequestOutsideRenderPassOperationContext();
scheduler.Record([staging_buf = staging.buffer,
dst_buf = *swizzle_table_buffer,
size = swizzle_table_size,
src_off = staging.offset](vk::CommandBuffer cmdbuf) {
const VkBufferCopy region{
.srcOffset = src_off,
.dstOffset = 0,
.size = size,
};
cmdbuf.CopyBuffer(staging_buf, dst_buf, region);
});
}
}
void TextureCacheRuntime::Finish() {
@@ -2484,18 +2450,13 @@ void TextureCacheRuntime::AccelerateImageUpload(
if (!Settings::values.gpu_unswizzle_enabled.GetValue() || !bl3d_unswizzle_pass) {
if (IsPixelFormatBCn(image.info.format) && image.info.type == ImageType::e3D) {
ASSERT_MSG(false, "GPU unswizzle is disabled for BCn 3D texture");
ASSERT(false && "GPU unswizzle is disabled for BCn 3D texture");
}
ASSERT(false);
return;
}
if (bl3d_unswizzle_pass &&
IsPixelFormatBCn(image.info.format) &&
image.info.type == ImageType::e3D &&
image.info.resources.levels == 1 &&
image.info.resources.layers == 1) {
if (bl3d_unswizzle_pass && IsPixelFormatBCn(image.info.format) && image.info.type == ImageType::e3D && image.info.resources.levels == 1 && image.info.resources.layers == 1) {
return bl3d_unswizzle_pass->Unswizzle(image, map, swizzles, z_start, z_count);
}
@@ -1,4 +1,4 @@
// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2019 yuzu Emulator Project
@@ -130,9 +130,6 @@ public:
std::optional<ASTCDecoderPass> astc_decoder_pass;
std::optional<BlockLinearUnswizzle3DPass> bl3d_unswizzle_pass;
vk::Buffer swizzle_table_buffer;
VkDeviceSize swizzle_table_size = 0;
std::optional<MSAACopyPass> msaa_copy_pass;
const Settings::ResolutionScalingInfo& resolution;
std::array<std::vector<VkFormat>, VideoCore::Surface::MaxPixelFormat> view_formats;
+3 -18
View File
@@ -1,3 +1,6 @@
// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
@@ -23,24 +26,6 @@ constexpr u32 GOB_SIZE_SHIFT = GOB_SIZE_X_SHIFT + GOB_SIZE_Y_SHIFT + GOB_SIZE_Z_
constexpr u32 SWIZZLE_X_BITS = 0b100101111;
constexpr u32 SWIZZLE_Y_BITS = 0b011010000;
using SwizzleTable = std::array<std::array<u32, GOB_SIZE_X>, GOB_SIZE_Y>;
/**
* This table represents the internal swizzle of a gob, in format 16 bytes x 2 sector packing.
* Calculates the offset of an (x, y) position within a swizzled texture.
* Taken from the Tegra X1 Technical Reference Manual. pages 1187-1188
*/
constexpr SwizzleTable MakeSwizzleTable() {
SwizzleTable table{};
for (u32 y = 0; y < table.size(); ++y) {
for (u32 x = 0; x < table[0].size(); ++x) {
table[y][x] = ((x % 64) / 32) * 256 + ((y % 8) / 2) * 64 + ((x % 32) / 16) * 32 +
(y % 2) * 16 + (x % 16);
}
}
return table;
}
/// Unswizzles a block linear texture into linear memory.
void UnswizzleTexture(std::span<u8> output, std::span<const u8> input, u32 bytes_per_pixel,
u32 width, u32 height, u32 depth, u32 block_height, u32 block_depth,