XAudio2: Don't quit on failed CoInitializeEx()

It returns an error code when already initialized
Merge pull request #361 from Exzap/tweaks
2026-07-06 00:19:59 -07:00 · 2022-10-13 12:18:34 +02:00 · 2022-10-12 15:25:01 +02:00 · 2022-10-12 15:23:04 +02:00 · 2022-10-12 14:27:01 +02:00 · 2022-10-12 13:10:57 +02:00
98 changed files with 1685 additions and 467 deletions
@@ -30,9 +30,11 @@ bin/Cemu_*.ilk
 bin/Cemu.exe.backup
 bin/mlc01/*
 bin/settings.xml
+bin/network_services.xml
 bin/title_list_cache.xml
 bin/debugger/*
 bin/sdcard/*
+bin/screenshots/*

 !bin/shaderCache/info.txt
 bin/shaderCache/*
@@ -13,3 +13,6 @@
 [submodule "dependencies/Vulkan-Headers"]
 	path = dependencies/Vulkan-Headers
 	url = https://github.com/KhronosGroup/Vulkan-Headers
+[submodule "dependencies/imgui"]
+	path = dependencies/imgui
+	url = https://github.com/ocornut/imgui
@@ -33,7 +33,7 @@ To compile Cemu, a recent enough compiler and STL with C++20 support is required
   `cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DCMAKE_C_COMPILER=/usr/bin/clang-12 -DCMAKE_CXX_COMPILER=/usr/bin/clang++-12 -G Ninja -DCMAKE_MAKE_PROGRAM=/usr/bin/ninja`

 #### For Arch and derivatives:
-`sudo pacman -S git cmake clang ninja nasm base-devel linux-headers gtk3 libsecret libgcrypt systemd freeglut zip unzip libpulse`
+`sudo pacman -S --needed git cmake llvm clang ninja nasm base-devel linux-headers gtk3 libsecret libgcrypt systemd freeglut zip unzip libpulse`

 #### For Fedora and derivatives:
 `sudo dnf install git cmake clang ninja-build nasm kernel-headers gtk3-devel libsecret-devel libgcrypt-devel systemd-devel freeglut-devel perl-core zlib-devel cubeb-devel`
@@ -65,7 +65,10 @@ To compile Cemu, a recent enough compiler and STL with C++20 support is required
 below, built in LLVM, and Xcode LLVM don't support the C++20 feature set required. Currently, 
 LLVM 15 isn't supported due to compatibility issues with Boost dependency. The OpenGL graphics
 API isn't support on MacOS, Vulkan must be used. Additionally Vulkan must be used through the 
-Molten-VK compatibility layer.
+Molten-VK compatibility layer.  
+
+### Installing brew
+`/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"`

 ### Installing dependencies
 `brew install git cmake llvm@14 ninja nasm molten-vk`
@@ -73,7 +76,7 @@ Molten-VK compatibility layer.
 ### Build Cemu using cmake and clang
 1. `git clone --recursive https://github.com/cemu-project/Cemu`
 2. `cd Cemu`
-3. `cmake -S . -B build -DCMAKE_BUILD_TYPE=release -DPUBLIC_RELEASE=ON 
+3. `cmake -S . -B build -DCMAKE_BUILD_TYPE=release
   -DCMAKE_C_COMPILER=/usr/local/opt/llvm@14/bin/clang -DCMAKE_CXX_COMPILER=/usr/local/opt/llvm@14/bin/clang++ -G Ninja`
 4. `cmake --build build`
 5. You should now have a Cemu executable file in the /bin folder, which you can run using `./bin/Cemu_release`.
@@ -1,6 +1,7 @@
 cmake_minimum_required(VERSION 3.21.1)

 option(ENABLE_VCPKG "Enable the vcpkg package manager" ON)
+option(PORTABLE "All data created and maintained by Cemu will be in the directory where the executable file is located" ON)
 set(EXPERIMENTAL_VERSION "" CACHE STRING "") # used by CI script to set experimental version

 if (EXPERIMENTAL_VERSION)
@@ -30,6 +31,10 @@ set(CMAKE_EXPORT_COMPILE_COMMANDS ON)

 add_compile_definitions($<$<CONFIG:Debug>:CEMU_DEBUG_ASSERT>) # if build type is debug, set CEMU_DEBUG_ASSERT

+if(PORTABLE)
+	add_compile_definitions(PORTABLE)
+endif()
+
 set_property(GLOBAL PROPERTY USE_FOLDERS ON)

 # enable link time optimization for release builds
@@ -83,7 +88,6 @@ find_package(Threads REQUIRED)
 find_package(SDL2 REQUIRED)
 find_package(CURL REQUIRED)
 find_package(pugixml REQUIRED)
-find_package(imgui REQUIRED)
 find_package(RapidJSON REQUIRED)
 find_package(Boost COMPONENTS program_options filesystem nowide REQUIRED)
 find_package(libzip REQUIRED)
@@ -6,10 +6,6 @@ set(LIBAVCDEC_X86_INCLUDES "common/x86" "decoder/x86")

 include_directories("common/" "decoder/" ${LIBAVCDEC_X86_INCLUDES})

-if((CMAKE_C_COMPILER_ID MATCHES "GNU") OR (CMAKE_C_COMPILER_ID MATCHES "Clang"))
-	add_compile_options(-mssse3 -mavx2)
-endif()
-
 add_library (ih264d 
 "common/ih264_buf_mgr.c"
 "common/ih264_buf_mgr.h"
@@ -56,6 +56,11 @@
 #include "ih264_platform_macros.h"
 #include "ih264_intra_pred_filters.h"

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif

 /*****************************************************************************/
 /* Chroma Intra prediction 8x8 filters                                       */
@@ -93,6 +98,8 @@
 *
 ******************************************************************************
 */
+
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_chroma_8x8_mode_horz_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -169,6 +176,8 @@ void ih264_intra_pred_chroma_8x8_mode_horz_ssse3(UWORD8 *pu1_src,
 *
 *******************************************************************************
 */
+
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_chroma_8x8_mode_vert_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -237,6 +246,8 @@ void ih264_intra_pred_chroma_8x8_mode_vert_ssse3(UWORD8 *pu1_src,
 *
 ******************************************************************************
 */
+
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_chroma_8x8_mode_plane_ssse3(UWORD8 *pu1_src,
                                                  UWORD8 *pu1_dst,
                                                  WORD32 src_strd,
@@ -53,6 +53,12 @@
 #include "ih264_deblk_edge_filters.h"
 #include "ih264_macros.h"

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif
+
 /*****************************************************************************/
 /* Function Definitions                                                      */
 /*****************************************************************************/
@@ -91,6 +97,8 @@
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+
+ATTRIBUTE_SSSE3
 void ih264_deblk_chroma_vert_bs4_ssse3(UWORD8 *pu1_src,
                                       WORD32 src_strd,
                                       WORD32 alpha_cb,
@@ -274,6 +282,8 @@ void ih264_deblk_chroma_vert_bs4_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+
+ATTRIBUTE_SSSE3
 void ih264_deblk_chroma_horz_bs4_ssse3(UWORD8 *pu1_src,
                                       WORD32 src_strd,
                                       WORD32 alpha_cb,
@@ -424,6 +434,8 @@ void ih264_deblk_chroma_horz_bs4_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+
+ATTRIBUTE_SSSE3
 void ih264_deblk_chroma_vert_bslt4_ssse3(UWORD8 *pu1_src,
                                         WORD32 src_strd,
                                         WORD32 alpha_cb,
@@ -645,6 +657,8 @@ void ih264_deblk_chroma_vert_bslt4_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+
+ATTRIBUTE_SSSE3
 void ih264_deblk_chroma_horz_bslt4_ssse3(UWORD8 *pu1_src,
                                         WORD32 src_strd,
                                         WORD32 alpha_cb,
@@ -829,6 +843,8 @@ void ih264_deblk_chroma_horz_bslt4_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+
+ATTRIBUTE_SSSE3
 void ih264_deblk_chroma_vert_bs4_mbaff_ssse3(UWORD8 *pu1_src,
                                             WORD32 src_strd,
                                             WORD32 alpha_cb,
@@ -963,6 +979,8 @@ void ih264_deblk_chroma_vert_bs4_mbaff_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+
+ATTRIBUTE_SSSE3
 void ih264_deblk_chroma_vert_bslt4_mbaff_ssse3(UWORD8 *pu1_src,
                                               WORD32 src_strd,
                                               WORD32 alpha_cb,
@@ -53,6 +53,12 @@
 #include "ih264_deblk_edge_filters.h"
 #include "ih264_macros.h"

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif
+
 /*****************************************************************************/
 /* Function Definitions                                                      */
 /*****************************************************************************/
@@ -87,6 +93,7 @@
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_deblk_luma_vert_bs4_ssse3(UWORD8 *pu1_src,
                                     WORD32 src_strd,
                                     WORD32 alpha,
@@ -508,6 +515,7 @@ void ih264_deblk_luma_vert_bs4_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_deblk_luma_horz_bs4_ssse3(UWORD8 *pu1_src,
                                     WORD32 src_strd,
                                     WORD32 alpha,
@@ -847,6 +855,7 @@ void ih264_deblk_luma_horz_bs4_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_deblk_luma_vert_bslt4_ssse3(UWORD8 *pu1_src,
                                       WORD32 src_strd,
                                       WORD32 alpha,
@@ -1142,6 +1151,7 @@ void ih264_deblk_luma_vert_bslt4_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_deblk_luma_horz_bslt4_ssse3(UWORD8 *pu1_src,
                                       WORD32 src_strd,
                                       WORD32 alpha,
@@ -1439,6 +1449,7 @@ void ih264_deblk_luma_horz_bslt4_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_deblk_luma_vert_bs4_mbaff_ssse3(UWORD8 *pu1_src,
                                           WORD32 src_strd,
                                           WORD32 alpha,
@@ -1758,6 +1769,7 @@ void ih264_deblk_luma_vert_bs4_mbaff_ssse3(UWORD8 *pu1_src,
 /*         12 02 2015   Naveen Kumar P  Initial version                      */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_deblk_luma_vert_bslt4_mbaff_ssse3(UWORD8 *pu1_src,
                                             WORD32 src_strd,
                                             WORD32 alpha,
@@ -52,6 +52,12 @@
 #include <immintrin.h>
 #include <smmintrin.h>

+#ifdef __GNUC__
+#define ATTRIBUTE_SSE42 __attribute__((target("sse4.2")))
+#else
+#define ATTRIBUTE_SSE42
+#endif
+
 /*
 ********************************************************************************
 *
@@ -87,6 +93,7 @@
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSE42
 void ih264_ihadamard_scaling_4x4_sse42(WORD16* pi2_src,
                                       WORD16* pi2_out,
                                       const UWORD16 *pu2_iscal_mat,
@@ -202,6 +209,7 @@ void ih264_ihadamard_scaling_4x4_sse42(WORD16* pi2_src,
    _mm_storeu_si128((__m128i *) (&pi2_out[8]), src_r2_r3);
 }

+ATTRIBUTE_SSE42
 void ih264_ihadamard_scaling_2x2_uv_sse42(WORD16* pi2_src,
                                          WORD16* pi2_out,
                                          const UWORD16 *pu2_iscal_mat,
@@ -50,6 +50,12 @@
 #include "ih264_trans_quant_itrans_iquant.h"
 #include <immintrin.h>

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif
+
 /*
 ********************************************************************************
 *
@@ -85,6 +91,7 @@
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSSE3
 void ih264_ihadamard_scaling_4x4_ssse3(WORD16* pi2_src,
                                       WORD16* pi2_out,
                                       const UWORD16 *pu2_iscal_mat,
@@ -54,6 +54,12 @@
 #include "ih264_platform_macros.h"
 #include "ih264_inter_pred_filters.h"

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif
+
 /*****************************************************************************/
 /* Constant Data variables                                                   */
 /*****************************************************************************/
@@ -87,6 +93,7 @@
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_luma_copy_ssse3(UWORD8 *pu1_src,
                                      UWORD8 *pu1_dst,
                                      WORD32 src_strd,
@@ -213,6 +220,7 @@ void ih264_inter_pred_luma_copy_ssse3(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_luma_horz_ssse3(UWORD8 *pu1_src,
                                      UWORD8 *pu1_dst,
                                      WORD32 src_strd,
@@ -478,6 +486,7 @@ void ih264_inter_pred_luma_horz_ssse3(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_luma_vert_ssse3(UWORD8 *pu1_src,
                                      UWORD8 *pu1_dst,
                                      WORD32 src_strd,
@@ -764,6 +773,7 @@ void ih264_inter_pred_luma_vert_ssse3(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_luma_horz_hpel_vert_hpel_ssse3(UWORD8 *pu1_src,
                                                     UWORD8 *pu1_dst,
                                                     WORD32 src_strd,
@@ -1488,6 +1498,7 @@ void ih264_inter_pred_luma_horz_hpel_vert_hpel_ssse3(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_luma_horz_qpel_ssse3(UWORD8 *pu1_src,
                                           UWORD8 *pu1_dst,
                                           WORD32 src_strd,
@@ -1782,6 +1793,7 @@ void ih264_inter_pred_luma_horz_qpel_ssse3(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_luma_vert_qpel_ssse3(UWORD8 *pu1_src,
                                           UWORD8 *pu1_dst,
                                           WORD32 src_strd,
@@ -2107,6 +2119,7 @@ void ih264_inter_pred_luma_vert_qpel_ssse3(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_luma_horz_qpel_vert_qpel_ssse3(UWORD8 *pu1_src,
                                                     UWORD8 *pu1_dst,
                                                     WORD32 src_strd,
@@ -2675,6 +2688,7 @@ void ih264_inter_pred_luma_horz_qpel_vert_qpel_ssse3(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_luma_horz_qpel_vert_hpel_ssse3(UWORD8 *pu1_src,
                                                     UWORD8 *pu1_dst,
                                                     WORD32 src_strd,
@@ -3285,6 +3299,7 @@ void ih264_inter_pred_luma_horz_qpel_vert_hpel_ssse3(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_luma_horz_hpel_vert_qpel_ssse3(UWORD8 *pu1_src,
                                                     UWORD8 *pu1_dst,
                                                     WORD32 src_strd,
@@ -3991,6 +4006,7 @@ void ih264_inter_pred_luma_horz_hpel_vert_qpel_ssse3(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_inter_pred_chroma_ssse3(UWORD8 *pu1_src,
                                   UWORD8 *pu1_dst,
                                   WORD32 src_strd,
@@ -50,6 +50,12 @@
 #include "ih264_trans_quant_itrans_iquant.h"
 #include <immintrin.h>

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif
+
 /*
 ********************************************************************************
 *
@@ -98,6 +104,7 @@
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSSE3
 void ih264_iquant_itrans_recon_4x4_dc_ssse3(WORD16 *pi2_src,
                                   UWORD8 *pu1_pred,
                                   UWORD8 *pu1_out,
@@ -224,6 +231,7 @@ void ih264_iquant_itrans_recon_4x4_dc_ssse3(WORD16 *pi2_src,
 *******************************************************************************
 */

+ATTRIBUTE_SSSE3
 void ih264_iquant_itrans_recon_8x8_dc_ssse3 (WORD16 *pi2_src,
                                         UWORD8 *pu1_pred,
                                         UWORD8 *pu1_out,
@@ -385,6 +393,7 @@ void ih264_iquant_itrans_recon_8x8_dc_ssse3 (WORD16 *pi2_src,
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSSE3
 void ih264_iquant_itrans_recon_chroma_4x4_dc_ssse3(WORD16 *pi2_src,
                                   UWORD8 *pu1_pred,
                                   UWORD8 *pu1_out,
@@ -50,6 +50,12 @@
 #include "ih264_trans_quant_itrans_iquant.h"
 #include <immintrin.h>

+#ifdef __GNUC__
+#define ATTRIBUTE_SSE42 __attribute__((target("sse4.2")))
+#else
+#define ATTRIBUTE_SSE42
+#endif
+
 /*
 ********************************************************************************
 *
@@ -97,6 +103,7 @@
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSE42
 void ih264_iquant_itrans_recon_4x4_sse42(WORD16 *pi2_src,
                                   UWORD8 *pu1_pred,
                                   UWORD8 *pu1_out,
@@ -348,6 +355,7 @@ void ih264_iquant_itrans_recon_4x4_sse42(WORD16 *pi2_src,
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSE42
 void ih264_iquant_itrans_recon_chroma_4x4_sse42(WORD16 *pi2_src,
                                   UWORD8 *pu1_pred,
                                   UWORD8 *pu1_out,
@@ -50,6 +50,12 @@
 #include "ih264_trans_quant_itrans_iquant.h"
 #include <immintrin.h>

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif
+
 /*
 ********************************************************************************
 *
@@ -97,6 +103,7 @@
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSSE3
 void ih264_iquant_itrans_recon_4x4_ssse3(WORD16 *pi2_src,
                                         UWORD8 *pu1_pred,
                                         UWORD8 *pu1_out,
@@ -366,6 +373,7 @@ void ih264_iquant_itrans_recon_4x4_ssse3(WORD16 *pi2_src,
 *******************************************************************************
 */

+ATTRIBUTE_SSSE3
 void ih264_iquant_itrans_recon_8x8_ssse3(WORD16 *pi2_src,
                                         UWORD8 *pu1_pred,
                                         UWORD8 *pu1_out,
@@ -75,6 +75,12 @@
 #include "ih264_platform_macros.h"
 #include "ih264_intra_pred_filters.h"

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif
+


 /*******************    LUMA INTRAPREDICTION    *******************/
@@ -114,6 +120,7 @@
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_4x4_mode_vert_ssse3(UWORD8 *pu1_src,
                                               UWORD8 *pu1_dst,
                                               WORD32 src_strd,
@@ -173,6 +180,7 @@ void ih264_intra_pred_luma_4x4_mode_vert_ssse3(UWORD8 *pu1_src,
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_4x4_mode_horz_ssse3(UWORD8 *pu1_src,
                                               UWORD8 *pu1_dst,
                                               WORD32 src_strd,
@@ -238,6 +246,7 @@ void ih264_intra_pred_luma_4x4_mode_horz_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_4x4_mode_dc_ssse3(UWORD8 *pu1_src,
                                             UWORD8 *pu1_dst,
                                             WORD32 src_strd,
@@ -316,6 +325,7 @@ void ih264_intra_pred_luma_4x4_mode_dc_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_4x4_mode_diag_dl_ssse3(UWORD8 *pu1_src,
                                                  UWORD8 *pu1_dst,
                                                  WORD32 src_strd,
@@ -400,6 +410,7 @@ void ih264_intra_pred_luma_4x4_mode_diag_dl_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_4x4_mode_diag_dr_ssse3(UWORD8 *pu1_src,
                                                  UWORD8 *pu1_dst,
                                                  WORD32 src_strd,
@@ -487,6 +498,7 @@ void ih264_intra_pred_luma_4x4_mode_diag_dr_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_4x4_mode_vert_r_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -579,6 +591,7 @@ void ih264_intra_pred_luma_4x4_mode_vert_r_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_4x4_mode_horz_d_ssse3(UWORD8 *pu1_src,
                                           UWORD8 *pu1_dst,
                                           WORD32 src_strd,
@@ -675,6 +688,7 @@ void ih264_intra_pred_luma_4x4_mode_horz_d_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_4x4_mode_vert_l_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -764,6 +778,7 @@ void ih264_intra_pred_luma_4x4_mode_vert_l_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_4x4_mode_horz_u_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -864,6 +879,7 @@ void ih264_intra_pred_luma_4x4_mode_horz_u_ssse3(UWORD8 *pu1_src,
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_8x8_mode_vert_ssse3(UWORD8 *pu1_src,
                                               UWORD8 *pu1_dst,
                                               WORD32 src_strd,
@@ -921,6 +937,7 @@ void ih264_intra_pred_luma_8x8_mode_vert_ssse3(UWORD8 *pu1_src,
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_8x8_mode_horz_ssse3(UWORD8 *pu1_src,
                                               UWORD8 *pu1_dst,
                                               WORD32 src_strd,
@@ -985,6 +1002,7 @@ void ih264_intra_pred_luma_8x8_mode_horz_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_8x8_mode_dc_ssse3(UWORD8 *pu1_src,
                                             UWORD8 *pu1_dst,
                                             WORD32 src_strd,
@@ -1078,6 +1096,7 @@ void ih264_intra_pred_luma_8x8_mode_dc_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_8x8_mode_diag_dl_ssse3(UWORD8 *pu1_src,
                                                  UWORD8 *pu1_dst,
                                                  WORD32 src_strd,
@@ -1176,6 +1195,7 @@ void ih264_intra_pred_luma_8x8_mode_diag_dl_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_8x8_mode_diag_dr_ssse3(UWORD8 *pu1_src,
                                                  UWORD8 *pu1_dst,
                                                  WORD32 src_strd,
@@ -1278,6 +1298,7 @@ void ih264_intra_pred_luma_8x8_mode_diag_dr_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_8x8_mode_vert_r_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -1398,6 +1419,7 @@ void ih264_intra_pred_luma_8x8_mode_vert_r_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_8x8_mode_horz_d_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -1502,6 +1524,7 @@ void ih264_intra_pred_luma_8x8_mode_horz_d_ssse3(UWORD8 *pu1_src,
 *
 *******************************************************************************/

+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_8x8_mode_vert_l_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -1598,6 +1621,7 @@ void ih264_intra_pred_luma_8x8_mode_vert_l_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_8x8_mode_horz_u_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -1699,6 +1723,7 @@ void ih264_intra_pred_luma_8x8_mode_horz_u_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_16x16_mode_vert_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -1778,6 +1803,7 @@ void ih264_intra_pred_luma_16x16_mode_vert_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_16x16_mode_horz_ssse3(UWORD8 *pu1_src,
                                                 UWORD8 *pu1_dst,
                                                 WORD32 src_strd,
@@ -1875,6 +1901,7 @@ void ih264_intra_pred_luma_16x16_mode_horz_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_16x16_mode_dc_ssse3(UWORD8 *pu1_src,
                                               UWORD8 *pu1_dst,
                                               WORD32 src_strd,
@@ -1998,6 +2025,7 @@ void ih264_intra_pred_luma_16x16_mode_dc_ssse3(UWORD8 *pu1_src,
 *  None
 *
 *******************************************************************************/
+ATTRIBUTE_SSSE3
 void ih264_intra_pred_luma_16x16_mode_plane_ssse3(UWORD8 *pu1_src,
                                                  UWORD8 *pu1_dst,
                                                  WORD32 src_strd,
@@ -50,6 +50,12 @@

 #include <immintrin.h>

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif
+
 /**
 *******************************************************************************
 *
@@ -78,6 +84,7 @@



+ATTRIBUTE_SSSE3
 void ih264_memcpy_mul_8_ssse3(UWORD8 *pu1_dst, UWORD8 *pu1_src, UWORD32 num_bytes)
 {
    int col;
@@ -117,6 +124,7 @@ void ih264_memcpy_mul_8_ssse3(UWORD8 *pu1_dst, UWORD8 *pu1_src, UWORD32 num_byte
 */


+ATTRIBUTE_SSSE3
 void ih264_memset_mul_8_ssse3(UWORD8 *pu1_dst, UWORD8 value, UWORD32 num_bytes)
 {
    int col;
@@ -49,6 +49,12 @@

 #include <immintrin.h>

+#ifdef __GNUC__
+#define ATTRIBUTE_SSSE3 __attribute__((target("ssse3")))
+#else
+#define ATTRIBUTE_SSSE3
+#endif
+

 /**
 *******************************************************************************
@@ -89,6 +95,7 @@
 *******************************************************************************
 */

+ATTRIBUTE_SSSE3
 void ih264_pad_left_luma_ssse3(UWORD8 *pu1_src,
                               WORD32 src_strd,
                               WORD32 ht,
@@ -156,6 +163,7 @@ void ih264_pad_left_luma_ssse3(UWORD8 *pu1_src,
 *******************************************************************************
 */

+ATTRIBUTE_SSSE3
 void ih264_pad_left_chroma_ssse3(UWORD8 *pu1_src,
                                 WORD32 src_strd,
                                 WORD32 ht,
@@ -222,6 +230,7 @@ void ih264_pad_left_chroma_ssse3(UWORD8 *pu1_src,
 *******************************************************************************
 */

+ATTRIBUTE_SSSE3
 void ih264_pad_right_luma_ssse3(UWORD8 *pu1_src,
                                WORD32 src_strd,
                                WORD32 ht,
@@ -289,6 +298,7 @@ void ih264_pad_right_luma_ssse3(UWORD8 *pu1_src,
 *******************************************************************************
 */

+ATTRIBUTE_SSSE3
 void ih264_pad_right_chroma_ssse3(UWORD8 *pu1_src,
                                  WORD32 src_strd,
                                  WORD32 ht,
@@ -51,6 +51,12 @@
 #include "ih264_structs.h"
 #include "ih264_trans_quant_itrans_iquant.h"
 #include <immintrin.h>
+
+#ifdef __GNUC__
+#define ATTRIBUTE_SSE42 __attribute__((target("sse4.2")))
+#else
+#define ATTRIBUTE_SSE42
+#endif
 /**
 *******************************************************************************
 *
@@ -103,6 +109,7 @@
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSE42
 void ih264_resi_trans_quant_4x4_sse42(UWORD8 *pu1_src, UWORD8 *pu1_pred,
                                      WORD16 *pi2_out, WORD32 src_strd, WORD32 pred_strd,
                                      const UWORD16 *pu2_scale_matrix, const UWORD16 *pu2_threshold_matrix,
@@ -376,6 +383,7 @@ void ih264_resi_trans_quant_4x4_sse42(UWORD8 *pu1_src, UWORD8 *pu1_pred,
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSE42
 void ih264_resi_trans_quant_chroma_4x4_sse42(UWORD8 *pu1_src,UWORD8 *pu1_pred,WORD16 *pi2_out,
                                            WORD32 src_strd,WORD32 pred_strd,
                                            const UWORD16 *pu2_scale_matrix,
@@ -663,6 +671,7 @@ void ih264_resi_trans_quant_chroma_4x4_sse42(UWORD8 *pu1_src,UWORD8 *pu1_pred,WO
 *
 */

+ATTRIBUTE_SSE42
 void ih264_hadamard_quant_4x4_sse42(WORD16 *pi2_src, WORD16 *pi2_dst,
                          const UWORD16 *pu2_scale_matrix,
                          const UWORD16 *pu2_threshold_matrix, UWORD32 u4_qbits,
@@ -892,6 +901,7 @@ void ih264_hadamard_quant_4x4_sse42(WORD16 *pi2_src, WORD16 *pi2_dst,
 *
 */

+ATTRIBUTE_SSE42
 void ih264_hadamard_quant_2x2_uv_sse42(WORD16 *pi2_src, WORD16 *pi2_dst,
                            const UWORD16 *pu2_scale_matrix,
                            const UWORD16 *pu2_threshold_matrix, UWORD32 u4_qbits,
@@ -50,6 +50,12 @@
 #include "ih264_platform_macros.h"
 #include "ih264_weighted_pred.h"

+#ifdef __GNUC__
+#define ATTRIBUTE_SSE42 __attribute__((target("sse4.2")))
+#else
+#define ATTRIBUTE_SSE42
+#endif
+
 /*****************************************************************************/
 /*  Function definitions .                                                   */
 /*****************************************************************************/
@@ -82,6 +88,7 @@
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSE42
 void ih264_default_weighted_pred_luma_sse42(UWORD8 *pu1_src1,
                                            UWORD8 *pu1_src2,
                                            UWORD8 *pu1_dst,
@@ -245,6 +252,7 @@ void ih264_default_weighted_pred_luma_sse42(UWORD8 *pu1_src1,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSE42
 void ih264_default_weighted_pred_chroma_sse42(UWORD8 *pu1_src1,
                                              UWORD8 *pu1_src2,
                                              UWORD8 *pu1_dst,
@@ -375,6 +383,7 @@ void ih264_default_weighted_pred_chroma_sse42(UWORD8 *pu1_src1,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSE42
 void ih264_weighted_pred_luma_sse42(UWORD8 *pu1_src,
                                    UWORD8 *pu1_dst,
                                    WORD32 src_strd,
@@ -605,6 +614,7 @@ void ih264_weighted_pred_luma_sse42(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSE42
 void ih264_weighted_pred_chroma_sse42(UWORD8 *pu1_src,
                                      UWORD8 *pu1_dst,
                                      WORD32 src_strd,
@@ -814,6 +824,7 @@ void ih264_weighted_pred_chroma_sse42(UWORD8 *pu1_src,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSE42
 void ih264_weighted_bi_pred_luma_sse42(UWORD8 *pu1_src1,
                                       UWORD8 *pu1_src2,
                                       UWORD8 *pu1_dst,
@@ -1101,6 +1112,7 @@ void ih264_weighted_bi_pred_luma_sse42(UWORD8 *pu1_src1,
 /*                      Senthoor                                             */
 /*                                                                           */
 /*****************************************************************************/
+ATTRIBUTE_SSE42
 void ih264_weighted_bi_pred_chroma_sse42(UWORD8 *pu1_src1,
                                         UWORD8 *pu1_src2,
                                         UWORD8 *pu1_dst,
@@ -60,6 +60,12 @@

 #include "ih264d_structs.h"

+#ifdef __GNUC__
+#define ATTRIBUTE_SSE42 __attribute__((target("sse4.2")))
+#else
+#define ATTRIBUTE_SSE42
+#endif
+

 /**
 *******************************************************************************
@@ -79,6 +85,7 @@
 *
 *******************************************************************************
 */
+ATTRIBUTE_SSE42
 void ih264d_init_function_ptr_sse42(dec_struct_t *ps_codec)
 {
    ps_codec->pf_default_weighted_pred_luma = ih264_default_weighted_pred_luma_sse42;
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Exzap	d251ce07e0	XAudio2: Don't quit on failed CoInitializeEx() It returns an error code when already initialized	2022-10-13 12:18:34 +02:00
ExzapandGitHub	f42bebd196	Merge pull request #361 from Exzap/tweaks Fix encoding error in input profiles + update metainfo	2022-10-12 15:25:01 +02:00
Exzap	0412dec078	Fix metainfo Comment out vcs-browser url type for now. It's a pretty recent addition to the standard and is considered an error by some older utilities	2022-10-12 15:23:04 +02:00
Exzap	f65dbe8437	Fix encoding error in input profile filenames - Controller profile filenames now encode unicode characters correctly - Removed dependency on boost::filesystem. There is still an indirect dependency on it from another boost module it seems - Refactored some code to use FileStream instead of ifstream/ofstream	2022-10-12 14:27:01 +02:00
SSimcoandGitHub	8b3f36ad50	Use correct preprocessor check for Linux (#360 )	2022-10-12 13:10:57 +02:00
SSimcoandGitHub	d6ba61cf64	Add support for non portable mode (#356 )	2022-10-12 08:03:26 +02:00
ExzapandGitHub	2b9edced81	Minor tweaks and code clean up (#357 )	2022-10-11 09:17:34 +02:00
MythicalPlayzandGitHub	b07e9efba4	Add support for choosing network service (incl Pretendo+Custom) (#302 )	2022-10-11 04:04:47 +02:00
ExzapandGitHub	52cc7c5996	Follow imgui recommendation and streamline build dependencies (#355 )	2022-10-11 01:43:15 +02:00
goeiecool9999andGitHub	431c5a101f	Linux: Print demangled symbols on backtrace (#312 )	2022-10-10 02:35:04 +02:00
TillsunsetandGitHub	0c9fb3143f	memory optimization, using posix_memalign (#350 )	2022-10-09 10:43:45 +02:00
TillsunsetandGitHub	638e9e1f87	Workaround for the h264 video crash on macOS (#348 )	2022-10-09 08:45:26 +02:00
TillsunsetandGitHub	b724a657e6	MoltenVk: Add missing texture decoders (#332 )	2022-10-08 15:07:54 +02:00
bslhqandGitHub	551f821109	Auto resize last column (#265 )	2022-10-07 14:30:06 +02:00
emiylandGitHub	00968acc1d	dedicated decoder for R4G4 and R4G4B4A4 to R8G8B8A8 (#331 )	2022-10-07 02:39:06 +02:00
emiylandGitHub	4519a59d74	[ih264] per-function target attribute on clang and GCC (#328 )	2022-10-04 15:24:14 +02:00
purofleandGitHub	8a0fe21589	[docs] add `--needed` in ArchLinux dependencies (#324 )	2022-10-03 13:05:42 +02:00
TillsunsetandGitHub	fb5ecca157	Vulkan: Use correct texture clear in LatteDraw_handleSpecialState8_clearAsDepth (#321 )	2022-10-02 19:18:35 +02:00
TillsunsetandGitHub	11f6e2b7ee	Vulkan: Implement texture decoder for R5G6B5_UNORM to R8G8B8A8_UNORM (#320 )	2022-10-02 01:48:13 +02:00
emiylandGitHub	9541c8ae85	MoltenVk: Workaround for unsupported format R5_G6_B5_UNORM (#318 )	2022-09-30 18:07:00 +02:00
ExzapandGitHub	cceb4f6d0e	Vulkan: Always disable blending for integer formats (#317 ) Should fix a warning in the Vulkan validation layer and avoid a sigtrap in MoltenVk	2022-09-30 15:59:16 +02:00
emiylandGitHub	ecfbbd4e26	MoltenVK: Workaround for unsupported formats (#315 )	2022-09-30 15:28:56 +02:00
Narr the RegandGitHub	3767257220	nfp: Fix corruption, correct structs and use write counters (#310 )	2022-09-29 13:00:46 +02:00
TillsunsetandGitHub	3fb4b5e26c	MacOS+Linux: Use CLOCK_MONOTONIC_RAW over CLOCK_MONOTONIC (#313 ) On MacOS this fixes the framerate being too high due to discontinuities in the timer that drives the emulated vsync. It also fixes behavior of the GetTickCount() wrapper.	2022-09-29 11:36:27 +02:00
UltraHDRandGitHub	a28d67bafd	Remove -DPUBLIC_RELEASE=ON from macOS command (#309 )	2022-09-27 22:18:35 +02:00
goeiecool9999andGitHub	6ecc4be0da	Posix/Linux: Add setting to disable coredumps	2022-09-27 13:58:50 +02:00
goeiecool9999andGitHub	35afb99c99	[docs] Add llvm as a required package for Arch Linux (#308 )	2022-09-27 12:48:35 +02:00
SSimcoandGitHub	25dae98ce0	Fix crash on GTK when a gfx pack preset value is changed (#300 )	2022-09-26 07:53:10 +02:00
emiylandGitHub	53c7daa603	[docs] Add brew installation instructions for macos (#303 )	2022-09-25 21:38:31 +02:00