Release 1.0.15

* Several functions optimized for AVX-512 support. * Fixed several issues reported by PVS Studio static analyzer. * Fixed syntax error in C interface, covered with tests. * Bugfix in horizontal summing functions (invalid register clobber list). * Some AMD-related optimizations. * Updated module versions in dependencies.
lsp-plugins · Sep 9, 2023 · a6f91e4 · a6f91e4
2 parents 65b5724 + 478e851
commit a6f91e4
Show file tree

Hide file tree

Showing 65 changed files with 4,127 additions and 690 deletions.
diff --git a/.cproject b/.cproject
@@ -30,6 +30,7 @@
 								</option>
 								<option IS_BUILTIN_EMPTY="false" IS_VALUE_EMPTY="false" id="gnu.cpp.compiler.option.preprocessor.def.368930916" name="Defined symbols (-D)" superClass="gnu.cpp.compiler.option.preprocessor.def" useByScannerDiscovery="false" valueType="definedSymbols">
 									<listOptionValue builtIn="false" value="LSP_TESTING"/>
+									<listOptionValue builtIn="false" value="LSP_IDE_DEBUG"/>
 								</option>
 								<option id="gnu.cpp.compiler.option.dialect.std.380024909" name="Language standard" superClass="gnu.cpp.compiler.option.dialect.std" useByScannerDiscovery="true" value="gnu.cpp.compiler.dialect.c++11" valueType="enumerated"/>
 								<inputType id="cdt.managedbuild.tool.gnu.cpp.compiler.input.424525884" superClass="cdt.managedbuild.tool.gnu.cpp.compiler.input"/>
@@ -44,6 +45,7 @@
 								</option>
 								<option IS_BUILTIN_EMPTY="false" IS_VALUE_EMPTY="false" id="gnu.c.compiler.option.preprocessor.def.symbols.1421051177" name="Defined symbols (-D)" superClass="gnu.c.compiler.option.preprocessor.def.symbols" useByScannerDiscovery="false" valueType="definedSymbols">
 									<listOptionValue builtIn="false" value="LSP_TESTING"/>
+									<listOptionValue builtIn="false" value="LSP_IDE_DEBUG"/>
 								</option>
 								<inputType id="cdt.managedbuild.tool.gnu.c.compiler.input.2008435369" superClass="cdt.managedbuild.tool.gnu.c.compiler.input"/>
 							</tool>
@@ -85,6 +87,18 @@
 							<outputType id="org.eclipse.cdt.managedbuilder.ui.rcbs.outputtype.218466097" name="Resource Custom Build Step Output Type"/>
 						</tool>
 					</fileInfo>
+					<fileInfo id="cdt.managedbuild.config.gnu.exe.debug.1330341797.281573242" name="avx512.cpp" rcbsApplicability="disable" resourcePath="src/main/x86/avx512.cpp" toolsToInvoke="cdt.managedbuild.tool.gnu.cpp.compiler.exe.debug.1715496680.752248820">
+						<tool id="cdt.managedbuild.tool.gnu.cpp.compiler.exe.debug.1715496680.752248820" name="GCC C++ Compiler" superClass="cdt.managedbuild.tool.gnu.cpp.compiler.exe.debug.1715496680">
+							<option id="gnu.cpp.compiler.option.other.other.2124416907" name="Other flags" superClass="gnu.cpp.compiler.option.other.other" useByScannerDiscovery="false" value="-c -fmessage-length=0 -mavx512f -mavx512vl" valueType="string"/>
+							<inputType id="cdt.managedbuild.tool.gnu.cpp.compiler.input.1847585465" superClass="cdt.managedbuild.tool.gnu.cpp.compiler.input"/>
+						</tool>
+						<tool customBuildStep="true" id="org.eclipse.cdt.managedbuilder.ui.rcbs.874817721" name="Resource Custom Build Step">
+							<inputType id="org.eclipse.cdt.managedbuilder.ui.rcbs.inputtype.22498286" name="Resource Custom Build Step Input Type">
+								<additionalInput kind="additionalinputdependency" paths=""/>
+							</inputType>
+							<outputType id="org.eclipse.cdt.managedbuilder.ui.rcbs.outputtype.1153584601" name="Resource Custom Build Step Output Type"/>
+						</tool>
+					</fileInfo>
 					<fileInfo id="cdt.managedbuild.config.gnu.exe.debug.1330341797.356003736" name="sse4.cpp" rcbsApplicability="disable" resourcePath="src/main/x86/sse4.cpp" toolsToInvoke="cdt.managedbuild.tool.gnu.cpp.compiler.exe.debug.1715496680.73118722">
 						<tool id="cdt.managedbuild.tool.gnu.cpp.compiler.exe.debug.1715496680.73118722" name="GCC C++ Compiler" superClass="cdt.managedbuild.tool.gnu.cpp.compiler.exe.debug.1715496680">
 							<option id="gnu.cpp.compiler.option.other.other.824484852" name="Other flags" superClass="gnu.cpp.compiler.option.other.other" useByScannerDiscovery="false" value="-c -fmessage-length=0 -msse4 -msse4a" valueType="string"/>
@@ -220,6 +234,7 @@
 								</option>
 								<option IS_BUILTIN_EMPTY="false" IS_VALUE_EMPTY="false" id="gnu.cpp.compiler.option.preprocessor.def.397756050" name="Defined symbols (-D)" superClass="gnu.cpp.compiler.option.preprocessor.def" useByScannerDiscovery="false" valueType="definedSymbols">
 									<listOptionValue builtIn="false" value="LSP_TESTING"/>
+									<listOptionValue builtIn="false" value="LSP_IDE_DEBUG"/>
 								</option>
 								<option id="gnu.cpp.compiler.option.dialect.std.2124347448" name="Language standard" superClass="gnu.cpp.compiler.option.dialect.std" useByScannerDiscovery="true" value="gnu.cpp.compiler.dialect.c++11" valueType="enumerated"/>
 								<inputType id="cdt.managedbuild.tool.gnu.cpp.compiler.input.1646920213" superClass="cdt.managedbuild.tool.gnu.cpp.compiler.input"/>
@@ -234,6 +249,7 @@
 								</option>
 								<option IS_BUILTIN_EMPTY="false" IS_VALUE_EMPTY="false" id="gnu.c.compiler.option.preprocessor.def.symbols.392178909" name="Defined symbols (-D)" superClass="gnu.c.compiler.option.preprocessor.def.symbols" useByScannerDiscovery="false" valueType="definedSymbols">
 									<listOptionValue builtIn="false" value="LSP_TESTING"/>
+									<listOptionValue builtIn="false" value="LSP_IDE_DEBUG"/>
 								</option>
 								<inputType id="cdt.managedbuild.tool.gnu.c.compiler.input.1546071444" superClass="cdt.managedbuild.tool.gnu.c.compiler.input"/>
 							</tool>
@@ -353,8 +369,10 @@
 	</storageModule>
 	<storageModule moduleId="org.eclipse.cdt.core.LanguageSettingsProviders"/>
 	<storageModule moduleId="refreshScope" versionNumber="2">
+		<configuration configurationName="DebugLinux"/>
 		<configuration configurationName="Debug Linux"/>
 		<configuration configurationName="Debug Win"/>
+		<configuration configurationName="DebugWin"/>
 		<configuration configurationName="Release">
 			<resource resourceType="PROJECT" workspacePath="/lsp-dsp-lib"/>
 		</configuration>
@@ -364,4 +382,4 @@
 	</storageModule>
 	<storageModule moduleId="org.eclipse.cdt.internal.ui.text.commentOwnerProjectMappings"/>
 	<storageModule moduleId="org.eclipse.cdt.make.core.buildtargets"/>
-</cproject>
+</cproject>
diff --git a/CHANGELOG b/CHANGELOG
@@ -2,6 +2,14 @@
 * RECENT CHANGES
 *******************************************************************************
 
+=== 1.0.15 ===
+* Several functions optimized for AVX-512 support.
+* Fixed several issues reported by PVS Studio static analyzer.
+* Fixed syntax error in C interface, covered with tests.
+* Bugfix in horizontal summing functions (invalid register clobber list).
+* Some AMD-related optimizations.
+* Updated module versions in dependencies.
+
 === 1.0.14 ===
 * Implemented pcomplex_r2c instruction set.
 * Updated build scripts.

diff --git a/README.md b/README.md
@@ -6,8 +6,8 @@ This library provides set of functions that perform SIMD-optimized
 computing on several hardware architectures.
 
 Currently supported set of SIMD extensions:
-  * i586 architecture (32-bit): SSE, SSE2, SSE3, AVX, AVX2 and FMA3;
-  * x86_64 architecture (64-bit): SSE, SSE2, SSE3, AVX, AVX2 and FMA3;
+  * i586 architecture (32-bit): SSE, SSE2, SSE3, AVX, AVX2, FMA3 and AVX512;
+  * x86_64 architecture (64-bit): SSE, SSE2, SSE3, AVX, AVX2, FMA3 and AVX512;
   * armv7 architecture (32-bit): NEON;
   * AArch64 architecture (64-bit): ASIMD.
 
@@ -32,8 +32,7 @@ Current set of functions provided:
   * Interpolation functions;
   * Some set of function to work with 3D mathematics.
 
-Supported platforms
-======
+## Supported platforms
 
 The build and correct unit test execution has been confirmed for following platforms:
 * FreeBSD
@@ -42,29 +41,26 @@ The build and correct unit test execution has been confirmed for following platf
 * Windows 32-bit
 * Windows 64-bit
 
-Supported architectures
-======
+## Supported architectures
 
 The support of following list of hardware architectures has been implemented:
-* i386 (32-bit) - full support.
-* x86_64 (64-bit) - full support.
+* i386 (32-bit) - full support (AVX-512 on the way).
+* x86_64 (64-bit) - full support (AVX-512 on the way).
 * ARMv6A - full support.
 * ARMv7A - full support.
-* AArch64 - most functions.
+* AArch64 - full support.
 
 For all other architectures the generic implementation of algorithms is used, without any
 architecture-specific optimizations. 
 
-Requirements
-======
+## Requirements
 
 The following packages need to be installed for building:
 
 * gcc >= 4.9
 * make >= 4.0
 
-Building
-======
+## Building
 
 To build the library, perform the following commands:
 
@@ -112,8 +108,8 @@ To build source code archive with all possible dependencies, run:
 make distsrc
 ```
 
-Usage
-======
+## Usage
+
 
 Here's the code snippet of how the library can be initialized and used in C++:
 
@@ -203,4 +199,6 @@ int main(int argc, const char **argv)
 
 ```
 
+## SAST Tools
 
+* [PVS-Studio](https://pvs-studio.com/en/pvs-studio/?utm_source=website&utm_medium=github&utm_campaign=open_source) - static analyzer for C, C++, C#, and Java code.
diff --git a/include/lsp-plug.in/dsp/common/3dmath/types.h b/include/lsp-plug.in/dsp/common/3dmath/types.h
@@ -29,96 +29,88 @@
 #define DSP_3D_MAXVALUE         1e+20f
 #define DSP_3D_MAXISECT         8
 
-#ifdef __cplusplus
-namespace lsp
+LSP_DSP_LIB_BEGIN_NAMESPACE
+
+#pragma pack(push, 1)
+typedef struct LSP_DSP_LIB_TYPE(point3d_t)
+{
+    float       x, y, z, w;
+} LSP_DSP_LIB_TYPE(point3d_t);
+
+typedef struct LSP_DSP_LIB_TYPE(vector3d_t)
+{
+    float       dx, dy, dz, dw;
+} LSP_DSP_LIB_TYPE(vector3d_t);
+
+typedef struct LSP_DSP_LIB_TYPE(color3d_t)
+{
+    float       r, g, b, a;
+} LSP_DSP_LIB_TYPE(color3d_t);
+
+typedef struct LSP_DSP_LIB_TYPE(ray3d_t)
+{
+    LSP_DSP_LIB_TYPE(point3d_t)     z;          // The start point: x, y, z = point coordinates
+    LSP_DSP_LIB_TYPE(vector3d_t)    v;          // The spread vector: dx, dy, dz = direction
+} LSP_DSP_LIB_TYPE(ray3d_t);
+
+typedef struct LSP_DSP_LIB_TYPE(bound_box3d_t)
+{
+    LSP_DSP_LIB_TYPE(point3d_t)     p[8];       // Bounding-box contains 8 points
+} LSP_DSP_LIB_TYPE(bound_box3d_t);
+
+typedef struct LSP_DSP_LIB_TYPE(segment3d_t)
+{
+    LSP_DSP_LIB_TYPE(point3d_t)     p[2];
+} LSP_DSP_LIB_TYPE(segment3d_t);
+
+typedef struct LSP_DSP_LIB_TYPE(triangle3d_t)
+{
+    LSP_DSP_LIB_TYPE(point3d_t)     p[3];       // Vertexes: x, y, z = vertex coordinates, w = length of the corresponding edge
+    LSP_DSP_LIB_TYPE(vector3d_t)    n;          // Normal: dx, dy, dz = normal coordinates, dw = plane equation coefficient
+} LSP_DSP_LIB_TYPE(triangle3d_t);
+
+typedef struct LSP_DSP_LIB_TYPE(matrix3d_t)
+{
+    float       m[16];      // Matrix data
+} LSP_DSP_LIB_TYPE(matrix3d_t);
+
+typedef struct LSP_DSP_LIB_TYPE(raw_triangle_t)
+{
+    LSP_DSP_LIB_TYPE(point3d_t)     v[3];
+} LSP_DSP_LIB_TYPE(raw_triangle_t);
+
+#pragma pack(pop)
+
+typedef enum LSP_DSP_LIB_TYPE(axis_orientation_t)
 {
-    namespace dsp
-    {
-#endif /* __cplusplus */
-
-    #pragma pack(push, 1)
-        typedef struct LSP_DSP_LIB_TYPE(point3d_t)
-        {
-            float       x, y, z, w;
-        } LSP_DSP_LIB_TYPE(point3d_t);
-
-        typedef struct LSP_DSP_LIB_TYPE(vector3d_t)
-        {
-            float       dx, dy, dz, dw;
-        } LSP_DSP_LIB_TYPE(vector3d_t);
-
-        typedef struct LSP_DSP_LIB_TYPE(color3d_t)
-        {
-            float       r, g, b, a;
-        } LSP_DSP_LIB_TYPE(color3d_t);
-
-        typedef struct LSP_DSP_LIB_TYPE(ray3d_t)
-        {
-            LSP_DSP_LIB_TYPE(point3d_t)     z;          // The start point: x, y, z = point coordinates
-            LSP_DSP_LIB_TYPE(vector3d_t)    v;          // The spread vector: dx, dy, dz = direction
-        } LSP_DSP_LIB_TYPE(ray3d_t);
-
-        typedef struct LSP_DSP_LIB_TYPE(bound_box3d_t)
-        {
-            LSP_DSP_LIB_TYPE(point3d_t)     p[8];       // Bounding-box contains 8 points
-        } LSP_DSP_LIB_TYPE(bound_box3d_t);
-
-        typedef struct LSP_DSP_LIB_TYPE(segment3d_t)
-        {
-            LSP_DSP_LIB_TYPE(point3d_t)     p[2];
-        } LSP_DSP_LIB_TYPE(segment3d_t);
-
-        typedef struct LSP_DSP_LIB_TYPE(triangle3d_t)
-        {
-            LSP_DSP_LIB_TYPE(point3d_t)     p[3];       // Vertexes: x, y, z = vertex coordinates, w = length of the corresponding edge
-            LSP_DSP_LIB_TYPE(vector3d_t)    n;          // Normal: dx, dy, dz = normal coordinates, dw = plane equation coefficient
-        } LSP_DSP_LIB_TYPE(triangle3d_t);
-
-        typedef struct LSP_DSP_LIB_TYPE(matrix3d_t)
-        {
-            float       m[16];      // Matrix data
-        } LSP_DSP_LIB_TYPE(matrix3d_t);
-
-        typedef struct LSP_DSP_LIB_TYPE(raw_triangle_t)
-        {
-            LSP_DSP_LIB_TYPE(point3d_t)     v[3];
-        } LSP_DSP_LIB_TYPE(raw_triangle_t);
-
-    #pragma pack(pop)
-
-        typedef enum LSP_DSP_LIB_TYPE(axis_orientation_t)
-        {
-            AO3D_POS_X_FWD_POS_Y_UP,
-            AO3D_POS_X_FWD_POS_Z_UP,
-            AO3D_POS_X_FWD_NEG_Y_UP,
-            AO3D_POS_X_FWD_NEG_Z_UP,
-            AO3D_NEG_X_FWD_POS_Y_UP,
-            AO3D_NEG_X_FWD_POS_Z_UP,
-            AO3D_NEG_X_FWD_NEG_Y_UP,
-            AO3D_NEG_X_FWD_NEG_Z_UP,
-
-            AO3D_POS_Y_FWD_POS_X_UP,
-            AO3D_POS_Y_FWD_POS_Z_UP,
-            AO3D_POS_Y_FWD_NEG_X_UP,
-            AO3D_POS_Y_FWD_NEG_Z_UP,
-            AO3D_NEG_Y_FWD_POS_X_UP,
-            AO3D_NEG_Y_FWD_POS_Z_UP,
-            AO3D_NEG_Y_FWD_NEG_X_UP,
-            AO3D_NEG_Y_FWD_NEG_Z_UP,
-
-            AO3D_POS_Z_FWD_POS_X_UP,
-            AO3D_POS_Z_FWD_POS_Y_UP,
-            AO3D_POS_Z_FWD_NEG_X_UP,
-            AO3D_POS_Z_FWD_NEG_Y_UP,
-            AO3D_NEG_Z_FWD_POS_X_UP,
-            AO3D_NEG_Z_FWD_POS_Y_UP,
-            AO3D_NEG_Z_FWD_NEG_X_UP,
-            AO3D_NEG_Z_FWD_NEG_Y_UP
-        } LSP_DSP_LIB_TYPE(axis_orientation_t);
-
-#ifdef __cplusplus
-    }
-}
-#endif /* __cplusplus */
+    AO3D_POS_X_FWD_POS_Y_UP,
+    AO3D_POS_X_FWD_POS_Z_UP,
+    AO3D_POS_X_FWD_NEG_Y_UP,
+    AO3D_POS_X_FWD_NEG_Z_UP,
+    AO3D_NEG_X_FWD_POS_Y_UP,
+    AO3D_NEG_X_FWD_POS_Z_UP,
+    AO3D_NEG_X_FWD_NEG_Y_UP,
+    AO3D_NEG_X_FWD_NEG_Z_UP,
+
+    AO3D_POS_Y_FWD_POS_X_UP,
+    AO3D_POS_Y_FWD_POS_Z_UP,
+    AO3D_POS_Y_FWD_NEG_X_UP,
+    AO3D_POS_Y_FWD_NEG_Z_UP,
+    AO3D_NEG_Y_FWD_POS_X_UP,
+    AO3D_NEG_Y_FWD_POS_Z_UP,
+    AO3D_NEG_Y_FWD_NEG_X_UP,
+    AO3D_NEG_Y_FWD_NEG_Z_UP,
+
+    AO3D_POS_Z_FWD_POS_X_UP,
+    AO3D_POS_Z_FWD_POS_Y_UP,
+    AO3D_POS_Z_FWD_NEG_X_UP,
+    AO3D_POS_Z_FWD_NEG_Y_UP,
+    AO3D_NEG_Z_FWD_POS_X_UP,
+    AO3D_NEG_Z_FWD_POS_Y_UP,
+    AO3D_NEG_Z_FWD_NEG_X_UP,
+    AO3D_NEG_Z_FWD_NEG_Y_UP
+} LSP_DSP_LIB_TYPE(axis_orientation_t);
+
+LSP_DSP_LIB_END_NAMESPACE
 
 #endif /* LSP_PLUG_IN_DSP_COMMON_3DMATH_TYPES_H_ */
diff --git a/include/lsp-plug.in/dsp/common/bitmap.h b/include/lsp-plug.in/dsp/common/bitmap.h
@@ -24,31 +24,24 @@
 
 #include <lsp-plug.in/dsp/common/types.h>
 
-#ifdef __cplusplus
-namespace lsp
+LSP_DSP_LIB_BEGIN_NAMESPACE
+
+typedef struct LSP_DSP_LIB_TYPE(bitmap_t)
 {
-    namespace dsp
-    {
-#endif /* __cplusplus */
-
-        typedef struct LSP_DSP_LIB_TYPE(bitmap_t)
-        {
-            int32_t     width;
-            int32_t     height;
-            int32_t     stride;
-            uint8_t    *data;
-        } LSP_DSP_LIB_TYPE(bitmap_t);
-
-
-        typedef void (* LSP_DSP_LIB_TYPE(bitmap_render_func_t))(
-            LSP_DSP_LIB_TYPE(bitmap_t) *dst,
-            const LSP_DSP_LIB_TYPE(bitmap_t) *src,
-            ssize_t x,
-            ssize_t y);
-#ifdef __cplusplus
-    } /* namespace dsp */
-} /* namespace lsp */
-#endif /* __cplusplus */
+    int32_t     width;
+    int32_t     height;
+    int32_t     stride;
+    uint8_t    *data;
+} LSP_DSP_LIB_TYPE(bitmap_t);
+
+
+typedef void (* LSP_DSP_LIB_TYPE(bitmap_render_func_t))(
+    LSP_DSP_LIB_TYPE(bitmap_t) *dst,
+    const LSP_DSP_LIB_TYPE(bitmap_t) *src,
+    ssize_t x,
+    ssize_t y);
+
+LSP_DSP_LIB_END_NAMESPACE
 
 #include <lsp-plug.in/dsp/common/bitmap/b1b8.h>
 #include <lsp-plug.in/dsp/common/bitmap/b2b8.h>

diff --git a/include/lsp-plug.in/dsp/common/bitmap/b1b8.h b/include/lsp-plug.in/dsp/common/bitmap/b1b8.h
@@ -28,7 +28,7 @@
  * Put the source 1-bit bitmap to destination 8-bit bitmap,
  * the result pixel value will be computed as: result[i] = src[i]
  */
-LSP_DSP_LIB_SYMBOL(void, bitmap_put_b1b8, LSP_DSP_LIB_TYPE(LSP_DSP_LIB_TYPE(bitmap_t)) *dst, const LSP_DSP_LIB_TYPE(bitmap_t) *src, ssize_t x, ssize_t y);
+LSP_DSP_LIB_SYMBOL(void, bitmap_put_b1b8, LSP_DSP_LIB_TYPE(bitmap_t) *dst, const LSP_DSP_LIB_TYPE(bitmap_t) *src, ssize_t x, ssize_t y);
 
 /**
  * Put the source 1-bit bitmap to destination 8-bit bitmap,