open source release

.clang-format

@@ -0,0 +1,28 @@
+BasedOnStyle: Google
+ColumnLimit: 120
+IndentWidth: 4
+AlignAfterOpenBracket: Align
+BreakBeforeBraces: Custom
+BraceWrapping:
+  AfterUnion: true
+  AfterEnum: true
+  AfterStruct: true
+  SplitEmptyFunction: true
+  AfterNamespace: true
+  AfterClass: true
+  AfterFunction: true
+  AfterControlStatement: true
+AllowShortIfStatementsOnASingleLine: false
+IndentCaseLabels: false
+DerivePointerAlignment: false
+PointerAlignment: Left
+AlignTrailingComments: true
+AllowShortBlocksOnASingleLine: false
+AlignConsecutiveDeclarations: true
+AlignConsecutiveAssignments: true
+AllowAllParametersOfDeclarationOnNextLine: false
+BinPackArguments: false
+BinPackParameters: false
+AccessModifierOffset: -4
+TabWidth: 4
+UseTab: Never

.gitignore

@@ -1,22 +1,11 @@
-*.vcxproj
-*.filters
-*.obj
-*.tlog
-*.pdb
-*.lib
-*.exp
-*.ilk
-*.log
-*.suo
-*.cache
-*.idb
-*.user
-*.dll
-*.exe
-*.opendb
-*.db
-*.sln
-*.d
-*.o
-*.a
-*.so
+build/
+*.json
+*.xcworkspacedata
+*.plist
+*.xcuserstate
+*.xcuserstate
+core/.DS_Store
+*.json
+resources/
+src/core/src/vlk/kernels/*.comp.*
+src/core/src/vlk/compiled*spv.h

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "third_party/gtest"]
+	path = third_party/gtest
+	url = https://github.com/google/googletest.git

CI_WORKFLOW.md

@@ -0,0 +1,100 @@
+# RadeonRays
+
+https://github.com/Radeon-Pro/RadeonRays
+
+## Build
+
+### Requirements
+
+* Cmake 3.12+
+* VS 2019
+* Windows 10 + latest updates
+* MacOS 10.15 (10.14 - build ok)
+* Ubuntu latest LTS (18.04)
+
+### Dependencies
+
+* Ubuntu
+    * fmt
+
+    ```bash
+    $ sudo apt install libfmt-dev
+    ```
+
+    * spdlog
+    https://github.com/gabime/spdlog
+
+    ```bash
+    $ git clone https://github.com/gabime/spdlog.git
+    $ cd spdlog && mkdir build && cd build
+    $ cmake .. && make -j
+    $ sudo make install
+    ```
+
+* macOS
+
+    ```bash
+    brew install fmt
+    brew install spdlog
+    ```
+
+* Windows
+
+    1. Install with `vcpkg` and use `CMAKE_PREFIX_PATH` for build
+    2. Install form sources
+
+    ```cmd
+    git clone https://github.com/gabime/spdlog.git
+    mkdir build
+    cd build
+    cmake ..
+    cmake --build . --config Release --target INSTALL
+    ```
+
+    ```cmd
+    git clone https://github.com/fmtlib/fmt.git
+    mkdir build
+    cd build
+    cmake ..
+    cmake --build . --config Release --target INSTALL
+    ```
+### Build options
+
+```
+EMBEDDED_KERNELS=ON
+ENABLE_TESTING=ON
+CMAKE_BUILD_TYPE=Release
+```
+
+* Windows
+
+```cmake
+ENABLE_DX12=ON
+ENABLE_VULKAN=ON
+```
+
+* Lunix
+
+```cmake
+ENABLE_VULKAN=ON
+CMAKE_CXX_FLAGS="-std=gnu++17"
+```
+
+* OSX
+
+```cmake
+CMAKE_CXX_FLAGS="-std=c++17"
+CMAKE_MACOSX_RPATH=ON
+```
+
+## Tests
+
+> :warning: Windows required beta driver with ray-traicing support
+
+[resources](resources) dir is required for tests
+
+### GPUs
+
+* vega56/64
+* navi (5700/5700XT)
+* nvidia 1080/2070/2080

CMakeLists.txt

@@ -0,0 +1,74 @@
+cmake_minimum_required(VERSION 3.12)
+
+project(radeonrays CXX)
+include(cmake/StandardProjectSettings.cmake)
+
+set(CMAKE_ARCHIVE_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/bin)
+set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/bin)
+set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/bin)
+
+# Link this 'library' to set the c++ standard / compile-time options requested
+add_library(project_options INTERFACE)
+target_compile_features(project_options INTERFACE cxx_std_17)
+
+# Link this 'library' to use the warnings specified in CompilerWarnings.cmake
+add_library(project_warnings INTERFACE)
+
+# sanitizer options if supported by compiler
+include(cmake/Sanitizers.cmake)
+enable_sanitizers(project_options)
+
+# enable doxygen
+include(cmake/Doxygen.cmake)
+enable_doxygen()
+
+# allow for static analysis options
+include(cmake/StaticAnalyzers.cmake)
+
+option(BUILD_SHARED_LIBS "Enable compilation of shared libraries" ON)
+option(ENABLE_TESTING "Enable Test Builds" ON)
+option(ENABLE_DX12 "Enable DX12 backend" OFF)
+option(ENABLE_VULKAN "Enable Vulkan backend" OFF)
+option(EMBEDDED_KERNELS "Enable embedding kernels/shaders into library" OFF)
+
+# Very basic PCH example
+option(ENABLE_PCH "Enable Precompiled Headers" OFF)
+if (ENABLE_PCH)
+    # This sets a global PCH parameter, each project will build its own PCH, which
+    # is a good idea if any #define's change
+    # 
+    # 
+    target_precompile_headers(project_options INTERFACE <vector> <string> <map> <utility>)
+endif()
+
+if(ENABLE_VULKAN)
+    include(cmake/KernelUtils.cmake)
+endif(ENABLE_VULKAN)
+
+if(ENABLE_TESTING)
+    enable_testing()
+    set(gtest_force_shared_crt ON CACHE BOOL "Use /MD and /MDd" FORCE)
+    add_subdirectory(third_party/gtest)
+
+    set(THIRD_PARTY_TARGETS
+        gtest
+        gtest_main
+        gmock
+        gmock_main)
+
+    foreach(TGT ${THIRD_PARTY_TARGETS})
+        set_property(TARGET ${TGT} PROPERTY FOLDER "third_party")
+    endforeach()
+
+    add_subdirectory(test)
+endif(ENABLE_TESTING)
+
+if(ENABLE_FUZZING)
+    message(
+        "Building Fuzz Tests, using fuzzing sanitizer https://www.llvm.org/docs/LibFuzzer.html"
+    )
+    add_subdirectory(fuzz_test)
+endif(ENABLE_FUZZING)
+
+add_subdirectory(src)
+add_subdirectory(bvh_analyzer)

README.md

@@ -1,12 +1,8 @@
-# RadeonRays 4.0
-
-## Important
-
-RadeonRays 2.0 SDK (OpenCL) has been moved to 'legacy-2.0' branch.
+# RadeonRays 4.1
 
 ## Summary
 
-RadeonRays is a ray intersection acceleration library for heterogeneous hardware and software systems. AMD developed RadeonRays to help developers make the most of GPU, APUs and CPUs, and to eliminate the need to maintain hardware-dependent code.
+RadeonRays is a ray intersection acceleration library. AMD developed RadeonRays to help developers make the most of GPU and to eliminate the need to maintain hardware-dependent code.
 
 The library offers a well-defined C API for scene building and performing asynchronous ray intersection queries.
 
@@ -16,17 +12,15 @@ RadeonRays is not limited to AMD hardware, a specific operating system or graphi
 
 The library supports the following graphics and GPGPU frameworks as its backends:
 
-- DirectX 12
-- Metal
+- DirectX12
 - Vulkan
 
 ## System Requirements
 
 RadeonRays requires a PC with the following software and hardware:
 
-- DirectX12: a 64-bit version of Windows® 10, and a GPU and drivers that supports DirectX12 features
-- Metal: a 64-bit version of MacOS® X 10.15 or later, and a discrete GPU that supports the MPS acceleration structure
-- Vulkan: a 64-bit version of Windows® 10 or Linux, and a GPU and drivers that support Vulkan version 1.2
+- DirectX12: a 64-bit version of Windows® 10, and a GPU and drivers that supports DirectX12 features
+- Vulkan: a 64-bit version of Windows® 10 or Linux, and a GPU and drivers that support Vulkan version 1.2
 
 ## Documentation
 

bvh_analyzer/CMakeLists.txt

@@ -0,0 +1,11 @@
+find_package(OpenMP)
+
+file(GLOB HEADER_FILES ${CMAKE_CURRENT_SOURCE_DIR}/*.h)
+file(GLOB SOURCE_FILES ${CMAKE_CURRENT_SOURCE_DIR}/*.cpp)
+
+add_executable(bvh_analyzer ${HEADER_FILES} ${SOURCE_FILES})
+
+target_link_libraries(bvh_analyzer PRIVATE project_options)
+if(OpenMP_CXX_FOUND)
+    target_link_libraries(bvh_analyzer PRIVATE OpenMP::OpenMP_CXX)
+endif()

bvh_analyzer/aabb.h

@@ -0,0 +1,103 @@
+/**********************************************************************
+Copyright (c) 2020 Advanced Micro Devices, Inc. All rights reserved.
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+********************************************************************/
+#pragma once
+#include <cfloat>
+#include <ostream>
+
+#include "float2.h"
+#include "float3.h"
+
+namespace bvh
+{
+struct Aabb
+{
+    //<! Create AABB from a single point.
+    Aabb() : pmin{FLT_MAX, FLT_MAX, FLT_MAX}, pmax{-FLT_MAX, -FLT_MAX, -FLT_MAX} {}
+    //<! Create AABB from a single point.
+    Aabb(const float3& p) : pmin(p), pmax(p) {}
+    //<! Create AABB from min and max points.
+    Aabb(const float3& mi, const float3& ma) : pmin(mi), pmax(ma) {}
+    //<! Create AABB from another AABB.
+    Aabb(const Aabb& rhs) : pmin(rhs.pmin), pmax(rhs.pmax) {}
+    //<! Grow AABB to enclose itself and another AABB.
+    Aabb& Grow(const Aabb& rhs)
+    {
+        pmin = vmin(pmin, rhs.pmin);
+        pmax = vmax(pmax, rhs.pmax);
+        return *this;
+    }
+    //<! Grow AABB to enclose itself and another point.
+    Aabb& Grow(const float3& p)
+    {
+        pmin = vmin(pmin, p);
+        pmax = vmax(pmax, p);
+        return *this;
+    }
+    //<! Box center.
+    float3 Center() const { return (pmax + pmin) * 0.5; }
+
+    //<! Box extens along each axe.
+    float3 Extents() const { return pmax - pmin; }
+    //<! Calculate AABB union.
+    static Aabb Union(const Aabb& rhs, const Aabb& lhs)
+    {
+        Aabb result(vmin(lhs.pmin, rhs.pmin), vmax(lhs.pmax, rhs.pmax));
+        return result;
+    }
+
+    //<! Box extens along each axe.
+    float Area() const
+    {
+        float3 ext = Extents();
+        return 2 * (ext.x * ext.y + ext.x * ext.z + ext.y * ext.z);
+    }
+
+    //<! Calculate AABB vs ray intersection distances.
+    float2 Intersect(const float3& invD, const float3& oxInvD, float minT, float maxT) const
+    {
+        float3 f    = fma(pmax, invD, oxInvD);
+        float3 n    = fma(pmin, invD, oxInvD);
+        float3 tmax = vmax(f, n);
+        float3 tmin = vmin(f, n);
+        float  t1   = fminf(fminf(fminf(tmax.x, tmax.y), tmax.z), maxT);
+        float  t0   = fmaxf(fmaxf(fmaxf(tmin.x, tmin.y), tmin.z), minT);
+        return float2{t0, t1};
+    }
+
+    bool Includes(Aabb const& rhs) const
+    {
+        float3 min_diff = rhs.pmin - pmin;
+        float3 max_diff = pmax - rhs.pmax;
+        return !(min_diff.x < -1e-8f || min_diff.y < -1e-8f || min_diff.z < -1e-8f || max_diff.x < -1e-8f ||
+                 max_diff.y < -1e-8f || max_diff.z < -1e-8f);
+    }
+
+    //<! Min point of AABB.
+    float3 pmin;
+    //<! Max point of AABB.
+    float3 pmax;
+};
+
+inline std::ostream& operator<<(std::ostream& oss, const Aabb& aabb)
+{
+    oss << "{ min: [" << aabb.pmin.x << ", " << aabb.pmin.y << ", " << aabb.pmin.z << "], ";
+    oss << " max: [" << aabb.pmax.x << ", " << aabb.pmax.y << ", " << aabb.pmax.z << "] }";
+    return oss;
+}
+}  // namespace bvh