// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions
// are met:
//  * Redistributions of source code must retain the above copyright
//    notice, this list of conditions and the following disclaimer.
//  * Redistributions in binary form must reproduce the above copyright
//    notice, this list of conditions and the following disclaimer in the
//    documentation and/or other materials provided with the distribution.
//  * Neither the name of NVIDIA CORPORATION nor the names of its
//    contributors may be used to endorse or promote products derived
//    from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ''AS IS'' AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
// PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Copyright (c) 2008-2025 NVIDIA Corporation. All rights reserved.
// Copyright (c) 2004-2008 AGEIA Technologies, Inc. All rights reserved.
// Copyright (c) 2001-2004 NovodeX AG. All rights reserved.

#include "PxgArrayConverter.h"

#include "foundation/PxUserAllocated.h"

#include "PxPhysXGpu.h"
#include "PxgKernelWrangler.h"
#include "PxgKernelIndices.h"
#include "PxgInterpolation.h"

using namespace physx;

#if ENABLE_KERNEL_LAUNCH_ERROR_CHECK
	#define checkCudaError() { cudaError_t err = cudaDeviceSynchronize(); if (err != 0) printf("Cuda error file: %s, line: %i, error: %i\n", PX_FL, err); }	
#else
	#define checkCudaError() { }
#endif

#define THREADS_PER_BLOCK 256

PxgArrayConverter::PxgArrayConverter(PxgKernelLauncher& kernelLauncher)
{
	mKernelLauncher = kernelLauncher;
}

void PxgArrayConverter::interleaveGpuBuffers(const PxVec4* vertices, const PxVec4* normals, PxU32 length, PxVec3* interleavedResultBuffer, CUstream stream)
{
	const PxU32 numThreadsPerBlock = THREADS_PER_BLOCK;
	const PxU32 numBlocks = (length + numThreadsPerBlock - 1) / numThreadsPerBlock;
	mKernelLauncher.launchKernel(PxgKernelIds::util_InterleaveBuffers, numBlocks, numThreadsPerBlock, 0, stream,
		vertices, normals, length, interleavedResultBuffer);
	checkCudaError();
}