nvidia compatibility

demo/gpudemo/GpuDemo.h

@@ -37,9 +37,9 @@ public:
                     :useOpenCL(true),
                     preferredOpenCLPlatformIndex(-1),
                     preferredOpenCLDeviceIndex(-1),
-					arraySizeX(10),
-		arraySizeY(20),
-		arraySizeZ(10),
+					arraySizeX(40),
+		arraySizeY(40),
+		arraySizeZ(40),
 		m_useConcaveMesh(false),
 		gapX(14.3),
 		gapY(14.0),

demo/gpudemo/main_opengl3core.cpp

@@ -381,7 +381,8 @@ int main(int argc, char* argv[])
 	
 	args.GetCmdLineArgument("selected_demo",selectedDemo);
 
-	useNewBatchingKernel = args.CheckCmdLineFlag("new_batching");
+	if (args.CheckCmdLineFlag("new_batching"))
+		useNewBatchingKernel = true;
 	bool benchmark=args.CheckCmdLineFlag("benchmark");
 	dump_timings=args.CheckCmdLineFlag("dump_timings");
 	ci.useOpenCL = !args.CheckCmdLineFlag("disable_opencl");

opencl/gpu_rigidbody/host/Solver.cpp

@@ -17,7 +17,7 @@ subject to the following restrictions:
 #include "Solver.h"
 
 ///useNewBatchingKernel  is a rewritten kernel using just a single thread of the warp, for experiments
-bool useNewBatchingKernel = false;
+bool useNewBatchingKernel = true;
 
 #define SOLVER_SETUP_KERNEL_PATH "opencl/gpu_rigidbody/kernels/solverSetup.cl"
 #define SOLVER_SETUP2_KERNEL_PATH "opencl/gpu_rigidbody/kernels/solverSetup2.cl"