ex_voxelBlockManager_host_cuda: add -fopenmp-simd compile flag

Activates #pragma omp simd hints in decodeInverseMaps and
buildMaskPrefixSums without requiring the OpenMP runtime library,
yielding ~10-15% faster CPU decode throughput.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Signed-off-by: Efty Sifakis <esifakis@nvidia.com>

Author: sifakis

nanovdb/nanovdb/examples/CMakeLists.txt

@@ -117,8 +117,8 @@ nanovdb_example(NAME "ex_coarsen_nanovdb_cuda" OPENVDB)
 nanovdb_example(NAME "ex_voxelBlockManager_host_cuda")
 if(TARGET ex_voxelBlockManager_host_cuda)
   target_compile_options(ex_voxelBlockManager_host_cuda PRIVATE
-    $<$<COMPILE_LANGUAGE:CUDA>:-Xcompiler=-mavx2>
-    $<$<COMPILE_LANGUAGE:CXX>:-mavx2>)
+    $<$<COMPILE_LANGUAGE:CUDA>:-Xcompiler=-mavx2,-fopenmp-simd>
+    $<$<COMPILE_LANGUAGE:CXX>:-mavx2 -fopenmp-simd>)
 endif()
 
 if(CUDAToolkit_FOUND)