Cycles:

* OpenCL now only uses GPU/Accelerator devices, it's only confusing if CPU
  device is used, easy to enable in the code for debugging.
* OpenCL kernel binaries are now cached for faster startup after the first
  time compiling.
* CUDA kernels can now be compiled and cached at runtime if the CUDA toolkit
  is installed. This means that even if the build does not have CUDA enabled,
  it's still possible to use it as long as you install the toolkit.

intern/cycles/kernel/kernel_compat_cuda.h

@@ -21,14 +21,14 @@
 
 #define __KERNEL_GPU__
 #define __KERNEL_CUDA__
+#define CCL_NAMESPACE_BEGIN
+#define CCL_NAMESPACE_END
 
 #include <cuda.h>
 #include <float.h>
 
 #include "util_types.h"
 
-CCL_NAMESPACE_BEGIN
-
 /* Qualifier wrappers for different names on different devices */
 
 #define __device  __device__ __inline__
@@ -60,7 +60,5 @@ typedef texture<uchar4, 2, cudaReadModeNormalizedFloat> texture_image_uchar4;
 
 #define kernel_data __data
 
-CCL_NAMESPACE_END
-
 #endif /* __KERNEL_COMPAT_CUDA_H__ */