Same as title.
I found beta4 doesn't support it for CPU and GPU.
have checked it, beta3 don't support double either
probably beta2 the same since it's older
beta4 don't support as well
No extensions are currently supported for GPU currently. There is no double support currently. In case of CPU, a device query will give you the supported extensions.
all I mention are for CPU in beta3 beta4 maybe beta2 (but I get the same result for GPU in beta4)
Double precision floating point is not currently supported in the OpenCL beta release. We start introducing various pieces of DPFP support in OpenCL over the next year. Some of the basic arithmetic functions will be introduced first with the math function support likely taking longer. Since full DPFP support is an optional extension in the OpenCL spec, we are concentrating first improving the performance and other aspects of the required spec first.