No, you can't do in OpenCL right now. However, we are considering this feature for a future release. The Khronos OpenCL working group is also aware of a request for this.
You can do that with AMD GPUs if you have the time to patch GPU ISA.
See GCN instruction set arch , load/store instructions have a bit called 'SLC', - System Level Coherent, if it is flipped the GPU basically bypasses all its caches.