VGA Passthrough Overhead

I never had the opportunity to test the overhead of VGA Passthrough.  I had a gaming VM that I recently turned into a physical computer.  During the VM days, the performance on the games that I played was fine.  I had no complaints.  I tried to run Dolphin to emulate the Gamecube and the Wii, but I could only get around 45 FPS on the lowest resolution.  I also played around with Bitcoin mining from inside of the VM.  This is where I am getting my benchmark for overhead.  When the VGA card was being passed through to a VM, I was generating approximately 184 Mhash/s.  Now that there is no passthrough/virtualization layer, I can get around 358 Mhash/s.  That is about a 94% improvement.  These numbers come from snapshots in time.  They do not correspond to an average of an sorts.  Although the GPU is exactly the same (AMD Radeon HD 7870), the CPU's were different.  The VM had a AMD Phenom(tm) II X6 1090T Processor running at 3.2 Ghz and the VM only got 2 cores.  The new setup is an AMD FX 4100 running at 3.6 Ghz.  Since there is no virtualization, the computer gets all 4 cores.  Also, the VM only had 4GB of RAM while the physical has 12GB of RAM.  The CPU and RAM shouldn't have that much of an impact on the OpenCL program running.  Emperically, this is a comparison of an OpenCL program running on the same video card in two different computers; one of them virtualized.  This means you shouldn't quote this blog as claiming the all PCI/VGA Passthrough has a  49% performance penalty.