If the PG could get the GPU client to work like this, they would. Unfortunately, GPUs have never been designed to handle multi-tasking very well since normally they're only doing one thing at a time, i.e. showing the pretty graphics of the game you're playing. Compare that to a CPU, which has always had to carry out various OS-related tasks while running all of the foreground programs you run, and you should see why the CPU client works better with other tasks than the GPU client.
Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
The GPU client is considered a high performance client, like SMP. Neither are designed to run on "spare" background CPU cycles. It's counter-intuitive to the design goals, and the goals of the project.
I wouldn't say never, but let's try to get a good working GPU client first, and then they can try for other configurations.