Isn't VILW how a number of GPUs worked internally? That said GPU isn't the same as GPC
Some older ones, yeah (TeraScale comes to mind) but modern ones are more like RISC with whopping levels of SIMD. It turns out that VLIW was hard for them too.
They are used in a lot of DSP chips too, where you (hopefully) have very simple branching if any and nice data access patterns.
And typically just fast RAM everywhere instead of caches, so you don't have cache misses. (The flip side is that you typically have very _little_ RAM.)