We solved that almost a decade ago now with HBM. Sure, the latencies aren't amazing, but the power consumption numbers are and large caches can hide the higher access latencies pretty well in almost all cases.
Only time that I can remember HBM being used with some kind of integrated graphics was strange Intel NUC with Vega GPU and IIRC correctly they were on the same die.
That product had an Intel CPU and AMD GPU connected via PCIe on the same package, not the same die. It was a neat experiment, but it was really just a packaging trick.
