IF cache is fundamental to Navi 2 and later AMD GPUs. This is not some small design add-on. If he was anywhere close to being deeply involved then it would exist in ARC.
I'm saying that when he left AMD, Navi2 was still early in it's design cycle. After all, he left 5+ years ago, and rumors were swirling long before that time of deep internal dissent.
Are you telling me that in the 3 years between him leaving and the release of Navi 2, all design factors, or even most, were finalized?
My point is, I do not accept anymore the claim that he had that much to do with the Navi 2 design from a technological standpoint. He was involved fully with Vega, and this played exactly as ARC. Too big and power hungry for the performance, plus the PR spin almost identical. Sure, it's all by chance it followed him to Intel.
I will throw another item in the ring:
Google thinks Raja made rx6000
...
I speculate GCN, Polaris, and Vega were Raja's predecessors creations as much as they were Raja. In short, Raja was bringing someone else's design to fruition.
RDNA1, the rx5000 series was Raja's only fully baked creation at AMD. It is very different from GCN, and came into existence during Raja's tenure. It did not exist prior to Raja.
RDNA2, the rx6000, is Raja's successors implementing improvements on Raja's design. Many of which were likely Raja's vision after he learned his lessons from RDNA1.
https://wccftech.com/amd-replaces-raja-koduri-two-heavyweights-lead-graphics-rtg/
In other words, there is a good reason the rx6800 is referred to as Raja's baby. The shaders are reworked, mesh shaders, and sampler feedback all added for round two. None of that stuff came from the CPU side.
I also speculate that the rx7000 series will be the first GPU we see that is Mike Rayfield and David Wang's vision.
---------------------------
The biggest problem with Raja is he over promises and is a bit of a
<insert profanity here>. However, it is unfair to blame him for Intel upper management failures. Failures we have seen in other intel products.