That's really ignorant given that Intel has thousands of software engineers supporting hundreds of opensource projects you use daily. Including Linux where Intel has consistently a top ten contributor for years.
This mistake could easily have been in other vendors Linux GPU drivers, they in the end don't have nearly the same priority (and in turn resources) as the Windows GPU drivers. And it's a very easy mistake to find. And I don't know if anyone even cared about ray tracing with Intel integrated graphics on Linux desktops (and in turn no one profiled it deeply). I mean ray tracing is generally something you will do much less likely on a integrated GPU. And it's a really easy mistake to make.
And sure I'm pretty sure their software department(s?) have a lot of potential for improvement, I mean they probably have been hampered by the same internal structures which lead to Intel faceplanting somewhat hard recently.
Even so, the very first thing anybody learns about GPU programming is to use the VRAM on the card whenever possible, and to minimize transfers back and forth between VRAM and main memory. This is a super basic mistake that should have been caught by some kind of test suite, at least.
spicymaki|3 years ago
gumby|3 years ago
drfuchs|3 years ago
dathinab|3 years ago
This mistake could easily have been in other vendors Linux GPU drivers, they in the end don't have nearly the same priority (and in turn resources) as the Windows GPU drivers. And it's a very easy mistake to find. And I don't know if anyone even cared about ray tracing with Intel integrated graphics on Linux desktops (and in turn no one profiled it deeply). I mean ray tracing is generally something you will do much less likely on a integrated GPU. And it's a really easy mistake to make.
And sure I'm pretty sure their software department(s?) have a lot of potential for improvement, I mean they probably have been hampered by the same internal structures which lead to Intel faceplanting somewhat hard recently.
actually_a_dog|3 years ago