Totally agree. Experienced degraded RAM on the suspected mined 3090 I had for about 24 hours. There was snow all over the screen when the RAM became too hot from running the UE5 Matrix demo.
Totally agree. Experienced degraded RAM on the suspected mined 3090 I had for about 24 hours. There was snow all over the screen when the RAM became too hot from running the UE5 Matrix demo.It degrades/ becomes faulty if run long enough and hot enough, sometimes above its TJmax. Cryptominers trying to juice every hash are prime candidates for that kind of abuse.
People think it's because of Arc falling short of expectations, but the 2 year delay on PVC is more likely to be the reason he was fired.Welp. Raja is out of Intel.
Who is replacing him? Lisa?but the 2 year delay on PVC is more likely to be the reason he was fired.
Welp. Raja is out of Intel.
Welp. Raja is out of Intel.
Kinda impressive: https://ieeexplore.ieee.org/author/37611561100Intels GPU chief architect David Blythe moved to AMD by the way which maybe is a bigger deal. I hope it's not a bad sign for Battlemage.
I'm not. My predictions are rarely true. I probably sealed his fate by predicting that he would one day replace Pat as Intel CEO. Well, he still could. Maybe not in my lifetime. (see what I did there? )I am shocked, shocked I tell you! /s
Yeah. Intel better put out a statement ASAP!
Add it to Su's long list of f yous to intel and Gunslinger!But why does AMD need him? Did they hire him just to spite Intel?
I don't think Intel needs more messed up ceos who can't differentiate their head from their bum.I'm not. My predictions are rarely true. I probably sealed his fate by predicting that he would one day replace Pat as Intel CEO. Well, he still could. Maybe not in my lifetime. (see what I did there? )
People think it's because of Arc falling short of expectations, but the 2 year delay on PVC is more likely to be the reason he was fired.
It's both. PVC was originally on Intel 7nm, and due to expected low yields they had a billion small chiplets. When it was clear Intel 7nm would not be ready in time, they switched to TSMC 5nm but decided to stick to the small chiplet strategy which increased the complexity of the design and packaging costs, despite the fact that TSMC 5nm can easily yield even 400mm²+ chips.Finally. Time for Pat to put these foolish ambitions to rest.
Don't think you can blame Raja for that. Blame TMG.
Raja messing up the HPC GPU roadmap until 2025 (at least) is almost certainly the reason he was fired.
or maybe he simply didn't want to deal with Raja anymore?Intels GPU chief architect David Blythe moved to AMD by the way which maybe is a bigger deal. I hope it's not a bad sign for Battlemage.
They stripped him of all management responsibilities a few months back. They gave him a fancy new title to distract from that, but his fate was sealed at that point. It's a pretty typical song and dance for corporations like this.Charlie is saying the leaving is amicable. Based on @Exist50 saying leaving was inevitable, maybe he's leaving after demotion back few months ago.
My understanding is that the client graphics business group went under her, while the server business group and all the shared stuff (i.e. most of the engineering teams) went under the DCAI business group. Which is honestly kinda strange when you look at how Intel has things arranged on the CPU side.So since Lisa Pearce is the general manager of AXG for client, is she taking on more responsibilities now?
They can still try to figure out ways to give us cheap performant 16GB or even 24GB cards. Sure, it won't be as fast as a 7900 XTX or a 4090 but the extra RAM would still help it be more appealing to gamers who detest the 4070 and below.I don't think they'll kill Arc, but it's tough to see a path to them legitimately competing with Nvidia, or even AMD.