grow a plant, hug your dog, lift heavy, eat healthy, be a nerd, play a game and help each other out
Conversly, the apple silicon products ship huge, expensive dies fabbed on leading TSMC processes which sip power relative to contemporaries. You can have excellent power efficiency on a large die at a specific frequency range, moreso than a smaller die clocked more aggressively.
my charger is fine, but could you pet the cat for me? 🥺
Good to know, that’s not the one I had in mind, however.
For whatever reason I thought PMOS was based on Manjaro. Could be something as silly as associating one green logo with another.
As much as I want that to be the case, I don’t think full mobile gnu+Linux is really ready to use daily?
I haven’t exactly been keeping up with things, mind you
I’ve been lucky enough to dumb guy my fedora install since 28, and it’s been pretty decent to me. Granted I’m not using nvidia graphics, and I feel like that could throw a big spanner in the works for regular users. It’s a big enough leap getting into the mindset of installing software from Distro repos rather than directly from the vendor.
I hope the newer nv open kernel modules don’t stay out of tree. Also hope that NVK will give users the ability to just plug and play with mesa drivers in the future.
This video is so fucking funny I didn’t care that it’s almost four hours long lmao
What I was alluding to with regards to idle mclk behaviour is that there are two factors at play: vertical balanking interval (intrinsic to available display modes for each physical monitor) and combined display bandwidth (cumulative of all connected displays to the adapter).
Your mclk will idle high with ‘incompatible’ VBIs, and it’ll also idle high to sustain a lot of display throughput.
This can be observed regardless of GFX vendor, though symptoms may vary somewhat between them. I suppose it could be considered a limitation of GDDR (the same behaviour was never really observed on HBM GPUs like the Vega 64 or Radeon VII)
That said, friends of mine with nvidia gpus have fixed various multi-display specific issues using nvidia profile inspector
Yikes I wasn’t aware of the second part
I was about to ask, isn’t this guy a prolific dickhead?
I don’t know if it was a bug so much as a deficiency. OS Improvements to branch prediction will most likely not be backported to Win10
I don’t think this is related to the OS. What displays do you have connected?
It’s like that episode of futurama - the mirror wernstrom put in space to reflect sunlight, which gets tapped by a little space rock, and tilts into a solar powered death beam
I gather that the nt kernel isn’t inherently bad, rather that the aging win32 subsystem is the problem.
the reset situation may improve in the not too distant future: https://www.phoronix.com/news/AMDGPU-Per-Ring-Resets
who asked for this?
Higher end phones have the capability to gear down to 1hz to save power on static representation. Would be nice to see that on notebook eDP and hell, even with dekstop monitors too.
the fact that valve went and provided official support for a popular, third party, higher res display is pretty wild.
Correct - FSR already applies CAS. I don’t think applying another CAS pass on top of that will work out too well.
FSR already incorporates CAS towards the end of the scaling process. The Adrenalin equivalent is called RIS but applies CAS to the entire rendered frame. I believe some apps allow you to tune CAS individually (2077 comes to mind?)
This outlines several issues, a key one is outbidding apple for wafer alloc on leading processes. They primarily sell such high margin products that I suppose they can go full send on huge dies with no sweat. Similarly, the 4090’s asking price was likely directly related to it’s production cost. A chunky boy with a huge l2$.
I like the way Mike Clark frames challenges in semi eng as a balancing act between area, power, freq and performance (IPC); like a chip that’s twice as fast but twice the size of its predecessor is not considered progress.
I wish ultra-efficient giga dies were more feasible but it’s kind of rough when TSMC has been unmatched for so long. I gather Intel’s diverting focus in 18A, and I hope that turns out well for them.
I’m not sure that arm as an ISA (or even RISC) is inherently more efficient than CISC today, particularly when we look at Qualcomm’s latest efforts in notebooks, more that Apple have extremely proficient designers and benefit from vertical integration.