Getting ROCM to work properly is like herding cats.
You need a custom implementation for the specific operating system, the driver version must be locked and compatible, especially with a Workstation / WRX card, the Pro drivers are especially prone to breaking, you need the specific dependencies to be compiled for your variant of HIPBlas, or zLUDA, if that doesn’t work, you need ONNX transition graphs, but then find out PyTorch doesn’t support ONNX unless it’s 1.2.0 which breaks another dependency of X-Transformers, which then breaks because the version of HIPBlas is incompatible with that older version of Python and …
Inhales
And THEN MAYBE it’ll work at 85% of the speed of CUDA. If it doesn’t crash first due to an arbitrary error such as CUDA_UNIMPEMENTED_FUNCTION_HALF
You get the picture. On Nvidia, it’s click, open, CUDA working? Yes?, done. You don’t spend 120 hours fucking around and recompiling for your specific usecase.
Also, you need a supported card. I have a potato going by the name RX 5500, not on the supported list. I have the choice between three rocm versions:
An age-old prebuilt, generally works, occasionally crashes the graphics driver, unrecoverably so… Linux tries to re-initialise everything but that fails, it needs a proper reset. I do need to tell it to pretend I have a different card.
A custom-built one, which I fished out of a docker image I found on the net because I can’t be arsed to build that behemoth. It’s dog-slow, due to using all generic code and no specialised kernels.
A newer prebuilt, any. Works fine for some, or should I say, very few workloads (mostly just BLAS stuff), otherwise it simply hangs. Presumably because they updated the kernels and now they’re using instructions that my card doesn’t have.
#1 is what I’m actually using. I can deal with a random crash every other day to every other week or so.
It really would not take much work for them to have a fourth version: One that’s not “supported-supported” but “we’re making sure this things runs”: Current rocm code, use kernels you write for other cards if they happen to work, generic code otherwise.
Seriously, rocm is making me consider Intel cards. Price/performance is decent, plenty of VRAM (at least for its class), and apparently their API support is actually great. I don’t need cuda or rocm after all what I need is pytorch.
So, AMD has started slapping the AI branding on to some of their products, but they haven’t leaned in to it quite as hard as Nvidia has. They’re still focusing on their core product line up and developing the actual advancements in chip design.
I think it’s in the pipeline. AMD has bought Xilinx, which builds FPGAs and already had some AI specific cores in their processors. I believe they’re developing that further and integrating it in their GPUs now.
Two to three meals a day, almost no snacks, generally a decent amount of fiber. Mom's basically the same and I think grandmother was. Mom has been diagnosed with various forms of IBS. Dad has Celiac's and a DNA test I took said increased risk.
If I go keto, almost all the issues disappear. Trying to do that is basically impossible whilst living with my wife because I can't just not make food and not keep anything I shouldn't eat in the house (my willpower eventually crumbles when I'm busy or stressed).
T2 is definitely the best terminator film, but you’re missing out if you discount all the sequels. Dark Fate at least is pretty darn good, and it’s basically a direct sequel to T2, so you don’t have to watch all the films in between.
I had genuinely forgotten about the sequel until I saw this. Started wondering how I had missed that and then I remembered it was a straight to streaming cash grab. Time to go back to being blissfully ignorant.
I had never heard of the sequel until a day or two ago when the YT algorithm fed me Schaffrillas’ video about it. I still haven’t actually watched it, and based on that review I think I’ll keep it that way.
This is the first time I’ve ever heard of it and it looks awful. That’s paw-patrol level of animation right there, and it definitely sits in the uncanny valley of animation for me.
I don’t think it’s a problem, more like a situation. You are not doing anything wrong or stupid, just interested in something new and promising and have the resources to pursue it. Good for you, may you find gold.
If you want to skip having a big ass bag full of liquids, many products are available in solid form. Toothpaste comes in tablets, shampoo comes in bars, and shave lotion also is available in bars. Then you can save your liquid quota for what really matters, like a wide assortment of personal lubricants.
As someone who has German as their second and English as their third language, I’ve never misunderstood that line like that. That’s hella funny though.
I like to be able to sing along to songs when I’m alone in the car, so even if I don’t understand the meaning of the words, I like to know the words.
I also enjoy word play, and Du Hast has some of that. So knowing the bit of trivia about ‘Hast’ and ‘Hasst’ being homophones in German and meaning ‘have’ and ‘hate’ respectively, and the main portion of the lyrics being wedding vows adds a layer of enjoyment to the song for me.
Personally, I prefer things I don’t understand because I don’t have to mentally deal with whatever bullshit they are saying. I can sing it a thousand times without ever thinking too much about it because I know the sounds and not the meaning of the words.
I can belt out a ton of Japanese or Russian music, because I started listening to help my language learning (classes, not self-guided), but I don’t actually understand the songs. I “know the words”, but that’s it.
memes
Newest
This magazine is from a federated server and may be incomplete. Browse more on the original instance.