371–380 of 510 posts
Earlier quoted context omitted.
my $5k m3 max 128gb disagrees
Doubt it, a year ago useful local LLMs on a Mac (via something like ollama) was barely taking off. If what you say it's true you were among the first 100 people on the planet who were doing this; which btw, further supports my argument on how extremely rare is that use case for Mac users.
If they end up actually shipping this, lots of people will buy these machines to get an AArch64 Linux workstation—even if they are not interested in AI or Nvidia GPUs. At $3,000, it will be considerably cheaper than alternatives available today (except for SoC boards with extremely poor performance, obviously). I also expect that Nvidia will use its existing distribution channels for this, giving consumers a shot at…
> At $3,000, it will be considerably cheaper than alternatives available today $3000 gets me a 64-core Altra Q64-22 from a major-enough SI today: https://system76.com/desktops/thelio-astra-a1-n1/configure And of course if you don't care about the SI part, then you can just buy that motherboard & CPU directly for $1400 https://www.newegg.com/asrock-rack-altrad8ud-1l2t-q64-22-amp... with the 128-core variant being $240…
Still I expect the Nvidia systems will be easier to get, especially for (de jure) consumers.
I'm looking at my Jetson Nano in the corner which is fulfilling its post-retirement role as a paper weight because Nvidia abandoned it in 4 years. Nvidia Jetson Nano, A SBC for "AI" debuted with already aging custom Ubuntu 18.04 and when 18.04 went EOL, Nvidia abandoned it completely without any further updates to its proprietary jet-pack or drivers and without them all of Machine Learning stack like CUDA, Pytorch et…
$100M, 2.35MW, 6000 ft^2
>>Designed for AI researchers, data scientists, and students, Project Digits packs Nvidia’s new GB10 Grace Blackwell Superchip, which delivers up to a petaflop of computing performance for prototyping, fine-tuning, and running AI models.
$3000, 1kW, 0.5 ft^2
Earlier quoted context omitted.
I mean I can get a Snapdragon X Elite laptop for $1200 that'll have a faster CPU than the one in the Digits, too...
Their speeds should be very similar, but which is faster is uncertain. There have not been any published benchmarks demonstrating the speed of Cortex-X925 in a laptop/mini-PC environment. In smartphones, Cortex-X925 and Snapdragon Elite have very similar speeds in single thread. For multithreaded applications, 10 big + 10 medium Arm cores should be somewhat faster than 12 Snapdragon Elite. The fact that NVIDIA Digits…
Earlier quoted context omitted.
For programs dominated by iterations over arrays, these 10 Arm Cortex-X925 + 10 Cortex-A725, all 20 together, should have a throughput similar with only 10 of the 16 cores of Strix Halo (assuming that Strix Halo has full Zen 5 cores, which has not been confirmed yet). For programs dominated by irregular integer and pointer operations, like software project compilation, 10 Arm Cortex-X925 + 10 Cortex-A725 should have…
How did you come up with these numbers? There don't seem to be many shipping products with these cores. In fact, the only one I could find was the Dimensity 9400 with a single X925 and older generation A720s. And of course the Dimensity is a mobile SoC, so clocks will be low. Are you projecting based on Arm's stated improvements from their last gen? In that case, what numbers are you using as your baseline?
That means a total of 80 execution pipelines for NVIDIA Digits, 48 execution pipelines for Snapdragon Elite and 128 equivalent execution pipelines for Strix Halo, taking into account only the complete execution pipelines, otherwise for operations like FP addition, which can be done in any pipeline, there would be 256 equivalent execution pipelines for Strix Halo.
Because the clock frequencies for multithreaded applications should be similar, if not better for Strix Halo, there is little doubt that the throughput for applications dominated by array operations should be at least 128/80 for Strix Halo vs. NVIDIA Digits, if not much better, because for many instructions even more execution pipelines are available and Zen 5 also has a higher IPC when executing irregular code, especially vs. the smaller Cortex-A725 cores. Therefore the throughput of NVIDIA Digits is smaller or at most equal in comparison with the throughput of 10 cores of Strix Halo.
On the other hand, for integer/pointer processing code, the number of execution units in a Cortex-925 + a Cortex-725 is about the same as in 2 Zen 5 cores. Therefore the 20 Arm cores of NVIDIA Digits have about the same number of execution units as 20 Zen 5 cores. Nevertheless, the occupancy of the Zen 5 execution units will be higher for most programs than for the Arm cores, especially because of the bigger and better cache memories, and also because of the lower IPC of Cortex-A725. Therefore the 20 Arm cores must be slower than 20 Zen 5 cores, probably only equivalent with about 15 Zen 5 cores, but the exact equivalence is hard to predict, because it depends on the NVIDIA implementation of things like the cache memories and the memory controller.
I feel this is bigger than the 5x series GPUs. Given the craze around AI/LLMs, this can also potentially eat into Apple’s slice of the enthusiast AI dev segment once the M4 Max/Ultra Mac minis are released. I sure wished I held some Nvidia stocks, they seem to be doing everything right in the last few years!
Will there really be a mac mini wirh Max or Ultra CPUs? This feels like somewhat of an overlap with the Mac Studio.
0. https://www.macstadium.com/blog/m4-mac-mini-review
1. https://www.apple.com/mac/compare/?modelList=Mac-mini-M4,Mac...
Earlier quoted context omitted.
Now that the majority of their revenue is from data centers instead of Windows gaming PCs, you'd think their relationship with Linux should improve or already has.
It's possible. I haven't had a system completely destroyed by Nvidia in the last few years, but I've been assuming that's because I've gotten in the habit of just not touching it once I get it working...
In case you're curious, I googled. It runs this thing called "DGX OS": "DGX OS 6 Features The following are the key features of DGX OS Release 6: Based on Ubuntu 22.04 with the latest long-term Linux kernel version 5.15 for the recent hardware and security updates and updates to software packages, such as Python and GCC. Includes the NVIDIA-optimized Linux kernel, which supports GPU Direct Storage (GDS) without addit…
I wonder what kind of spyware is loaded onto DGX OS. Oh, sorry I mean telemetry.
Earlier quoted context omitted.
The market heavily disagrees with you. "The global gaming market size was valued at approximately USD 221.24 billion in 2024. It is forecasted to reach USD 424.23 billion by 2033, growing at a CAGR of around 6.50% during the forecast period (2025-2033)"
Farmville style games underwent similar explosive estimates of growth, up until they collapsed. Much of the growth in gaming of late has come from exploitive dark patterns, and those dark patterns eventually stop working because users become immune to them.
They did not collapse, they moved to smartphones. The "free"-to-play gacha portion of the gaming market is so successful it is most of the market. "Live service" games are literally traditional game makers trying to grab a tiny slice of that market, because it's infinitely more profitable than making actual games.
>those dark patterns eventually stop working because users become immune to them.
Really? Slot machines have been around for generations and have not become any less effective. Gambling of all forms has relied on the exact same physiological response for millennia. None of this is going away without legislation.