I can't know what Ascalon will actually be, but back in April/May 2025 there were actual performance numbers presented by Tenstorrent, and I analyzed what was shown. I concluded that Ascalon would be the x86_64 equivalent of an i5-9600K.
That's useable for many applications, but it's not going to change the world. A lot of "micro PCs" with low power CPUs are well past that now. If that's what Ascalon turns out to be, it will amount to an SBC class device.
I don't know what bubble you are living in, but the i5-9600K is many steps up beyond "SBC class".
The Raspberry Pi 5 results on Geekbench 6 are all over the place. A score between 500 to 900 in single core and a 2000 multi core score.
Radxa 4 is an SBC based around the N100 and it basically gets the same or slightly higher performance as the Raspberry Pi 5.
Meanwhile the i5-9600K gets a score of 1677 in single core, which is 83% of the performance of the entire Raspberry Pi 5 and gets a score of 6199 when using multiple cores, that's 3x the performance.
I'd call this at least "Laptop class" and you even admitted yourself back in 2025 that you're using a processor on that level.
My bubble includes a number of SBCs and embedded boards from Advantech, frequently using Ryzen embedded (V1000 class) CPUs.
SBC is too vague I suppose. Past the Raspberry Pi form factor SBC class, there are many* SBC vendors with Core i5-1340P and similar CPUs today. That's a 2023 device, and just past a 2018 i5-9600K, aligning well with what I claimed.
In 2025+, such a CPU is not a desktop class device, and is sufficient only in low cost laptops (but in much lower power form.) A MacBook Neo A18, for example, is considerably better than a i5-9600K.
It would be great if Tentorrent actually yields such a product, and if, based on later performance projections that appeared in late 2025, Ascalon is actually faster, but, as I said, the world will not change much. RISC-V developers will appreciate compiling like it's 2019, but that's as far as it will go.
* LattePanda Sigma, ASROCK NUC, DFROBOT, Premio and many NAS and industrial devices.
TBH I still don't really get how it's different from MIPS. As far as I can tell... Loongson seems to be really just MIPS, while LoongArch is MIPS with some extra instructions.
Wait, this is a modern-ish ISA with a software-managed TLB, I didn’t realize that! The manual seems a bit unhappy about that part though:
> In the current version of this architecture specification, TLB refill and consistent maintenance between TLB and page tables are still [sic] all led by software.
(purely on vibes) loongson feels to me like an intermediate step/backup strategy rather than a longterm target (though they'll probably power govt equipment for decades of legacy either way :p)
Last I looked (about a year ago,) IBM is 3 things: Software licensing, services and Big Iron. The companies' revenue is split roughly equally among these three areas.
An interesting perspective of IBM is its relative position. It's leveled off at about $60b/y, after a lengthy decline. It is far overmatched by many big tech companies today in terms of revenue.
It's a niche business, serving niche demands. I think IBM's moat is that most of its business is highly uninteresting: industrialized box ticking work, deeply entangled by contracts and a strong need for continuity by its customers.
I actually had a recent encounter with one of IBM's products. A commercial B2B REST API I created was analyzed by an IBM vulnerability scanning platform on behalf of a major US municipality. It didn't find anything actually critical, but there were some worthwhile points in the report, and working around a false positive was a frustration. The product, in this case, is diffusion of responsibility.
On the Big Iron end, IBM isn't really selling hardware. They selling an ecosystem: services, software, support, continuity (over decades,) etc. It pleases me that they chose to stick to Power: it's nice to know Itanium didn't kill off every enterprise RISC platform.
Maybe, one day, some major quantum computing breakthrough happens at IBM. As far as I can see, that's the only play they have that could change their trajectory. In the meantime, they have a large software portfolio and plenty of institutions that will keep signing contracts long after I'm gone.
Looking will blow up too many cushy deals for too much of the Powers That Be. A great deal of it is non-show "chairmanship" jobs for the family and friends of politicians. Legal bribes.
Feeding Our Future was another fine example of the shenanigans that go on in the US. Power Forward Communities was setup with $100 and captured $2 billion in EPA grants; caught while still doing only token work and not yet having been drained into the pockets of the favored. Abundant Blessings in CA was another nest of fraud; in criminal court right now.
Seems like you can't go more than a couple days without another non-profit scam mess hitting headlines.
Can you explain what you're referring to about Power Forward Communities? As far as I can tell it's a network of established non profits like Habitat for Humanity and Rewiring America, it seems they did more than token work in things like electrification before their grant was rescinded.
The actual org itself acts as an umbrella to coordinate work among the participating non-profits.
OK - except I recall a tour of Japanese graduate students at CompuMentor in San Francisco, studying the whole setup.. the reason? there are no "non-profits" in Japan (at that time, still?). CompuMentor was a great example -- both dipping deeply into the tills with special sales and large steady cash flows AND serving a genuinely underserved niche.
Throw-down on some EPA effort As If That Is Typical, is intellectually dishonest. Mitigation and remediation are expensive and take time. And also there is substantial abuse and greenwashing. So you throw out the baby with the bathwater, so to speak.
"Its all a scam" says the barstool attorney, doing nothing.
> so there should be no significant design changes
The NRC frequently changes requirements for reactors while they're under construction. The NRC does not waive the right to demand changes merely due to prior design approval. This is a novel (for the US) design, so there will be unanticipated changes as the project progresses.
Russia has been operating two sodium cooled fast reactors for decades. The BN-600 and BN-800 are both operating today. The early history of the BN-600 was... interesting, suffering (at least) 14 sodium fires due to leaks. This "Natrium" design is similar; a sodium pool with two sodium loops. They are taking on the additional challenge of storing a massive quantity of molten salt. It's going to take a lot of effort by many steely eyed missile people to make this happen.
Trump issued an EO in 2025 that's supposed to make the NRC more circumspect about requiring changes of approved designs. Then there is all the pull Gates has. Wyoming is no hotbed of anti-nuclear activism. So that's all to TerraPower's favor. But TerraPower will need to fully utilize all the tailwind it can find to make this work.
"Is something like this competitive, or preferred, in certain applications?"
They cite a very specific use case in the linked story: Virtualized RAN. This is using COTS hardware and software for the control plane for a 5G+ cell network operation. A large number of fast, low power cores would indeed suit such a application, where large numbers of network nodes are coordinated in near real time.
It's entirely possible that this is the key use case for this device: 5G networks are huge money makers and integrators will pay full retail for bulk quantities of such devices fresh out of the foundry.
> how do you get them off the shelf if you also need TB of memory
You make products for well capitalized wireless operators that can afford the prevailing cost of the hardware they need. For these operations, the increase in RAM prices is not a major factor in their plans: it's a marginal cost increase on some of the COTS components necessary for their wireless system. The specialized hardware they acquire in bulk is at least an order of magnitude more expensive than server RAM.
Intel will sell every one of these CPUs and the CPUs will end up in dual CPU SMP systems fully populated with 1-2 TB of DDR5-8000 (2-4GB/core, at least) as fast as they can make them.
I do likr the idea that capitalism can always ignore the broader base of consumers and just raise prices. Eventually, therell only be one viagra pill bought by trillionaires at 1$ million dollars.
> I wonder which approach is more capital efficient? Which is more time efficient?
I don't. I wonder whether US astronauts are going to die on the surface of the moon while the world watches in 4K. I believe, to my great relief, that by some minor miracle, we've ended up with a NASA administrator that is wondering the same thing, and also has the temerity to make some really hard calls, despite what is doubtless an enormous amount of pressure. I've been analyzing his words and speech. There is just no bullshit in him, and he clearly doesn't suffer fools. You can see it. He's like something out of SAC from the Cold War.
NASA is in desperate need of exactly that. Perhaps that's not the correct, permanent disposition for all things at all times, but if the US and NASA are actually going to engage in another Space Race, this time with China, we very much need it at this time.
There is an incentive to use higher power. Push the edge of safety limits to achieve higher performance from lower cost devices, for example.
It occurs to me there is an opportunity here. Passive lidar detectors sampling fleets of vehicles in the real world, measuring compliance and detecting outliers, would be interesting. A well placed, stationary device could sample thousands of vehicles every day. Patterns will emerge among manufacturers. Failure modes will be seen.
Cursory queries on this reveal nothing. Apparently, no one is doing this. We're all relying on front end certification and compliance. No thought given to the real world of design flaws, damage, faulty repairs, unanticipated failure modes, etc.
Apparently there are lidar jammers. I bet those are rigorously compliant with Class 1 safety regs... No one manufacturing those is ever going to think; "hey, why not a 50W pulse train?"
Thing is you can make a 3d printer; it's basically CNC stuff with a different tool. I suppose fabricating your own 3D printer needs to be legally ensnarled as well.
Purely performative power grabbing. There is no epidemic of ghost gun violence. These measures would not stop it if there were. The new legal thicket this creates will exclusively harm innocent people.
This is about notching a victory: making others bend the knee to the prerogatives of some pressure group. Nothing more. Behind it are wealthy pearl clutching virtue signalers. In front of it there are non-profit grifters and politicians with campaigns to fund, and in the middle lobbyists milk both sides. Everyone mouthing obligatory moral panic narratives to keep the money flowing.
> Thing is you can make a 3d printer; it's basically CNC stuff with a different tool.
Yes, but no too. I've built and purchased many 3d printers. You can make a 3d printer, but can you make one that works reliably as something like a washing machine with little to no tinkering or adjustment? Bambu Lab can sell you that for less than three hundred bucks. Just give it a file, feed it plastic, and it will rip.
I can now build a 3d printer that reliable, but only with parts and tools from other people and only after experience. Realistically not being able to buy a 3d printer off the shelf means it's going to be inaccessible for most people.
At this point the most likely place for truly competitive RISC-V to appear is China.
reply