Hacker News Reader

Comment by gchadwick | Hacker News Reader

I am a little surprised to see this. I'd imagine NASA would chose a CPU with an already proven track record (especially for something so wide ranging, the press release says it expected to be used for 'virtually every future space mission, from planetary exploration to lunar and Mars surface missions'. This is a new design from SiFive and there's not a huge amount of SiFive IP around yet to demonstrate how good (or otherwise) their verification is. Running into a hardware bug whilst your CPU is in space is not good.

Still good SiFive have convinced NASA otherwise, they must have a pretty strong verification story behind the scenes.

View on HN

The whole point of choosing SiFive over anything else is to encourage competition.

SpaceX is similar while they are very successful it also encourages competition in a space that really needed it and now there are so many other companies doing smaller launches that don’t make business sense to SpaceX.

I absolutely love that NASA is doing this AND encouraging the RISC-V ecosystem. Maybe it's impossible, I don't know, but if we have an open soruce alternative for hardware with the kind of reach that Linux has in software i think that's the best way forward.

I agree open source hardware would be great but SiFive is a closed source vendor like many others.

It's RISC-V itself that has a permissive license, allowing anyone to make an implementation open or closed source.

An open ISA is a good start. It means short of any closed-source extensions the code can move to another chip vendor. With smart modularization of the code, even parts using closed-source extensions could be potentially retargeted faster than moving to a whole new ISA. Finding a radiation hardened complete solution that's totally open source could be a tough request to fill.

> short of any closed-source extensions the code can move to another chip vendor

That's a huge limitation. It's unfortunate that RISC-V allows for closed implementations (IP) and also closed ISA extensions.

I think it's a rather pragmatic decision given corporate capitalism is the economic model under which most processor design and trade happens, at least toward the higher end. The good news is since the main ISA and several open extensions exist, any open source hardware implementation of those aren't hindered by the ISA. That's also true for SPARC, POWER, and a few others of course. But RISC-V seems to be the belle of the ball and apparently simpler to build a hardware design around.

Someone, somewhere may eventually form a coalition to pay TSMC or Samsung to generate an in-house spec for a high-performance RISC-V processor with an open-source license on the hardware design, too. Some places use RISC-V in products where the processor is another line item in the BOM and not the centerpiece of a SOC or dev board, like Western Digital using it in storage products. A group of companies and institutions could very conceivably get things where we'd wish now that the open ISA has set the stage.

> rather pragmatic decision given corporate capitalism

Supporting a system that centralized designs of critical semiconductors in the hands of few companies and manufacturing in the hands of TSMC is not very pragmatic. If anything it's very ideological.

Acknowledging that's the system under which something has happened does not imply, let alone assure, personal support for that system overall. The real world doesn't bow silently in deference to our hopes and dreams.

> The real world doesn't bow silently in deference to our hopes and dreams.

You are implying that socioeconomical systems are "the real world" and somehow they just happen to exist independently from our "hopes and dreams".

It's the complete opposite. Unlike solar flares and ocean tides, socioeconomical systems are entirely the product of human decisions.

>It's unfortunate that RISC-V allows for closed implementations (IP) and also closed ISA extensions.

It is rather fortunate. Else, it couldn't possibly aspire to be the standard ISA for absolutely everything.

I agree. NASA has hit the jackpot by using fixed-price contracts from vendors which don't have a legacy track record from the Apollo days.

The Cost-plus contracts have made them fat and lazy and somewhat remind me of that Bugs Bunny cartoon where the cats don't mind the mice emptying the fridge.

NASA is taking a small risk, but the rewards can, as SpaceX has demonstrated, be HUGE.

SiFive is a new company (with backing from large companies like Qualcomm), but the people working there are industry experts with decades of experience who know the value of verification to both designers and customers.

One of the main value adds of an open ISA + open reference implementations Chisel/Chipyard + access to RTL (I think?) is that LOTS of people are hungry for really good multi-core out-of-order CPU pipelines with super-stringent levels of provable correctness. I think the tooling ecosystem is on the right track in terms of providing a FOSS toolchain that supports this. It's not there yet, but you're average ECE master's student could probably teach themselves chipyard and start their own Rocket fork which is much easier to test/verify at the basic-block level than a lot of other tooling I've used.

Note that X280 is not OoO. It's the same proven dual-issue in-order U74 core (similar to ARM A55) what has been out for a few years, and is just now hitting Raspberry Pi levels of price in the VisionFive 2 and Pine64 Star64. The X280 just has an added RISC-V Vector unit.

Also because the CPU layout is generated by software, maybe it is easier to add custom constraints specific for space.

The alternative is the ancient PowerPC-based RAD series of which the most recent incarnation is now almost 2 decades old.

NASA is partitioned between the (IMHO limited) parts that actually do stuff and the golly-geewhiz-PR stuff. People who are planning next gen planetary missions are considering trusted, proven rad hard platforms. This is just PR to distract in its own small way from the SLS debacle.

What debacle? Is it dead?

Money spent vs results over time. Results excluding Boeing & subcontractor revenue. SLS was originally sold as cost effective reuse of existing SSMEs combined with relatively simple tankage to get a cheap large booster. Against those metrics it’s a debacle, unclear if it ever will fly, especially more than once.

While I agree about SLS, and I'm also hopeful about SpaceX's Starship stack, I'd really like to see a successful test. They're working on it, but just imagine how much closer they could have been with even a fraction of this SLS boondoggle contributed.

If NASA is supposed to be a multi-state grant to the sciences, I'd much rather they focus the funding where it will deliver results that benefit the public commons. The jobs program for obsolete and finicky space tech is a dis-service to the public and even the workers who's skills are in questionably useful specialties.

Compared to Starliner and its move from Atlas V to Vulcan [0], SLS is a paragon of incremental success. Additionally, to be fair to SLS, many of the problems associated with the program have to do with the mobile launch platform, which was built for the previous Constellation program and required considerable refit for SLS. [1]

0. https://arstechnica.com/science/2022/09/nasa-will-pay-boeing...

1. https://en.wikipedia.org/wiki/Exploration_Ground_Systems#Lau...

> Against those metrics it’s a debacle, unclear if it ever will fly, especially more than once.

Not to mention a national security nightmare. Imagine a world without the COTS program, where we would most likely still be waiting for whatever version of Starliner that we finally got. We would right now be reliant on Russia to return our astronauts to earth from the ISS. Can you even imagine what we’d have to give up for their safety?

This alternate reality could yield a good movie script. Think of American astronauts trying to hijack a Russian Soyuz docking at the station to get back to earth.

The SLS was pretty much designed by Congress. Design choices were made primarily to keep jobs in plants which were previously used for Space Shuttle parts.

With its impending first launch, a lot of discussion is popping up again about it arguably being way too slow to develop, overly expensive, and not fit for the intended mission profile.

Criticism that SLS is unfit for the intended mission profile is misguided. SLS never had an intended mission profile. The mandate was always to build a rocket in these places and with these contractors and at fabulous expense, and any notion of what would be done when/if that boondoggle I mean rocket ever flew was the mere coda of an afterthought.

Yeah the engineers were really fucked in their options and it shows in their evaluation.

They were supposed to build a 130 to LEO rocket that should launch the first time in 2016 (min 70t) and use existing contractors. That is kind of insane.

So NASA basically allow their internal teams to come up with Block upgrades based systems and that's where the whole SLS Block 1a, 1b, 1c comes from.

The problem with this was (and is) that they had no reason to rush to a quick block 1 as there were really no missions for it.

Had they been given until 2020 developing a single core modern Saturn V would have been a much better design (this is clearly evident in their internal design evaluation documents). The had already put a lot of work into J-2x and modern F-1 version was attainable. My alternative would have been to use a whole bunch of SpaceX Merlin 1D instead but they never considered that. This version would also have been much closer to the 130 tons in the first version.

And it could have been evolved to be reusable unlike the current SLS.

What people from the outside don't really see is the NASA internal competition. Johnson Space Center clearly wanted the Shuttle derived version, Kennedy Space Center really wanted to Saturn V style rocket. Some at NASA HQ wanted to give it as a contract to SpaceX/ULA.

> This is just PR to distract in its own small way from the SLS debacle.

You're implying a degree of coordination which organizations the size of NASA just don't have. Artemis has had two scrubbed launches, they didn't put out this announcement to distract from it. I doubt someone went over to SiFive and said, "Hey, help us distract from the Artemis I launch problems and we'll give you a nice contract."

I don’t think coordination has to be explicit. Seeing meh PR and thinking, “hey maybe we should step up the advanced technology press releases” is enough. As for NASA contracts, it’s almost harder to name someone who doesn’t have even a tiny one, even cranks. Also it’s not like 2 Artemis failures are in a vacuum - it’s the culmination of a decade of failure and misspent funds.

>>> This is just PR to distract in its own small way from the SLS debacle.

> Seeing meh PR and thinking, “hey maybe we should step up the advanced technology press releases” is enough. As for NASA contracts, it’s almost harder to name someone who doesn’t have even a tiny one, even cranks.

Except no one cares about the instruction set of space computers, except a small cadre of computer geeks.

A story no one cares about is a bad thing to use as a distraction.

I agree with you. I meant it as part of the flux of NASA tech press releases. It could be some CPU thing, it could be a magic space drive, it could be the official kitty litter of the moon base. ;)

You are overthinking it.

Does it stay crunchy in moon milk?

Yes, it's a ridiculous claim. HSPC has been in the works for several years now, and is ran thru JPL which is completely unaffiliated with Artemis.

Reply on news.ycombinator.com