Raptor Computing Systems Community Forums (BETA)
Water Cooler => General OpenPOWER Discussion => Topic started by: surf on July 30, 2020, 06:14:32 pm
-
I was wondering if there is any news about Raptor. They don't seem to post any news here or on their web page. Do they have any new products coming out? How are they weathering the plague? etc.?
The talospace blog seems to be the best source of power9 and/or Raptor news that I've seen...
-
Personally, I can empathize with all those small businesses operating in the free and open source technology space who may also be impacted by things out of their control, whether it is a loss of sales, loss of colleagues, loss of family or all of the above. On the other hand, I don't want to speculate about Raptor or any other specific business.
If any small business is looking for community support at this time, I hope they will be able to reach out to the right supporters in the community and find a constructive way forward.
Looking at Raptor in particular: I had deferred buying new workstations for a number of years. But with the increase in working from home, it became important for me to get a new workstation in 2020 and Raptor was high on my list. Not everybody is fortunate enough to be purchasing a workstation this year but if you know people who need to maximize their productivity while working from home, suggesting they consider Raptor's products may be helpful. That is why I tried to capture some of my own purchasing experience here (https://forums.raptorcs.com/index.php/topic,167.0.html).
-
The talospace blog seems to be the best source of power9 and/or Raptor news that I've seen...
*bows slightly*
Raptor does have a Twitter. Quitting Twitter and Facebook was one of the best things I did in my life, but they do put things on @raptorcompsys.
-
Indeed, our Twitter feed is the main place we tend to post minor updates or news articles. That said with the COVID19 situation we've been a bit less active with the global community overall; our intent is that once things return to more normal we'll be able to ramp up our social media and marketing again.
We miss you all at the face to face conferences; those were excellent venues for more niche product lines like ours and we have yet to find a viable substitute. Here's hoping 2021 will bring back the more decentralized physical events (i.e. supplant the Google/Amazon/Microsoft/Intel/AMD-dominated online events) and we'll get you see you in person with some of the technologies we're working on for 2021 / 2022!
Side note: Condor was in fact cancelled due to COVID19. We didn't want to have to do that, but economic concerns regarding launching a brand new product into a soft market with limited IBM support won out in the end. We're focusing our efforts on other open, owner controlled, ppc64le technologies, so stay tuned! 8)
-
Indeed, our Twitter feed is the main place we tend to post minor updates or news articles.
Thanks for the reply. I wish you guys luck with your open source projects, and I will stay tuned!
FWIW when I go to the twitter web page I get a cute blue cartoon picture of a bird. If you (or someone) could post relevant news here or on the Raptor web page I would appreciate it.
-
Second that. A Raptor news section would be good on this board. I only joined Twitter because of Raptor ...
-
Raptor may not want to have all these extra chores though. A lot of organizations recently started hiring people in eastern European countries to help with things like this.
For example,
- phpList has set up a small office in Albania
- Debian had an Outreachy intern from Albania to handle contact DebConf sponsors
- Prishtina Hackerspace, in Kosovo, has received funding from other groups to hire a publicity officer (https://forum.flossk.org/t/flossk-is-hiring-project-writer-and-communications-specialist/1275) on a permanent basis
The wage expectations vary, starting from about $300/month for a student in a non-technical field. There are a small number of really good developers there but they insist on globally competitive rates of pay. In between those two extremes there are many possibilities or opportunities to piggy back on other groups there.
-
We miss you all at the face to face conferences; those were excellent venues for more niche product lines like ours and we have yet to find a viable substitute. Here's hoping 2021 will bring back the more decentralized physical events (i.e. supplant the Google/Amazon/Microsoft/Intel/AMD-dominated online events) and we'll get you see you in person with some of the technologies we're working on for 2021 / 2022!
I always hope to know more about Axon AIO, especially now that Power 10 is still far away ...! I hope you will soon give us some news of what these new Power 9s will look like and if we can use them to upgrade, obviously accompanied by the new RAM that AXON AIO requires ... We always stay connected ... :-)
-
The Blackbird shows 'backordered' on the Raptor web page. Anyone know when it will be available again?
-
I don't have an answer about the Blackbird
From my personal analysis, I feel that many people considering a Blackbird might get more advantages from a Talos II Lite, it is only about 10% more expensive but there are benefits as outlined on the comparison page here (https://wiki.raptorcs.com/wiki/RCS_Platform_Comparison).
In particular, using more than 2 memory channels or more than 8 cores both give you significant performance benefits if that is necessary for your workload. It can also take a GPU wider than 2 slots because there is nothing else beyond the GPU slot.
-
The Blackbird shows 'backordered' on the Raptor web page. Anyone know when it will be available again?
I do not know anything about their manufacturing approach, but it may be the kind of thing that production is awaiting a certain number of orders to be reached before making a run of boards.
-
Raptor don't wait for orders. A new batch of Blackbird mainboards is on the way (https://twitter.com/RaptorCompSys/status/1277419609684140033?s=20).
-
Raptor don't wait for orders. A new batch of Blackbird mainboards is on the way (https://twitter.com/RaptorCompSys/status/1277419609684140033?s=20).
Thanks. I already placed an order for a 2nd board, since right now I am not in a position experiment on my flagship and all of my X86 systems are currently tied up with distributed computing projects.
-
The Blackbird shows 'backordered' on the Raptor web page.
Does anyone have news about this? I emailed raptor a month ago and never heard back...
-
Only this (https://twitter.com/RaptorCompSys/status/1312169464465514496?s=20). But it's already more than six weeks old.
-
As of today, sadly no news. (https://twitter.com/RaptorCompSys/status/1332962121315999745?s=20)
I think, I would pick a Talos-II lite if I want to buy a POWER9 mainboard.
-
Please have a good look at my comments comparing Blackbird with Talos II Lite (https://danielpocock.com/talos-II-quickstart/)
Basically, for anybody choosing between Blackbird and the Talos II Lite, I feel that Talos II Lite is the better choice. It only costs a little bit more, maybe 10% extra but it gives you 4 memory channels and supports up to 22 core CPUs.
The new Radeon RX 6800 XT appears to be an optimal choice for multi-seat, multi-monitor or graphics-intensive workloads. Unfortunately, it is wider than 2 slots. If you put it in a Blackbird then it overhangs the 8x slot. On a Talos II Lite, the 16x slot is on the other side so a large GPU doesn't overhang the 8x slot.
The Talos II Lite mainboard is in stock (https://www.raptorcs.com/content/TL1MB1/intro.html)
The web site doesn't give a bundle price but you can email Raptor and ask them if they will offer a bundle.
-
I still have not seen replies to emails or any updates on their web site. However, they did answer the phone and I was told that they are currently expecting blackbird boards to be fabricated in February.
-
Any updates? I think I saw Talospace mention an IRC conversation...
-
Please have a good look at my comments comparing Blackbird with Talos II Lite (https://danielpocock.com/talos-II-quickstart/)
Basically, for anybody choosing between Blackbird and the Talos II Lite, I feel that Talos II Lite is the better choice. It only costs a little bit more, maybe 10% extra but it gives you 4 memory channels and supports up to 22 core CPUs.
The new Radeon RX 6800 XT appears to be an optimal choice for multi-seat, multi-monitor or graphics-intensive workloads. Unfortunately, it is wider than 2 slots. If you put it in a Blackbird then it overhangs the 8x slot. On a Talos II Lite, the 16x slot is on the other side so a large GPU doesn't overhang the 8x slot.
The Talos II Lite mainboard is in stock (https://www.raptorcs.com/content/TL1MB1/intro.html)
The web site doesn't give a bundle price but you can email Raptor and ask them if they will offer a bundle.
I believe the company is fully aware of those drawbacks and going to address them in the next revision of Blackbird.
-
When the new Blackbird is available I'll be happy to update my blog about it
I suspect each user has different priorities:
- for some users the GPU width is the biggest issue
- for other users the CPU core limit is the biggest issue
I suspect fewer people will be worried about the 2 memory channel issue but as part of the overall picture, it swayed me towards the bigger boards.
-
I am of the opinion that what the Power line lacks is an ATX form factor. I hope at this point that having already made the prototype of the Condor, Raptor will restart from that board to make a new motherboard with this form factor and I am sure that he will please everyone without distinction. The ATX format can guarantee multiple memory channels, multiple PCIe ports and everything you need for a single CPU sock, so the best of Talos but more compact and for a single microprocessor.
-
Where are you guys getting your information?
I still have not seen any updates here or on their web page, so I emailed and called Raptor, and left a voice mail... no response in any form so far. Is Raptor still in business?
-
Hi, yes of course it is in business, only it has more difficulty managing communication due to the negative period caused by Covid. Have patience they will answer ...
-
Has anyone heard any news about when Blackbirds will be coming back in stock? I tried asking Raptor support and got not response. It's also been almost a year since I originally ordered, so I'm wondering if they will even come back at all at this point. I understand Covid probably doesn't help this situation, but I wish they kept us in the loop, even if the news isn't good ;)
As an aside, I know the T2 Lite exists, but I was going to use this for a workstation with somewhat limited space, so having a micro ATX board is helpful. It's too late for that now anyway, since T2 Lites are backordered too...
-
To be honest, I would change the order to a Talos-II lite. I don't think they will have the Blackbird back in stock quickly.
Price-wise, it hardly makes a difference. But you need a bigger case, of course, unfortunately.
How about the Dune Pro (https://www.dunecase.com)?
If you can't reach anyone via support, I would try Twitter. If you don't have a Twitter account, you can give me your ticket number and I'll write to Raptor.
-
To be honest, I would change the order to a Talos-II lite. I don't think they will have the Blackbird back in stock quickly.
Price-wise, it hardly makes a difference. But you need a bigger case, of course, unfortunately.
I just double-checked the T2 lite specs and in addition to the case size, which is a bit annoying but probably workable with a case like you suggested, there were a couple of other Blackbird-specific features I wanted (mostly to reuse hardware I already have):
- On-board audio output
- SATA Ports
So assuming I also wanted to add a GPU, getting equivalent features would probably require 3 slots, but the T2 lite only has 2, so that is a bit of a problem.
If you can't reach anyone via support, I would try Twitter. If you don't have a Twitter account, you can give me your ticket number and I'll write to Raptor.
I don't have a Twitter account, but if you could have them look at ticket #337978 it would be much appreciated.
-
You're welcome.
https://twitter.com/mpc7500v2/status/1410334278186160136
Yes, Blackbird has audio, SATA and HDMI. But the number of PCIe slots are equal.
-
Here you will find a comparison of the different mainboards:
https://wiki.raptorcs.com/wiki/RCS_Platform_Comparison
-
You're welcome.
https://twitter.com/mpc7500v2/status/1410334278186160136
Yes, Blackbird has audio, SATA and HDMI. But the number of PCIe slots are equal.
Thank you :). And when I was referencing the slots, I meant that since the Blackbird has built-in audio and SATA, I wouldn't need cards for that, so I would have 1 spare PCIe slot instead of being 1 short. I probably should have been more clear about that. Not to mention the optional SAS/SATA addon has closed firmware according to the wiki, which while the disks themselves would all have closed firmware anyway, I'm trying to avoid as much as possible.
Here you will find a comparison of the different mainboards:
https://wiki.raptorcs.com/wiki/RCS_Platform_Comparison
That's a handy little comparison chart. That kind of stuff is very helpful, not sure if that exact page is one I saw but the wiki was super helpful for me back when I placed my order. It's a shame though, if the T2 Lite had either of the Blackbird's integrated components, I could make some room and get that instead (if it wasn't backordered, that is).
-
You're right. As for audio, you could use a cheap USB sound device. I'm using my AMD graphic card with Kernel 5.4.
-
So I did get a response from Raptor (thank you for the help with that), this is what they said:
... we have not been wanting to give a date only to have it pushed back again as the latest supply chain cut or manufacturing delay happens. That said, we have a *tentative* in-stock date of August 2021 at this point, without any known blockers that would delay it further.
So there's some good news at least, with it (hopefully) only being a few months away. I've waited this long, so I might as well wait a bit longer ;)
-
That's very good news for you. Fingers crosed :)
-
You're right. As for audio, you could use a cheap USB sound device. I'm using my AMD graphic card with Kernel 5.4.
Hey MPC, but do you still use kernel 5.4 today?
-
Yes, correct
-
The integrated audio on the Blackbird is weak on lows and bass, and the mic input needs to be turned all the way up seemingly. So you're not missing much in that regard. Like you, I am patiently awaiting more Blackbird stock. It would be neat if RCS could share which parts are holding up the process, so at least we could monitor component stock through customs channels. Its a shame that these made-in-USA boards all use parts from overseas anyway.
-
That's a handy little comparison chart.
Thanks for this feedback
The integrated audio on the Blackbird is weak on lows and bass, and the mic input needs to be turned all the way up seemingly.
I'm using the Soundblaster X-Fi USB device
Output: Talos II -> USB cable -> X-Fi -> S/PDIF (fibre optic, digital) -> Harmon Kardon AV system -> B&W DM604
Input: Rode lapel mic -> TRRS / 3.5mm converter -> 1/4" converter -> X-FI -> USB -> Talos II
It is working really well
For digital output to S/PDIF you don't need expensive hardware, any USB-to-S/PDIF device is satisfactory
Output is easy, but for microphone input, every component is significant.
-
Yes, correct
I suppose you are doing this because if I remember correctly when Kernel 5.6 came out you started having audio problems via HDMI from the GPU. But haven't you tried with the latest versions and compiling a kernel with 4k pages in order to get the GPU working properly and see how the audio is now? It is a pity that for such a thing you have to remain anchored to an old kernel ... For example, I realized that up to version 5.6.19, the web cam through applications usable through browsers for example, did not work. As soon as I used newer Kernel versions like 5.10, the web cam started working fine, so they added or updated drivers to use this feature. And I think that, like this one, also others so it is a pity that we must remain tied to kernels that are now outdated in my opinion ...
-
The page size doesn’t make any difference.
-
If I do not set the page size in 4K, Linux does not start with the Navi 10 GPU, we have already seen it some time ago with our friend Pocock, even the latest Kernel Fedora, which people like TLE, have made work with Nano GPU , it doesn't work for me with Navi 10, I have to set the page in 4K and from that moment in fact the Kernels compile them myself and they go great.
-
I was reading something elsewhere and happend upon some raptor news:
https://nitter.net/RaptorCompSys/status/1435510763402244105
-
Interview with T Pearson (https://aphid.fireside.fm/d/1437767933/2b9b637d-6a01-491e-bab6-000ec4e37fee/69743ed1-e106-408b-b11a-166ef778e553.mp3) from: https://player.fireside.fm/v2/ak5KcU-1+x6U6CntI/twitter. They go in to detail on some things like Power 10's non-free components. It's over an hour but worth a listen.
-
I see that the prices on the web site have been updated. Could we get some sort of news besides that please?
-
Still hoping for news about Blackbird stocks - I asked on Twitter late last week and there hasn’t been a peep. I realize the supply chain is borked, but it’s been more than eight months since I placed my order.
-
Unfortunately I haven't heard much either internally. I don't think you're the only one in that boat.
-
I think some of this is out of Raptor's control
There is widespread discussion elsewhere about IBM wrecking things in Red Hat, CentOS and Fedora, POWER10 not being 100% open and Google has been wrecking things in Debian. Coincidentally, IBM and Google are the two key players in OpenPOWER. I don't want to gripe about it, only to express what it may mean for everybody who already bought in to this platform.
They had an OpenPOWER room at FOSDEM, they accepted my talk and then they canceled it, this is incredibly nasty stuff. We go to FOSDEM every year as volunteers. It was online this year, the Google people don't have to look the volunteers in the eye because it is all remote so they brought this dirty behavior into FOSDEM.
On a platform like POWER where there are not so many developers to begin with you can't do stuff like that. If people see one volunteer being hurt then ten other volunteers will avoid the platform. People don't care who is right or wrong, when they get the feeling of conflict, they decide to give it a pass or come back and look again in 12 months. That makes it much harder for Raptor to sell to volunteer developers.
Debian has started spending a lot of money on a lawsuit recently. I don't want to hijack this thread with details of the lawsuit, you can download the dossier if you really want to (https://debian.community/wipo-udrp-response-private-confidential/), the only thing I want to emphasize is that 17 developers resigned. 15 of those developers were removed from the keyring on 7 June (https://danielpocock.com/ubuntu-underage-girl-debian-mass-resignations/). Most of them will probably not make any statement about their resignation, most people don't like to take sides but there is a cause and effect: when conflict starts, some people quit.
This is all out of Raptor's control of course but it is a risk to the platform.
Personally, having contributed to patching packages for POWER9, I'm optimistic that lessons learnt from porting work on this platform will be easily transposed to ARM64 and RISC V. Raptor has made the motherboards to a high standard and most people seem to agree they will last a long time, hopefully long enough for RISC V to appear on our desktops too (https://en.wikipedia.org/wiki/RISC-V#Implementations).
-
We would respectfully ask that the discussion here remain on topic as much as possible. While RISC-V and ARM remain attractive from a cost perspective, we do want to remind everyone involved that all current ASIC implementations of RISC-V -- and all reasonably powerful ARM devices -- are actually more closed and require more blobs than POWER10 does. While at least right now we won't build POWER10 systems due to the blobs resident in those CPUs and associated interface devices, it should also be apparent that current RISC-V and ARM implementations are a step even further in the wrong direction.
We believe there is a future for the POWER platform and its truly open, standardized ISA -- especially with projects like LibreSoC already underway, and internal projects (some of which are already yielding public results in the Kestrel OpenPOWER soft BMC project), we would advise against switching to blob-filled, proprietary platforms just to "hit back" at IBM.
For clarity: we do not agree with where IBM is going with the POWER platform with POWER10. We also do not believe that IBM has the ability to restrict what can be done with the OpenPOWER ecosystem now or in the future. They are (were) a major player, yes, but at the end of the day they are unable to call back or restrict what other companies and individuals are able to do -- and are already starting to do -- with the ISA. The best way to keep things open in the short term, when also looking at long-term effects, would be to simply standardize the open software ecosystem on the POWER9 ISA vs. the POWER10 ISA. At least for now, as this would further encourage the use of open chips vs. chips that require binary components, since POWER9 would remain the baseline ISA compatibility level for said new devices.
Hopefully this will spark further on-topic discussion. We're not going anywhere, and we refuse to build and ship blob-infested hardware, so RISC-V remains a no-go for us. Hopefully Debian will also continue to show this blob-free focus in the future, as Raptor and Debian have been fairly well aligned on this topic for many years.
...typing this from a Talos II workstation with Debian and Ungoogled Chromium installed.
-
Raptor has made the motherboards to a high standard and most people seem to agree they will last a long time, hopefully long enough for RISC V to appear on our desktops too (https://en.wikipedia.org/wiki/RISC-V#Implementations).
If you look at that comment, there is nothing in it to suggest an open RISC V will arrive imminently. In fact, given that nobody is holding their breath for open RISC V, the comment could be seen as deliberately optimistic about Talos II boards running for years to come due to their quality.
we would advise against switching to blob-filled, proprietary platforms just to "hit back" at IBM.
There was nothing in the post to suggest people "hit back" at IBM
It is just a reality check, that is all. We can see the way people started building Alma Linux and other continuations of CentOS. That is not to "hit back" at Red Hat or IBM, they are building that because they need it and it was the right thing to do.
Given the communities are not so big, these situations do lead to people duplicating effort (e.g. Rocky Linux) and other inefficiencies that may have been avoidable. Rather than having 3 or 4 forks of CentOS, developers doing exactly the same thing in parallel, it would be interesting if some of that developer effort went to POWER9 porting.
Speaking as a developer, I fully respect the right of any developer, whether it is a lone volunteer or a giant company like IBM to change their direction. It then raises the question about how other people work around that.
For example, do you see the IBM POWER9 chips continuing to be available in sufficient quantities for the Raptor ecosystem?
Do you see any other manufacturer coming along with a 100% open chip to continue from POWER9?
The best way to keep things open in the short term, when also looking at long-term effects, would be to simply standardize the open software ecosystem on the POWER9 ISA vs. the POWER10 ISA.
Could you define that? For example, which key software products need to commit to that statement? In practice, how many of the developers on that part of the open source ecosystem are employed by IBM / Red Hat and could that take them down a POWER10 path?
...typing this from a Talos II workstation with Debian and Ungoogled Chromium installed
Does this mean the Chromium libs are now available for building other things? If so, I might have another look at some projects that were pending for me to port.
-
If you look at that comment, there is nothing in it to suggest an open RISC V will arrive imminently. In fact, given that nobody is holding their breath for open RISC V, the comment could be seen as deliberately optimistic about Talos II boards running for years to come due to their quality.
Out main point was that the first part could be taken as RISC-V being the inevitable long-term succesor to POWER, when we're fairly certain that would not be the case, especially in the blob-free / owner-controlled sphere. Regardless, we do appreciate the note on quality -- that's an area we've put a lot of time, effort, and resources into.
There was nothing in the post to suggest people "hit back" at IBM
It is just a reality check, that is all. We can see the way people started building Alma Linux and other continuations of CentOS. That is not to "hit back" at Red Hat or IBM, they are building that because they need it and it was the right thing to do.
This wasn't directed so much to you as it was to the general developer community. We've seen some knee-jerk reactions when bad news comes out, including some people that basically just gave up and said "I'm doing x86 only, ME and vendor blobs are inevitable".
Speaking as a developer, I fully respect the right of any developer, whether it is a lone volunteer or a giant company like IBM to change their direction. It then raises the question about how other people work around that.
Indeed. For us, that's why we have such a stong requirement for owner control, including opening and standardization of the ISA itself. At least this removes all of the artifical barriers that would otherwise be thrown up. For example, Intel and AMD want to make gaming and streaming consumer systems -- they need the ME and PSP to do that, but since the ISA is not open that now steps on everyone else's rights to use the systems in other ways without effectively allowing Intel/AMD access to the data on them, because no one else can (legally) make compatible CPUs that also meet the blob-free / owner-controlled requirements.
For example, do you see the IBM POWER9 chips continuing to be available in sufficient quantities for the Raptor ecosystem?
Yes, there are many, many years worth of the CPUs available.
Do you see any other manufacturer coming along with a 100% open chip to continue from POWER9?
Short answer: yes. Long answer: [redacted] skunkworks [redacted].
They're still planned, just delayed from COVID and the recent macroeconomic meltdown. LibreSoC is also working in the background and contining to make progress, we're not looking at a single pathway to the required silicon here, just that all pathways produce 100% blob free ppc64le ISA 2.07+ compatible devices.
Could you define that? For example, which key software products need to commit to that statement? In practice, how many of the developers on that part of the open source ecosystem are employed by IBM / Red Hat and could that take them down a POWER10 path?
Great question! We'd say just having the main binary distros (Debian, Fedora, SuSE?) ensure they keep their package archives compatible with POWER9 vs. requiring POWER10 is enough. Then the only other group that needs to be on-board is the JIT writers -- don't use POWER10-specific instructions. To be honest, this is going to happen naturally anyway, since no one that we know of is making POWER10 systems that are would be desktop-class or exist outside of a cloud environment, let alone open systems. This all solely due to IBM's poor decision to close parts of the POWER10 platform, it's quite sad.
Does this mean the Chromium libs are now available for building other things? If so, I might have another look at some projects that were pending for me to port.
Yes, we've been investing significant resources in keeping a POWER build of Chromium available, tracking upstream Debian including the security patches but also including the Ungoogled patchset. Our thought was that since Google absolutely refuses to upstream the POWER port (our suspicion is because it is an owner controlled, blob-free platform, this would interfere with the long-term goal of mandated low-level tracking for advertising), why enable any of the Google services at all?
The patches are also fairly easy to unroll in debian/series if you did want to just build a stock Debian Chromium for POWER. In any case, we'd love to see the base patches integrated into the official Debian builds, maybe you could help us get some traction there?
Builds are currently here:
https://quickbuild.io/~raptor-engineering-public/+archive/ubuntu/chromium/+packages
dget -x / apt-get source work against that repository.
Google's unfortunate stance on upstreaming is basically "we won't do it and we won't tell you why".
https://chromium-review.googlesource.com/c/chromium/src/+/3133001
Applying Occam's Razor against that yields a few concerning options, including the potential existence of a third party agreement that would prohibit it. As such, the remaining patches need to be carried downstream in various distros; they're already carried downstream for Gentoo etc., see e.g. https://bugs.gentoo.org/669748 .
-
For example, do you see the IBM POWER9 chips continuing to be available in sufficient quantities for the Raptor ecosystem?
Yes, there are many, many years worth of the CPUs available.
In this respect POWER9 is far more secure than POWER10 or any of its competitors.
Three years ago 14LPP wafers were running in New York (East Fishkill, I think, but maybe Malta) and production was starting up in Dresden as a second site. There are probably additional sites by now; my attention has been focused elsewhere lately. In any case, just those two locations alone are a whole lot more geopolitical security than the rest of the industry has. 14LPP isn't the same as IBM's special eDRAM-cap variant of 14nm, but it would be very unusual for it to not be running from the same sites as the less-flashy merchant foundry wafers.
Don't worry about supply of chips. Supply of blackbird motherboards, on the other hand...
Do you see any other manufacturer coming along with a 100% open chip to continue from POWER9?
Short answer: yes. Long answer: [redacted] skunkworks [redacted].
LibreSoC is also working in the background and contining to make progress,
I've been having a hard time finding information about their 180nm tapeout. The chips came back almost a year ago; are any data available? How did things turn out? Surely there's been time for several iterations with a FIB by now...
we're not looking at a single pathway to the required silicon here, just that all pathways produce 100% blob free ppc64le ISA 2.07+ compatible devices.
Unfortunately getting the foundries to care about anything other than your organization's market cap is a gigantic obstacle these days. Design quality and engineering talent are not taken into consideration anymore.
-
including the potential existence of a third party agreement that would prohibit it.
I'm quite sure one exists, although less sure that it is the entire explanation for the situation.
One of the major concessions to get Hollywood to stop insisting on browser plugins (Flash and Silverlight) was the browser vendors agreeing to never allow their brands to be placed on a piece of software that didn't support EME, as a condition of receiving CDM licenses (widevine, etc). Unfortunately User-Agent has made brands and trademarks part of protocols, but that's another story....
Anyways, this licensing condition is the reason for weird situations like:
- Builds of Firefox that make no changes other than disabling EME (https://wiki.parabola.nu/Iceweasel) being forced to use a different name.
- Firefox suddenly and silently flag ignoring the --disable-eme flag since September 8th, 2017 (https://hg.mozilla.org/releases/mozilla-aurora/rev/afc827378c1075c2d849f07f64a4021235a51586) -- so the only way to truly disable EME is to patch the source code like Tor-Browser (https://gitweb.torproject.org/tor-browser.git/commit/?h=geckoview-96.0.3-11.0-1&id=952eef1f393989d027fc1c4364bb6dc59d8b1f1) does. This gives Mozilla a toehold to claim that what you're compiling "isn't Firefox" and politely ask you to not use their trademark.
- (I speculate) Google dragging its feet on powerpc64le. Having to get Widevine working on powerpc64le and then maintain it is a burden for them, which is a factor in their decision.
You might have better traction asking the QT folks to integrate the patches into QTwebengine. They support widevine but don't distribute the binary themselves, which strongly implies that they are not allowed to do so. The only reason they wouldn't be allowed to do this is lack of a licensing agreement. If they don't have a licensing agreement then they aren't subject to the "everywhere or nowhere" requirement.
I fear that the effort to merge the Firefox powerpc64le JIT support will hit similar nontechnical roadblocks. I hope I'm wrong about that.
-
I fear that the effort to merge the Firefox powerpc64le JIT support will hit similar nontechnical roadblocks.
I don't think so, insofar as I have unofficial OKs once I get it to a point I'm happy with it. I'm just not happy with it yet.
-
I fear that the effort to merge the Firefox powerpc64le JIT support will hit similar nontechnical roadblocks.
I don't think so, insofar as I have unofficial OKs once I get it to a point I'm happy with it.
Very glad to hear that!
-
For example, do you see the IBM POWER9 chips continuing to be available in sufficient quantities for the Raptor ecosystem?
Yes, there are many, many years worth of the CPUs available.
And even if there weren't, aftermarket availability would persist. One can still find piledriver and bulldozer Opterons for socket G34 all these years later being sold out of recycling operations and private sellers. I know I've got IBM Sforza socket CPUs laying around unused right now, that could find their way to ebay in such an event. I think it's the fact that there is a specialized microcosm for both of the previous examples.
This wasn't directed so much to you as it was to the general developer community. We've seen some knee-jerk reactions when bad news comes out, including some people that basically just gave up and said "I'm doing x86 only, ME and vendor blobs are inevitable".
I've seen that defeatist mentality in all manner of other freed technology where it's always rationalized away as "you'll never be able to 100% avoid malicious functionality so you might as well use ____. It's what everyone else is using anyway". I believe this qualifies as nirvana fallacy. Then again, I can't call myself a developer. So I have no plans to stop using my RCS board(s) unless something better comes along.
I fear that the effort to merge the Firefox powerpc64le JIT support will hit similar nontechnical roadblocks.
I don't think so, insofar as I have unofficial OKs once I get it to a point I'm happy with it. I'm just not happy with it yet.
I'm looking forward to the work getting mainlined :D
-
I discussed the state of my Raptor order last week and was told they’d received a shipment of Blackbirds and would resume shipping shortly. I was even told that they would be able to ship mine out within a week, though I haven’t gotten a shipment update or tracking number yet. I really hope that info was accurate.
-
That's fantastic! When did you place an order for one? Hopefully my order will be filled as well; I placed mine almost a year and a half ago
-
That's fantastic! When did you place an order for one? Hopefully my order will be filled as well; I placed mine almost a year and a half ago
I placed mine in late September of last year. Cross your fingers.
edit: Got an email this evening confirming shipment, with a tracking number. What a weekend for me to go out of town... but next week I'm free to set it up!
-
Excellent!
-
Going on a bit over 2 years since I ordered my Blackbird, haven't heard anything yet. Hopefully they didn't forget about me :'(
Glad others are finally getting theirs though!
-
I placed mine in late September of last year. Cross your fingers.
edit: Got an email this evening confirming shipment, with a tracking number. What a weekend for me to go out of town... but next week I'm free to set it up!
That's great to hear! I hope all goes well. It sounds like the Free Software Foundation might be eyeing some Blackbirds (https://archive.ph/kxCoA) too.
-
A formal update on Blackbird has been released (https://twitter.com/RaptorCompSys/status/1548061751396028421)
Offical update on #Blackbird : Our commit date is August 31, 2022 for order fulfillment & restock. It's been a challenging year with supply issues, fab closures, massive inflation, and COVID delays everywhere, but owner controlled desktop computing will be available again soon!
First, we'd like to thank everyone here for their patience. Rest assured we've been burning the midnight oil and applying significant resources over a long period of time to ensure that the Blackbird would be available again as soon as possible, while also trying to mitigate price increases. This was all being done while we were still providing a workable hardware and software stack for desktop use -- as an example, we continue to maintain Chromium for ppc64le, and Chromium is a complex piece of software with a fast major and security release cadence. Without your financial support in ordering these owner controlled platforms, none of this would be possible.
Second, we'd definitely like to hear back from you all when you do receive your units -- public tweets, reviews, etc. are much appreciated, and will help drive further adoption of the platform and of owner controller computing in general. We note that the FSF is slowly attempting to transition to blob-free systems (https://www.fsf.org/blogs/sysadmin/closing-in-on-fully-free-bioses-with-the-fsf-tech-team) and especially given the shift to everything-as-a-service this goal is more important than ever.
Thank you all for your patience during these extremely challenging times, and we hope that the platform is worth the wait!
-
Excellent! I'll take two Arctic Terns now, Alex.
-
Great. Does this also mean faster boot times?
-
Thank you all for your patience during these extremely challenging times, and we hope that the platform is worth the wait!
Level heads and long term perspectives prevail in tumultuous times. I hope you at Raptor know just how important the work that you're doing is.
Second, we'd definitely like to hear back from you all when you do receive your units -- public tweets, reviews, etc. are much appreciated, and will help drive further adoption of the platform and of owner controller computing in general.
I will be able run and review more elaborate testing once I have a duplicate staging system available to try the crazier things on. My one and only Blackbird being a critical primary system has been a source of caution.
-
Deleted - don’t want to clutter the thread with off-topic stuff, but if anybody can lend insight on why I can’t get date and hwclock to agree, I’d be grateful. Thread here: https://forums.raptorcs.com/index.php/topic,7.msg3065.html#msg3065
-
>>This all solely due to IBM's poor decision to close parts of the POWER10 platform, it's quite sad.
Re: those blobs, based on GITHUB links from Twitter post (listed below), seem to be related to non-IBM components; very possible IBM is not allowed to make the source code available.
PCIe I/O provided by Synopsis: "ricmata and op-jenkins Synopsys firmware 2.04p fixes DFE slicer calibration"
https://github.com/open-power/hcode/blob/master-p10/import/chips/p10/procedures/ppe/iop/
https://www.synopsys.com/designware-ip/interface-ip/pci-express/pci-express-5.html
https://www.synopsys.com/dw/ipdir.php?ds=dwc_pcie5_phy
DDIMM memory buffer "Explorer" firmware provided by Microsemi:
https://github.com/open-power/ocmb-explorer-fw/
https://www.microsemi.com/document-portal/doc_download/1244316-smc-1000-8x25g-smart-memory-controller
https://www.anandtech.com/show/14706/microchip-announces-dram-controller-for-opencapi-memory-interface
Disappointing for sure, and may not be able to change going forward.
-
>>This all solely due to IBM's poor decision to close parts of the POWER10 platform, it's quite sad.
seem to be related to non-IBM components very possible IBM is not allowed to make the source code available.
And you think they didn't know that when they made the decision to use those components?
-
In (some) fairness to IBM, Raptor systems -- despite their cost and their visibility -- are considered the "low end" of the OpenPOWER ecosystem. IBM makes their money on their big institutional partners who don't care much about the things we do (openness, auditability), and it's more important to IBM to give them a new performance shiny to keep them in the sales-and-service fold lest they jump ship for x86. If this was what got them to market quicker, then we lose out. That's just the way the business is.
That said, IBM has also taken a bit of a black eye over Power10 as a result and because Raptor systems *are* so visible, it's harmed their secondary goal to make the architecture more generally relevant again. I think this will be factored into Power11 but there's never any guarantee.