SoylentNews is people
SoylentNews
Is it time For open processors? Jonathan Corbet over at lwn.net seems to think so. He lists several ongoing initiatives such as OpenPOWER, OpenSPARC and OpenRISC, but feels that most of the momentum is in the RISC-V architecture right now.
Given the complexity of modern CPUs and the fierceness of the market in which they are sold, it might be surprising to think that they could be developed in an open manner. But there are serious initiatives working in this area; the idea of an open CPU design is not pure fantasy.
[...] Much of the momentum these days, instead, appears to be associated with the RISC-V architecture. This project is primarily focused on the instruction-set architecture (ISA), rather than on specific implementations, but free hardware designs do exist. Western Digital recently announced that it will be using RISC-V processors in its storage products, a decision that could lead to the shipment of RISC-V by the billion. There is a development kit available for those who would like to play with this processor and a number of designs for cores are available.
Unlike OpenRISC, RISC-V is intended to be applicable to a wide range of use cases. The simple RISC architecture should be relatively easy to make fast, it is hoped. Meanwhile, for low-end applications, there is a compressed instruction-stream format intended to reduce both memory and energy needs. The ISA is designed with the ability for specific implementations to add extensions, making experimentation easier and facilitating the addition of hardware acceleration techniques.
[...] RISC-V seems to have quite a bit of commercial support behind it — the RISC-V Foundation has a long list of members. It seems likely that this architecture will continue to progress for some time.
(Score: 2) by fyngyrz on Thursday January 25 2018, @01:33AM (1 child)
They do for consumer acceptance. That's why you're not going to get these into the consumer space unless they're so fabulous they can emulate the old stuff at equivalent speed.
The usual run of desktop computer consumers — and there are a huge number of them — by and large, don't care about servers, processors in their TVs or phones, or Raspberry pis. They care about Office, Photoshop, Autocad, Excel, games, and so on. Either you run that stuff like it was your best friend, or you're dead in the water for the desktop and the likes of Intel and AMD will keep on keeping on owning that space.
The vertical markets you're talking about exist apart from any issues with getting an open CPU to actually replace the current crop of closed CPUs.
(Score: 2) by DannyB on Thursday January 25 2018, @02:33PM
If you read the list of things I mentioned (TiVo's, Smart TVs, Smartphones, etc), I would dare say that qualifies as the consumer space.
I don't think of those as vertical markets. Consumer products that sell in the tens, or hundreds of millions let alone billions are not exactly what I would call vertical markets. By that definition I could say Windows 10 is a vertical market and we know that is not true.
I consider vertical markets as something that is (1) highly specialized, AND (2) has a small but loyal market share. The consumer products I mentioned (Smart TVs) might fit #1 (and I don't think they do), but definitely don't fit #2. Vertical market would be specialized software for a lawyer's office, or doctors office, or your local library, or the place that changes your oil. A limited market and highly specialized.
I think you're talking more about fashion and popularity contest. I'm talking about making big money by selling (or licensing) billions and billions of chips running Linux. And boards with these chips. And support chips. And the programming that goes into these devices.
A few years back, and I don't have a link handy, I saw a graph showing how the sheer numbers of Android (not including iPhone!) devices would exceed the number of Windows PCs and Laptops in a few years (which is now past).
While I understand the attachment to the way things were with Microsoft's monopoly PCs and concern about squeezing every last drop of performance, I think the world has changed and is changing. Windows PCs just don't have the importance they once had. You mention consumer acceptance, most consumers can do everything they need to do daily with nothing more than a web browser, eg, a Chromebook. Not all. But a surprisingly large number. Not everyone needs photoshop. Or they can use some web based dumbed down app. And the state of things today is not the end state. Amazing things are being done within the browser already that suggest that one possible future is that the "browser" might be the replacement for Windows in the future for all types of consumer apps -- even apps like Photoshop.
With Microsoft no longer having quite the power and dominance it once had, we've seen a number of changes at Microsoft. It should be quite informative that Microsoft has embraced ARM processors for pragmatic reasons. That Microsoft has opened up .NET considerably more. That Microsoft has offered both SQL Server and SQL Server Management Studio on Linux, what is the world coming to! That Microsoft offers Office on other platforms such as Android and Chromebooks. (Never mind the technical implementation, but consider it from the 'perception' of consumers.) That Microsoft has Windows Subsystem for Linux, and openly admitted that the reason was 'to draw developers back to Microsoft'. That is quite telling. The reason I say all this is that is to reinforce that the importance of getting Microsoft Windows to run on a new chip simply may not be quite as important as you think it is. Important yes. But not the major factor.
I think there is a very bright future for new chip architectures. Despite the tarpit of Microsoft Windows. I would point out ARM as a huge success story. There is very probably more ARM processors than Intel processors in every day use. And that gap will only widen as ARM processors move into data centers. It's not that new processor architectures will need to adapt to Windows. It's the other way around. Microsoft will be forced into adopting to the newer generations of hardware -- IN THE LONG RUN. Not overnight. But in the long run. And it already has happened with ARM. It was unthinkable ten years ago that Microsoft would offer an ARM version of Windows. But here we are.
The Intel architecture is a dinosaur with 4+ decades of baggage. With all the variants, an immensely complex instruction set.
The lower I set my standards the more accomplishments I have.