#371

  Переглядів 128,859

Andreas Spiess

7 місяців тому

When I got these new RISC-V ESP32 boards in my mail, I asked myself: Is this new technology revolutionary as written everywhere? What are the advantages for a typical Maker? Time for a closer look. But pay attention: It will be a rough ride and not for the fainthearted because we will talk about “stacks,” “IP,” “ecosystems,” and a lot about standardization.
If you hang on till the end, you should have enough knowledge to impress your boss. But maybe you will not be happy.
I am a proud Patreon of @GreatScott! , @ElectroBOOM , @Electronoobs , @EEVblog , and others. No Docker, No Microsoft Teams, Zoom

Links:
Jeroen's Video: ukposts.info/have/v-deo/kGNqoqSHjqOc13U.html


00:00 Intro
01:08 Content
01:42 What is RISC-V? / RISC / CISC
03:59 RISC / CISC History
04:57 The Technology Stack
06:39 Standardization and Flexibility
08:53 Most important Learning
09:33 ISA (Chip Architecture)
10:37 Corporate Strategies (why is ARM so successful?)
14:03 RTL, FPGAs, Verification
15:05 The Ecosystem
15:30 Who needs RISC-V?
16:16 Linux as an Example for Open Source development
16:44 Other Open Source Chips and why RISC-V's timing is right
17:10 The Absent
17:33 The Proof (Nvidia bought ARM)
18:51 What is Open Source?
19:46 How to order our custom chip?
20:21 The ESP32-C3
22:10 There is Hope (SpriteTM and Hackaday)
22:41 The Future of RISC-V
23:37 Where to use the ESP32-C3?
24:04 Conclusions

The links above usually are affiliate links that support the channel (no additional cost for you).
Supporting Material and Blog Page: www.sensorsiot.org
Github: www.github.com/sensorsiot
My Patreon Page: www.patreon.com/AndreasSpiess
Discord: discord.gg/JfgDSa8
If you want to support the channel, please use the links below to start your shopping. No additional charges for you, but I get a commission (of your purchases the next 24 hours) to buy new stuff for the channel
My Amazon.com shop: www.amazon.com/shop/andreassp...
For Banggood bit.ly/2jAQEf4
For AliExpress: bit.ly/2B0yTLL
For Amazon.de: amzn.to/2r0ZCYI
For Amazon UK: amzn.to/2mxBaJf
For ebay.com: ebay.to/2DuYXBp

profile.php?...
spiessa
www.instructables.com/member/...
Please do not try to email me. This communication channel is reserved for my primary job
As an Amazon Associate, I earn from qualifying purchases

КОМЕНТАРІ
TheEvertw
TheEvertw День тому
Why is ST not jumping on the RISC-V bandwagon? Probably because it currently has little advantage over ARM, and for ST the switch to RISC-V is relatively easy. Their main IP, the various peripherals, are easy to integrate with another CPU core. And their market is more interested in price and how long a chip is supported than with using the latest hot ISA.
Andreas Spiess
Andreas Spiess День тому
I am not sure if it would be so easy if you look at their ecosystem (installed base, compilers, etc.). Microsoft needed a very long time to implement an architecture other than Intel. for example. Their advantage could be to save the license fees paid to ARM.
khushboo amin
khushboo amin Місяць тому
Loved your infotertenmaint.... Also loved your way of simplifying it
Andreas Spiess
Andreas Spiess Місяць тому
Glad you liked it
J. Barrett
J. Barrett Місяць тому
Thankfully, the open-source situation is a bit less dire than it might seem (although still the majority of RISC-V cores you can buy right now on the market are proprietary). SiFive's older designs, a bunch of Western Digital designs, Nvidia's RISC-V deep learning accelerator, Bluespec's cores, and research projects that seem to be fairly capable and a good base for potential commercial designs, like Rocket and BOOM from Berkeley, the SHAKTI initiative from IIT Madras, and RISCy_OOO from MIT. I know we outside of academia tend to be derisive of research projects ("research-quality software" is derisive for a reason), but these are real cores that *do* work, right now (don't try to build BOOM's head in silicon right now though, because someone accidentally introduced Meltdown on mainline...). The other really exciting thing is that there's been a lot of slow work around getting the tooling around building stuff to actually open up. Projects like OpenOCD have been around for a while for the programming side of things, but on the tooling side things haven't been great historically, but this is really starting to change: Verilog/SystemVerilog simulators like Icarus have been around for a while, but we're increasingly getting open tooling that can actually make the round-trip out to an FPGA. Also exciting is that BlueSpec is open-source now.
Andreas Spiess
Andreas Spiess Місяць тому
I agree with you on the cores. Where I see problems is with the periphery which is not standardized at all. So I fear that the CPU can be programmed, but the SOC cannot be used without proprietary tools.
Varun Durge
Varun Durge 2 місяці тому
Nobody’s gonna talk about 65nm Indian risc 5 processor?
Andreas Spiess
Andreas Spiess 2 місяці тому
I do not know. It always takes a while till things get well known.
Henky Prayoga
Henky Prayoga 2 місяці тому
Mind blowing!!!
Andreas Spiess
Andreas Spiess 2 місяці тому
:-)
Paco
Paco 3 місяці тому
Well RISC-V is open source to an extent. The core ISA and vector instructions (somewhat different to SIMD). But it also has a dark side into the custom extensions realm, for example a DSP, accelerators (matrix ops Etc.), some MCUs ext., GPU (despite a few open initiatives), ADs/DAs, etc. So must be taken with a grain of salt. Anyways, is way better than live into the x86 and ARM proprietary ISAs.
Frank Graffagnino
Frank Graffagnino 3 місяці тому
great video. thanks for the thorough explanation!
Andreas Spiess
Andreas Spiess 3 місяці тому
You are welcome!
MobiusHorizons
MobiusHorizons 3 місяці тому
I really appreciated the historical view you provided in this video. I think it was very helpful for framing the discussion. And I really appreciated the thoughts around standardization at one layer and the effects that has on flexibility above that layer. However I think you are missing two important aspects of the open source-ness of risc-v, which is the compiler ecosystem, and the ability of more people to get involved. Today on my mac with a version of clang installed from homebrew, I can compile C code for risc-v. I can do this without generating any cross compilers or compiling anything from source. it's just there in a readily available open source compiler. At the same time it's totally viable for me to build an emulator for risc-v allowing me to write code and run it. And more importantly this can be done in an education context, which means more people are getting experience learning about lower levels of the stack. This may not make a huge difference for makers right away, but I fully expect it to mean that future innovations in chips are more likely to happen on a risc-v base platform than on some totally proprietary platform. This should mean that people can move to new chips without needing as many layers of abstraction, or huge porting efforts to switch between.
Andreas Spiess
Andreas Spiess 3 місяці тому
For the CPU you are right. But I can not completely agree because most of the parts other than the CPU still are closed source. So I assume the manufacturer has to disclose information to build a compiler. And many SOC manufacturers do no more charge for their compilers. And that is what probably matters most for a typical user. But I am very interested where it leads and if also "closed shops" will stop develop their own tools because it is too expensive.
Ferenc Szabo
Ferenc Szabo 3 місяці тому
BTW there is a new player in the town, and on the paper it looks awesome the GD32VF103CBT6
Andreas Spiess
Andreas Spiess 3 місяці тому
Is it supported by the Arduino IDE?
Murray Madness
Murray Madness 4 місяці тому
Excellent overview. Having lived through all this too, I tend to think ARM will continue to dominate. With the car companies chip problem, maybe FPGA technology will take over, it was so promising back then, but afaik it has remained niche.
Andreas Spiess
Andreas Spiess 4 місяці тому
I agree. The ARM ecosystem is strong and their offering is very good.
Électro-Bidouilleur
Électro-Bidouilleur 4 місяці тому
A difficult subject to cover. Very well explained. Thanks!
Andreas Spiess
Andreas Spiess 4 місяці тому
Glad you enjoyed it!
Harry Kek
Harry Kek 5 місяців тому
The guy with the Swiss accent has a particularly sarcastic & interesting dry humour! Thank you for your Clear Concise lesson.
Andreas Spiess
Andreas Spiess 5 місяців тому
You are welcome!
Damián González
Damián González 5 місяців тому
This is not a UKposts video. This is a master class. Thank you professor!
Andreas Spiess
Andreas Spiess 5 місяців тому
Thank you for the nice words. You're welcome!
Nikola Radakovic
Nikola Radakovic 5 місяців тому
what a precise :) and clear explanation, not fluff straight to the point, echte Schweizer
Andreas Spiess
Andreas Spiess 5 місяців тому
Thank you!
Pavel Baidurov
Pavel Baidurov 5 місяців тому
Like from Russia
Andreas Spiess
Andreas Spiess 5 місяців тому
Благодарность
Luna Ravenheart
Luna Ravenheart 5 місяців тому
Just a little nitpick that'll get lost in the sea of existing comments: Windows, bless its terrible, complex, legacy-worshipping, capitalist heart, has run on Alpha and Itanium, albeit not for very long. It should still be consigned to the trash heap, but I want to make sure we have the history right before we trash it.
Andreas Spiess
Andreas Spiess 5 місяців тому
While I cannot agree with your judgement of Windows I knew that it ran on DEC Alphas. I worked for DEC during this time. But it was not important enough to make a dent in the history;-)
Lance Harvie
Lance Harvie 5 місяців тому
ARM really took off due to mobile computing because of low power. There are tradeoffs - CISC - Small code sizes, high cycles per second RISC - Low cycles per second, large code sizes
Andreas Spiess
Andreas Spiess 5 місяців тому
True. But also because Intel was not interested in this field till they were too late, I think. The PC and server business was very profitable back then with a monopoly.
Upcycle Electronics
Upcycle Electronics 5 місяців тому
You riding yet? I had my first night ride with a summer kit last night here in California :-) When looking at the Linux kernal, I get the impression most software drivers are reverse engineered. Linus has said before that he tries to use the latest hardware because everything old is broken in kernel space. I'm no kernel dev, and have no ability to contextualize this. I've run Gource on the Linux kernal and other project git repos where it's easy to see the periodic nature of development and how various software branches stagnate. If RISC-V is the standard and grows to the size and complexity of an x86, I hope there is a much greater potential for ongoing maintenance and development of existing hardware support. I think we have already seen the plateau of hardware due to quantum effect size constraints. Which should mean there is no longer a reason to have our disposable device culture. How the culture shifts back to a long term serviceable and maintainable hardware philosophy will be interesting in my opinion and is my main hope for RISC-V. -Jake
Andreas Spiess
Andreas Spiess 5 місяців тому
I started with the road bicycle (500km). The Harley is still in the garage. It is still cold here. Concerning obsolesce: As you mention, the crowd is a good protection. This is why I stick to Arduino IDE and Raspberry Pi, for example. They survived already now longer than most other things.
Gacheru Mburu
Gacheru Mburu 5 місяців тому
👍
Andreas Spiess
Andreas Spiess 5 місяців тому
:-)
Predabot __
Predabot __ 6 місяців тому
Algorithm comment yeah! :)
Sumit Gaur
Sumit Gaur 6 місяців тому
Nice
Andreas Spiess
Andreas Spiess 6 місяців тому
:-)
ramkumar reddy
ramkumar reddy 6 місяців тому
thanks andreas !!! you were ausome
Andreas Spiess
Andreas Spiess 6 місяців тому
Glad you liked it!
Torsten Rüger
Torsten Rüger 6 місяців тому
Good summary. Though the esp may be a bad example, it is a WiFi chip and not a general cpu. General cpus like alibabas 16 core android, or Syntacore 64 core general cpu may be better candidates. But the summary status true, it is not so important to end users. Only through the short on market forces will it affect us Thanks for another good one, Torsten
Andreas Spiess
Andreas Spiess 6 місяців тому
I assume we will see much more RISC-V chips like the specialized -C3 in the near future I do not see a break-trough in the general purpose high-end soon.
Layke Findley
Layke Findley 6 місяців тому
Lol, we do that voluntarily. Underrated quote.
Layke Findley
Layke Findley 6 місяців тому
@Andreas Spiess uhh I wish I remember the line we were referring to. I might watch again to let you know!
Andreas Spiess
Andreas Spiess 6 місяців тому
Unfortunately I do not understand what you mean :-(
TednTin
TednTin 6 місяців тому
I really love this video. Has explained in a systematic manner with basics. Edit: Can't imagine the amount of research needed for presenting this complex of a topic so appetizing.
Andreas Spiess
Andreas Spiess 6 місяців тому
Glad you like it! It took my whole business life to get all the info ;-)
Max Headrom
Max Headrom 6 місяців тому
I know people don't find Richard Stallman very sympathetic but he is correct - and I understand why he's so mad with Linus. Linus Torvalds created the Linux kernel but it was the GNU project that created all the other parts including the Compiler. SAP did do some very interesting things and has a professional Suze available - with a free version also available. Very nice job!
Max Headrom
Max Headrom 6 місяців тому
A question to the readers: anyone knows if it's still possible to run Linux on the PS3? Thanks!
Max Headrom
Max Headrom 6 місяців тому
Your observations about standardization can be applied to almost everything: the maker community uses it all the time when you buy stepper motors and other mechanical parts. Standardization gives us the ability to buy parts from a variety of manufacturers - in a way, Standardization created the maker community.
Max Headrom
Max Headrom 6 місяців тому
Chips are not everything: one also needs cold beer!
Max Headrom
Max Headrom 6 місяців тому
Mr. Spies: I think you forgot Motorola there. RISC does not make programs that longer since complex instructions are rarely used. The first ARM or Acorn RISC Machine was so power efficient when they first tested it it was drawing no current!!! They then realized they forgot to power it ... but it worked, nonetheless, only with the power supplied by the other connections. The guy who developed the instruction set is considered one of the most important women in computer history: Sophie Wilson (with Steve Furber). Your explanation about standardization is awesome! (F1 cars have the break on the left foot ... but we can't rent them).
Andreas Spiess
Andreas Spiess 6 місяців тому
For me, Motorola was more important in the smaller systems and in the 1980/90. That is why I subsumed them in the "others". I did not feel they had a big role towards RISC-V
Max Headrom
Max Headrom 6 місяців тому
My parents used some of the first Anti Biotics and Vaccines available: I have a high standard for calling things "revolutionary". Your channel is very good!
Rupesh Patel
Rupesh Patel 6 місяців тому
Nice
Andreas Spiess
Andreas Spiess 6 місяців тому
Thanks!
nsk ksn
nsk ksn 6 місяців тому
Andreas, this 'diluted' video was absolutely fantastic. Easily digestible. Thank you sharing this.
Andreas Spiess
Andreas Spiess 6 місяців тому
Glad you enjoyed it!
Duncan Walduck
Duncan Walduck 6 місяців тому
"We will see how... react..." (18:39 or so) - Indeed. With both Intel and AMD=Xilinx (= arch rival ATI) integrating ARM as a "hard processor system" in several of their 'more rounded' FPGA SOCs! AMD seem to have sold their hand in Tensilica to Broadcom, as far as I can quickly find, or your might get them pimping up that Xtensa archiecture along with Espressif -- up til now (and maybe still).
Duncan Walduck
Duncan Walduck 6 місяців тому
@Andreas Spiess If they go ahead and rip up the business model that ARM had, then they shouldn't be surprised if business goes elsewhere - especially with, well, other architectures maturing. Good signs initially that the RPi foundation got in and got their pipedream done. It seems maybe Sparkfun too [unless theirs is a 'module' - well, it has to be with radios, although that doesn't rule out custom silicon.] It was Acorn's own pipedream to make a microprocessor which _led_to_ ARM.
Andreas Spiess
Andreas Spiess 6 місяців тому
Things seem to move... I am not sure if buying ARM was a good idea and maybe they will be happy if it will not be allowed by governments...
DreaD
DreaD 6 місяців тому
Is there an odysee link to this episode?
Andreas Spiess
Andreas Spiess 6 місяців тому
I would hope so.
lola a
lola a 6 місяців тому
The increasing interest in RISC V from companies and institutions all over the world is also result of recent USA politic. People realize that just out of an arbitrary decision of Washington's administration the companies you source your chips/IP from can be forbidden to deliver in your country, even if they do ship this administration will require them to implement backdoors, ... But it's much harder to try to rule open source project than a private company's project, who will you sue ? The fact that the consortium's head moved to Switzerland follow that same logic. The stake is independence. If a bully country decide to make pressure on your supplier you can just go to any other and have another chip build for you from another country without having to rewrite your software. Just make sure you don't pay in US$ !!! Ask Huawei who invested billions dollars in 5G relying on Xilinx rfsoc technology that they can't purchase anymore. Almost all defense institution all over the world (all but US) are financing research projects around RISC V also for this reason. It's not so much about sharing, but more a way to be more resiliant toward bullies countries.
Popopopo
Popopopo 6 місяців тому
ARM first was british (and is still for now) and used in Acorn british microcomputer Acorn Archimed. It has been used in lot of computer/hardware before apple, and now half of higher part of top ten supercomputers are based on RISC architecture (first ARM by Fujitsu, Japan, then Power by IBM, USA, then Shunway, from China, the last one is the first to start new generation RISC in super-computers. European community is currently working on a continental made processor for supercalculator, mixing RISC ARM and RISC-V technologies. The first test supercomputer implementation is in Barcelona, and already powerfull. There are lot of RISC-V interesting cheap and powerfull boards, like Sipeed implementations, still in microcontroller market. But high frequency RISC-V chip come fastly, with Starfive processor runing at 3.5Ghz, you don't speak about V (ector processor) extension in RISC-V, this is a comeback of a very really powerfull architecture for massive computation, and will be a very interesting point in this standard, that lot of enterprises want.
Andreas Spiess
Andreas Spiess 6 місяців тому
Thank you for the additions.
anton garcias
anton garcias 6 місяців тому
In a led driver that I've bought recently there was a chip BL602 from Bouffalo labs. It's also a Risc V chip and probably suits well for large volumes. So, maybe is the new path for some embedded devices. Two months ago I wanted to investigate. But on the other hand also Expressif is about to launch the ESP32-S3 that seems impressive (at least on paper) and also comes with a Risc V low power processor. I think I'll wait for it.
Andreas Spiess
Andreas Spiess 6 місяців тому
I assume Espressif also knows the BL602 and do not want to loose the market ;-)
Jason Doege
Jason Doege 6 місяців тому
Crucially, the main aspect of RISC-V which is not open-source, is any individual implementation. One can not independently verify that the chip you have in your hand precisely matches the behavior of the open-source RTL that defines any particular RISC-V. In fact, the implementation most assuredly will differ. At the very least, manufacturing test structures that provide deep observability into the state of the uProc will have been added, frequently along with on-chip instrumentation. What is not open-source between RTL and silicon that should be for any device is: post-synthesis gate-level net-list byproduct of the place-and-route step along with the technology libraries, the LEF and DEF that describe the layout and, finally the GDS-II for the device. But, RISC-V providers will not release any of these design descriptions.
Andreas Spiess
Andreas Spiess 6 місяців тому
Thank you for your additions!
Juan Carlos Reyes Andrade
Juan Carlos Reyes Andrade 6 місяців тому
Nicely explained, thanks!
Andreas Spiess
Andreas Spiess 6 місяців тому
You're welcome!
DjDeets Dropping Those Funky Beats
DjDeets Dropping Those Funky Beats 6 місяців тому
Wonder how risc-v will compare to openpower 🤔
Andreas Spiess
Andreas Spiess 6 місяців тому
I do not think that a technical comparison matters for most of the people and the difference probably is small. I feel this has to do with politics. Why else do we need a new definition?
MadMatty72
MadMatty72 6 місяців тому
Truth - great vid
Andreas Spiess
Andreas Spiess 6 місяців тому
Thank you!
Egbert Sausage
Egbert Sausage 6 місяців тому
Excellent analysis
Andreas Spiess
Andreas Spiess 6 місяців тому
Thank you!
Gert van den Berg
Gert van den Berg 6 місяців тому
One of the big omissions is the VLIW processors, like the Itanium that Intel and HP cooperated on (It even had a Windows XP release) Windows NT supported several architectures....
Gert van den Berg
Gert van den Berg 6 місяців тому
I think the Itanium might have been killed by the problematic Windows port... (The x86 emulation was slow and 32-bit only, at a time that 16-bit apps were still quite common) (The IA64 initially had (slow) hardware x86 emulation, which was dropped when it became clear that software emulation performed better...) (PowerPC also started with a decently-sized group cooperating, which eventually fragmented - there were Solaris and Windows NT ports, which were never released / quickly abandoned...) (Killing x86 has been attempted several times...) (One of th eissues now is that the ecosystems are all more closed... A PC can run several operating systems - I can't get a generic install for a smartphone OS and run it on any ARM-based phone, with drivers for optimal performance of the device-specific hardware) (And you rarely have more than one OS to choose from) (Part of the reason that it works on x86 is a base set of standardised hardware, like VGA, etc. which works the same to get a basic system up, which can then load more drivers for the rest)
Andreas Spiess
Andreas Spiess 6 місяців тому
I knew about NT. I worked at DEC at this time and was disappointed that nobody wanted NT on our alpha...
Kevin Walters
Kevin Walters 6 місяців тому
Would be interesting to see some ADC tests on the new ESP32-C3. Espressif do not seem to have a good track record for producing decent ADCs compared to their competitors.
Andreas Spiess
Andreas Spiess 6 місяців тому
I assume they will use their current peripherals. But maybe it will once be supported by the Arduino IDE and we can test.
Kraftrad
Kraftrad 6 місяців тому
Can you explain why MIPS was not successful? Microchip advertised this some years ago as the future of their dsPICs
Andreas Spiess
Andreas Spiess 6 місяців тому
I do not know. Technology is not everything, I think. DEC had a 64bit processor 10 years before Intel and nobody was interested in it :-(
Pablo
Pablo 6 місяців тому
Thank you Andreas; excellent information and extremely clear.
Andreas Spiess
Andreas Spiess 6 місяців тому
You are welcome!
WazzaM
WazzaM 6 місяців тому
Ok... Nice video. I appreciated the details about RISC-V. You said at the start that you simplify things but they can mislead. 1. The early broad programming APIs were UNIX system calls and in the 8080 based operating system CPM. Microsoft's DOS was based on this but took standardisation many steps further with the idea of device drivers and DOS interrupts. 16 bit windows built in DOS. 2. Windows NT, later becoming the modern Windows, has long supported compilation to non-x86 ISAs. Originally, PowerPC, MIPS, Alpha, as well as Intel. 3. Originally Intel had partnered with AMD to produce some CPUs, like 40MHz 386 and 486 as well as some 286, from memory. That's how AMD became an x86 licensee. I had a 386 that had both AMD and Intel's name on it.
WazzaM
WazzaM 6 місяців тому
@Andreas Spiess Alpha was brilliant but needed more support to gain traction in the market. If I recall, AMD licensed the memory bus design for Athlon and AMD 64 bit extensions.
Andreas Spiess
Andreas Spiess 6 місяців тому
Thanks for your additions. As an ex DEC employee of course I knew about NT and Alpha. Unfortunately nearly nobody was interested :-(
Malte Plath
Malte Plath 6 місяців тому
Excellent! I really appreciate the historical background (even if very subjective and abbreviated) and the effort you put into explaining the economic context.
Andreas Spiess
Andreas Spiess 6 місяців тому
Glad you enjoyed it!
Today on the Bench
Today on the Bench 6 місяців тому
A few minor issues that I would like to correct: RISC architectures are generally slower than a well developed CISC one within the scope of applications that it were developed for. Since the CISC architecture can leverage more advanced functions to do more work without needing to cycle through any control logic between operations within the instruction. While a RISC architecture will need to implement the same instruction with a set of simpler instructions, where each of these instructions will need to be processed by our control logic. This decreases the performance of the RISC architecture, and usually also the power efficiency as well. Even with instruction compression (aka microcode) this problem still remains. (and yes, x86 does contain microcode as well, but then it is typically building further on top of what it already has. It does also do some simplifications of some instructions, but x86 is CISC. But x86 isn't a perfect CISC architecture, nor the only CISC architecture.) And your example of compiler complexity in regards to CISC and RISC, it is typically the opposite to what you described. Compiling on CISC tends to require more effort than a RISC architecture. Since we can't measure the intensity of the work of converting our code to instructions by how many instructions were required in the end product. It would be like comparing the complexity of a given code based on how many lines including comments it consists out of. Having RISC as a standardized ISA is also a bit bogus. Since different architectures can take fairly drastically different approaches to similar problems, for larger system related reasons, making it infeasible for them to share a common ISA. Ie, the future of RISC-V isn't going to create a standardized ISA in the market. And to be fair, even GNU/Linux is very fragmented in its support due to its various distributions that makes running software on it a living hell at times. ARM already is fairly fractured in a similar fashion, where one ARM chip doesn't run/support stuff natively, even if stuff is compiled for ARM. RISC-V is likely to end up in a similar situation in fairly short order. Making the standard more strict will only limit RISC-V's ability to be applicable for more varying approaches to architectures. In the end. The main advantages for RISC-V is that it can be used as a lower cost alternative to ARM in some sections. Where device makers can adapt the core to their needs without having to undergo the development of the whole thing themselves. In higher performance markets, it to a degree will have issues competing, since the RISC-V ISA is fairly limited in what architectures it can implement.
Andreas Spiess
Andreas Spiess 6 місяців тому
Thank you for your addition to the discussion!
R.
R. 6 місяців тому
Hello again from Tokyo Andreas! I felt the same way so we became RISC-V members.
Andreas Spiess
Andreas Spiess 6 місяців тому
Cool!
Luca L
Luca L 6 місяців тому
Waiting for them to be released, since I consider them for a new product my company is considering.
Luca L
Luca L 6 місяців тому
@Andreas Spiess yeah I figured, but since they are close to release the tool chain for the Risc V (currently beta) and they sending a bunch of preproduction models to youtubers, I hope it won't take them too long to release 😅
Andreas Spiess
Andreas Spiess 6 місяців тому
I had a pre-production version.
Jeff Chen
Jeff Chen 6 місяців тому
insightful observation! thanks for the video
Andreas Spiess
Andreas Spiess 6 місяців тому
Glad you liked it!
TheBronx
TheBronx 6 місяців тому
Thank you so much for this video!
Andreas Spiess
Andreas Spiess 6 місяців тому
You are welcome!
grepthis2000
grepthis2000 6 місяців тому
Excellent presentation and very informative. Thank you.
Andreas Spiess
Andreas Spiess 6 місяців тому
Glad you enjoyed it!
Ricardo Islas Ruiz
Ricardo Islas Ruiz 6 місяців тому
I just discovered your channel and I cannot stop watching your videos! Excellent!
Ricardo Islas Ruiz
Ricardo Islas Ruiz 6 місяців тому
@Andreas Spiess thank you so much! I have not worked with microcontrollers since a lot of time and yesterday with you videos I discovered the ESP32 familiy OMG! 😍 it is beautiful!
Andreas Spiess
Andreas Spiess 6 місяців тому
Welcome aboard the channel!
executive
executive 7 місяців тому
I always thought RISC processing predated CISC.
Andreas Spiess
Andreas Spiess 6 місяців тому
Not the name. The firs processors for sure had simpler instruction sets. But because lack of comparison they just were called „processors“
TalpaDK
TalpaDK 7 місяців тому
Actually the possibility to create very simple processors (even Arm as you showed carry along a lot of legacy instructions) opens up the possibility to create quite/very fast (clock speed) processors with a quite low power usage per performance.
TalpaDK
TalpaDK 6 місяців тому
@Andreas Spiess Not a problem... Then someone just needs to come up with a open source Really Reduced Instruction Set Computer or as they will call it RRISC :)
Andreas Spiess
Andreas Spiess 6 місяців тому
We will see how many instructions the set will have in 10 years. Instruction sets tend to get bigger and bigger ;-) But for the moment, you are right.
Stefanos Stamatiadis
Stefanos Stamatiadis 7 місяців тому
Great and in depth video. Kudos!!
Andreas Spiess
Andreas Spiess 7 місяців тому
Thank you!
Davide Perini
Davide Perini 7 місяців тому
Is it available for buy?
Andreas Spiess
Andreas Spiess 7 місяців тому
Not yet. I have pre-production units
gurbanliye
gurbanliye 7 місяців тому
Atmel and PIC owned by the same company, Microchip.
Andreas Spiess
Andreas Spiess 7 місяців тому
You are right.
Jeff Barbose
Jeff Barbose 7 місяців тому
You got your history seriously wrong. The original Macintosh has the Mac Toolbox. Search for the "Inside Macintosh" volumes. Even Microsoft developed Mac OS applications against them. the first version of Excel and Word were Macintosh applications back in 1985.
Andreas Spiess
Andreas Spiess 7 місяців тому
Where did I talk about the Macintosh? I am not aware that it was involved in the RISC-V story.
Glenn Hamblin
Glenn Hamblin 7 місяців тому
Standards are great, unfortunately they are always implemented in unstandard ways. 🙂
Glenn Hamblin
Glenn Hamblin 7 місяців тому
@Andreas Spiess Even a blind squirrel gets lucky and finds a nut somewhere. 🙂 Try your phone in Korea or singapore.
Andreas Spiess
Andreas Spiess 7 місяців тому
Fortunately not everywhere. My iPhone worked last time I went to the US. A novelty ;-)
ARM-POWER
ARM-POWER 7 місяців тому
MS Windows 10 runs natively on ARM64 since 2019 - MS offers their own laptop Surface X with 8-core ARM CPU from Qualcomm (core is ARM Cortex A76 with IPC about AMD Zen1, BTW the new CPU core Cortex X1 introduced in 2020 and in current phone Samsung S21 has IPC about +5% higher than AMD Zen3). So basically everybody can buy license and manufacture its own CPU with higher IPC than best x86 CPUs from AMD or Intel. Not speaking about Apple M1 - this CPU is +60% IPC over Zen3 and has double IPC than Intel Comet Lake or AMD Zen2. Apple M1 is MONSTER and shows how AMD and Intel are years behind in CPU development. For example: - integer execution units: M1 = 6x INT + 3x Branch = 9-wide ...... Zen3 = 4x INT + 1x Branch = 5-wide ....... Intel TGL = 4xINT(2xbranch shared) = 4-wide - L1 cache for instructions: M1 = 192 kB ....................................Ze3 = 32 kB (6x less) .................................. Intel TGL = 32 kB (6x less) - L2 cache: ..........................M1 = 12 MB ..................................... Zen3 = 0.5 MB (24x less)............................ Intel TGL = 1.2 kB (10x less) - Reorder Buffer: ................ M1= 630 .......................................... Zen3 = 256 (2.5x less)............................ Intel TGL = 350 (1.8x less) Not speaking that ARM64 instruction set is much better than old garbage x86: - better/relaxed memory model for higher IPC - 32 registers for INT and FPU while x86-64 has only 16/16 - ARMv8.6 has MATRIX calculation instructions - ARMs SVE2 SIMD supports up to 2048-bit vectors (AMD supports only AVX2 with only 256-bit) - SVE2 is flexible: supports 128-bit up to 2048-bit while same SW can run at all these HW variants (x86 cannot do that because SW has to match HW) - SVE2 supports size-less types and can process unlimited length vectors far bigger than 2048-bit - decoupled SW vector length from HW FPU width (sci-fi for x86) - ARM releases every year new update for instruction set, today we have ARMv8.6 and new ARMv9 is coming soon (probably 2022 with Makalu) - and as last Apple M1 CPU has no 32-bit compatibility (was abandoned in 2017 with 1st super wide 6xINT CPU core A11 Monsoon) - x86 CPU has to keep ancient 16-bit and 32-bit compatibility even nobody uses that today (wasting transistors) - ARM announced for 2022 brand new Cortex CPU core architecture codenamed Makalu with 64-bit only as Apple
Andreas Spiess
Andreas Spiess 7 місяців тому
Thanks for the comparison! I think I mentioned, "until recently, Windows only supported..." I am curious how the market will react to the M1 in the Apple computer and which companies will offer ARM PCs... Because Apple owns the whole stack it seems to be easier for them to change the silicon., They also did it twice before...
AlexanderN
AlexanderN 7 місяців тому
Actually the title was a bit misleading, I thought I would not spare that much time to watch that content, and shelved it. Got a bit of time and get acquainted with very thoughtful and well researched review covering very many aspects of technology, business and history of electronic developments. Excellent video Andreas, a real gem.
AlexanderN
AlexanderN 7 місяців тому
@Andreas Spiess Yes, coining the term RISC undeniably helped promoting the concept of having more registers and exchange data with the memory using the dedicated instructions only. But it could be confusing to those who joined the party later.
Andreas Spiess
Andreas Spiess 7 місяців тому
You are right with the expensive memory. And before RISC, nobody talked about CISC. We just had microprocessors. Only when RISC appeared they talked about CISC.
AlexanderN
AlexanderN 7 місяців тому
@Andreas Spiess I perceived the video would be mainly dedicated to the ESP32-C3 that does not have a robust toolchain at the moment thus not my piece of cake. The video was so much more than that. I would like to add one consideration to your CISC vs RISC discussion that was far from evident to me : CISC was not an oversight; at the time RAM was so expensive that it was much more economical to make the processor as sophisticated as possible to reduce the required code RAM footprint. (Just compare the number of FETs spent in a recent megaprocessor.com design on the decent 16 bits CPU and paltry 256 B memory.) The step change came along with the Gordon Moore's observation that was actually related to RAM chips. When there was enough fast RAM, design effort became focused on the CPU, and now the memory is lagging behind processors hence caches.
Andreas Spiess
Andreas Spiess 7 місяців тому
Thank you. Where do you think the title was misleading? I thought I covered the open source aspect in he video and how much open source the -C3 is.
Snake Sanders
Snake Sanders 7 місяців тому
That was a master class, Vielen Dank!
Andreas Spiess
Andreas Spiess 7 місяців тому
You are welcome!
Tobias Frei
Tobias Frei 7 місяців тому
Oh, schon vor ein paar Tagen gesehen. Danke Andreas für die Einschätzung zu RISC-V ☺️
Andreas Spiess
Andreas Spiess 7 місяців тому
Bitte, gern geschehen!
TheShorterboy
TheShorterboy 7 місяців тому
Ah ARM has been a round for decades dude it came out of the CISC RISC wars, they used to make the tiny controllers in goods, their rise after Apple is a different story, also IBM's "Power PC" is still a thing. The OS wars between Microsoft and CPM which microsoft won thanks to IBM didn't have anything to do with the Chip or quality of OS used, CPM ran an on a number of architectures from x86 to Z80 boards. Compilers notably GCC obviated the need for a standard CPU and Java along with every other interpreted language should have nailed that coffin shut a good decade ago. Where I work we use GCC/ARM on embedded and try to use Java, Python and TCL for all other server side work so we now don't care what CPU it runs and haven't for a good decade. Oh yeah the most popular operating system in the X86 world is Minix, it runs on the management engine in every chip. The computer world ended up the way it is because a risk averse managerial class bought whatever wouldn't get them fired, monopolists like IBM were not interested in supplying the small guy, it's the open source PC "ISA bus" (the reason you have a PC at home) and China with economies of scale that took it from there. Price for dev qty chips you can get from here cmp.imag.fr, it's the price for design suites(cadence etc) that will kill you. Also I can blow a J-Core j0 to an ICE40. Oh Chinese don't buy their IP cores dude the Allwinner SOC IP cores were rip offs, we had a guy work for us that had worked with fabs using the original cores and the Allwinner SOC's we were using the IO cores had bit reversed registers from Patented IP.
Andreas Spiess
Andreas Spiess 7 місяців тому
I am an EE with a PhD in Business Administration. I did this because I early understood that markets are very important for my life, too. This is why I probably focused more on this part than on technology. To understand RISC-V, markets are very important. You are right. ARM as an architecture started earlier. ARM the company was founded in 1990.
Koen Lefever
Koen Lefever 7 місяців тому
10:00 "Microsoft until recently only supported Intel ISA's" Windows NT4 also ran on the DEC Alpha, IBM PowerPC and MIPS R4000 ISA's back in the 1990s (and Windows XP & 2003 ran on Itanic, but that's Intel again).
Andreas Spiess
Andreas Spiess 7 місяців тому
You are right. As an ex DEC employee I am very aware of that fact. But it was not relevant, unfortunately.
Foto Ernst
Foto Ernst 7 місяців тому
Grüezi Herr Spiess, Han ein frog, ob es sich lohnt en MacPro 5.1 2010 z kaufe und es Upgrade für de gebruch vo Photoshop,Premiere Pro etc. worin felicht en nmöglichi Video Idee für Sie. Danke für Ihri Zit. LG A.Ernst
Foto Ernst
Foto Ernst 7 місяців тому
@Andreas Spiess Ja das wäre schön, aber ich hab bei einigen Videos eine Aufrüstung eines dieser MacPro 5.1 gesehen und das Ergebnis war verblüffend und ich war richtig erstaunt was dieser Rechner an Kompatibilität alles drauf hat. Leider entwickelt Apple keine solchen Individualisierterbaren Pc‘s. Trotzdem bin ich dankbar für ihre fachmännische Meinung. Ich will mich auch nochmal bei ihnen für den Super PC bedanken den Sie dem Fotolabor gebracht haben als der alte den Geist aufgab. Er ist sehr Leise und hat eine super Leistung, da macht das Arbeiten wieder viel mehr Freunde und ich hoffe den auch nach dem Sommer öfters benutzen zu können. Lg A.Ernst
Andreas Spiess
Andreas Spiess 7 місяців тому
Ich hab noch nie einen MAC gehabt. Aber ich würde nie einen so alten Computer kaufen. Den solltest du geschenkt bekommen...
Biddut Mitra
Biddut Mitra 7 місяців тому
Since when Chinese can "produce"? They are only copycat. As per Chinese "intention", there is always be "almost there" glitch. LOL. This feature is found in most Chinese products. Intentionally? Mostly I avoid using these, surely waste of time. Mark my words.
Andreas Spiess
Andreas Spiess 7 місяців тому
I am not sure if you know how much your live depends on Chinese manufacturing...
Jac
Jac 7 місяців тому
Hi Andreas, I loved the episode you made about fossa sat a year ago, it's was very interesting. I have been following the project since then and have been avidly following the telegram for it. Recently they have had a rebranding and released a new website tinygs.com take a look and see what you think, new projects in store maybe?
Andreas Spiess
Andreas Spiess 7 місяців тому
I am in contact with the developers.
ProgramOrBeProgrammed
ProgramOrBeProgrammed 7 місяців тому
I loved that chart (3:36) of all the Arm ISA levels, that's going in the collection. Thanks! Wow this was great video.
Andreas Spiess
Andreas Spiess 7 місяців тому
Glad you enjoyed it!
Scrap Womble Creatives
Scrap Womble Creatives 7 місяців тому
very interesting, I HAD TO WATCH IT THREE TIMES to understand it but alas you did warn us lol but thats my neurons getting lazy not the teacher
Andreas Spiess
Andreas Spiess 7 місяців тому
That is what I like with UKposts. I always have to use the replay function ;-)
Dan Bowkley
Dan Bowkley 7 місяців тому
Once upon a time, Windows actually did support other architectures: NT4 at least was also available for the DEC Alpha as well as MIPS and PowerPC. I ran it on an Alpha box for quite some time.
Kevin Walters
Kevin Walters 6 місяців тому
@Dan Bowkley The alphas were incredible at the time making the Intel x86 look like children's toys but the computers were expensive which probably answers part of the question about why they never became more common, at least as desktops, plus it's really about the software and a certain dominant, abusive player dictated a lot there. Intel's i860 stuff looked interesting for a while from a technology point of view. Windows NT on Alpha raises the curious question about how it ran on 64 bit hardware. I didn't know the Alpha has a 32 bit more until recently! That's amusing given the rest of the world was moving to 64 bit capable operating systems at the time.
Dan Bowkley
Dan Bowkley 7 місяців тому
@Andreas Spiess I never could figure out why it wasn't more popular. That computer was so fast I almost needed a seatbelt for my desk chair.
Andreas Spiess
Andreas Spiess 7 місяців тому
As an ex DEC employee I am well aware of that fact. I suffered a lot that nobody wanted our Alphas under NT ;-)
Ho Ki
Ho Ki 7 місяців тому
25:25 "Is RISC-V faster?" Perhaps this point is not so important (at least for me)!? Power consumption may be more important (for IoT). Or the fact that Intel in 2014 already had 1338 instructions in their ISA. Or that RISC-V's code size (with C extension) compares very well with ARM and Intel. We will see...it's an ARM's race! :)
Andreas Spiess
Andreas Spiess 7 місяців тому
As I mentioned: RISC-V in my eyes is not about technology...
Ho Ki
Ho Ki 7 місяців тому
Perhaps it's important to emphasize that SiFive offers: (1) a open source implementation of the ISA (which is basic in the sense that the performance is not great but sufficient to experiment) and (2) on top of that it sells/licenses IP for customers that want better performance, better power consumption, smaller silicon size, etc. SiFive shows up in you list at 19:44 with freedom and rocket ISA-implementations. This is a typical business model, for example OpenSPARC does the same. On important difference (I am not sure about the details): You as a chip builder are not allowed to extend the SPARC ISA with your own instruction, with RISC-V that is officially allowed (and done in practice).
Andreas Spiess
Andreas Spiess 7 місяців тому
Thank you for your additions.
IGnatius T Foobar
IGnatius T Foobar 7 місяців тому
This is one of many reasons I love Linux. It runs on everything.
Andreas Spiess
Andreas Spiess 7 місяців тому
The only problem (for me): There are many Linux :-(
SDWNJ
SDWNJ 7 місяців тому
Windows NT ran on DEC Alpha back in the day, but the application support was minimal. Then DEC came out with a binary compatibility layer that allowed x86 Windows apps to run on Alpha. Since, at the time, the fastest Alpha CPUs ran significantly faster than Intel CPUs, the software could run as fast or faster than on pentiums even while loosing some clock cycles to the binary compatibility translation.
Andreas Spiess
Andreas Spiess 7 місяців тому
You are right. I worked for DEC back then ;-)
Bob Weiram
Bob Weiram 7 місяців тому
Sorry it was first Xerox and then Macintosh that was responsible for why the ordinary person can use a computer today.
Andreas Spiess
Andreas Spiess 7 місяців тому
Inventing something is one thing. Bring it to the market is another. Winning the market is a third. All three are important in my view. This video is about RISC-V, not about computer history. This is why I had to omit most things.
codigoBinario
codigoBinario 7 місяців тому
Excellent review of the state of the question. You show the big picture in this video. Congrats and thanks Mr. Swiss Guy!
Andreas Spiess
Andreas Spiess 7 місяців тому
Many thanks!
Tom
Tom 7 місяців тому
I'd say the standard for trousers is that we wear some, not that we all wear the same ;)
Andreas Spiess
Andreas Spiess 7 місяців тому
:-)
George Leite
George Leite 7 місяців тому
Brings me back. I worked on Unix compilers from 88 to 95. I worked on every RISC chip mentioned, plus Intel and Motorola CISC. You covered it very well.
Andreas Spiess
Andreas Spiess 7 місяців тому
Thank you!
Glenn Stasse
Glenn Stasse 7 місяців тому
I worked at DEC from the 70s until it was gone. I saw some of this evolution up close. Our CISC Vaxes were wildly successful which also foretold their downfall. Eventually they got RISC versions (Alpha) going that both ate the golden goose Vaxen and was too late to market to save the company. (Did you know DEC also manufactured ARM chips? They soaked up excess chip manufacturing capacity that way.) New architectures come along and the successful ones overtake the predecessors. Microsoft can remain chip-agnostic as can Apple and others higher up the stack. Down in the stack is a tough place to survive. Something else is always on the horizon. Quantum anyone?
Andreas Spiess
Andreas Spiess 7 місяців тому
As an ex-DEC employee I understand what you wrote ;-) Unfortunately we did not understand that our value was VMS and not VAX. When RISC came, we dropped prices too fast to match HP et al. Also for the VMS machines (the customer could choose the OS and it was free of charge if I remember right). This is why DEC was killed, not the PC as many writers think. IBM did much better. They separated their commercial lines from the RISC lines and kept the prices high. And still, they were successful in the workstation business :-( And our CHIP CEO killed the last thing: The highly services business. Finally, DEC was sold for the (still existing) service business. I was no more there, but I cried when I heard that DEC was gone.
Peter Laidlaw
Peter Laidlaw 7 місяців тому
Excellent assessment. Please be careful, IBM will want to hire you!
Andreas Spiess
Andreas Spiess 7 місяців тому
As an ex-DEC employee this would not be easy...
Sandeep Kumar
Sandeep Kumar 7 місяців тому
"but the salaries were ok"
Andreas Spiess
Andreas Spiess 7 місяців тому
True!
Anders Jackson
Anders Jackson 7 місяців тому
Nice video, but on some places I don't agree, but then, I know you need simplifications. The oldest RISC CPU I worked with was an old PDP 12.
Kevin Walters
Kevin Walters 6 місяців тому
@Andreas Spiess IBM 801 gets mentioned a lot too as RISC forerunner.
Andreas Spiess
Andreas Spiess 7 місяців тому
I only heard "CISC" when RISC was invented. Before they were just CPUs and nobody cared. Anyway, RISC and CISC is relative and need each-other for definition, I think
Sun Wukong
Sun Wukong 7 місяців тому
I am 8:22 into this video and just because your explanations are so entertaining and simple, I hit the subscribe button. Well done, very well done. I am looking forward to see the rest of the video, now :-D
Andreas Spiess
Andreas Spiess 7 місяців тому
Welcome aboard the channel!
Da No
Da No 7 місяців тому
DANKE das ist mal super erklärt.
Andreas Spiess
Andreas Spiess 7 місяців тому
Bitte, gern geschehen!
Andrew Kroll
Andrew Kroll 7 місяців тому
Incorrect statement about Linux. I was using it back in 1991, and was a kernel dev.
Andreas Spiess
Andreas Spiess 7 місяців тому
About 4:19: In my humble opinion, beginning of the 1990 mainstream still were the other UNIX variants. As said, I had to simplify a lot.
Andrew Kroll
Andrew Kroll 7 місяців тому
@Andreas Spiess love your content regardless
Andrew Kroll
Andrew Kroll 7 місяців тому
@Andreas Spiess timestamp 4min 19sec Linux existed.
Andreas Spiess
Andreas Spiess 7 місяців тому
What exactly was wrong?
Scott Williams
Scott Williams 7 місяців тому
Let me just say: RPi5 on RISC-V
Andreas Spiess
Andreas Spiess 7 місяців тому
I do not think so.
BrainDoesMusic
BrainDoesMusic 7 місяців тому
Never watched such a dry thematic with so much joy. Great explanation, nice voice, good presentation. Keep up the good work.
Andreas Spiess
Andreas Spiess 7 місяців тому
Glad you enjoyed it!
Eugy08
Eugy08 7 місяців тому
Great video! My head really does hurt from abundance of information! Keep it up! My only concern for this topic is the participation of Chinese company like Huawei. I'd keep them away from all new tech conferences and workshops!
Andreas Spiess
Andreas Spiess 7 місяців тому
Thank you!
Phil Davis
Phil Davis 7 місяців тому
Great presentation, I learned a bunch of stuff that I hadn't before, despite my obsession with tech videos. Anyway, I understand your disappointment about the amount of open source on the silicon, but the piece that IS open source, I think, is exciting enough to still make it pretty exciting. That common standard you talked about will provide a free means to compatibility for a vast number of companies, and hopefully, software! I'm happy to wait for more open source silicon, because of the possibilities we will have now! unless I misunderstand something, which could easily happen here!
Andreas Spiess
Andreas Spiess 7 місяців тому
I am sure it has its potential. But a long way to go...
TDT Records
TDT Records 7 місяців тому
Epic presentation !! I am not grasping why the phrase is "everybody against ARM !! " what is the scoop about ARM ?
Andreas Spiess
Andreas Spiess 7 місяців тому
They are big and dominate a whole industry, that is all.
T λ C O. phox
T λ C O. phox 7 місяців тому
Maybe in the future we'd have a Scientific Socialist Society like Star Trek and we'll drop competition with each other, collaborate for the betterment of humanity as a whole and open source as much technology as possible. But that'd happen in many centuries later. Not this era sadly.
Andreas Spiess
Andreas Spiess 7 місяців тому
And I am even not sure it ever happens. The blueprint of nature seems to be different...
doobedoobedo1
doobedoobedo1 7 місяців тому
I think you'll find that in the UK we drive on the correct side of the road.
doobedoobedo1
doobedoobedo1 7 місяців тому
@Andreas Spiess I can see how a non-native speaker might see some confusion, but there is some satisfaction in being able to say that 'left is right and right is wrong' when it comes to which side to drive on :).
Andreas Spiess
Andreas Spiess 7 місяців тому
Correct side: OK. I found it interesting that the English "right" has two different meanings. I German we have two words (which are similar, but not the same)...
QC Support
QC Support 7 місяців тому
RISC-V: the ISA with the Swiss accent. As mentioned, RISC-V foundation moved to Switzerland. This was likely to prevent the US trade war with China from forcing RISC-V to de-license any Chinese companies (like Huawei with ARM). Given that China itself will be producing an ever increasing share of silicon, it's probably a good thing if the architecture is universal.
Andreas Spiess
Andreas Spiess 7 місяців тому
We have many global organizations here in Switzerland. We are probably small enough that nobody fears us ;-)
Aron Highgrove
Aron Highgrove 7 місяців тому
Windows NT ran on MIPS, PowerPC, Alpha decades ago... Even Itanium for a while. They just phased out support for non-x86 architectures when it wasn't in high demand anymore. Actually Windows NT was designed on non-Intel CPUs. And Intel adopted main frame features to match up Unix/multi user demands/features. Over time different architectures inspired each other and became more common. It's not that one ruled them all from the start. If there would have just been the IBM standard, we would not be close to where we are today. Competition of ideas is very important. You just need regular fusion and standardization of the best ideas, combined with freedom to deviate from it.
Andreas Spiess
Andreas Spiess 7 місяців тому
As an ex DEC employee I suffered because nobody wanted our Alphas with NT back then. Soo I know, but it was not important for this video :-(
Aron Highgrove
Aron Highgrove 7 місяців тому
Standards alone are not good, if the standard hasn't evolved and changed for a long enough period, to model many possible use cases, and distill it down to model that simplifies a lot. What we see today, especially in smartphone, is that standards are chosen to give manfuacturers control over clients and other vendors (app stores), acting as the middle man (Google everywhere, including paying). A standard is only as good as the abstraction that was chosen, it's not just a question of taste, but resonable compromise between felixibility and ease of use. There are many interesting approaches to this, but common to all of them, is that they need to be driven by experience and updated over a longer period of time before they are finalized. The waterfall model or trying to predict a good model from the get go is very hard. Iterations are almost impossible to avoid, and all stake holders should be included. Currently, people have much less influence than they used to. In Windows you cannot even control the color settings of individual elements anymore.
Andreas Spiess
Andreas Spiess 7 місяців тому
For me, the value of a standard is its spreading. There are many different ways of creating one. Windows is a very successful standard owned by one company, and all IEEE standards are industry standards. I go more for the "black box" approach where I ask myself: What is in for me? Driving on a particular side of a road was not innovated for quite some time, but it still is accepted.
#286 How does Software Defined Radio (SDR) work under the Hood? SDR Tutorial
27:20
Open Source 8.5 Digit Voltmeter from CERN: Build and Test
33:52
Marco Reps
Переглядів 304 тис.
Steve Jobs Insult Response - Highest Quality
5:15
Jonathan Field
Переглядів 10 млн
RISC-V is trying to launch an open-hardware revolution | Upscaled
14:14
An Open Source CPU!?
12:50
Linus Tech Tips
Переглядів 2,2 млн
RISC-V: The Next Ten Years
16:45
RISC-V International
Переглядів 6 тис.
3 тиждень - Танці з зірками. 8 сезон
3:9:31
Танці з зірками
Переглядів 221 тис.
2 тиждень - Танці з зірками. 8 сезон
3:6:10
Танці з зірками
Переглядів 457 тис.