Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

www2.eecs.berkeley.edu

Post reply on HN
Print view View original

61–70 of 105 posts

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#61

Post by 1000100_1000101 »

wtetzner wrote: post #55
Koshkin wrote: post #14

The title of the piece is somewhat misleading - the actual point was, "there is no good technical reason for the lack of free, open ISAs."

I wonder why this hasn't been an issue for Apple (or maybe it has?).

Apple was a co-founder of Arm [0]. "Arm was officially founded as a company in November 1990 as Advanced RISC Machines Ltd, which was a joint venture between Acorn Computers, Apple Computer (now Apple Inc.), and VLSI Technology (now NXP Semiconductors N.V)."

I'm not sure of their exact licensing terms, but I'm sure as a co-founder they're favourable.

[0] - https://newsroom.arm.com/blog/arm-official-history

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#62

Post by snvzz »

musicale wrote: post #60
phkahler wrote: post #33

Earlier quoted context omitted.

None of those arguments have held up over the last 10 years. RISC-V has all of the things they say you need.

Apple has a licensing deal with ARM through 2040, but they might get tired of the license fees at some point.

Source?

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#63

Post by eschaton »

bdowling wrote: post #26

Would copying an instruction set and ABI to make an interoperable processor and system be fair use in light of Google v. Oracle (2021) [0][1]? [0] https://www.supremecourt.gov/opinions/20pdf/18-956_d18f.pdf [1] https://en.wikipedia.org/wiki/Google_LLC_v._Oracle_America,_... . Edit: Changed phrasing of question. Also, to be clear I think the answer is probably yes.

It would in light of decades of case law prior to Google v. Oracle. An instruction set itself is not protectable IP, only descriptions and implementations are.

What restricts new implementations are:

1. Existing legal agreements, eg if you agree in a contract that you will treat an instruction set as protectable IP, you’d be violating the contract. (Assuming the contract is valid.)

2. Patents, if you need to violate a patent to implement an instruction set then you need to license or wait out the patent, or figure out a way to work around it.

I believe both of these were at issue in Intel v. AMD, since AMD was initially a licensed second source, and Intel thought you couldn’t implement the Pentium instruction set without violating its patents.

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#64

Post by eschaton »

bitwize wrote: post #54
bdowling wrote: post #26

Would copying an instruction set and ABI to make an interoperable processor and system be fair use in light of Google v. Oracle (2021) [0][1]? [0] https://www.supremecourt.gov/opinions/20pdf/18-956_d18f.pdf [1] https://en.wikipedia.org/wiki/Google_LLC_v._Oracle_America,_... . Edit: Changed phrasing of question. Also, to be clear I think the answer is probably yes.

You can patent an ISA. And then everyone who implements that ISA, in hardware or emulation, is infringing. Intel actually threatened lawsuits against Microsoft for implementing emulation of recent x86 instructions on ARM Windows.

You cannot patent an instruction set architecture, but you can patent mechanisms used in the implementation of the instruction set architecture. This is an extremely important distinction.

Usually these patents are written such that it’s difficult or impossible to implement the covered portions of the instruction set without violating the patent, but that’s by no means guaranteed.

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#65

Post by eschaton »

fidotron wrote: post #18
crote wrote: post #16

Earlier quoted context omitted.

So rather than getting stuck in potential future tarpit of AWS or GCS or Azure, or probably a dozen other companies, we should voluntarily put ourselves into the IP tarpit developed by ARM? How exactly is that a win? Over the last two decades ARM has developed a stranglehold on the non-x86 world, and they have already considered abusing this position to increase their profit margin[0]. As a chipmaker you're essential…

Arm didn't develop the IP tarpit, they're one of the few players that learned how to operate in it. The SuperH example is relevant because what Arm did was "that's neat, let's license it" for some of the Hitachi innovations, and then licensed it to other people too. This is a positive development, and how trade and innovation has worked through the most successful periods in history. There is a respect in which they…

You don’t actually believe patents and other licensing regimes are good, do you?

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#66

Post by bigyikes »

snvzz wrote: post #62
musicale wrote: post #60

Earlier quoted context omitted.

Apple has a licensing deal with ARM through 2040, but they might get tired of the license fees at some point.

Source?

GPT-4o retrieved this for me: https://www.macrumors.com/2023/09/06/apple-inks-new-deal-arm...

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#67

Post by eschaton »

hmry wrote: post #45
lambdaone wrote: post #42

Earlier quoted context omitted.

It is, however, in principle possible to prove that a processor implements the spec and only the spec; seach for "formal verification risc v" to find out more. Of course if someone can sneak a backdoor into the spec, all bets are off.

You would also need to prove that the physical processor in your hands was actually manufactured according to the verified design, and not a slightly different design with a back door added. Which is infeasible for all processors manufactured in the last 30 years.

And even if you did this, which may in principle be possible, you still wouldn’t be able to prove that there aren’t any backdoors leveraging unexpected physical interactions between components.

For example, even if everything was provably manufactured to spec, it could be laid out in a way that exposes side channels, enables rowhammer-like attacks, and so on.

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#68

Post by kragen »

bitwize wrote: post #54
bdowling wrote: post #26

Would copying an instruction set and ABI to make an interoperable processor and system be fair use in light of Google v. Oracle (2021) [0][1]? [0] https://www.supremecourt.gov/opinions/20pdf/18-956_d18f.pdf [1] https://en.wikipedia.org/wiki/Google_LLC_v._Oracle_America,_... . Edit: Changed phrasing of question. Also, to be clear I think the answer is probably yes.

You can patent an ISA. And then everyone who implements that ISA, in hardware or emulation, is infringing. Intel actually threatened lawsuits against Microsoft for implementing emulation of recent x86 instructions on ARM Windows.

arm thumb-2 is over 20 years old now, so any patents that cover necessary techniques to implement it are expired by now (unless they are lemelson-style submarine patents from much longer ago that issued very recently)

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#69

Post by pjmlp »

gregw2 wrote: post #17
snvzz wrote: post #13

Earlier quoted context omitted.

It is appalling how stupid whoever at ARM must have been, to respond and thus bring attention to RISC-V. Back then, RISC-V was not anywhere as well-known as it is today.

Stupid?! The type of reader paying $500/year for the Microprocessor Report (where this response article appeared) already knew. (Similarly if they were motivated to get it free or took time to read it through their university, company, pirate it, etc.) And the ARM response you'll didn't mention RISC-V by name specifically. The notion of an open source entity building an open or semi-open ecosystem cannibalizing even…

And 40 years later, after FOSS folks thought to have won, everyone is going with open core, finally realising why businesses don't want anything to do with GPL like licensing.

So anyone that thinks RISC-V isn't going to trail a similar path, is fooling themselves.

Re: Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)

#70

Post by pjmlp »

musicale wrote: post #60
phkahler wrote: post #33

Earlier quoted context omitted.

None of those arguments have held up over the last 10 years. RISC-V has all of the things they say you need.

Apple has a licensing deal with ARM through 2040, but they might get tired of the license fees at some point.

They are one of the ARM founders, their licensing deal is a special sauce no one else gets it.
Post reply on HN