HNHacker News
TopNewBestAskShowJobs

klelatti

10,089 karma · joined May 1, 2020

Writing a newsletter about computer history at thechipletter.substack.com
submissionscomments
klelatti··on Intel 18A Status Update: First Chips Booting, First Customer Tape-Out in H1'25
Very fair comment - clearly a lot has changed.

I do have to balance that a little with the fact that a lot is resting on the success of these nodes. It's almost the only good news Intel has, so we should be skeptical. That wasn't the case in 2017.

klelatti··on Intel 18A Status Update: First Chips Booting, First Customer Tape-Out in H1'25
Not just delayed repeatedly but also not a success.

The key point is taping out, first boot, etc does not imply a successful node.

klelatti··on Intel 18A Status Update: First Chips Booting, First Customer Tape-Out in H1'25
The original intent was to say that the facts speak for themselves.

I did think the link between Intel's confidence in 10nm and the current statements is self-evident, but it obviously wasn't for you so now changed.

klelatti··on Intel 18A Status Update: First Chips Booting, First Customer Tape-Out in H1'25
For those that are not aware Intel previously highlighted successful milestones for its 10nm process and claimed that it was on track. For example:

> Intel's official Twitter account has tweeted that Ice Lake has been taped in at the 10nm process.

> The company still holds the industry advantage in terms of process that they have always enjoyed (assuming you don't fall for the marketing names that other foundries employ which are not indicative of the physical process) and appears to be confident in its promised delivery of 10nm products.

https://wccftech.com/intel-ice-lake-processors-taped-in/

10nm in fact was disastrous for Intel.

klelatti··on Intel sells stake in chip designer Arm Holdings
Don’t read too much into this. Tiny stake that’s not material in terms of Intel’s finances.

Bought at the time of Arm’s float to show confidence in Arm and that Intel is a key partner - which it wants to be in the shape of Intel Foundry.

Changes nothing material in the relationship. More of a tidying-up exercise with a small profit than anything else.

Edit: This is a much more interesting story on the development of the Softbank / Arm / Intel relationship.

SoftBank scraps AI chips tie-up plan with Intel.

https://news.ycombinator.com/item?id=41265804

klelatti··on RP2350
> Notably, SiFive's designs generally halve the area of similarly performing ARM ones, while being slightly faster and using significantly less power.

Source?

klelatti··on Larry Tesler pioneered cut-and-paste, the one-button mouse, WYSIWYG (2005)
> He even convinced Apple to invest in a newly created company, Advanced RISC Machines Ltd., also in Cambridge, that would produce them.

And that stake was quite possibly crucial in helping Apple survive.

> Plus it's on record that Apple made a total of $1.1 billion out of selling those shares, which represented a profit of 366 times its original investment. That money helped Apple survive, and Jobs decision to cut the Newton — with its ARM processor — was also part of the surgery needed to keep Apple alive.[1]

[1] https://appleinsider.com/articles/23/09/05/apple-arm-have-be...

klelatti··on Hazard3: 3-stage RV32IMACZb* processor with debug
Sure and what is possible is that some users develop RISC-V based applications and RPi can offer a slightly cheaper version for those really price sensitive customers.

The comment I replied to was unduly alarmist though in suggesting Arm could make the Pico ‘expensive’ vs ‘cheap’ now with a royalty increase on an existing license.

klelatti··on Hazard3: 3-stage RV32IMACZb* processor with debug
This makes it sound as though

1. Arm can increase royalty rates on existing already shipping designs.

2. That increases in royalty rates would be material to the price paid by the end user - making the device ‘expensive’ for the end user.

Neither of these reflect the actual nature of licenses in practice.

klelatti··on Hazard3: 3-stage RV32IMACZb* processor with debug
Just to clarify

> so ARM code is emulated (varmulet) on RISC-V

As I initially read this the other way around.

klelatti··on Intel's Immiseration
That's a lot of fabs for a fabless semi company.
klelatti··on Intel's Immiseration
I get it that you don’t like Arm but that doesn’t change the fact that low power was and is central to their value proposition - and this latter fact doesn’t preclude other firms having low power offerings.
klelatti··on Intel's Immiseration
Agreed. That power efficiency is still a central part of the Arm value proposition though. Others are competing with real designs on this with Arm in laptops but not in - for example - smartphones.
klelatti··on Intel's Immiseration
> Intel at the time was fabless

????????!

klelatti··on Intel's Immiseration
You're conflating the characteristics of the ISA with the value proposition offered by the designs using it. Not the same at all.

Other historical architectures typically targeted higher performance.

Arm specifically went after low-power applications, which continues today when we see the priorities in the design of Arm and x86 cores, for example.

klelatti··on Intel's Immiseration
No it was a both a huge mistake and a symptom of underlying problems. Making smartphone SoCs is a huge profitable market that would have given Intel massive volumes to support R&D etc and slowed TSMC. The fact that they couldn’t manage it with every apparent advantage is very telling.
klelatti··on Intel's Immiseration
You’ve missed out one of Arm’s central value propositions which is power efficiency and the reason why it has more than 99% of the smartphone market.
klelatti··on Intel's Immiseration
> It feels disingenuous to say ARM is the panacea when designing ARM cores would have left Intel in an even worse position.

Sorry, where does the article say Intel should design Arm cores in 2024?

klelatti··on The Little Tech Agenda
> Regulatory agencies have been green lit to use brute force investigations, prosecutions, intimidation, and threats to hobble new industries, such as Blockchain.

"New industries such as Blockchain."

> Regulatory agencies are punitively blocking startups from being acquired by the same big companies the government is preferencing in so many other ways.

So Big Tech is bad except when it gives us a lucrative exit.

klelatti··on Testing AMD's Giant MI300X
Thanks so much for doing that. There are loads of people here who really appreciate it. We will stay tuned!
klelatti··on Testing AMD's Giant MI300X
Do you think this comment will make Hot Aisle more or less likely to loan out their hardware in the future?

Personally, I couldn't care less about the quality of copy. I do care about having access to similar hardware in the future.

klelatti··on The City of London which is not part of London (2016)
The FT did a recent - and very good - expose with more on how the city works in “Undemocratic, anachronistic, fantastic. How the City of London survives” [1] Paywalled but accessible via Google.

[1] https://www.ft.com/content/2b96763f-5cb2-475b-b20c-7c2d02050...

klelatti··on Demystifying NPUs: Questions and Answers
Thanks. I'm the author. I added some comments to this thread to try to help readers understand NPUs better. However, I'm afraid that this - which is pretty rude - as the top-voted comment means that I won't be reading or commenting on HN threads on my writing anymore.
klelatti··on Demystifying NPUs: Questions and Answers
Opaque blobs I believe in almost all cases!
klelatti··on Demystifying NPUs: Questions and Answers
NPUs are basically specialized for matrix multiplication, GPUs for more general parallel operations on multiple data (Single Instruction Multiple Thread) although modern GPUs also contain matrix multiplication units.

May be a degree of software compatibility at the highest level - eg PyTorch - but the underlying software will be very different.

klelatti··on Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)
No.

> we have entered into a new long-term agreement with Apple that extends beyond 2040, continuing … Apple’s access to the Arm architecture.

Clearly says that the agreement continues Apple’s access to the Arm architecture beyond 2040. That’s what a licensing deal is.

This is an important disclosure. Any attempt to pass something less than a licensing deal with this wording wouldn’t get pass the lawyers.

klelatti··on Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)
Neither of those say what your comment implied - that they get a special deal and that’s because they are a founder.
klelatti··on Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)
err...

> ... we have entered into a new long-term agreement with Apple that extends beyond 2040, continuing our longstanding relationship of collaboration with Apple and Apple’s access to the Arm architecture.

Arm's IPO F-1/A.

https://www.sec.gov/Archives/edgar/data/1973239/000119312523...

Which was linked in the MacRumors link.

klelatti··on Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)
Narrator: There was no source.
klelatti··on Instruction Sets Should Be Free: The Case for RISC-V [pdf] (2014)
My apologies too - didn't mean to sound critical!

Thanks for your comment on the analysis. I see this all the time, often in even more extreme form, such as Apple gets it all for free! You can look at Arm's accounts in the 1990s and prove that Apple never got it for free.

← PreviousPage 7 of 34Next →