Відео

they're basically decrypting the architecture of the graphics card once the graphics card gets released lol

Being a bad benchmark is part of what makes cinebench a *good* benchmark. So many people have run it that you can look up typical cinebench numbers for any retail CPU, and because it barely goes out to DRAM, the effect of people having wildly different memory clocks and timings is screened off. So if cinebench is far from nominal, you probably have something wrong with thermals/power delivery/SMM cycle stealing. Useless for choosing what CPU to buy, though.

It doesn't correlate much to any real apps I care about. In fact, I can barely extrapolate from any benchmark that's not the exact app I'm intending to use. But Cinebench is always given so much prominence and then doesn't tell me anything much that's useful IMO.

The statement "It will take time for software optimizations to catch up to Zen5 dual-wide frontend and having an optimized codepath for that" is valid ONLY for code that contains branches that exhibit dynamic/changing behavior at run-time, which makes it impossible to optimally reorder the basic blocks at compile-time. The question then is: what percentage of branches in real-world applications exhibits such dynamic behavior? For the theory "software needs to catch up to Zen5's dual-wide frontend" to be true, such branches must constitute at least 5% of all branches.

I suggested this, hypothetically, on a certain forum on that starts with L and ends with TT. Was attacked, ultimately personally, for doubting their lord and savior.

So, how long before I get a portal gun, like Rick?🤔😉✌️

As a technology industry hobbyist, I find it important to give credit where it’s due. AMD might not be here as we know it with without Jim Keller and his teams that redesign of its Zen architecture-an effort led by Jim Keller. Remarkably, this wasn’t Keller’s first-time reshaping AMD’s fortunes. In the late ’90s, he was instrumental when AMD first outpaced Intel and introduced x86-x64 with AMD64. Decades later, he was at the helm once again, orchestrating the Zen renaissance that put AMD back ahead of Intel. Despite his transformative contributions as chief architect, Keller rarely gets the spotlight he deserves. When Keller returned, I was so sure the company would do well that I bought AMD at $1.50. History has a way of repeating itself, especially when visionary leaders return to the companies they helped define. Steve Jobs built Apple into something extraordinary, then left, then Apple nearly went bankrupt (but saved by Microsoft of all things), then Jobs came back and transformed Apple into the world’s most valued company. Ironically, these visionaries often face internal skepticism, even from their own boards, who struggle to grasp their long-term vision. Yet, without such forward-thinkers, many of the world’s most iconic companies might never have reached their true potential.

All the great minds that worked on Zen really show in its performance !

The thing that's neat about risc-v (if I understand), is that beyond the core design the new optional stuff is defined in optional extensions. So if I want to make a music player, I could just buy a risc-v processor that only implements the core plus just the extensions that are of use for audio encoding decoding. I could leave off stuff related to graphics for example if that had no use in my music player

I think this might be the 12th time I'm watching this video. The importance of this video cannot be overstated

Amazing leader

I would like to see raspberry pi release a reduced x64 chip.

ISA doesn't matter. Let's talk about what does! The answer is always: That depends. As the software isn't written by humans anymore and code size is not an issue anymore the old requirements and constrains are irrelevant.

We write 2024, Mai. Let' face it, he has not foreseen the victory of Arm over x86 2022, when Apple already has switched gears, and he has not foreseen the raise of NVidia and GPU computing WILL be AI computing. So obviously, it was not so obvious. Finally, RISC (Arm) has beaten CISC (x86)- it was predicted more than 30 years ago, but didn't happen for some time.. I read the first books..

I have now seen multiple CPU designers, state that the architecture isn't really important. But in the CPUs actually out there there seems to be a huge power efficiency gap between ARM and AMD64.

Need moar JK.

ARM can't do division, pretty fail tbh

Now I understand why he comes in, designs an architecture, and then leaves for the next company. That way Future Jim won't have to deal with his mess.

Linear algebra is a high level description of potentially thousands or millions of multiplies and adds -- all very predictable from a terse equation and dependent on the exact data. This makes AI, Data Science and Statistics on a large scale possible. It should also enable physics and engineering calculations. All of this implemented in low level languages and callable from Python!

Why do people find it so hard to speak coherently these days? The interviewer is an example of that.

It could be an interesting interview if there was no kitchen background noise

"that's a problem for ron..." ... "later ron"

Instruction sets are like government. The bureaucracy exists to feed the bureaucracy.

Everybody keep saying instruction sets don't matter, except nobody could touch Apple in single thread performance with cores that run 30% higher clocks at 5x the power. Beat Apple, and then I'll believe "instruction sets don't matter"

Architecture shouldn't matter when you learn the best from each other. The issues arises when you have design decisions that's mutual exclusive in the long run and doesn't have a path forward.

What architecture/technology is Keller saying at 7m55s? The edit garbled the audio referring to an architecture that deprecated (sic.) a legacy mode. I'll have to dig out my architecture book.

Holy smokes, what a mind!

But "80% of executions being composed of 6 instructions" isn't the same as "80% of the EXECUTION TIME is spent on those same instructions".

LOL ~ I hate that, where future Jim comes back and goes "What the f ck did you do that for?"

How did Intel let Jim get away? I guess he probably felt limited there.

Somewhere between 20 and 80 percent 🤣😂

He explained everything so easily

This ceo may be technical but i would fire him as a marketer for the company.

Explains a lot....... thanks!!!

chiplet and ai processor is the future

When I saw Jim I knew it would be insanely great explanation.

Jim Keller is a smart dude

Oh, please, Patterson has been hyping his RISC for 40 years. He is just now competing with Raspberry and Orange Pi's. RISC-V has no discernible advantage over Intel, AMD, or ARM.

Okay but when will potato-computing supremacy be realized?

Absolutely golden content

ZEM arm never came to be right??

Hah. Keller has a painting from Vladimir Kusch behind him. A Russian painter now based in Maui

Is there a fully stable and official Python interpreter specifically tailored for RISC-V?

Lofty minds designing devices to be first utilized by the grosses souls.

why does every video begin with "What's your minimum specification?"

Very underrated guy. This should be a household name instead of guys like Musk.

I could listen to Jim Keller's insights for hours. Just serving him coffee I would feel like I'm wasting his time 😅

"what limit's computer performance is predictability". That's huge quote.

Jim gives the impression that he's a reluctant to be referred to as a mentor, but as a consequence of his unrelenting drive to complete the mission he's a still great mentor nonetheless.

No offence to the guy but I really could've used subtitles on this one. English is not my first language and I pretty much have no idea what he said.