The AMD offerings are much closer to M1 although they're not yet on TSMC 5nm so they don't quite match it. It's a historic event. Intel was #1 in laptops for an eternity. Even when the Pentium 4 was being outclassed by AMD Intel still kept the crown in mobile. This time around they first got overtaken by AMD and then by Apple and are now #3. Puts into perspective how huge of a miss their process node fail was.
Let’s remember AMD was absolute garbage for like 10 years until around 2016, when they finally bounced back. And they were getting closer and closer to bankruptcy, having to flog the silver - their fabs and even their campus. I’d say the Zen design and tsmc saved them (or Lisa Su and Keller).
Intel is in a better position financially than AMD was, and could catch up again. I tend to think it depends a lot on the organization and the people.
IC: A few people consider you 'The Father of Zen', do you think you’d scribe to that position? Or should that go to somebody else?
JK: Perhaps one of the uncles. There were a lot of really great people on Zen. There was a methodology team that was worldwide, the SoC team was partly in Austin and partly in India, the floating-point cache was done in Colorado, the core execution front end was in Austin, the Arm front end was in Sunnyvale, and we had good technical leaders. I was in daily communication for a while with Suzanne Plummer and Steve Hale, who kind of built the front end of the Zen core, and the Colorado team. It was really good people. Mike Clark's a great architect, so we had a lot of fun, and success. Success has a lot of authors - failure has one. So that was a success. Then some teams stepped up - we moved Excavator to the Boston team, where they took over finishing the design and the physical stuff, Harry Fair and his guys did a great job on that. So there were some fairly stressful organizational changes that we did, going through that. The team all came together, so I think there was a lot of camaraderie in it. So I won't claim to be the ‘father’ - I was brought in, you know, as the instigator and the chief nudge, but part architect part transformational leader. That was fun.
I don’t know the truth but that was spoken like a true humble leader. If I was forced to draw conclusions just based on that one exchange, I would agree that Jim Keller was an instrumental part of the successful design and implementation of the zen microarchitecture.
The whole interview was deeply inspiring. There is a very great deal to be learned from studying it. Listen carefully, and more than once! The audio is probably better than the text, at least first time through.
That and Microsoft has had an exclusivity agreement with Qualcomm for Windows on ARM. Once that agreement expires, I expect AMD to suddenly have some very interesting offerings.
After running benchmarks on Intel and AMD CPUs from that era with mitigations, it's clear Intel never really had a performance lead due to design. That alone rewrites the entire "state of AMD" narrative.
If Intel only had a competitive advantage during that era because they traded performance for security, was there ever really an advantage?
I personally don't think Gelsinger is going to be able to fix their culture issues. He's been more intent on pumping stock and asking for handouts than innovating, which is part of what got them where they are in the first place, for good or ill.
> they traded performance for security, was there ever really an advantage
Security is important, I would always prefer a secure product. But given design habits that elide security for performance, as well as a compromised supply chain, the only choice we have is to side with the devil(s) we know.
>Let’s remember AMD was absolute garbage for like 10 years until around 2016
After being ahead of Intel in the Pentium 4 era. The problem back then was marketing and giant amount of (probably illegal now) bundling that was rampant back then.
That last part is important. While Intel had good fab engineers, they also relied on cutthroat business deals requiring exclusivity to get discounts and promotional support and there were constant shenanigans with things like compiler support.
AMD had to make a much better product to get manufacturers to consider it, not just being price competitive. It took the P4 train wreck to get the market to shift but Intel had enough lock-in to make it to the Core generation without losing too much market share because so many of the vendors had those contracts.
And, to be clear, even though P4 was a disaster, Intel was STILL the market leader everywhere. They responded with the Core line only after years of AMD eating their lunch with the Athlon, Athlon 64, and Athlon XP line.
Thunderbird was released in 1999 and from there to the Core 2 Duo release in 2006, AMD was the performance leader (certainly at a huge discount compared to intel offerings).
> AMD was absolute garbage for like 10 years until around 2016
Their top performance was lower than Intel in many cases, but it was certainly not "absolute garbage". For low- to mid-range they offered similar performance with usually a (much) lower price point. For normal "average person" usage they were often the better choice in terms of "bang for your buck".
The main reason we were selling Intels is because we got a rebate from Intel for every CPU we sold. Financially it didn't really matter if we sold a €400 computer, €500, or €600 computer: the profit margin for us was roughly identical (a little bit more, but not much), but with Intel you got a rebate back-channelled, so then it did matter.
Well okay. But they had the same problem Intel is in now: they pushed an inefficient power hungry chip to the limit. So it was cheaper, and performance was only somewhat lower, but it was much hotter and used a lot of power —- so pretty useless for laptops.
On laptops AMD was indeed not very good; but their desktop CPUs – far more important in the 00s and early 10s than they are today – were pretty decent. That is not to say that Intel also didn't have good CPUs at the time, but (much) more expensive and for people just doing their browsing and occasional gaming on their desktop AMD was a solid (and cheaper!) choice IMO.
Intel is in an even better position now than last month, being handed $billions ($tens of billions?) of US tax dollars to fund building new fabs, which they would have had to build anyway. That will free up money to use in undercutting chip pricing, helping to bury AMD again.
Intel should realize at this point that their existential threat comes from TSMC, not AMD. AMD is one competitor, but TSMC is giving a huge boost to all of their competitors, particularly the ARM vendors who won’t just take some x86 market share but potentially destroy the entire x86 market at some point in the future.
The CPU is great. It’s power envelope and performance feel amazing.
My biggest complaint is the there is a very limited selection of Laptops with AMD’s chips, especially the top tier. The one I bought required me to replace the Wifi/Bluetooth card (it came with a barely “supported” MediaTek one) for Linux.
I have loved Linux for a couple decades. It was a difficult decision to migrate to the M1. Linux is so much more responsive and pliable. However Asus encouraged me. After owning three of their laptops in the past 18 months that began to fall apart anywhere from 3-12 months-I was done.
Unfortunately most 5/6900hs laptops are not flagship quality. Typically they are lower-mid range gaming units.
This is my first mac. The build quality is exceptional. I will just say I was expecting a better experience from an OS built by a trillion dollar company.
Similar position. The existence of Asahi Linux convinced me to buy my first Mac, since it increased the odds that my M1 Air would be usable (to me) long-term.
I haven't made the switch yet as my old Lenovo is still hanging on. Would you mind expanding on your gripes with MacOS, in particular the comment about responsiveness?
For me it is the little things. Like switching windows. Mac feels half a second slower then Linux and that delay make it feel less responsive. Opening up the terminal can iterm2 is another one. For me these things just adds up. I want my OS to get out of my way when I want to get work done.
I have turned off the genie effect and perhaps other animations, but my Ubuntu on my Lenovo still feels faster than the Mac.
Lenovo's is the only one I find with 16" 3840x2400 OLED, but just a 6850, $2800. Or with 6950 but just 1920x1200, $2635. None with both. Advantage, Radeon R6500M GPU. Doesn't say which wifi it has.
Zephyrus G14. I certainly wouldn’t swear off ASUS over it. After you upgrade the Wifi card (and, optionally, the SSD), it’s a great laptop; especially for Linux.
Me too. I just gave up and bought an ASUS H5600QM with a 5900HX (and 3840x2400 OLED, 32G socketed RAM, 2 NVMe sockets, and 3 physical touchpad buttons). If you act fast, you can still buy the version with Windows 10 and a GTX 3070 at $1999, instead of Windows 11 and a GTX 3060 for $254 more.
Build quality is excellent, but the first one died after 2 days: charge light wouldn't even go on. Waiting for #2. Wish me luck!
Its really interesting with Intel on mobile platforms during the P4 era. Their P4 mobile chips were often terrible for temps and power use, but their Centrino/Pentium M platform was excellent despite being based on the PIII. The P4's architecture became a dead end, while the Pentium M's essentially continued to be improved, scaled up, and became the Core series.
If they had tried to force the P4 mobiles instead of rethinking and retooling the PIII core with some of the P4's FSB innovations and other things, they probably wouldn't of had as competitive mobile processors and maybe wouldn't have dethroned AMD a few years later.
My first laptop had one of those P4-based CPUs. They were super terrible chips. I don't think they were really even mobile chips. I think my battery was good for about 25-30 minutes tops. And Dell put in a soft cap of 768MB of memory. I was pretty pissed that none of this was ever noted when I bought the laptop.
The AMD offerings are still very far from the M1. Try comparing the 6800U to the now 2-year old M1 in Geekbench. The M2 widens the gap even more.
The Ryzen chips are already clocking over 3 GHz, so there isn't much more scaling from power left. That's why 5nm Zen4 probably won't move the needle too much.
From your link: "Even under demanding multi-threaded workloads, the M2 MacBook Air was not nearly as warm as the other laptops tested"
Keep in mind the 6850U you're comparing against has a fan too. Notebookcheck says it has a 40W turbo on the gen 2 model, and the gen 3 Intel version has a 28W sustained boost. An M2 uses around 20W.
Also, a lot of those benchmarks are showing all x86 CPUs with a 3x+ lead, which indicates software optimization problems. Geekbench 5 is optimized for both arm64 and x86 and shows the M2 ahead of the 6800U. There are also just broken results like the LC0 test where the M1 is substantially faster than the M2. Overall, your results don't seem very valid.
> From your link: "Even under demanding multi-threaded workloads, the M2 MacBook Air was not nearly as warm as the other laptops tested"
> Overall, your results don't seem very valid.
They're not "my" results, and thermals were not part of the discussion.
Regarding performance, if one wants to be rigorous (and that's why I didn't state "68xx is faster than Mx"), one can't make absolute claims either way, as Torvalds himself has criticized Geekbench.
I still think that describing the performance difference as "not very far" is a valid assessment.
During the pentium4 era me and my friends all got mac laptops running powerpc. Our laptops could actually go on our laps without burning us and the powerbook versions were fast enough to emulate windows in a VM without feeling slow at all. My battery lasted quite a while for the time.
