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

Intel: Winning and Losing

abortretry.fail

Post reply on HN
Print view View original

81–90 of 110 posts

Re: Intel: Winning and Losing

#81

Post by xscott »

inkyoto wrote: post #77
phire wrote: post #67

Earlier quoted context omitted.

> is they promoted the myth that ISA has no impact on performance IMO, Intel (and AMD) did prove the impact of a legacy ISA was low enough to not be a competitive disadvantage. Not zero, but close enough for high-performance designs. In fact, I actually think the need to continue supporting the legacy x86 ISA was a massive advantage to Intel. It forced them to go down the path of massively out-of-order μarches at a p…

> In fact, I actually think need to continue supporting the legacy x86 ISA was a massive advantage to Intel . I think this is a myth that Intel (or somebody else) has invented in an attempt to save face. Legacy x86 instructions could have been culled from the silicon and implemented in the software as emulation traps – this has been done elsewhere nearly since the first revised CPU design came out. Since CPU's have b…

They tried this with Itanium and got beaten up constantly about how legacy performance was bad. Personally, I agree with you, but the market isn't rational. This paved the way for AMD to eat some of their lunch by making a "compatible" 64 bit ISA. Itanium could've been great for the kinds of workloads I was interested in at the time.

Re: Intel: Winning and Losing

#82

Post by vlovich123 »

phire wrote: post #67
fidotron wrote: post #29

The core problem at Intel is they promoted the myth that ISA has no impact on performance to such a degree they started fully believing it while also somehow believing their process advantage was unassailable. By that time they'd accumulated so many worthless departments that turning it around at any time after 2010 was an impossibility. You could be the greatest business leader in history but you cannot save Intel w…

> is they promoted the myth that ISA has no impact on performance IMO, Intel (and AMD) did prove the impact of a legacy ISA was low enough to not be a competitive disadvantage. Not zero, but close enough for high-performance designs. In fact, I actually think the need to continue supporting the legacy x86 ISA was a massive advantage to Intel. It forced them to go down the path of massively out-of-order μarches at a p…

> IMO, Intel (and AMD) did prove the impact of a legacy ISA was low enough to not be a competitive disadvantage. Not zero, but close enough for high-performance designs.

And Apple proved that in fact it was a significant problem once you factored into account performance per watt allowing them to completely spank AMD and Intel once those hit a thermal limit. There’s a benefit from being able to decode and dispatch multiple instructions in parallel vs having to emulate that through heuristically guessing at instruction boundaries and backtrack when you make a mistake (among other things).

Re: Intel: Winning and Losing

#83

Post by thijson »

acroyear wrote: post #16

Mr. Magoo-ism galore. Intel had constantly try to bring in visionaries, but failed over and over. With the exception of Jim Keller, Intel was duped into believing in incompetent people. At a critical juncture during the smart-phone revolution it was Mike Bell, a full-on Mr. Magoo. He never did anything after his stint with Intel worth mentioning - he was exposed as a pretender. Eric Kim would be another. Murthy Rendu…

Someone I knew that worked there said that the CPU business was like a giant tree, no other business could grow because of its shade. I remember Mike Bell was leading the x86 phone project, and later wearables. I thought an interesting data point is that he ended up at Rivian, but didn't last long there. A lot of the hype around him was that he kept claiming credit for the iPhone. He would threaten to leave Intel, and then Otellini would throw more money at him.

Re: Intel: Winning and Losing

#85

Post by icedchai »

bsder wrote: post #46
AnotherGoodName wrote: post #6

I'll give a viewpoint that the article reads like a listing of spec sheets and process improvements for CPUs of that era and not much else. Not really worth reading imho. I'd love some discussion on why Intel left XScale and went to Atom and i think Itanium is worthy of discussion in this era too. I don't really want a raw listing of [In year X Intel launched Y with SPEC_SHEET_LISTING features].

> i think Itanium is worthy of discussion in this era too Itanium was a massive technical failure but a massiver business success. Intel spent a gigabuck and drove every single non-x86 competitor out of the server business with the exception of IBM.

I remember the plethora of Unix workstations and servers in the 90's: Sun, HP, SGI, DEC, IBM. I'm skeptical Itanium killed them. It was software: plain old x86 and Linux killed them.

Re: Intel: Winning and Losing

#86

Post by jxjnskkzxxhx »

fidotron wrote: post #29

The core problem at Intel is they promoted the myth that ISA has no impact on performance to such a degree they started fully believing it while also somehow believing their process advantage was unassailable. By that time they'd accumulated so many worthless departments that turning it around at any time after 2010 was an impossibility. You could be the greatest business leader in history but you cannot save Intel w…

> they promoted the myth that ISA has no impact on performance

Could you clarify? What is "ISA", and why do you think it would have an impact on performance?

Re: Intel: Winning and Losing

#87

Post by icedchai »

igtztorrero wrote: post #3

The Atom model was the breaking point for Intel. No one forgives them for wasting their money on Atom-based laptops, which are slower than a tortoise. Never play with the customer's intelligence.

I had an early Atom "server" board. Boy was that thing slow.

Re: Intel: Winning and Losing

#88

Post by buescher »

zozbot234 wrote: post #39
buescher wrote: post #38

Earlier quoted context omitted.

The original NeXT computer was a gorgeously sexy machine but slow compared to competitive workstations and considered very expensive for what it was at the time. It also didn't have the software ecosystem of a less expensive loaded PC or loaded Mac II. It's easy to look back with hindsight and rose-tinted glasses, squint a little, and see a macOS machine but it wouldn't be that for many years.

I mean, the NeXT, Atari ST and Mac computers around that time were all m68k-based... And the Atari ST was the cheapest by far, since it was competing in the home computer market.

The Atari ST and similar machines like the Amiga and compact Macintoshes other than the SE/30 were not its competition, any more than the Sega Genesis was. Its immediate competition included Sun and SGI workstations (as well as other workstations) and the Mac II series - and for specific tasks, loaded 386DX and 486DX PCs. Sun was pivoting at that time to the SPARC platform and SGI to the MIPS platform, both away from Motorola 68K.

Re: Intel: Winning and Losing

#89

Post by icedchai »

acroyear wrote: post #26
KerrAvon wrote: post #12

Earlier quoted context omitted.

It doesn’t even have to be that negative. With the best intentions in the world, it’s rare to have a CEO who is fundamentally capable of understanding both the technology and the viable market applications of that technology. Steve Jobs didn’t manage to do it at NeXT.

NeXT was a failed rocket launch (analogous to early rocket failures within SpaceX). A great step forward and a necessary step in the evolution of the PC. I thought NeXT workstations were pretty bad-ass for their time and place. Recall that only 3 years prior to NeXT, was computers like the Atari ST .. what a vast difference!!

Also remember the original NeXT workstation was incredibly expensive compared to the "consumer" 68K machines like the ST, Amiga, and even Mac. The cube was roughly $6500 at the time (late 80's money, close to $18K today!) The base system had a magneto optical disk and didn't even include a hard drive.

The NeXT hardware was massively under powered for the software it ran. Other major workstation vendors like Sun were already moving to their own RISC hardware.

Re: Intel: Winning and Losing

#90

Post by icedchai »

buescher wrote: post #88
zozbot234 wrote: post #39

Earlier quoted context omitted.

I mean, the NeXT, Atari ST and Mac computers around that time were all m68k-based... And the Atari ST was the cheapest by far, since it was competing in the home computer market.

The Atari ST and similar machines like the Amiga and compact Macintoshes other than the SE/30 were not its competition, any more than the Sega Genesis was. Its immediate competition included Sun and SGI workstations (as well as other workstations) and the Mac II series - and for specific tasks, loaded 386DX and 486DX PCs. Sun was pivoting at that time to the SPARC platform and SGI to the MIPS platform, both away from…

There were some high end Ataris and Amigas (Atart TT 030, Amiga 3000, etc.) but they came out a bit later. There was even the A3000UX that ran a Unix port!

Still, I agree. The 68K workstation was essentially obsolete by the time NeXT shipped. Sun was shipping early Sparc systems around the same time. The writing was on the wall. No wonder they didn't stick with their own hardware for very long.

Post reply on HN