←back to thread

Athlon 64: How AMD turned the tables on Intel

(dfarq.homeip.net)
331 points giuliomagnifico | 2 comments | 25 Sep 25 18:09 UTC | HN request time: 0s | source
Show context
bigstrat2003 ◴[25 Sep 25 19:20 UTC] No.45377613[source]▶
I remember at the time thinking it was really silly for Intel to release a 64-bit processor that broke compatibility, and was very glad AMD kept it. Years later I learned about kernel writing, and I now get why Intel tried to break with the old - the compatibility hacks piled up on x86 are truly awful. But ultimately, customers don't care about that, they just want their stuff to run.
replies(5): >>45377925 #>>45379301 #>>45380247 #>>45385323 #>>45386390 #
wvenable ◴[25 Sep 25 21:23 UTC] No.45379301[source]▶
Intel might have been successful with the transition if they didn't decide to go with such radically different and real-world untested architecture for Itanium.
replies(2): >>45379461 #>>45380469 #
pixl97 ◴[25 Sep 25 21:37 UTC] No.45379461[source]▶
Well that and Itanium was eyewateringly expensive and standard PC was much cheaper for similar or faster speeds.
replies(1): >>45380251 #
Tsiklon ◴[25 Sep 25 22:48 UTC] No.45380251[source]▶
I think Itanium was a remarkable success in some other ways. Intel utterly destroyed the workstation market with it. HP-UX, IRIX, AIX, Solaris.

Itanium sounded the deathknell for all of them.

The only Unix to survive with any market share is MacOS, (arguably because of its lateness to the party) and it has only relatively recently went back to a more bespoke architecture

replies(5): >>45380339 #>>45380406 #>>45382516 #>>45383193 #>>45388301 #
icedchai ◴[25 Sep 25 22:55 UTC] No.45380339[source]▶
I'd argue it was Linux (on x86) and the dot-com crash that destroyed the workstation market, not Itanium. The early 2000s was awash in used workstation gear, especially Sun. I've never seen anyone with an Itanium box.
replies(3): >>45380551 #>>45381130 #>>45387724 #
1. tyingq ◴[25 Sep 25 23:18 UTC] No.45380551[source]▶
I think the idea there is that it's less direct. Intel's lack of interest in a 64-bit x86 spawned AMD x64. The failure of Itanium then let that Linux/AMD x64 kill off the workstation market, and the larger RISC/Unix market. Linux on 32 bit X86 or 64 bit RISC alone was making some headway there, but the Linux/x64 combo is what enabled the full kill off.
replies(1): >>45385498 #
2. p_l ◴[26 Sep 25 12:03 UTC] No.45385498[source]▶
Intel's lack of interest in delivering 64bit for "peons" running x86 also was part - I remember when first discussion in popular computer magazines showed of amd64, that intel's proposed timeline was discussed, and it very much indicated a wish to push for "buy our super expensive stuff" and trying to squeeze money.

Meanwhile the decision to keep Itanium on expensive but lower-volume market meant that there simply wasn't much market growth, especially once non-technical part of killing other RISCs failed. Ultimately Itanium was left as recommended way in some markets to run Oracle databases (due to partnership between Oracle and HP) and not much else, while shops that used other RISC platforms either migrated to AMD64, or moved to other RISC platforms (even forcing HP to resurrect Alpha for last one gen)