←back to thread

Athlon 64: How AMD turned the tables on Intel

(dfarq.homeip.net)
331 points giuliomagnifico | 1 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 #
drewg123 ◴[25 Sep 25 22:48 UTC] No.45380247[source]▶
It didn't help that Itanium was late, slow, and Intel/HP marketing used Itanium to kill off the various RISC CPUs, each of which had very loyal fans. This pissed off a lot of techies at the time.

I was a HUGE DEC Alpha fanboy at the time (even helped port FreeBSD to DEC Alpha), so I hated Itanium with a passion. I'm sure people like me who were 64-bit MIPS and PA-RISC fanboys and fangrirls also existed, and also lobbied against adoption of itanic where they could.

I remember when amd64 appeared, and it just made so much sense.

replies(3): >>45380466 #>>45381576 #>>45381749 #
kjs3 ◴[26 Sep 25 02:00 UTC] No.45381749[source]▶
PA-RISC fanboys and fangrirls

Itanic wasn't exactly HP-PA v.3, but it was a kissing cousin. Most of the HP shops I worked with believed the rhetoric it was going to be a straightforward if not completely painless upgrade from the PA-8x00 gear they were currently using.

Not so much.

The MIPS 10k line on the other hand...sigh...what might have been.

I remember when amd64 appeared, and it just made so much sense.

And you were right.

replies(2): >>45382385 #>>45385448 #
p_l ◴[26 Sep 25 11:56 UTC] No.45385448[source]▶
First generations of Itanium used same bus and support chips as last HP-PA, thus way simpler migration path involved - some servers even allowed to swap HP-PA for Itanium without replacing most of the server (similar as with rare VAX 7000 and VAX 10000, which could have CPU boards replaced with Alpha ones)
replies(1): >>45426176 #
kjs3 ◴[30 Sep 25 14:49 UTC] No.45426176{3}[source]▶
Yes, that was an interesting option, though not nearly as cheap on a lifecycle basis as one might hope. I don't know of anyone who upgraded this way, but obviously someone did. My clients who converted ran the HP-PA machines, brought in Itaniums, migrated and retired the HP-PA when they were amortized (or kept running code that didn't get the merced treatment).
replies(1): >>45435760 #
1. p_l ◴[01 Oct 25 09:09 UTC] No.45435760{4}[source]▶
I think HPPA->Itanium replacement without replacing the entire server was limited to Superdomes.

But it made it cheaper for HP to produce Itanium servers, though I bet they didn't pass those savings...