Comment by high_na_euv
16 days ago
Crazy that they need to write such things because incompetent investors think that ISA has huge implications
16 days ago
Crazy that they need to write such things because incompetent investors think that ISA has huge implications
It has huge implications because it makes competing in that market much harder due to licensing issues. Intel and AMD have a duopoly on the x86 market which compromises a huge chunk of server and personal computing, but that is changing fast. If they go ARM (or risc-v or whatever) they will have more competition to contend with, including their existing cloud computing clients designing their own chips and fabbing them with other foundries.
I was going to correct you on the duopoly, but apparently the Cyrix/Centaur/Via agreement expired some time ago.
Perf/Energy implications
The shocker is: a lot of engineers think that the ISA has huge implications.
There was an interview with one of the SPARC creators who said that a huge benefit of control of the instruction set was the ability to take the platform in directions that (Intel) resellers could not.
He was otherwise largely agnostic on the benefits of SPARC.
ISA shouldn’t be more than a 10% or 20% performance impact or so, per jim Keller
What this means is that a better ISA might permanently be one generation ahead in terms of performance
That's not trivial...
ISAs do have huge implications. A poorly designed ISA can balloon the instruction count, which has a direct impact on program size and the call stack.
Investors dont care about those nerdy details
The talk is about perf and energy usage, where diff between x86 and arm is not even close to what they believe