Re:The Itanium processor, part 3: The Windows calling conven...
by pcwalton on Wednesday July 29, 2015 @01:54PM
(#9970345)
The compiler problem here was in explicit scheduling, not counting outgoing registers. Modern C compilers for x86 architectures already do the latter.
Re:The Itanium processor, part 3: The Windows calling conven...
by acallan on Wednesday July 29, 2015 @02:09PM
(#9970463)
I recall learning that the important part of the optimization phase for Itanium was based on runtime performance analysis, not just static optimizations.
Re:The Itanium processor, part 3: The Windows calling conven...
by Someone on Wednesday July 29, 2015 @01:48PM
(#9970293)
That's true, but figuring out the maximum number of arguments passed to another function is trivial; I would think it isn't harder than determining how much space one needs for local variables in an Algol-like language.
Re:The Itanium processor, part 3: The Windows calling conven...
by elwin on Wednesday July 29, 2015 @01:50PM
(#9970310)
That's definitely true, but counting function parameters was only a small part of the difficulty. Weren't most of the problems related to optimization being harder and less effective than predicted?
Re:The Itanium processor, part 3: The Windows calling conven...
by nickpsecurity on Wednesday July 29, 2015 @02:01PM
(#9970398)
Because they had to deal with all the issues in Itanium Architecture Parts 1, 2, 3,..., n where the sum is a lot harder than this issue. ;)
Many of the accounts that I've read indicated the largest issue with Itanium was building effective compilers.