Re: Assembler versus ANSI C
From: JS (NuncEstBibendum_at_excite.com)
Date: 07/31/03
- Next message: Mark Wooding: "Re: Into the Fire"
- Previous message: Christian: "Re: Addition vs Multiplication on Pentium IV Processors"
- In reply to: Thomas Pornin: "Re: Assembler versus ANSI C"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]
Date: Thu, 31 Jul 2003 14:23:53 GMT
On Thu, 31 Jul 2003 12:34:50 +0000, Thomas Pornin wrote:
> -- On RISC architectures (Sparc, Alpha, PowerPC,...), careful C code can
> achieve almost the same efficiency than hand-optimized assembly. On those
> platforms, C is the way to go (with regards to assembly).
That's not my experience, at least not on PA-RISC and IA64. Using the
same mathematical approaches, coding the arbitrary length integer
arithmetic in assembly can provide a 3x boost in the private key
operation under PA-RISC. A full, IA64 assembly language implementation of
the modular exponentiation yields even better results.
- Next message: Mark Wooding: "Re: Into the Fire"
- Previous message: Christian: "Re: Addition vs Multiplication on Pentium IV Processors"
- In reply to: Thomas Pornin: "Re: Assembler versus ANSI C"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]
Relevant Pages
|
|
