OSNews

Having a Playstation or PS2 (oh, only the best-selling console in history, overall; and PS1: 2nd best-selling among non-handhelds), also an early PS3 model with hardware "emulation" of PS2, or maybe one of many consumer WiFi routers & NAS devices, brings geek points?
Hm, OK then.

Didn't Thom have, IIRC, a PS2 at some point? That's two MIPS processors right there... (the 2nd taking over as a main one in PS1 mode)

I also prefer MIPS ISA because it can trap on integer overflow which is nice for efficient Ada compilation.

But unfortunately nearly nobody use a language with this (nice) behaviour instead of stupid C/C++ or Java's behaviour on integer overflow, so it doesn't really matter: both ISAs are quite nice, much better than x86 anyway.

renox,

"I also prefer MIPS ISA because it can trap on integer overflow which is nice for efficient Ada compilation. "

You may be right about mips handling overflow better than x86, but I actually don't mind the way the x86 does it.

ADD [edi], dword 5 # cause overflow
JO xyz # optionally handle overflow
INTO # generate an interrupt on overflow
ADC [edi+4], dword 0 # add carry
CMOVO [edi], ... # clip the range
# do nothing, modulo arithmetic is often desirable.


"But unfortunately nearly nobody use a language with this (nice) behaviour instead of stupid C/C++ or Java's behaviour on integer overflow, so it doesn't really matter"


I share the same gripe of the C language. It offers no way to use or act upon the overflow, leading to less efficient algorithms.

Also, I think modulo arithmetic should be made explicit. Languages like C/Java that implicitly discard overflow information lead to bugs regardless of architecture. New languages should automatically assert errors on overflow unless told to do otherwise.