Linked by Kroc Camen on Tue 22nd Jun 2010 12:46 UTC
Amiga & AROS The fabled Amiga X1000 has been spotted in the wild, in the homeliest of places--Station X, a.k.a Bletchley Park. "The AmigaOne X1000 is a custom dual core PowerPC board with plenty of modern ports and I/O interfaces. It runs AmigaOS 4, and is supported by Hyperion, a partner in the project. The most interesting bit, though, is the use of an 500Mhz XCore co-processor, which the X1000's hardware designer describes as a descendant of the transputer - once the great hope of British silicon." With thanks to Jason McGint, 'Richard' and Pascal Papara for submissions.
Thread beginning with comment 431323
To view parent comment, click here.
To read all comments associated with this story, please click here.
Member since:

Where the predominant wisdom for RISC machines was that the complexity was going to be transferred to the compiler.

Complexity of what?

It is common misunderstanding what making things easier for compilers, it will somehow complicate things for programmers. This is not true. Assembly programmers benefit from it MORE.

Which makes it a hoot to hear the arguments by people who haven't programmed any major piece of code in assembler to croon about how great RISC designs are for bare metal programming.

Ok. So these who say what RISC is simpler to program in asm you classify as uneducated guess.
I have a lot of assembly experience (10+ years of 100% assembly).
I'm familiar with Z80, AVR, x86, 68K, ARM, MIPS, SPARC, CELL.
And I can say what RISC designs are MUCH simpler to code in ASM then CISC.
Simple and straightforward uniform 3/4-operand instruction set is a key.
68k is close, but it is 2-operand. x86 with it's idiotisms like dedicated registers for specific instruction is nowhere as near.
I need to memorize less things with RISC and instructions do not have awkward restrictions because of brain-damaged instruction encoding.

There is an old but still good article on RISC-CISC debate

Reply Parent Score: 3