Re: [openrisc] Huffman encoding operands

["Damjan Lampret" <lampret@opencores.org>]

----- Original Message -----
From: Larry Doolittle <ldoolitt@recycle.lbl.gov>
To: <openrisc@opencores.org>
Sent: Friday, May 26, 2000 8:06 PM
Subject: [openrisc] Huffman encoding operands

[cut]
> I disagree.  Instruction set compression (not necessarily Huffman)
> is a good thing, we all know, as it reduces memory bandwidth, and
> increases (fixed size) cache effectiveness, at the expense of slightly
> more complex instruction decoding.  And yes, you can compress operands.

Sure you can compress almost everything. But I am just afraid we will add
too much complexity to the architecture. I am not even sure if we really
want to squeez everything into 16 bits (ok, Jimmy says that mixing 16 and
32-bit long insn is too complex). How about 24-bit long insns with all
functions aligned at 4 bytes?

regards,
Damjan