Am 07.09.2017 20:03 schrieb "Timothy Pearson" < tpearson@raptorengineering.com>:
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1
On 09/07/2017 10:11 AM, Peter Stuge wrote:
ron minnich wrote:
I don't think we can assume that an open, unlicensed instruction set guarantees open, unlicensed, blob-free CPUs and platforms.
This is of course absolutely accurate.
But a freely licensed ISA and implementation(s) thereof are *one step* in the right direction, and a significant one.
RISC-V is not so much a guarantee of anything as it is a potential enabler of something.
The fabulous thing about RISC-V is what makes ARM successful; there can and will be multiple different silicon vendors, offering products with many different features and tradeoffs.
Some can be top performance but proprietary. Some can be transparent/open but slower.
We already have this (think cheap ARM SoCs vs. a Xeon). In practice it means that if you want to use a computer for real work (such as developing libre software) you have to go proprietary, which is not what I think we want to see here.
OpenPOWER is the first attempt to change this that we have seen in a long time. I'm honestly surprised at the overall community betting on a long shot (RISC-V) vs. using what's available and open right now (POWER9); could anyone shed some light on these decision making processes?
There is no coherent decision making process.
open ISA and core design does not guarantee open silicon, and in fact one could argue that it will mean any performance improvements end up highly locked under NDA and similar to avoid competitors coming online and ruining tens of millions of dollars of investment for even one SoC improvement.
- -- Timothy Pearson Raptor Engineering +1 (415) 727-8645 (direct line) +1 (512) 690-0200 (switchboard) https://www.raptorengineering.com
-- coreboot mailing list: coreboot@coreboot.org https://mail.coreboot.org/mailman/listinfo/coreboot