Ideally, the metrics that we settle on would be architecture agnostic and have some sort of conversion metric to map it onto any specific architecture. An Intel based architecture is going to perform vastly different from an ARM based one for example.

Simple example: The PS3 PPE and Xbox 360 CPU are RISC processors that run at 3.2GHz, but their non-vector performance is rather poor. You’d be lucky to get about 33% effective utilization out of them (up to 50%, tops, but that’s really pushing it), so if you were to map this onto another architecture, you’d have at least a 3x conversion from this end alone (the other end could also have a scaling factor). 

Ultimately, how these values are expressed isn’t the important part. It’s the ability to measure the impact of a change that’s important. If some metric changes by, say, 5%, then it doesn’t really matter if it’s expressed in MIPS, INTOPS, MB or GB. The fact that it changed is what matters and what the effect is on the baseline (that ultimately could be expressed as a certain specific hardware configuration). It would probably be practical to have a number of comparable concrete min spec configurations and even more ideal would be if people in the community would have these systems up and running to do actual on-target performance benchmarks.


jp


On Jul 2, 2015, at 8:13 PM, Jeremy Rubin <jeremy.l.rubin.travel@gmail.com> wrote:

Might I suggest that the min-spec, if developed, target the RISC-V Rocket architecture (running on FPGA, I suppose) as a reference point for performance? This may be much lower performance than desirable, however, it means that we don't lock people into using large-vendor chipsets which have unknown, or known to be bad, security properties such as Intel AMT.

In general, targeting open hardware seems to me to be more critical than performance metrics for the long term health of Bitcoin, however, performance is still important.

Does anyone know how the RISC-V FPGA performance stacks up to, say, a Raspberry Pi?

On Thu, Jul 2, 2015 at 10:52 PM, Owen Gunden <ogunden@phauna.org> wrote:
I'm also a user who runs a full node, and I also like this idea. I think Gavin has done some back-of-the-envelope calculations around this stuff, but nothing so clearly defined as what you propose.

On 07/02/2015 08:33 AM, Mistr Bigs wrote:
I'm an end user running a full node on an aging laptop.
I think this is a great suggestion! I'd love to know what system
requirements are needed for running Bitcoin Core.

On Thu, Jul 2, 2015 at 6:04 AM, Jean-Paul Kogelman
<jeanpaulkogelman@me.com <mailto:jeanpaulkogelman@me.com>> wrote:

    I’m a game developer. I write time critical code for a living and
    have to deal with memory, CPU, GPU and I/O budgets on a daily basis.
    These budgets are based on what we call a minimum specification (of
    hardware); min spec for short. In most cases the min spec is based
    on entry model machines that are available during launch, and will
    give the user an enjoyable experience when playing our games.
    Obviously, we can turn on a number of bells and whistles for people
    with faster machines, but that’s not the point of this mail.

    The point is, can we define a min spec for Bitcoin Core? The number
    one reason for this is: if you know how your changes affect your
    available budgets, then the risk of breaking something due to
    capacity problems is reduced to practically zero.



_______________________________________________
bitcoin-dev mailing list
bitcoin-dev@lists.linuxfoundation.org
https://lists.linuxfoundation.org/mailman/listinfo/bitcoin-dev

_______________________________________________
bitcoin-dev mailing list
bitcoin-dev@lists.linuxfoundation.org
https://lists.linuxfoundation.org/mailman/listinfo/bitcoin-dev

_______________________________________________
bitcoin-dev mailing list
bitcoin-dev@lists.linuxfoundation.org
https://lists.linuxfoundation.org/mailman/listinfo/bitcoin-dev