Swiss speed page is a bit out of date...

It’s not been updated since may ’09. Somebody could have a lot of fun updating that and comparing numbers...

tim
--
tim Rowledge; [hidden email]; http://www.rowledge.org/tim
Useful random insult:- Doesn't just know nothing; doesn't even suspect much.

DYAC - *swiki* speed page, of course!

tim
--
tim Rowledge; [hidden email]; http://www.rowledge.org/tim
Oxymorons: Working vacation

On Mon, Jan 02, 2017 at 05:28:43PM -0800, tim Rowledge wrote:
> DYAC - *swiki* speed page, of course!

Uhm ... which page is this? href?

Dave

> On 02-01-2017, at 5:50 PM, David T. Lewis <[hidden email]> wrote:
>
> On Mon, Jan 02, 2017 at 05:28:43PM -0800, tim Rowledge wrote:
>> DYAC - *swiki* speed page, of course!
>
> Uhm ... which page is this? href?

Aargh! http://wiki.squeak.org/squeak/768 is the one.

Every now and then I randomly hit the swiki to see if I can improve a page. Too often it becomes Wumpus Hunt and I get lost in a maze of twisty passages, all alike in their interconnected outdatedness. I rather suspect that what we should do is make a new front page, start linking actually useful and current pages from there and then do a big garbage collect.


tim
--
tim Rowledge; [hidden email]; http://www.rowledge.org/tim
A)bort, R)etry, P)ee in drive door

On 1/3/17, tim Rowledge <[hidden email]> wrote:
>
>> On 02-01-2017, at 5:50 PM, David T. Lewis <[hidden email]> wrote:
>>
>> On Mon, Jan 02, 2017 at 05:28:43PM -0800, tim Rowledge wrote:
>>> DYAC - *swiki* speed page, of course!
>>
>> Uhm ... which page is this? href?
>
> Aargh! http://wiki.squeak.org/squeak/768 is the one.

Yes, the
    how fast is Squeak?
is interesting for historical reasons?

I however do not see which benchmark was run. Would be interesting to
have some current results for comparison, e.g. RPi....

> On 19-01-2017, at 1:42 AM, H. Hirzel <[hidden email]> wrote:
>
> I however do not see which benchmark was run. Would be interesting to
> have some current results for comparison, e.g. RPi….

For this page it was always what is now included as #tinyBenchmarks - runnable from the 'About Squeak’ window. It’s not a very meaningful benchmark to be honest, but then very few are.

On the Pi3 with a CogSpur VM we get 280M bc/sec and 16M sends/sec. It’s quite sobering to look back at the ~10 year old results for then-new expensive machine and see them well beaten by a $35 ‘toy’.

tim
--
tim Rowledge; [hidden email]; http://www.rowledge.org/tim
An algorithm must be seen to be believed.

> On 19-01-2017, at 3:21 PM, Ben Coman <[hidden email]> wrote:
>
>
> And imagine where we will be in another 10 years.

Well it should be interesting. I suspect we’re near the end of single core performance increases of any dramatic degree. So we should be thinking of ways to make good use of many-core systems for Squeak.

Note that on a good modern x86 desktop you can anticipate something like 3B bytecodes/sec and 200M sends/sec - and at that level it probably makes the benchmark even less meaningful.

tim
--
tim Rowledge; [hidden email]; http://www.rowledge.org/tim
No, I don't explode cats. It's way too difficult to coax them into the microwave