Is there an issue with the tests? Surprised that vibe.d is not higher in the rating...


https://www.techempower.com/benchmarks/#section=data-r14&hw=ph&test=fortune

Ali

On Wednesday, 7 June 2017 at 09:44:55 UTC, Ali Çehreli wrote:
> Is there an issue with the tests? Surprised that vibe.d is not higher in the rating...
>
>
> https://www.techempower.com/benchmarks/#section=data-r14&hw=ph&test=fortune
>
> Ali

Same for me.
I used a lot of Java (Jetty, Tomcat) and Groovy (Grails) stuff before using D (vibe.d).
On my machine I got a factor of 10-50 in difference. Vibe.d was always much faster.

So where are the results coming from?

Regards, Ozan

On Wednesday, 7 June 2017 at 14:56:56 UTC, Ozan wrote:
> On Wednesday, 7 June 2017 at 09:44:55 UTC, Ali Çehreli wrote:
>> Is there an issue with the tests? Surprised that vibe.d is not higher in the rating...
>>
>>
>> https://www.techempower.com/benchmarks/#section=data-r14&hw=ph&test=fortune
>>
>> Ali
>
> Same for me.
> I used a lot of Java (Jetty, Tomcat) and Groovy (Grails) stuff before using D (vibe.d).
> On my machine I got a factor of 10-50 in difference. Vibe.d was always much faster.
>
> So where are the results coming from?
>
> Regards, Ozan

I second this.

I have always had better performance with vibe.d versus other frameworks.

On Thu, Jun 08, 2017 at 12:18:21AM +0300, ketmar via Digitalmars-d wrote:
> Ozan wrote:
> 
> > On Wednesday, 7 June 2017 at 09:44:55 UTC, Ali Çehreli wrote:
> > > Is there an issue with the tests? Surprised that vibe.d is not higher in the rating...
> > > 
> > > https://www.techempower.com/benchmarks/#section=data-r14&hw=ph&test=fortune
> > > 
> > Same for me.
> > I used a lot of Java (Jetty, Tomcat) and Groovy (Grails) stuff
> > before using D (vibe.d).
> > On my machine I got a factor of 10-50 in difference. Vibe.d was
> > always much faster.
> > 
> > So where are the results coming from?
> 
> most of it came from microbenchmarking. "how fast can we parse json and query db?" wow, what a great benchmark! surely, we don't need to do any data processing, let's measure raw speed of parsing data, and then throwing it away!

Yes, data processing performance is not important; parsing is what we must optimize!


T

-- 
A program should be written to model the concepts of the task it performs rather than the physical world or a process because this maximizes the potential for it to be applied to tasks that are conceptually similar and, more important, to tasks that have not yet been conceived. -- Michael B. Allen

Ozan wrote:

> On Wednesday, 7 June 2017 at 09:44:55 UTC, Ali Çehreli wrote:
>> Is there an issue with the tests? Surprised that vibe.d is not higher in the rating...
>>
>> https://www.techempower.com/benchmarks/#section=data-r14&hw=ph&test=fortune
>>
> Same for me.
> I used a lot of Java (Jetty, Tomcat) and Groovy (Grails) stuff before using D (vibe.d).
> On my machine I got a factor of 10-50 in difference. Vibe.d was always much faster.
>
> So where are the results coming from?

most of it came from microbenchmarking. "how fast can we parse json and query db?" wow, what a great benchmark! surely, we don't need to do any data processing, let's measure raw speed of parsing data, and then throwing it away!

On Wednesday, 7 June 2017 at 21:18:21 UTC, ketmar wrote:
> Ozan wrote:
>
>> On Wednesday, 7 June 2017 at 09:44:55 UTC, Ali Çehreli wrote:
>>> Is there an issue with the tests? Surprised that vibe.d is not higher in the rating...
>>>
>>> https://www.techempower.com/benchmarks/#section=data-r14&hw=ph&test=fortune
>>>
>> Same for me.
>> I used a lot of Java (Jetty, Tomcat) and Groovy (Grails) stuff before using D (vibe.d).
>> On my machine I got a factor of 10-50 in difference. Vibe.d was always much faster.
>>
>> So where are the results coming from?
>
> most of it came from microbenchmarking. "how fast can we parse json and query db?" wow, what a great benchmark! surely, we don't need to do any data processing, let's measure raw speed of parsing data, and then throwing it away!

Wow. Answer was actually visible before the OP. THAT is what I would call fast. Did you use vibe.d?

On 06/08/2017 05:09 AM, Dominikus Dittes Scherkl wrote:

> Wow. Answer was actually visible before the OP. THAT is what I would
> call fast. Did you use vibe.d?

Your answer hasn't arrived yet. Using something other than vibe.d? :p

Ali

On Thursday, 8 June 2017 at 15:40:37 UTC, Ali Çehreli wrote:
> On 06/08/2017 05:09 AM, Dominikus Dittes Scherkl wrote:
>
> > Wow. Answer was actually visible before the OP. THAT is what
> I would
> > call fast. Did you use vibe.d?
>
> Your answer hasn't arrived yet. Using something other than vibe.d? :p
>
> Ali

lol, your answer did arrive before OP.

Am 07.06.2017 um 11:44 schrieb Ali Çehreli:
> Is there an issue with the tests? Surprised that vibe.d is not higher in the rating...
> 
> 
> https://www.techempower.com/benchmarks/#section=data-r14&hw=ph&test=fortune
> 
> Ali

There are thread scaling issues in the tested version. The test setup there uses a 40 core server (plus hyper threading), so this cripples the results. I've fixed a few issues in the latest betas, but I can't say for sure if those were the only ones, because my tests were only on a 2-core i7 (it scales like it should there now).

They introduced "continuous benchmarking" with more frequent preview results now, which should hopefully make fixing this more realistic for the next round.