Re: CPU stress tests for LilyPond

[Thomas Scharkowski]

For comparison:
My iMac late 2013 Intel i5 3,2 GHz 8 GM RAM needs 27.4“
Both macOS Monterey 12.0.1 btw

> Am 02.12.2021 um 09:05 schrieb Thomas Scharkowski <t.scharkowski@t-online.de>:
> 
> Hi,
> 
> the Carver takes 10.6“ to compile on my MacBook Pro M1 16GB RAM with LilyPond 
> 2.23.5
> 
> Hth
> 
> 
>> Am 02.12.2021 um 02:55 schrieb Paolo Prete <paolopr976@gmail.com>:
>> 
>> Note too that there's a list of the results for the Gzip test:
>> 
>> https://openbenchmarking.org/test/pts/compress-gzip
>> 
>> From this list it appears to me that Intel Core i5-11600k could be the 
>> "gold" PC for LilyPond...  
>> 
>> On Thu, Dec 2, 2021 at 2:41 AM Paolo Prete <paolopr976@gmail.com> wrote:
>> Hello Hans,
>> 
>> I don't think this test can give reliable results for what we need to 
>> compare.
>> With my processor (Intel Celeron N3350) it took 96 seconds to compile 
>> MSDN.ly 
>> 
>> But my CPU is listed with score 287:
>> https://browser.geekbench.com/processors/intel-celeron-n3350
>> ---> (1712 / 287)
>> 
>> From what I see,  is it true that geekbench 5 is single core, but it 
>> intensively uses RAM and the test we need should not be focused on RAM. I 
>> would consider a Gzip compression test, instead.
>> 
>> https://openbenchmarking.org/vs/Processor/Apple%20M1,Intel%20Celeron%20J3455
>> 
>> (note that it compares Apple M1 with Celeron J3455, which is NOT my CPU, but 
>> it should be very similar for single-core tests.)
>> 
>> The result is 91 / 40 which is very similar to 96 seconds / 40 seconds 
>> (Jacque's test)  . I don't know if this is a coincidence and please, if you 
>> all have more data, share it.
>> 
>> 
>> 
>> 
>> 
>> On Tue, Nov 30, 2021 at 5:56 PM Hans Åberg <haberg-1@telia.com> wrote:
>> So, to illustrate the idea of using the benchmark at the list below, it 
>> might be the Mac mini (Late 2020) with single-core score 1712 and the other 
>> Macs of this year have a similar performance. It gives for the iMac 2008 
>> used a single-core score 372 (depending on model), and it took 4–5 minutes 
>> to compile the same example. Then 1712/407 = 4.6, and dividing 4 minutes 
>> with that gives 53 seconds, and this ignores speedups in lilypond self, but 
>> it seems one can get a rough idea of performance this way.
>> 
>> https://browser.geekbench.com/mac-benchmarks
>> 
>> 
>>> On 30 Nov 2021, at 16:36, Jacques Menu <imj-muzhic@bluewin.ch> wrote:
>>> 
>>> Hello,
>>> 
>>> Here is what I get for this 102 page score:
>>> 
>>> jacquesmenu@macmini > time lilypond MSDM.ly
>>> GNU LilyPond 2.22.1
>>> ;;; note: auto-compilation is enabled, set GUILE_AUTO_COMPILE=0
>>> ;;;       or pass the --no-auto-compile argument to disable.
>>> … … … …
>>> real  0m39.590s
>>> user  0m37.119s
>>> sys   0m2.285s
>>> 
>>> jacquesmenu@macmini > ls -sal MSDM.*
>>>   8 -rw-------@ 1 jacquesmenu  staff    2695 Nov 17  2016 MSDM.ly
>>>  88 -rw-r--r--  1 jacquesmenu  staff   42641 Nov 30 16:32 MSDM.mid
>>> 1888 -rw-r--r--  1 jacquesmenu  staff  963019 Nov 30 16:32 MSDM.pdf
>>> 
>>> The machine is a Mac Mini M1, 8GB RAM, 256 GB disk.
>>> 
>>> JM
>>> 
>>>> Le 30 nov. 2021 à 15:28, Hans Åberg <haberg-1@telia.com> a écrit :
>>>> 
>>>> 
>>>>> On 30 Nov 2021, at 14:26, Paolo Prete <paolopr976@gmail.com> wrote:
>>>>> 
>>>>> I need to buy a new PC, more powerful than the one I own. The CPU and RAM 
>>>>> must be chosen on the time required to produce LilyPond output. Are there 
>>>>> any test sheets with different CPUs and the time they take to output a 
>>>>> score that takes a long time to compile? In case this doesn't exist 
>>>>> specifically for LilyPond, is there anything equivalent I can use?
>>>> 
>>>> There are general benchmarks, like those below, maybe the single core ones 
>>>> can be useful.
>>>> 
>>>> https://browser.geekbench.com
>>>> https://browser.geekbench.com/mac-benchmarks
>>>> 
>>>> 
>>>> 
>>> 
>> 
> 
>