Chun, Sungjin wrote:
> When this will be in the official VMs? And to use or benefit this
> improvement should
> previous code (especially Seaside, I'm using it) be modified?

I think that you read the results wrong... the new code runs the
benchmark about 8x slower than the existing code.

Cheers,
Josh




>
> Thanks
>
>
> On May 1, 2009, at 5:11 AM, Igor Stasenko wrote:
>
>> 2009/4/30 Andreas Raab <andreas.raab at gmx.de>:
>>> A better benchmark is attached. It allows adjusting the number of
>>> processes
>>> and the total time the benchmark should run and answers the number of
>>> process switches per second. This is our "standard" process switch
>>> benchmark. Run it like here:
>>>
>>> 100 "processes" benchSwitch: 5. "seconds"
>>>
>>
>> I have built a new VM with closure support (VMMaker.dtl.120).
>> A changeset can be loaded to VMMaker w/o changes, except changing the
>> Interpreter class redefinition.
>> All is needed is to add 3 class vars to Interpreter manually:
>> ProcessActionIndex InterruptedProcessIndex InterruptProcessIndex
>>
>> Running squeak-3.10 (no closure compiler).
>>
>> 100 "processes" benchSwitch: 5. "seconds"
>>
>> Processor fallbackToOldScheduler
>>
>> '1,156,135 switches/sec'
>> '1,144,994 switches/sec'
>> '1,147,744 switches/sec'
>>
>> AdvancedProcessorScheduler install
>>
>> '148,067 switches/sec'
>> '141,211 switches/sec'
>> '141,692 switches/sec'
>> '148,650 switches/sec'
>>
>> (1156/148) ~~ 7.8 ratio
>>
>>
>>
>>> This will switch between 100 processes for 5 seconds.
>>>
>>> Cheers,
>>>  - Andreas
>>>
>>> Andreas Raab wrote:
>>>>
>>>> Igor Stasenko wrote:
>>>>>
>>>>> A quick comparion for Delays:
>>>>>
>>>>>       delay := Delay forMilliseconds: 1.
>>>>>       bag := Bag new.
>>>>>       1000 timesRepeat:[bag add: [delay wait] timeToRun].
>>>>>       bag sortedCounts
>>>>>
>>>>> on my 4-core box it yields:
>>>>>
>>>>> - with AdvancedProcessorScheduler install
>>>>>  a SortedCollection(951->2 49->1)
>>>>>
>>>>> - with Processor fallbackToOldScheduler
>>>>>  a SortedCollection(953->2 47->1)
>>>>>
>>>>> - with old VM
>>>>>  a SortedCollection(952->2 47->1 1->3)
>>>>>
>>>>> not much overhead huh? :)
>>>>
>>>> That's not exactly the kind of benchmark I was looking for (if your
>>>> process scheduler takes milliseconds to do a switch I think we're
>>>> not even
>>>> close to the ballpark ;-) More interesting for comparison is this
>>>> (requires
>>>> closures):
>>>>
>>>>  semas := Array new: 10000.
>>>>  plist := Array new: 10000.
>>>>  1 to: semas size do:[:i| semas at: i put: Semaphore new].
>>>>  1 to: plist size-1 do:[:i| plist at: i put: [(semas at: i) wait.
>>>> (semas
>>>> at:i+1) signal] fork].
>>>>  [semas first signal. semas last wait] timeToRun.
>>>>
>>>> Cheers,
>>>>  - Andreas
>>>>
>>>>
>>>
>>>
>>>
>>>
>>>
>>
>>
>>
>> -- 
>> Best regards,
>> Igor Stasenko AKA sig.
>>
>>
>
>