Logic 7.2/Intel Performance Comparisons

Just came across this piece in a MacWorld mailing.
http://www.macworld.com/2006/04/firstlooks/logicprotests/index.php?lsrc=mwweek-0 501

Thanks for the tip. Exact same issue. I poked around Logic for half an hour before I realized something was just plain missing. Many differences on intel Macs. Might be good to have a site dedicated to avoiding these pitfalls.
Christian

Similar Messages

Performance Comparisons

I ma looking for performance comparisons of WebLogic Server on Sun server compared
to an Intel server. I am looking for the number of transactions per second that
can be processed on say a 4-way Wintel server as opposed to a Sun UE or, better
yet, a SunFire 280. Can anyone provide me with this information or point me towards
a source where I can find it?
Thanks!
Greg

Greg Wojtak wrote:
>
I ma looking for performance comparisons of WebLogic Server on Sun server compared
to an Intel server. I am looking for the number of transactions per second that
can be processed on say a 4-way Wintel server as opposed to a Sun UE or, better
yet, a SunFire 280. Can anyone provide me with this information or point me towards
a source where I can find it?
Thanks!Good question in my opinion ... but this is
a more generel question to java between Solaris and
Wintel ..
But seems you have an 4 Processor Intel Box ..
and only a two processor Solaris Box ..
and also the Ultra III processor have a by
far lower taktrate , right ?
The result should be obvious ..
The more generell question is, whether
the Java-Threads can ran so nice on
all processors, as they do on Solaris ..
and also whether you have so much memory
as you can have under Solaris ?
The Thread handling is still totaly different
under Windows and Solaris .. Wintel makes a times
sliced scheduling between the threads .. and
Solaris uses still the concept of LWPs which
are managed by the kernel .. not the threads
themselved are scheduled by the kernel ..
I recently heared during a SUN talk that SUN thought now, that
the overhead in the kernel for the scheduling in not longer
too high .. and they provide in the upcomming Solaris 2.9
a new thread modell which does the scheduling inside of
the kernel ..
I would assume, that a heavy threaded application performs
better on Solaris .. but this is only an assumption ..
I never had the time to measure this ..
Good luck !
Frank

Performance comparisons of DES and AES

Hi,
Has anyone gathered data in regards to performance comparison of AES vs DES using the JCE in java?
I would be interested in finding which is faster.
Thanks,
Dan

Oh, sorry by the truncated table. I've pasted an abridged version of the "openssl speed" output.
I will paste the unabridged version of "openssl speed des" output (openssl is a C crypto toolkit, not a Java toolkit).
To get the most accurate results, try to run this
program when this computer is idle.
First we calculate the approximate speed ...
Doing des cbc 20971520 times on 16 size blocks: 20971520 des cbc's in 8.11s
Doing des cbc 5242880 times on 64 size blocks: 5242880 des cbc's in 7.97s
Doing des cbc 1310720 times on 256 size blocks: 1310720 des cbc's in 7.86s
Doing des cbc 327680 times on 1024 size blocks: 327680 des cbc's in 7.78s
Doing des cbc 40960 times on 8192 size blocks: 40960 des cbc's in 7.24s
Doing des ede3 6990506 times on 16 size blocks: 6990506 des ede3's in 6.33s
Doing des ede3 1747626 times on 64 size blocks: 1747626 des ede3's in 6.31s
Doing des ede3 436906 times on 256 size blocks: 436906 des ede3's in 6.27s
Doing des ede3 109226 times on 1024 size blocks: 109226 des ede3's in 6.26s
Doing des ede3 13653 times on 8192 size blocks: 13653 des ede3's in 6.08s
OpenSSL 0.9.7d 17 Mar 2004
built on: Thu Apr 22 13:21:37 2004
options:bn(64,32) md2(int) rc4(idx,int) des(idx,cisc,4,long) aes(partial) idea(int) blowfish(idx)
compiler: cl /MD /W3 /WX /G5 /Ox /O2 /Ob2 /Gs0 /GF /Gy /nologo -DOPENSSL_SYSNAME_WIN32 -DWIN32_LEAN_AND_MEAN -DL_ENDIAN -DDSO_WIN32 -DBN_ASM -DMD5_ASM -DSHA1_ASM -DRMD160_ASM /Fdout32dll -DOPENSSL_NO_KRB5
available timing options: TIMEB HZ=1000
timing function used: ftime
The 'numbers' are in 1000s of bytes per second processed.
type             16 bytes     64 bytes    256 bytes   1024 bytes   8192 bytes
des cbc          41374.15k    42106.20k    42695.55k    43123.55k    46377.93k
des ede3         17675.11k    17719.91k    17849.97k    17852.74k    18398.65k

How does logical volume helps in performance in AIX..Should have posted IBM

We are setting up a new DB server and the disks are in RAID5 config,Does putting data and index in different logical volumes helps in performance

(I hope I'm not falling for April Fools joke here...)
Hi Maran,
As someone already answered, if both volumes are striped against all available disks, you can put everything in one volume and expect equal or better performance.
However, I want to warn you from optimizing the disk structure without knowing that your database will really bottleneck on disk access to index and data blocks. My storage manager and I wasted countless hours with such optimizations before realizing that we are wasting our time because the application code contains so many functions that disk IO is not even close to being an issue.
-- Chen

Looking for Performance Comparisons Between JRockit 6 and Sun Java SE 6

Hello,
Can someone point me to some performance comparisons (benchmarks, etc.) between the JRockit and Sun JVMs?
Thanks in advance.

Hi Ben.
Before I send to to the SPEC sites (which can be a tad hard to parse) I must ask - What application or type of application are you interested in? The answer will vary a bit depending on what you need.

Performance comparison of J2sdkee1.3.1's JMS and iPlanet MQ 2.0

I am evaluating two JMS APIs: The free one comes with J2sdkee 1.3.1 and the iPlanet Message Queue for Java 2.0 (free for development and evaluation, not free on Production environment).
I created two JSP pages running under Tomcat 3.3. One JSP page is calling a Java class 1 which uses j2sdkee1.3.1 JMS API: it creates InitialContext() and lookups for QueueConnectionFactory & Queue, then sends a text message to the Queue.
I did a little performance improvement by putting this process into a static method init(), so it will be called only once. The latter request will only send message.
The second JSP page is calling a Java class 2 which doesn't use JNDI, instead, it calls the new QueueConnectionFactory/QueueConnection classes provided by iPlanet MQ API.
I found out that InitialContext() call and lookup process is taking quite a long time in the first case. After that, sending message is quite fast. However, if "j2ee" is shutdown in the middle, the JSP page can't recover unless I restarted Tomcat server.
The performance of iPlanet MQ API is pretty good even if the QueueConnectionFactory/QueueConnection classes are created for each request. And it can recover after the Broker is restarted.
Anybody experienced in using J2sdkee1.3.1 JMS API? If you know a better way to improve performance other than the static method init() which can't recover, please share your information. Appreciate it.
Thanks,
Ye

Your performance comparison should be identical in all ways except for the particular server you are trying to evaluate. which should be relatively painless, given the use of JNDI.
At the very least, ignore the JNDI lookup in your first test.
I have found the j2ee JMS provider (the free one) to be quite slow, and also have found a bug with the shutdown and startup process changing the message order. which is a fundamental error.
I have used IBM MQ (websphere MQ) and found it to be very fast and worked as expected. I have not used their pub/sub product (which i suspect is based on Talarian.)
I favour servers built in native code, and integrate using JMS. just like I prefer Oracle over a pure Java RDBMS, but like the ease of integration offered with JDBC.
I would avoid webstyle start-up companies like Iplanet. That joint effort seems like a desperate attempt at reviving Netscape thru technology, rather than thru a business concept.

Apache-Netscape webserver plugin performance comparison WL8.1

Hi,
Can anyone guide me abt the performance comparisons between apache and netscape plug-in.
which one of the above wuold be best for WLP .l,Windows 2003 Server,Oracle 9i.
Thanks,
sumit
([email protected])

Hi,
Can anyone guide me abt the performance comparisons between apache and netscape plug-in.
which one of the above wuold be best for WLP .l,Windows 2003 Server,Oracle 9i.
Thanks,
sumit
([email protected])

Servlets/JDBC vs. servlets/EJB performance comparison/benchmark

I have a PHB who believes that EJB has no ___performance___ benefit
against straightforward servlets/JSP/JDBC. Personally, I believe that
using EJB is more scalable instead of using servlets/JDBC with
connection pooling.
However, I am at a lost on how to prove it. There is all the theory, but
I would appreciate it if anyone has benchmarks or comparison of
servlets/JSP/JDBC and servlets/JSP/EJB performance, assuming that they
were tasked to do the same thing ( e.g. performance the same SQL
statement, on the same set of tables, etc. ).
Or some guide on how to setup such a benchmark and prove it internally.
In other words, the PHB needs numbers, showing performance and
scalability. In particular, I would like this to be in WLS 6.0.
Any help appreciated.

First off, whether you use servlets + JDBC or servlets + EJB, you'll
most likely spend much of your time in the database.
I would strongly suggest that you avoid the servlets + JDBC
architecture. If you want to do straight JDBC code, then it's
preferable to use a stateless session EJB between the presentation layer
and the persistence layer.
So, you should definitely consider an architecture where you have:
servlets/jsp --> stateless session ejb --> JDBC code
Your servlet / jsp layer handles presentation.
The stateless session EJB layer abstracts the persistence layer and
handles transaction demarcation.
Modularity is important here. There's no reason that your presentation
layer should be concerned with your persistence logic. Your application
might be re-used or later enhanced with an Entity EJB, or JCA Connector,
or a JMS queue providing the persistence layer.
Also, you will usually have web or graphic designers who are modifying
the web pages. Generally, they should not be exposed to transactions
and jdbc code.
We optimize the RMI calls so they are just local method calls. The
stateless session ejb instances are pooled. You won't see much if any
performance overhead.
-- Rob
jms wrote:
>
I have a PHB who believes that EJB has no ___performance___ benefit
against straightforward servlets/JSP/JDBC. Personally, I believe that
using EJB is more scalable instead of using servlets/JDBC with
connection pooling.
However, I am at a lost on how to prove it. There is all the theory, but
I would appreciate it if anyone has benchmarks or comparison of
servlets/JSP/JDBC and servlets/JSP/EJB performance, assuming that they
were tasked to do the same thing ( e.g. performance the same SQL
statement, on the same set of tables, etc. ).
Or some guide on how to setup such a benchmark and prove it internally.
In other words, the PHB needs numbers, showing performance and
scalability. In particular, I would like this to be in WLS 6.0.
Any help appreciated.--
Coming Soon: Building J2EE Applications & BEA WebLogic Server
by Michael Girdley, Rob Woollen, and Sandra Emerson
http://learnweblogic.com

Performance comparisons between Apple's SSD's and hard drives

Am looking for objective performance data comparing SSD's in Apple's MacBook Pro versus Apple's hard drives in MacBook Pro. I've read some material in Tom's Hardware but am looking for specific device comparisons of these storage types in MacBooks. Seek/latency/read transfer rates/write transfer rates/reliability/etc.

Thanks for the information!! I've book-marked the site and plan to refer to it often.

Logical Standby Apply Process Performance

Hello,
We are testing our logical standby database for sql apply process.We run batch jobs in our active database and monitor the standby database for the time it takes to bring the database in sync following are the steps we follow:
1) Insure active and standby are in sync.
2) Stop sql apply on standby database.
3) Run Batch job on active database.
4) After completion of the job on active,start sql apply on standby.
Following are the details of the time taken by sql apply,based on the previous runs:
1st. 654K volume = 4 hrs (2727 records per min)
2nd. 810K volume = 8 hrs 45 mins (1543 records per min)
3rd. 744K volume = 7 hrs 17 mins (1704 records per min)
Following are the details of the logical stdby parameters :
MAX_SGA 100
MAX_SERVERS 15
PREPARE_SERVERS 4
APPLY_SERVERS 8
MAX_EVENTS_RECORDED 10000
RECORD_SKIP_ERRORS TRUE
RECORD_SKIP_DDL TRUE
RECORD_APPLIED_DDL FALSE
RECORD_UNSUPPORTED_OPERATIONS FALSE
EVENT_LOG_DEST DEST_EVENTS_TABLE
LOG_AUTO_DELETE TRUE
LOG_AUTO_DEL_RETENTION_TARGET 1440
PRESERVE_COMMIT_ORDER TRUE
ALLOW_TRANSFORMATION FALSE
can we ensure SQL apply process to apply data in consistent volume,Is it okay for a sql apply process to take same amount of time what the actual batch takes in active instance,can we further tweak apply process to get better performance.
Please help.
Thank you !!

Following are the details of the time taken by sql apply,based on the previous runs:
1st. 654K volume = 4 hrs (2727 records per min)
2nd. 810K volume = 8 hrs 45 mins (1543 records per min)
3rd. 744K volume = 7 hrs 17 mins (1704 records per min)
Following are the details of the logical stdby parameters :
Hi,
By looking at the above apply rate, the apply process is working normally and not having issues.
Since it's a bulk batch data update in PRIMARY, it's obvious and quite normal that it will take time in STANDBY database to get applied and in sync with PRIMARY.
Still, if you need to consider improving the performance, look out for adjusting the APPLIER & PREPARER process. (parameteres, APPLY_SERVERS & PREPAR_SERVERS).

Intel Performance

How does a Intel Pentium 4 running Solaris 8 compare in performance to a new Sun Blade 100.
I already have installed in a old pentium just for fun. Now I want to try something a bit bigger...

That´s absolutely true ! But of course nobody likes to talk about it. The whole creative suite applications run slow, especially Illustrator - you can´t use it at the moment. But it´s the same story with Word and PowerPoint. Oh my god, i bought a computer that is slower than my old 3 years old powerbook. Apple has to be blaimed for fooling its customers with wrong promises !!! You know something ? If i open an Illustrator document on MacOSX it takes 1 minute ! 1 Minute !
The same document, opened on windows (boot camp on the same machine) shows up in 8 seconds !!! You Apple-maniacs out there - do you like that ?
Mac book pro Mac OS X (10.4.6)

Database Performance Comparison on Linux n WindowNT

Hi Everybody,
We have an Application running on Oracle7.3 n WindowNT. Now we are shifting this to Oracle8i (Rel 2). OS platform is not yet
decided. We are asked to submit a performance report of Oracle8i on Linux and Oracle8i on WindowsNT. How can we make a comparison of Oracle8i on WinowsNT n Linux(RedHat6.2).
Also if any body knows any web site related to this, please let me know the same also.
Thanks n Regards,
Hari
null

I did something like that a little while ago, so here's a summary of what I did and what I learned:
I also wanted to select a server OS for a data warehouse, and I did some head-to-head comparisons (same machine, just booted into different OS varieties, loading the same data). I used Red Hat 6.0 and 6.2, SuSE 6.3 and 6.4, and Mandrake 7.0 and 7.1, plus NT4.
Overall, I found that any Linux outperformed NT--but not by enough to make that a major factor in selection. Subjectively, I also found that everything I did was just a little bit less straightforward, a little bit less convenient in Red Hat than it was in any other Linux distribution I tried--but again, not necessarily enough to make a big difference in selection.
I also had more crashes and lockups with NT than I did with any Linux, but that may be more a reflection of my skill at administering NT vs. my skill at administering Linux.
I'd say it's definitely worth your while to evaluate Linux, and I'd suggest that you have a look at several Linux distributions while you're at it. Personally, I like SuSE and dislike Red Hat.

Performance comparisons between POF & open source serialization mechanism?

I'm curious whether anyone has done any comparisons of performance and serialized object sizes between POF and open source mechanisms such as Google Protocol Buffers and Thrift, both of which seem to be becoming quite popular. Personally, I dislike having to write a separate schema and then generate classes from it, which Protocol Buffers and Thrift require you to do, and I vastly prefer POF's mechanism of keeping everything in the code (although I wish the POF annotation framework was officially supported). But aside from that, I'd prefer to use Coherence for many of the purposes that some of my co-workers are currently using other solutions for, and this would be useful information to have in making the case.
FWIW, I hope someone at Oracle is seriously considering open-sourcing POF. I don't think that anyone who would've bought a Coherence license would decide not to because they could get POF for free. They'd just go and use something else, like the aforementioned Protocol Buffers and Thrift. Not only are many companies adopting these as standards, but as has been mentioned in other threads on this forum, that's exactly what even some Coherence users are doing:
Re: POF compatibility across Coherence versions
I really wish I could to encourage developers that I work with to give POF a look as an alternative to those two (both of which we're currently using), regardless of whether or not they plan on using Coherence in the immediate future. As things stand right now, I can't use Coherence for code that needs to be shared with people in other groups who haven't adopted Coherence yet. But if I could use POF outside of Coherence, it would probably be acceptable to those folks as a generic serialization mechanism, and it would make migrating such code to Coherence at some point down the road that much easier. If, on the other hand, I have to write that code around, say, Protocol Buffers, then it becomes much harder to later justify creating and maintaining POF as a second serialization mechanism for the same set of objects, which means it's much harder to justify using Coherence for those objects.
In short, making POF usable outside of Coherence, and who knows, maybe even getting it supported in popular open source projects such as Cassandra (which, as I understand it, uses Thrift) would make it easier to adopt Coherence in environments where objects are already persisted in other systems.
That's my two cents.

Hi,
Thank you for links. It is very interesting.
I have implemented POF serialization plugin for this benchmark http://wiki.github.com/eishay/jvm-serializers/
You can get code, run benchmark for yourself and compare result.
Handmade POF serialization http://gridkit.googlecode.com/svn/wiki/snippets/CoherencePofSerializer.java
Reflection POF serialization http://gridkit.googlecode.com/svn/wiki/snippets/CoherencePofReflection.java
Also you should put a two line in BenchmarkRunner.java, all other instructions are on jvm-serializers project page.
          Protobuf.register(groups);
          Thrift.register(groups);
          ActiveMQProtobuf.register(groups);
          Protostuff.register(groups);
          Kryo.register(groups);
          AvroSpecific.register(groups);
          AvroGeneric.register(groups);
// register POF tests here
          CoherencePofSerializer.register(groups);
          CoherencePofReflection.register(groups);
          CksBinary.register(groups);
          Hessian.register(groups);
          JavaBuiltIn.register(groups);
          JavaManual.register(groups);
          Scala.register(groups);A few comments on result.
* Micro benchmark is a micro benchmark, I saw quite differnt results then comparis java vs POF vs POF reflection on own domain objects.
* POF score very good compared to protocols like Protobuf or Thrift, especially on deserialization.
* Kryo project is quite interesting, I'm going to give it a try in next project for sure.
Again, thanks a lot for a link.

Reaktor running in Logic on new intel I-mac 20", 2GB memory,

Hi folks, just bought a new i-mac dual intel chippy thing and have been running Logic and Reaktor as an audio unit. Several problems
1. Reaktor seems to take up loads of processing power on some ensembles, is there anything I can do to optimise it e.g. should I install it on my sepereate firewire hard drive? Should I leave the processor hungry ensembles alone?
2. Should it really slow Logic down, is there something I'm missing? I do have the latest update for Reaktor but have not installed it until I get online to authorise.
3. Can i run Logic off my seperate hard drive? Is this the best way?
4. My previous i-mac single processor seemed to handle this all better with less memory CPU power available.
5. My M-audio Firewire audiophile drive ris not loading. Are there issues with the new intel macs? Do I need to update my driver for this?
Many thanks
Imac Intel Dual 20" Mac OS X (10.4.8) sep. hard drive,

2. Should it really slow Logic down, is there
something I'm missing? I do have the latest update
for Reaktor but have not installed it until I get
online to authorise.
Here's your main issue right now. Reaktor only came out in UB format, last week. (version 5.1.2 - the update you would've downloaded)
So, you will need to run that update and activate it for it to work properly with your Intel procs.
Be careful with the NI's service center, as I had all sorts of issues with it last week, whilst trying to update Komplete4 to UniBinary.

Cannot open logic song on intel mac

I have a problem with a logic song using logic 7.2.3 on a ppc g5 and a macbook pro.
Using the g5 I can open the song but trying the same with the intel macbook pro (also with 7.2.3.) I receive the message that the song is defect, the dialog offers to repair the song but this doesnt succeed.
It tried already to save a new project of the song but the same happens again.
Any advice would be great otherwise I will have to rebuild the whole song. Thanks in advance...

What you can try is get yourself a copy of Logic 6 (if you don't have it, look here : http://download.info.apple.com/AppleSupportArea/emagic/ ) and then open the song in L6 on your G5. Then save it again, from L6, and try to open the resulting file again on the intel mac.
If this fails, you can also try to use Logic 6 on your MBP and see if that works 'directly'.
Good luck !

Logic 7.2/Intel Performance Comparisons

Similar Messages

Maybe you are looking for