Win 7 on multicore not faster than XP

[PeterCH]

"InfoWorld's Andrew Binstock tests whether Windows 7's threading advances fulfill the promise of improved performance and energy reduction. He runs Windows XP Professional, Vista Ultimate, and Windows 7 Ultimate against Viewperf and Cinebench benchmarks using a Dell Precision T3500 workstation, the price-performance winner of an earlier roundup of Nehalem-based workstations. 'What might be surprising is that Windows 7's multithreading changes did not deliver more of a performance punch,' Binstock writes of the benchmarks, adding that the principal changes to Windows 7 multithreading consist of increased processor affinity, 'a wholly new mechanism that gets rid of the global locking concept and pushes the management of lock access down to the locked resources,' permitting Windows 7 to scale up to 256 processors without performance penalty, but delivering little performance gains for systems with only a few processors. 'Windows 7 performs several tricks to keep threads running on the same execution pipelines so that the underlying Nehalem processor can turn off transistors on lesser-used or inactive pipelines,' Binstock writes. 'The primary benefit of this feature is reduced energy consumption,' with Windows 7 requiring 17 percent less power to run than Windows XP or Vista."

http://tech.slashdot.org/story/09/10/21/1234214/Windows-7-On-Multicore-mdash-How-Much-Faster

Well if that 17% benefit can be significant - if 1. it's under all circumstances not just heavy use in >2 core CPUs and 2. CPU power draw is a significant power draw - then Win 7 is beneficial because it allows laptops to crunch numbers longer while under battery draw and - it's better for the environment and the utilities' bill -it could be a reason to upgrade - the only one so far. However, it's not faster for multiple cores.

 

[phiber]

Interesting, i thought they had made leaps and bounds... At least i can get longer battery life on my work laptop (thats if they upgrade from xp to 7).

 

[adrianx]

I predict that for the first few weeks/months after release, most MS-enamoured folk will "feel" that it is much faster and works much better than anything else on earth. That will be the the honeymoon period....

I still get caught in that same trap myself, but I'm beginning to learn to be cautiously optimistic about most things technological. I also try to avoid most of the hype. Baby steps.

 

[I am Penguin]

http://tech.slashdot.org/story/09/10/21/1234214/Windows-7-On-Multicore-mdash-How-Much-Faster

Well if that 17% benefit can be significant - if 1. it's under all circumstances not just heavy use in >2 core CPUs and 2. CPU power draw is a significant power draw - then Win 7 is beneficial because it allows laptops to crunch numbers longer while under battery draw and - it's better for the environment and the utilities' bill -it could be a reason to upgrade - the only one so far. However, it's not faster for multiple cores.

It said not "much" faster for a "few" cores but can scale up to 256 cores? Thus very apt for multi CPU server boards and future Xmulticore processors.
Interesting.

http://www.infoworld.com/d/windows/windows-7-multicore-how-much-faster-325

InfoWorld's tests show that speed isn't the only benefit, or necessarily the main one

These results suggests that when considering Windows 7, performance should be viewed as a reasonable justification for upgrading from Windows XP, but not a driver for migration from Vista

http://www.infoworld.com/d/windows/windows-7-multicore-how-much-faster-325?page=0,0

Thus Peter your title is again biased opinion and misinformation (FUD) as windows 7 IS FASTER THAN xp with further performance increase/scaling as more cores/CPU's are installed in the hardware, it is clearly stated that with lower core system the performance increase will not be MUCH but it is there.

So the conclusion is as we experienced a faster OS.

Do yourself a favour and install a Windows7 system then we talk.

I concur about the power saving as that could be beneficial for laptops but that will not be a real consideration for most users.

 

[PeterCH]

It said not "much" faster for a "few" cores but can scale up to 256 cores? Thus very apt for multi CPU server boards and future Xmulticore processors.
Interesting.



http://www.infoworld.com/d/windows/windows-7-multicore-how-much-faster-325?page=0,0

Thus Peter your title is again biased opinion and misinformation (FUD) as windows 7 IS FASTER THAN xp with further performance increase/scaling as more cores/CPU's are installed in the hardware, it is clearly stated that with lower core system the performance increase will not be MUCH but it is there.

So the conclusion is as we experienced a faster OS.

Do yourself a favour and install a Windows7 system then we talk.

I concur about the power saving as that could be beneficial for laptops but that will not be a real consideration for most users.

You're WRONG.

You missed this:

Windows 7 includes a wholly new mechanism that gets rid of the global locking concept and pushes the management of lock access down to the locked resources. This permits Windows 7 to scale up to 256 processors without performance penalty. On systems with only a few processors, however, the old kernel dispatcher lock was not overburdened, so this new mechanism provides no noticeable improvement in threading performance on desktops and small servers.

So no- not FUD.

You're trolling again.

Power saving is a consideration for everyone, especially if you have many computers running. 17% less power use on systems which are running 24/7 is significant. However, that's not the reason shills like you push Win 7. It's debatable how much power saving it will bring - will it justify the R2000+ price tag of Windows 7 and cost of reinstall and hassles with upgrading all the associated software and whether the cost to the environment of making that copy of Windows (creating the DVD, printing the box, transport costs) are not bigger in terms of the carbon footprint than the power saved. 17% after all is at full CPU load and not when machine is using less than full CPU load, neither does it include power consumed by the GPU, harddrives and screen backlight, ie that 17% is 17% of CPU power draw only and not of total power draw and under heavy use probably ONLY.

In another InfoWorld article posted here earlier this year, they mentioned you need 64 cores to start taking advantage of Windows 7.

 

[I am Penguin]

You're WRONG.

You missed this:



So no- not FUD.

You're trolling again.

And Peter You read what you want to, selective reading. Again read this, what the reviewer and article writer said.

InfoWorld's tests show that speed isn't the only benefit, or necessarily the main one

These results suggests that when considering Windows 7, performance should be viewed as a reasonable justification for upgrading from Windows XP, but not a driver for migration from Vista

Then again look at the table of the tests.

 

[PeterCH]

And Peter You read what you want to, selective reading. Again read this, what the reviewer and article writer said.

InfoWorld's tests show that speed isn't the only benefit, or necessarily the main one

Then look at the table of the tests.[/QUOTE]

Read the article again, they don't say Windows 7 is faster, in fact they say there is no performance difference.

In terms of the numbers, those are artificial and not real world figures, after all even VISTA beats Windows 7.

BTW the 17% saving is only on Nehalem Xeon processors.

 

[I am Penguin]

Then look at the table of the tests.

Read the article again, they don't say Windows 7 is faster, in fact they say there is no performance difference.

In terms of the numbers, those are artificial and not real world figures, after all even VISTA beats Windows 7.

BTW the 17% saving is only on Nehalem Xeon processors.

Yeah Peter I take what you say with Brandy and Disprins as YOU only read and comprehend VERY selectively. I quoted you what the original writer stated and posted the table Yet you prefer to differ. We just loose more repect for your BIASED point of view every day. Lets see how others interpret what the writer said. NOwhere in both written scripts (links posted)have I seen the text your OP title states and what you claim. In fact I saw exactly the opposite!

 

[PeterCH]

Read the article again, they don't say Windows 7 is faster, in fact they say there is no performance difference.

In terms of the numbers, those are artificial and not real world figures, after all even VISTA beats Windows 7.

BTW the 17% saving is only on Nehalem Xeon processors.

Yeah Peter I take what you say with Brandy and Disprins as YOU only read and comprehend VERY selectively. I quoted you what the original writer stated and posted the table Yet you prefer to differ. We just loose more repect for your BIASED point of view every day. Lets see how others interpret what the writer said. NOwhere in both written scripts (links posted)have I seen the text your OP title states and what you claim. In fact I saw exactly the opposite![/QUOTE]

Windows 7 is faster with many cores on the newest Nehalem CPUs but not faster with the standard number of cores.

As for the benchmarks they don't comment on them, but Vista outperforms Win 7 in them too.

The Cinebench benchmark is a ratio that measures how much faster the multiple threads are than running the benchmark with one thread; it's a true measure of how the threading scales when measured by rendering performance. Cinebench showed negligible differences in performance across the three operating systems -- both with SMT disabled and with SMT enabled. However, unlike with Viewperf, the results for all three Windows were distinctly better with SMT enabled; i.e., Cinebench rendering ran nearly 20 percent faster on eight threads (SMT on) than four (SMT off), regardless of the version of Windows. This divergence between the two benchmarks regarding SMT's benefit underscores the need for testing its effect on your existing applications before deciding whether to enable it.

and

Nehalems are much more powerful than predecessors, and they provide, as we have seen, considerable energy savings when teamed up with an OS that leverages them effectively. Among Microsoft offerings, Windows 7 is the software that does this best.

The results are not real world.

 

[I am Penguin]

Part1

Yeah Peter I take what you say with Brandy and Disprins as YOU only read and comprehend VERY selectively. I quoted you what the original writer stated and posted the table Yet you prefer to differ. We just loose more repect for your BIASED point of view every day. Lets see how others interpret what the writer said. NOwhere in both written scripts (links posted)have I seen the text your OP title states and what you claim. In fact I saw exactly the opposite!

Windows 7 is faster with many cores on the newest Nehalem CPUs but not faster with the standard number of cores.

As for the benchmarks they don't comment on them, but Vista outperforms Win 7 in them too.



and



The results are not real world.

Lets look at facts boy!

What is MAXON CINEBENCH?

CINEBENCH is a real-world test suite that assesses your computer's performace capabilities. MAXON CINEBENCH is based on MAXON's award-winning animation software CINEMA 4D, which is used extensively by studios and production houses worldwide for 3D content creation. MAXON software has been used in blockbuster movies such as Spider-Man, Star Wars, The Chronicles of Narnia and many more.

MAXON CINEBENCH runs several tests on your computer to measure the performance of the main processor and the graphics card under real-world circumstances. The benchmark application makes use of up to 16 CPUs or CPU cores and is available for Windows (32-bit and 64-bit) and Macintosh (PPC and Intel-based).

The resulting values among different operating systems are 100% comparable and therefore very useful with regard to purchasing decision making. It can also be used as a marketing tool for hardware vendors or simply to compare hardware among colleagues or friends.

How Does MAXON CINEBENCH Work?

The test procedure consists of two main components: The first test sequence is dedicated to the computer's main processor. A 3D scene file is used to render a photoreaslistic image. The scene makes use of various CPU-intensive features such as reflection, ambient occlusion, area lights and procedural shaders. During the first run the benchmark only uses one CPU (or CPU core) to ascertain a reference value. On computers that have multiple CPUs or CPU cores and on those that simulate multiple CPUs (via HyperThreading or similar technolgies), MAXON CINEBENCH will run a second test using all available CPU power.

The second test measures graphics card performance and is run inside the 3D editor window. The project file used can test all graphics cards that support the OpenGL standard. In this scene, only the camera was animated. This scene places medium to low demands on graphics cards and tests the maximum speed with which the scene can be properly

These are supplied facts not sucked out of my cock or thumb!
Now here is the crunch!

Who Should Use MAXON CINEBENCH?

There is a wide range of applications for a real-world benchmarking tool like MAXON CINEBENCH. Anyone who needs to compare the performance of computer hardware should put MAXON CINEBENCH into his or her toolbox. Contrary to abstract benchmarks, which only test specific functions of CPUs or GPUs, a real-world benchmark applies a user's common tasks to measure a system's performance.

Note: testing the hardware performance NOT OS system performance therefore the small/very little difference as the same hardware was used during testing of all the systems YET the Windows7 did better than XP by a full 3% increase. Windows7 is not a hardware accelerator but a OS (OPERATING SYSTEM)

 

[I am Penguin]

Part2

What SPECviewperf® Does and Doesn't Do

Nearly all benchmarks are designed for a specific purpose. Quite often, however, users broaden that purpose beyond what the benchmark is designed to do, or in some cases they assume the benchmark can't do something that it actually can do. The SPECviewperf® benchmark is no different: it has been both overextended and underappreciated, sometimes reducing its overall value to the user. Here is a closer look at SPECviewperf: what it is and what it can and can't do.

SPECviewperf measures the 3D rendering performance of systems running under OpenGL. The SPECopcSM project group has worked with independent software vendors (ISVs) to obtain tests, data sets and weights that constitute what is called a viewset. Each viewset represents the graphics rendering portion of an actual application. The ISVs that develop SPECopc viewsets have provided percentage weights for each test for which a performance number is reported. ISVs have defined these percentages to indicate the relative importance of a test within the overall application.

SPECviewperf offers the following characteristics:

•It provides a single-source code for apples-to-apples comparison and performance tuning across different hardware platforms.
•It runs on multiple operating systems.
•It runs across different processors.
•It runs on multiple windowing environments.
•It encompasses a wide variety of OpenGL features and rendering techniques.
•It is easily accessible through the SPECopc project subcommittee, ftp and through OpenGL sample disk distribution.
Several factors make SPECviewperf unique from other benchmarks:

•It uses datasets that are designed for and used by real applications.
•It uses rendering parameters and models selected by independent software vendors (ISVs) and graphics users.
•It produces numbers based on frames per second, a measurement with which users can readily identify.
•It provides one number for each rendering path using one data set.
What SPECviewperf Measures

SPECviewperf measures performance for the following entities:

•3D primitives, including points, lines, line_strip, line_loop, triangles, triangle_strip, triangle_fan, quads and polygons;
•attributes per vertex, per primitive and per frame;
•lighting;
•texture mapping;
•alpha blending;
•fogging;
•anti-aliasing; and
•depth buffering.

The Five-Step Program

SPECviewperf is not a single-number benchmark. In order to use it to its fullest advantage, ISVs and users need to relate the benchmark to their actual applications. Here are the five steps recommended for using SPECviewperf effectively:

1.Identify software code paths that are important to the application.
2.Identify the primitives used within the application.
3.Select datasets that are most appropriate to the application. The datasets should reflect the level of geometry and rasterization found in the application.
4.Identify attributes and the level at which they are applied (per vertex, per primitive or per frame).
5.Assign a weight to each path based on the percentage of time in each path and the importance of the path to the application.

What SPECviewperf Can't Do

Although SPECviewperf is a good tool for measuring OpenGL performance as it relates to applications, like all benchmarks it has limitations. Most important of these is that it cannot be used to compare performance across different application programming interfaces (APIs). Also, it does not run itself; users must participate in the benchmarking process. When testing and reporting results, SPECviewperf does not account for the following key factors:

•effects caused by switching primitives,
•input effects on the event loop,
•user interface rendering and management,
•complex motion of multiple models,
•effects of CPU load on the graphics subsystem,
•color index visual performance, and
•multi-context, multi-window effects

Now again this bench is more related to rendering of the GUI , what you see etc. In that test we see a 67.3% increase above XP. Now really I cannot see or argue your point as what I note you are trying to deflect this topic to a vista comparison. The topic clearly states "XP is not faster". What were you reading? Japanese Anime subtitle text again?

C'mon Peter for Pete's sake grow up now. I am sure you are my age if not even older. Stop your all out life task and effort to prove a fact that does and cannot even exist. FFS.

Windows XP is not faster than Windows7. Nobody ever argued about Vista but YOU. Windows7 is as you said Vista clone so differences can be smal and then you have to wait for the SP's to come for Windows7 to compare with Vista.

But Maybe just maybe you will be prepared to read about other tests.

Windows 7 beta 1 performance - How does the OS compare to Vista and XP?

How does Windows 7 beta 1 compare to Vista and XP in terms of performance? That’s a question that’s been hitting my inbox regularly over the past few weeks. Let’s see if we can’t answer it!


The tests

There are 23 tests in all, most of which are self explanatory:

1.Install OS - Time it takes to install the OS
2.Boot up - Average boot time to usable desktop
3.Shut down - Average shut down time
4.Move 100MB files - Move 100MB of JPEG files from one hard drive to another
5.Move 2.5GB files - Move 2.5GB of mixed size files (ranging from 1MB to 100MB) from one hard drive to another
6.Network transfer 100MB files - Move 100MB of JPEG files from test machine to NAS device
7.Network transfer 2.5GB files - Move 2.5GB of mixed size files (ranging from 1MB to 100MB) from test machine to NAS device
8.Move 100MB files under load - Move 100MB of JPEG files from one hard drive to another while ripping DVD to .ISO file
9.Move 2.5GB files under load - Move 2.5GB of mixed size files (ranging from 1MB to 100MB) from one hard drive to another while ripping DVD to .ISO file
10.Network transfer 100MB files under load - Move 100MB of JPEG files from test machine to NAS device while ripping DVD to .ISO file
11.Network transfer 2.5GB files under load - Move 2.5GB of mixed size files (ranging from 1MB to 100MB) from test machine to NAS device while ripping DVD to .ISO file
12.Compress 100MB files - Using built-in ZIP compression
13.Compress 1GB files - Using built-in ZIP compression
14.Extract 100MB files - Using built-in ZIP compression
15.Extract 1GB files - Using built-in ZIP compression
16.Install Office 2007 - Ultimate version, from DVD
17.Open 10 page Word doc - Text only
18.Open 100 page Word doc - Text and images only
19.Open simple Excel doc - Basic formatting
20.Open complex Excel doc - Including formula and charts
21.Burn DVD - Win 7 beta 1 .ISO to disc using CDBurnerXP
22.Open 10 page PDF - Text only, using latest Adobe Reader 8
23.Open 100 page PDF - Text and images, using latest Adobe Reader 8

These series of tests will pitch Windows 7 build 7000 32-bit against Windows Vista SP1 32-bit and Windows XP SP3 32-bit. The scoring for each of the tests is simple. (For PeterCH to understand) The winning OS scores 1, the runner up 2 and the loser scores a 3. The scores are added up and the OS with the lowest score at the end wins
The results

Here are the results of the tests for the two systems:

Conclusion

The bottom line is that the more I use Windows 7 the more I like it. Sure, we’re looking at a beta build here and not the final code, so things could change between now and release (although realistically final code ends up being faster than beta code). Also I still have some nagging issues relating to the interface, and some concerns that the UAC changes will break applications and other code, especially installers, but overall Windows 7 beta 1 is a robust, solid bit of code.

Sure, Windows 7 is not XP, and never will be (thankfully). And if you’re put off by things such as activation and DRM, then Windows isn’t the OS for you (good news is there are others to choose from). But if you’re looking for a solid OS then Windows 7 seems ready to deliver just that - a fast, reliable, relatively easy to use platform for your hardware and software.

That bit speaks directly to You Peter, For Pete's sake, God forbid you ever even do yourself the mental harm to ever buy or even steal Windows7.
I (If I were You) will then not be able to live with myself knowing and having to be reminded every day when I use the OS system how wrong, childish, stupid and ignorant I have been for fighting against my own better judgement and will. (That is If i had your attitude and drive to kick and fight against real facts, figures and other members "REAL LIFE" experiences as you do about Windows7 for the last period of time. (a year?)

Now go dig up some more incorrectly PeterCH interpreted Windows7 dirt to try and NOT convince us anything about Windows7. FFS.

 

[killadoob]

Peter are you blind?

Seriously man you only extract what suites your argument, look at those tests again and this time put your bottle cap glasses on so you can see.

 

[kilobits]

Staring at a glowing fruit logo all day makes one snowblind.... turn.. the... notebook... round... to... use... it... keyboard... must... be... beneath... fingers....

 

[MielieSpoor]

http://tech.slashdot.org/story/09/10/21/1234214/Windows-7-On-Multicore-mdash-How-Much-Faster

Well if that 17% benefit can be significant - if 1. it's under all circumstances not just heavy use in >2 core CPUs and 2. CPU power draw is a significant power draw - then Win 7 is beneficial because it allows laptops to crunch numbers longer while under battery draw and - it's better for the environment and the utilities' bill -it could be a reason to upgrade - the only one so far. However, it's not faster for multiple cores.

Damn just when I thought you are not coming back! Dude, get lost!! You are fighting a battle you have lost a long time ago! For everyone on this forum's sake just stop it now!

We all know that you are theeee biggest apple fanboy in the world so stop criticizing stuff you know nothing about!

 

[d0b33]

7 is lame, I won't be paying for it...

Performance

Windows 7 feels faster than Windows XP and Vista, but it turns out that's not always the case -- sometimes, it's the slowest of the three operating systems. We tested four 32-bit Windows operating systems: Windows 7 RTM build 7600, Windows 7 Release Candidate build 7100, Windows Vista with Service Pack 2 and Windows XP SP3, all on an Inspiron Desktop 530 mini-tower running an Intel Core 2 Duo Processor E4500 at 2.20GHz, with a 128MB Nvidia 8300 GS graphics card, 4GB of RAM and two 320GB SATA 7,200rpm hard drives.

http://crave.cnet.co.uk/software/0,39029471,49303203-7,00.htm

 

[I am Penguin]

7 is lame, I won't be paying for it...

http://crave.cnet.co.uk/software/0,39029471,49303203-7,00.htm

Sure, we all know why! Point is many others will. For every one negative review dug up we can find ten positive reviews. Early days yet we have of course to wait and see what brings. Nothing like real world experiences and the Internet.

My gut feeling is that in a few months this will all be but forgotten by a few stern die-hard's, used to pay nothing for their use of brilliant software as they would use it in the sly but bash it in the open.

 

[PeterCH]

Damn just when I thought you are not coming back! Dude, get lost!! You are fighting a battle you have lost a long time ago! For everyone on this forum's sake just stop it now!

We all know that you are theeee biggest apple fanboy in the world so stop criticizing stuff you know nothing about!

The article clearly states there is no increase in performance. That's their interpretation. Post what you want, but unless the article says what you want it to say and not that 'there's no difference' - ie the professionals (and not a group of IT lackeys) say so - well I'll agree.

Secondly this is for Nehalem CPUs - which will come with OEM Win7 anyway. For Core 2 Duo and prior it makes no performance increase to upgrade, and Win XP virtual machine takes a definite performance drop on Win 7.

Insult me all you want, but if you are not able to see this, I can't help you.

Refer to my earlier replies.

 

[PeterCH]

My gut feeling is that in a few months this will all be but forgotten by a few stern die-hard's, used to pay nothing for their use of brilliant software as they would use it in the sly but bash it in the open.

I'm sure the Win XP virtual machine will outperform Win XP native.

I have no issues, if it really performs well I can more than afford a dozen Retail copies. I just don't see a need.

 

[I am Penguin]

The article clearly states there is no increase in performance. That's their interpretation. Post what you want, but unless the article says what you want it to say and not that 'there's no difference' - ie the professionals (and not a group of IT lackeys) say so - well I'll agree.

Secondly this is for Nehalem CPUs - which will come with OEM Win7 anyway. For Core 2 Duo and prior it makes no performance increase to upgrade, and Win XP virtual machine takes a definite performance drop on Win 7.

Insult me all you want, but if you are not able to see this, I can't help you.

Refer to my earlier replies.

The article does at no point state as you see and say it and neither what the topic header say. Just quote those statements you read for all to see!

And thanks but no thanks we do not need help at all!

I see now you changed the topic/argument to WIN XP virtual machine?

Please!

 

[phiber]

Now even more interesting than PeterCH's post is these results:

Here are the results of the tests for the two systems:

http://i.zdnet.com/blogs/02-01-2009-12-34-11.png

http://i.zdnet.com/blogs/02-01-2009-12-35-16.png

Since my work won't support OS X, i really now hope they switch to Windows7 because XP is seriously lagging behind now