Yea let's just completely overlook the fact that the iPad Pro stylus costs an additional $100+ after tax and the Smart Keyboard costs another $170+ and yet you're comparing the iPad Pro price by itself versus the Surface Book price which includes a keyboard and stylus FREE. Surface Pro 4 includes the stylus for free and the keyboard is only $130.
But no big deal right? Facts don't matter when you're a fanboy defending Apple. Also.... REAL benchmarks show that the Surface Book is THREE times faster than a Macbook Pro. That doesn't matter either of course....
"To get a Surface Pro 4 that has more CPU power than iPad Pro, you have to upgrade to the $1299 version powered by an Intel Core i5, which costs as much as Apple's 13 inch MacBook Pro."
No. You can get the $999 version, which is also powered by an Intel i5.
"However, the i5-powered Surface Pro 4 costs $500 more than an iPad Pro."
The $1299 model also comes with eight times the storage and twice the memory of the $799 iPad Pro. And includes the stylus, which is a $99 add-on for the iPad Pro.
If you compare the more similarly specced i5 / 4GB / 128GB model of the Surface Pro 4 instead, the iPad Pro is only $50 cheaper. Throw in the stylus and the iPad Pro is $50 more expensive. Add a keyboard to both and the iPad Pro is $90 more expensive.
Same reason why Windows is such a poor development platform..... install bash shell with all the utilities and all the unix utilities etc..... oh yeah.... right.... a few attempts to make it bearable but all utter failures.... It is why Windows is just not suitable....
The last quarter I could find estimates for the Surface Pro 3 was 1.3 million units..... a mere fraction of the iPad Air sales during the same quarter - which according to the mass media is a very poor sales number. It should be interesting to see if the very niche iPad Pro outsells 1.3 million in the first quarter supplies are not constrained.
1.3M Surface Pro 3s sold isn't bad compared to 4.8M macs sold Q3 2015. Sales and revenues slumped since then because the Surface 3 is old and Surface 4 due.
If MS can move 2M Surface Pro 4 and Surface Books combined that's pretty danged good. These things are priced at MBA/MBP levels...not iPad levels.
1.3M Surface Pro 3s sold isn't bad compared to 4.8M macs sold Q3 2015. Sales and revenues slumped since then because the Surface 3 is old and Surface 4 due.
If MS can move 2M Surface Pro 4 and Surface Books combined that's pretty danged good. These things are priced at MBA/MBP levels...not iPad levels.
Wait - I thought we're talking about the platform that finally merges the best of both worlds and will supplant them both as the future of computing. This is the compelling platform that does it all!
So that's 1.3M Surface books vs. 4.8M Macs PLUS ALL iPADS, ANDROID TABLETS, AND WINDOWS MACHINES SOLD.
Wait - I thought we're talking about the platform that finally merges the best of both worlds and will supplant them both as the future of computing. This is the compelling platform that does it all!
So that's 1.3M Surface books vs. 4.8M Macs PLUS ALL iPADS, ANDROID TABLETS, AND WINDOWS MACHINES SOLD.
Surface Pro and Surface Book compete directly with the MacBook, MacBook Air, and MacBook Pro. If they're able to rival the sales of those within 5 years of launching, that would make for an extremely successful business! That's not even considering indirect revenue impact.
At this time it's unclear what the iPad Pro is competing against. It seems there are three possible goals for it:
1) That perhaps some will decide to try it as a MacBook replacement instead of a Surface Pro.
2) That it will prevent some developers (particularly those targeting specific vertical/niche markets) from exploring the Surface Pro for pen-focused scenarios.
3) That it will spur an upgrade cycle of existing iPads, sales of which have been declining for a while.
It's possible some combination of all three will happen. Or that none will happen. I find #1 unlikely. Not because I think the Surface Pro is taking a lot of MacBook users, but because I don't think the iPad Pro is a suitable replacement for MacBooks (mainly the MBA) for most Mac buyers at this point. Maybe someday, but not today.
If someone purchases an iPad Pro who would have bought a MacBook (and not defected to a Surface or other PC), then it's probably a loss for Apple, and sales in that bucket would not be meeting Apple's goals. If it meets any of its goals in the market, though, then these cases may be considered "acceptable cannibalization."
1.3M Surface Pro 3s sold isn't bad compared to 4.8M macs sold Q3 2015. Sales and revenues slumped since then because the Surface 3 is old and Surface 4 due.
If MS can move 2M Surface Pro 4 and Surface Books combined that's pretty danged good. These things are priced at MBA/MBP levels...not iPad levels.
It also includes the Surface (not pro) 3 - it is not broken out.
Quote:
Originally Posted by BrandonLive
Surface Pro and Surface Book compete directly with the MacBook, MacBook Air, and MacBook Pro. If they're able to rival the sales of those within 5 years of launching, that would make for an extremely successful business! That's not even considering indirect revenue impact.
At this time it's unclear what the iPad Pro is competing against. It seems there are three possible goals for it:
1) That perhaps some will decide to try it as a MacBook replacement instead of a Surface Pro.
2) That it will prevent some developers (particularly those targeting specific vertical/niche markets) from exploring the Surface Pro for pen-focused scenarios.
3) That it will spur an upgrade cycle of existing iPads, sales of which have been declining for a while.
It's possible some combination of all three will happen. Or that none will happen.
If someone purchases an iPad Pro who would have bought a MacBook (and not defected to a Surface or other PC), then it's probably a loss for Apple, and sales in that bucket would not be meeting Apple's goals. If it meets any of its goals in the market, though, then these cases may be considered "acceptable cannibalization."
When you talk about the surface line it is not broken out.... so it would be a mix of Surface and Surface Pro in those numbers -- the only thing we have is the gross revenue and then we have to make assumptions how much is the surface, surface pro and now surface book, how much is accessories (keyboard and pen etc.).
Right now I don't see the iPad Pro cannibalizing the Macbook... different use case and the excitement seems to be coming from people that are looking for something different. The iPad itself "cannibalized" the market - but mostly PCs.... and the Mac sales went up while PC sales dropped (generally speaking).
When you talk about the surface line it is not broken out.... so it would be a mix of Surface and Surface Pro in those numbers -- the only thing we have is the gross revenue and then we have to make assumptions how much is the surface, surface pro and now surface book, how much is accessories (keyboard and pen etc.).
I don't think the MacBook numbers are broken out either. However, the reports I've seen show the Pro to the majority of Surface revenue thus far. The regular Surface 3 is not really position against anything in Apple's line-up, though. Perhaps the iPad Air, but really it's more positioned as a competitor for $500 small laptops.
Quote:
Right now I don't see the iPad Pro cannibalizing the Macbook... different use case and the excitement seems to be coming from people that are looking for something different. The iPad itself "cannibalized" the market - but mostly PCs.... and the Mac sales went up while PC sales dropped (generally speaking).
That's not what the word "cannibalized" means. If you take market from competitors, that is not cannibalization. That word refers to have one product take away sales from another of the same vendor's products. Apple expects the iPad Pro to cannibalize some MacBook sales, they've said as much. Tim Cook has also said that there's been some iPad cannibalization of Mac sales in the past, but that he doesn't consider it to be a problem. As I said, so long as the product succeeds enough in its own goals, some amount of that is acceptable.
I haven't seen evidence that the iPad has had any significant impact on PCs. It's at best a small factor in the "mobile" trend which is dominated by smartphones. Indeed, the iPad seems to have been affected by the same problem affecting PCs - a lack of desire/incentive for the sort of upgrade cycles seen in the past for PC and in the present for phones.
However, the PC market is still far larger than the iPad market (or the tablet market in general), and showing signs of stabilization while iPad sales decrease at a much faster rate. There are also problems with how the tablet market has been defined in recent years. Mini tablets and something like the iPad Pro are hardly worth grouping together. It's surely harder to compare markets when they're ill-defined. In some cases the mini tablets fill the same role as smartphones for certain buyers. Whereas the larger ones sometimes fill the role of a PC/laptop. In the future it may make more sense to start lumping mini tablets in with phones, and large tablets in with laptops. The mid-size tablets (like the Air and Surface 3) have been the worst performing in the market, so it will be interesting to see what the future holds for them.
Erm, wot? The Surface Pro line has a full active digitizer, just like the iPad Pro has. If you look at the iFixit teardown, there is dedicated silicon supporting the stylu. Microsoft even bought the technology from the original manufacturer (N-Trig).
If you look at direct comparisons, there seems to be little consensus on which input device is better, but agreement that they are in the same class. Both devices sport an excellent display. Palm rejection on both are broadly praised as excellent. There is some negligible difference in input lag, possibly in Apple's favor, but it is unclear whether the difference is hardware or software. Some have reported that pressure sensitivity works a bit better in the Pencil, but on the flip side a lot of users enjoy the eraser and interchangeable tips on the Pen.
In the end, it's likely just a matter of taste (and availability for your platform of choice of course).
"...despite the iPad Pro having an extra million and a half more pixels to manage on the screen."
A little math challenged aren't you? I'd like to know how you concluded that the iPad Pros 2732x2048 screen has 1.5 million more pixels than the Surface Pro 4's 2736x1824 screen. That will definitely be interesting.
As for the Surface Pro 4 being more expensive that the iPad Pro, the cheapest iPad is only cheaper because it's a stripped model with a come-on price. The basic iPad Pro only has 32 GB of storage for $799. To get the iPad with a more respectable 128 GB costs $949. To quote your 11/13/15 article:
"...we believe most users will probably want to opt for the 128-gig model, as 32 gigabytes could fill up rather quickly with apps, videos and other content..."
You can't even increase the storage on the iPad Pro, so when so fill up your meger 32 GB, you're SOL. The minimum storage on the Surface is 128 GB.
The $899 Surface includes 128 GB of storage and the Surface pen, so its actually more affordable than the iPad Pro. The Surface that is over 20% faster on geekbench than the iPad Pro is only $999 with 128 GB of storage. When you consider that it also includes the Surface pen, its also more "affordable" than the iPad.
Wait - I thought we're talking about the platform that finally merges the best of both worlds and will supplant them both as the future of computing. This is the compelling platform that does it all!
So that's 1.3M Surface books vs. 4.8M Macs PLUS ALL iPADS, ANDROID TABLETS, AND WINDOWS MACHINES SOLD.
Not at $700 for the base model which hopefully no one buys because it's rather anemic.
I do believe that Geekbench markets itself as a CPU benchmarking application so they are likely also doing benchmarking of the operating system and compilers in relation and then factoring out the OS and compiler bias
Why? Why would you factor out compiler "bias" if that compiler performance ultimately is what produces good (or bad) results by giving you better performance through better generated binary?
I believe you are wrong. GB doesn't market itself as such. They simply say that you can compare results from various platforms because they represent the same workload.
But if your operating system is very bad at scheduling task and as a result, performance of your app is bad, factoring that OS out makes NO SENSE whatsoever!
Why? Why would you factor out compiler "bias" if it is ultimately that produces good (or bad) results by giving you better performance!
Factoring out iOS or compiler doesn't make any sense if you wanna have a realistic benchmark!
you factor it out because the test is suppose to measure the relative CPU performance - not the ecosystem, not the operating system, not the compiler .... just the CPU. The other problem is that if the compiler optimizes a loop that does nothing - it could analyze that the code is not used for anything and remove it.... basically removing what was doing the benchmarking. I understand they are trying to benchmark the CPU in isolation of everything... but I could have misunderstood so take it with a grain of salt.
It really comes down to what the benchmark is trying to measure.
you factor it out because the test is suppose to measure the relative CPU performance - not the ecosystem, not the operating system, not the compiler .... just the CPU. The other problem is that if the compiler optimizes a loop that does nothing - it could analyze that the code is not used for anything and remove it.... basically removing what was doing the benchmarking. I understand they are trying to benchmark the CPU in isolation of everything... but I could have misunderstood so take it with a grain of salt.
It really comes down to what the benchmark is trying to measure.
"you factor it out because the test is suppose to measure the relative CPU performance - not the ecosystem"
You do realize that CPU without OS can't do anything, right?
Hence, it makes ZERO sense to "factor out" OS scheduler, for example.
p.s. I think you have a very vague understanding (understatement) of how OS works and what it actually does.
"you factor it out because the test is suppose to measure the relative CPU performance - not the ecosystem"
You do realize that CPU without OS can't do anything, right?
Hence, it makes ZERO sense to "factor out" OS scheduler, for example.
p.s. I think you have a very vague understanding (understatement) of how OS works and what it actually does.
Actually a CPU can do things without an operating system.... I have written bootstrap loaders and executable code using assembly language before..... but that was back really early on ....
It makes perfect sense if your benchmark is trying to give you a CPU score relative to other CPUs.
Also, if you have a problem of benchmarking something in isolation, then you should also have problems with the benchmark for not adding a certain mix of graphical usage etc -- because most people would not use just the scheduler etc.
Actually a CPU can do things without an operating system.... I have written bootstrap loaders and executable code using assembly language before..... but that was back really early on ....
That is irrelevant since OS utilizes scheduler that affects performance and bootstrap - doesn't. And ALL of todays consumer grade OSs do have multitasking - hence they all rely on a task scheduler.
And when you run your app, that OS scheduler SCHEDULES your app to be run on a certain core(cores) in a specific order/time.
Factoring out that part of performance will give you unrealistic performance that you will never be able to achieve in a real world OS + app use.
Quote:
It makes perfect sense if your benchmark is trying to give you a CPU score relative to other CPUs.
Yes, please explains to me this. I have Blender3D rendering a scene on Win7 and Ubuntu 14. Hardware was the same in both cases.
Ubuntu based Blender took 25% less time to render a scene, comparing to Win7 case.
If I follow your method of eliminating OS from the equation, I will be left with some hypothetical and absolutely useless benchmark that will not represent a real-world scenario..
Since Geekbench is a processor benchmark and not a system benchmark, we wanted Geekbench scores to be similar across operating systems when run on identical hardware. There will always be some variation between operating systems, but our goal was to understand the sources of the variation and minimize those sources when possible. The build servers were a convenient place to test this, so I added a step to the Pulse builds that runs Geekbench on each server and exports the results to JSON using the --saveoption of the Geekbench command line tool.
Comments
Yea let's just completely overlook the fact that the iPad Pro stylus costs an additional $100+ after tax and the Smart Keyboard costs another $170+ and yet you're comparing the iPad Pro price by itself versus the Surface Book price which includes a keyboard and stylus FREE. Surface Pro 4 includes the stylus for free and the keyboard is only $130.
But no big deal right? Facts don't matter when you're a fanboy defending Apple. Also.... REAL benchmarks show that the Surface Book is THREE times faster than a Macbook Pro. That doesn't matter either of course....
No. You can get the $999 version, which is also powered by an Intel i5.
"However, the i5-powered Surface Pro 4 costs $500 more than an iPad Pro."
The $1299 model also comes with eight times the storage and twice the memory of the $799 iPad Pro. And includes the stylus, which is a $99 add-on for the iPad Pro.
If you compare the more similarly specced i5 / 4GB / 128GB model of the Surface Pro 4 instead, the iPad Pro is only $50 cheaper. Throw in the stylus and the iPad Pro is $50 more expensive. Add a keyboard to both and the iPad Pro is $90 more expensive.
Same reason why Windows is such a poor development platform..... install bash shell with all the utilities and all the unix utilities etc..... oh yeah.... right.... a few attempts to make it bearable but all utter failures.... It is why Windows is just not suitable....
Cygwin says hello.
Cygwin says hello.
Cygwin is a hack and a piece of crap. Not really a great environment. (Yes, I have had previous experience with it).
Cygwin is a hack and a piece of crap. Not really a great environment. (Yes, I have had previous experience with it).
I disagree. I've been using it for years to port Unix scripts to windows environments.
The last quarter I could find estimates for the Surface Pro 3 was 1.3 million units..... a mere fraction of the iPad Air sales during the same quarter - which according to the mass media is a very poor sales number. It should be interesting to see if the very niche iPad Pro outsells 1.3 million in the first quarter supplies are not constrained.
1.3M Surface Pro 3s sold isn't bad compared to 4.8M macs sold Q3 2015. Sales and revenues slumped since then because the Surface 3 is old and Surface 4 due.
If MS can move 2M Surface Pro 4 and Surface Books combined that's pretty danged good. These things are priced at MBA/MBP levels...not iPad levels.
Wait - I thought we're talking about the platform that finally merges the best of both worlds and will supplant them both as the future of computing. This is the compelling platform that does it all!
So that's 1.3M Surface books vs. 4.8M Macs PLUS ALL iPADS, ANDROID TABLETS, AND WINDOWS MACHINES SOLD.
Wait - I thought we're talking about the platform that finally merges the best of both worlds and will supplant them both as the future of computing. This is the compelling platform that does it all!
So that's 1.3M Surface books vs. 4.8M Macs PLUS ALL iPADS, ANDROID TABLETS, AND WINDOWS MACHINES SOLD.
Surface Pro and Surface Book compete directly with the MacBook, MacBook Air, and MacBook Pro. If they're able to rival the sales of those within 5 years of launching, that would make for an extremely successful business! That's not even considering indirect revenue impact.
At this time it's unclear what the iPad Pro is competing against. It seems there are three possible goals for it:
1) That perhaps some will decide to try it as a MacBook replacement instead of a Surface Pro.
2) That it will prevent some developers (particularly those targeting specific vertical/niche markets) from exploring the Surface Pro for pen-focused scenarios.
3) That it will spur an upgrade cycle of existing iPads, sales of which have been declining for a while.
It's possible some combination of all three will happen. Or that none will happen. I find #1 unlikely. Not because I think the Surface Pro is taking a lot of MacBook users, but because I don't think the iPad Pro is a suitable replacement for MacBooks (mainly the MBA) for most Mac buyers at this point. Maybe someday, but not today.
If someone purchases an iPad Pro who would have bought a MacBook (and not defected to a Surface or other PC), then it's probably a loss for Apple, and sales in that bucket would not be meeting Apple's goals. If it meets any of its goals in the market, though, then these cases may be considered "acceptable cannibalization."
1.3M Surface Pro 3s sold isn't bad compared to 4.8M macs sold Q3 2015. Sales and revenues slumped since then because the Surface 3 is old and Surface 4 due.
If MS can move 2M Surface Pro 4 and Surface Books combined that's pretty danged good. These things are priced at MBA/MBP levels...not iPad levels.
It also includes the Surface (not pro) 3 - it is not broken out.
Surface Pro and Surface Book compete directly with the MacBook, MacBook Air, and MacBook Pro. If they're able to rival the sales of those within 5 years of launching, that would make for an extremely successful business! That's not even considering indirect revenue impact.
At this time it's unclear what the iPad Pro is competing against. It seems there are three possible goals for it:
1) That perhaps some will decide to try it as a MacBook replacement instead of a Surface Pro.
2) That it will prevent some developers (particularly those targeting specific vertical/niche markets) from exploring the Surface Pro for pen-focused scenarios.
3) That it will spur an upgrade cycle of existing iPads, sales of which have been declining for a while.
It's possible some combination of all three will happen. Or that none will happen.
If someone purchases an iPad Pro who would have bought a MacBook (and not defected to a Surface or other PC), then it's probably a loss for Apple, and sales in that bucket would not be meeting Apple's goals. If it meets any of its goals in the market, though, then these cases may be considered "acceptable cannibalization."
When you talk about the surface line it is not broken out.... so it would be a mix of Surface and Surface Pro in those numbers -- the only thing we have is the gross revenue and then we have to make assumptions how much is the surface, surface pro and now surface book, how much is accessories (keyboard and pen etc.).
Right now I don't see the iPad Pro cannibalizing the Macbook... different use case and the excitement seems to be coming from people that are looking for something different. The iPad itself "cannibalized" the market - but mostly PCs.... and the Mac sales went up while PC sales dropped (generally speaking).
Originally Posted by bkkcanuck
When you talk about the surface line it is not broken out.... so it would be a mix of Surface and Surface Pro in those numbers -- the only thing we have is the gross revenue and then we have to make assumptions how much is the surface, surface pro and now surface book, how much is accessories (keyboard and pen etc.).
I don't think the MacBook numbers are broken out either. However, the reports I've seen show the Pro to the majority of Surface revenue thus far. The regular Surface 3 is not really position against anything in Apple's line-up, though. Perhaps the iPad Air, but really it's more positioned as a competitor for $500 small laptops.
That's not what the word "cannibalized" means. If you take market from competitors, that is not cannibalization. That word refers to have one product take away sales from another of the same vendor's products. Apple expects the iPad Pro to cannibalize some MacBook sales, they've said as much. Tim Cook has also said that there's been some iPad cannibalization of Mac sales in the past, but that he doesn't consider it to be a problem. As I said, so long as the product succeeds enough in its own goals, some amount of that is acceptable.
I haven't seen evidence that the iPad has had any significant impact on PCs. It's at best a small factor in the "mobile" trend which is dominated by smartphones. Indeed, the iPad seems to have been affected by the same problem affecting PCs - a lack of desire/incentive for the sort of upgrade cycles seen in the past for PC and in the present for phones.
However, the PC market is still far larger than the iPad market (or the tablet market in general), and showing signs of stabilization while iPad sales decrease at a much faster rate. There are also problems with how the tablet market has been defined in recent years. Mini tablets and something like the iPad Pro are hardly worth grouping together. It's surely harder to compare markets when they're ill-defined. In some cases the mini tablets fill the same role as smartphones for certain buyers. Whereas the larger ones sometimes fill the role of a PC/laptop. In the future it may make more sense to start lumping mini tablets in with phones, and large tablets in with laptops. The mid-size tablets (like the Air and Surface 3) have been the worst performing in the market, so it will be interesting to see what the future holds for them.
Erm, wot? The Surface Pro line has a full active digitizer, just like the iPad Pro has. If you look at the iFixit teardown, there is dedicated silicon supporting the stylu. Microsoft even bought the technology from the original manufacturer (N-Trig).
If you look at direct comparisons, there seems to be little consensus on which input device is better, but agreement that they are in the same class. Both devices sport an excellent display. Palm rejection on both are broadly praised as excellent. There is some negligible difference in input lag, possibly in Apple's favor, but it is unclear whether the difference is hardware or software. Some have reported that pressure sensitivity works a bit better in the Pencil, but on the flip side a lot of users enjoy the eraser and interchangeable tips on the Pen.
In the end, it's likely just a matter of taste (and availability for your platform of choice of course).
A little math challenged aren't you? I'd like to know how you concluded that the iPad Pros 2732x2048 screen has 1.5 million more pixels than the Surface Pro 4's 2736x1824 screen. That will definitely be interesting.
As for the Surface Pro 4 being more expensive that the iPad Pro, the cheapest iPad is only cheaper because it's a stripped model with a come-on price. The basic iPad Pro only has 32 GB of storage for $799. To get the iPad with a more respectable 128 GB costs $949. To quote your 11/13/15 article:
"...we believe most users will probably want to opt for the 128-gig model, as 32 gigabytes could fill up rather quickly with apps, videos and other content..."
You can't even increase the storage on the iPad Pro, so when so fill up your meger 32 GB, you're SOL. The minimum storage on the Surface is 128 GB.
The $899 Surface includes 128 GB of storage and the Surface pen, so its actually more affordable than the iPad Pro. The Surface that is over 20% faster on geekbench than the iPad Pro is only $999 with 128 GB of storage. When you consider that it also includes the Surface pen, its also more "affordable" than the iPad.
Wait - I thought we're talking about the platform that finally merges the best of both worlds and will supplant them both as the future of computing. This is the compelling platform that does it all!
So that's 1.3M Surface books vs. 4.8M Macs PLUS ALL iPADS, ANDROID TABLETS, AND WINDOWS MACHINES SOLD.
Not at $700 for the base model which hopefully no one buys because it's rather anemic.
It also includes the Surface (not pro) 3 - it is not broken out.
I was under the impression that everyone thinks those didn't sell well at all.
I do believe that Geekbench markets itself as a CPU benchmarking application so they are likely also doing benchmarking of the operating system and compilers in relation and then factoring out the OS and compiler bias
Why? Why would you factor out compiler "bias" if that compiler performance ultimately is what produces good (or bad) results by giving you better performance through better generated binary?
I believe you are wrong. GB doesn't market itself as such. They simply say that you can compare results from various platforms because they represent the same workload.
But if your operating system is very bad at scheduling task and as a result, performance of your app is bad, factoring that OS out makes NO SENSE whatsoever!
Why? Why would you factor out compiler "bias" if it is ultimately that produces good (or bad) results by giving you better performance!
Factoring out iOS or compiler doesn't make any sense if you wanna have a realistic benchmark!
you factor it out because the test is suppose to measure the relative CPU performance - not the ecosystem, not the operating system, not the compiler .... just the CPU. The other problem is that if the compiler optimizes a loop that does nothing - it could analyze that the code is not used for anything and remove it.... basically removing what was doing the benchmarking. I understand they are trying to benchmark the CPU in isolation of everything... but I could have misunderstood so take it with a grain of salt.
It really comes down to what the benchmark is trying to measure.
you factor it out because the test is suppose to measure the relative CPU performance - not the ecosystem, not the operating system, not the compiler .... just the CPU. The other problem is that if the compiler optimizes a loop that does nothing - it could analyze that the code is not used for anything and remove it.... basically removing what was doing the benchmarking. I understand they are trying to benchmark the CPU in isolation of everything... but I could have misunderstood so take it with a grain of salt.
It really comes down to what the benchmark is trying to measure.
"you factor it out because the test is suppose to measure the relative CPU performance - not the ecosystem"
You do realize that CPU without OS can't do anything, right?
Hence, it makes ZERO sense to "factor out" OS scheduler, for example.
p.s. I think you have a very vague understanding (understatement) of how OS works and what it actually does.
"you factor it out because the test is suppose to measure the relative CPU performance - not the ecosystem"
You do realize that CPU without OS can't do anything, right?
Hence, it makes ZERO sense to "factor out" OS scheduler, for example.
p.s. I think you have a very vague understanding (understatement) of how OS works and what it actually does.
Actually a CPU can do things without an operating system.... I have written bootstrap loaders and executable code using assembly language before..... but that was back really early on ....
It makes perfect sense if your benchmark is trying to give you a CPU score relative to other CPUs.
Also, if you have a problem of benchmarking something in isolation, then you should also have problems with the benchmark for not adding a certain mix of graphical usage etc -- because most people would not use just the scheduler etc.
Actually a CPU can do things without an operating system.... I have written bootstrap loaders and executable code using assembly language before..... but that was back really early on ....
That is irrelevant since OS utilizes scheduler that affects performance and bootstrap - doesn't. And ALL of todays consumer grade OSs do have multitasking - hence they all rely on a task scheduler.
And when you run your app, that OS scheduler SCHEDULES your app to be run on a certain core(cores) in a specific order/time.
Factoring out that part of performance will give you unrealistic performance that you will never be able to achieve in a real world OS + app use.
Yes, please explains to me this. I have Blender3D rendering a scene on Win7 and Ubuntu 14. Hardware was the same in both cases.
Ubuntu based Blender took 25% less time to render a scene, comparing to Win7 case.
If I follow your method of eliminating OS from the equation, I will be left with some hypothetical and absolutely useless benchmark that will not represent a real-world scenario..
So, what is the point of such benchmark then?
http://www.primatelabs.com/blog/2013/12/developing-a-cross-platform-benchmark/