Database Users

Which is faster: [1000Mhz, 10Mflops] or [500Mhz, 20Mflops]? My thoughts.

I ask because different roms and kernels offer different benefits. Some allow you to overclock. Some allow you to get high Mflops running Linpack.
Mflops is a measure of how fast calculations are being performed (forgive my butchered definition). Mhz is how fast info is being processed. Which is king?
For example, I can underclock my processor to save battery life, but am using a ROM that generates high Mflops in Linpack. OR, I could overclock my processor for performance on a ROM that does not generate high Mflops.
Which would be faster?
My next question is: Do Mflops really matter? From Wikipedia:
"...a hand-held calculator must perform relatively few FLOPS. Each calculation request, such as to add or subtract two numbers, requires only a single operation, so there is rarely any need for its response time to exceed what the operator can physically use. A computer response time below 0.1 second in a calculation context is usually perceived as instantaneous by a human operator,[2] so a simple calculator needs only about 10 FLOPS to be considered functional."
Click to expand...
Click to collapse
If once a certain Mflop is reached the calculation seems "instantaneous," then who cares if they are higher than instantaneous? Will we ever really "perceive" the benefit of 50Mflops on our phones?
Anybody that can shed some light on this for me? It would be much appreciated!

For every-day use, you will notice a much larger impact with the higher clock speed.

TheBiles said:
For every-day use, you will notice a much larger impact with the higher clock speed.
Click to expand...
Click to collapse
What other use is there? Do you mean that processor speed is more important for speeding up the UI?

I would like to see an intelligent answer to this question with data or at least a solid theory to support it.

i may not be able to provide you with an engineers answer
but imma say... the one that sucks up less battery and provides fast calculations is the winner. so a 500mhz proc running higher flops would be my best decision
heck, i dunno.

That increase in mflops is from jit compiling java apps. The core os and browser are already native as are 3d games. They might speed up some from less java overhead.

MHz is not a measurement of "how fast info is processed", it is the clock speed of the processor. All it signifies is the rate at which the processor performs its operations. 1,000 MHz means the CPU has 1,000,000,000 cycles per second. Some operations will take one cycle to perform, other operations will take several cycles. Most software, unless it is exceptionally well written (in assembly language, which I don't believe can be executed on android) will require millions of CPU operations to perform whatever task it is trying to perform.
Increasing your clock speed while keeping all other things equal will increase all of your computing power and should give a useful gain in performance.
Linpack measures numeric floating point calculations. This is one of many types of tasks that a CPU must perform. Linpack is not an overall measurement of system performance, it's a measure of pure numeric (floating point) processing power. I have no idea how some roms manage to improve Linpack that dramatically, and you'd need to know that in order to truely answer your question. It seems likely to me that it's just a floating point optimization method that gives the higher scores, in this case floating point operations are the only things that would be improved.
The simple answer is that it depends what you want to do with your phone. If you do something with a lot of floating point calculation (3d games are an example, but they would typically use 3d hardware acceleration rather than cpu power, I'm not sure exactly how the snapdragon is designed so I'm not sure that they are not one and the same), you would get more performance out of the system with the higher linpack score. The higher clock speed on the other hand would provide you more overall benefit, it would make everything faster instead of just one area.

mhz doesn't necessarily mean speed. It's a easy, barely valid way to compare speeds to like model and generation processors only.
Platform independent benchmarks are much more important and reliable for judging speed. Therefore, a 500mhz processor that performs 20mflops is faster (at least in floating point operations) than a 1000mhz processor that performs 10 mflops.
Also realize, floating point operations per second are only one small part of a computer's performance. There's Specviewperf for Graphics performance, for instance, or general performance benchmarks like the whetstone or dhrystone.

Lets me see if I can shed some light:
In a basic processor you have 4 general tasks performed: Fetching, Decoding, Execution, and Writeback.
Processor clock rate (despite what people think) is not indicative of speed. It is an indicator of the number of wave cycles per second. Depending on the amount of work per cycle that a processor can do, then determines the "speed" of a processor. For instance an Intel 3ghz processor may be able to execute 100 integer calculations per cycle for a total of 300 billion calculations per second; but an AMD 3ghz processor could be able to do 200 integer calculations per second effectively making it the more efficient and "faster" processor.
A perfect example of this is the Hummingbird vs Snapdragon debate. Two processors at the same speed, yet Samsung claims the Hummingbird is faster due to the higher amount of work per cycle that can be executed.
The next step in the chain then comes when determining the types of calculations performed. An AMD processor may work better with a customized Linux based system that uses a higher level of floating point calculations, while an Intel processor may be better suited to a Windows system that uses a high level non-floating integers.
The next question is this: does your phone, a Linux based system use a high enough level Floating Point operations to make a difference in overall performance?
Google apparently does. However, Floating Point operations are simply a generic benchmark of a single facet of the operating system as a whole. Less wave cycles per second will decrease the overall potential of work, thereby decreasing performance in cases where the work needed to be executed exceeds the number of available waves.
Therefore, I would vote for the higher processor speeds, unless the only programs you execute use Floating Points.
Scientific enough?
Feel free to PM me with questions, or post here...
There are other factors that greatly affect processors as well, such as latency, BUS speed, and RAM available for buffering, but I didn't want to do an information overload.
~Jasecloud4

Sorry, I was assuming we were talking about the same processor (namely, the EVO's) clocked at two different speeds. It would make sense that the slower clock speed vielded more Mflops if it had JIT enabled, but I still think you would find the UI snappier with a higher-clocked ROM without JIT.

I notice a greater speed improvement from jit more than a faster processor speed. Especially with apps that have to load your whole system like autostarts. Battery life however, I'm still learning about. With Damage and being OC'd battery life was great. I'm currently on the latest CM nightly with jit and setcpu. We'll see how that compares.
Sent from my EVO using xda App

Quick off-topic question, then we'll get back on topic. Does the CyanogenMod build have the FPS broken?

TheBiles said:
Sorry, I was assuming we were talking about the same processor (namely, the EVO's) clocked at two different speeds. It would make sense that the slower clock speed vielded more Mflops if it had JIT enabled, but I still think you would find the UI snappier with a higher-clocked ROM without JIT.
Click to expand...
Click to collapse
lol you say that as if you dont actually know it...
deep inside we both know it though...
but seriously, both of biles' post on P1 sum up the question from the OP. Trust us

Tilde88 said:
lol you say that as if you dont actually know it...
deep inside we both know it though...
but seriously, both of biles' post on P1 sum up the question from the OP. Trust us
Click to expand...
Click to collapse
I'm a computer engineer, so I at least like to assume that I know what I'm talking about...

This thread is comparing Apples to Oranges. If the number of waves per second on a processor is increased, then the number of floating point calculations will increase, if every other factor remains the same.
It stands to reason that when two systems, one at 500MC/psec is pitted against another at 1000MC/psec with both systems running the same OS and JIT enabled, the one running at 1000MC/psec will have a higher number of floating points calculated.
~Jasecloud4

jasecloud4 said:
This thread is comparing Apples to Oranges. If the number of waves per second on a processor is increased, then the number of floating point calculations will increase, if every other factor remains the same.
It stands to reason that when two systems, one at 500MC/psec is pitted against another at 1000MC/psec with both systems running the same OS and JIT enabled, the one running at 1000MC/psec will have a higher number of floating points calculated.
~Jasecloud4
Click to expand...
Click to collapse
True, but I don't think we're talking about identical ROMS, since different ROMS have different abilities to OC and/or run JIT.

dglowe343 said:
I notice a greater speed improvement from jit more than a faster processor speed. Especially with apps that have to load your whole system like autostarts.
Click to expand...
Click to collapse
Running the nightly CM Froyo ROM right now and Autostarts is also the only app I have perceived to have a significant speed improvement from JIT. It really is the 2-5x faster that Google claimed JIT would be, but I've yet to see any other apps that benefit as much as Autostarts. Everything else seems the same as a non-JIT 2.1 ROM.
Haven't tried any games since getting the phone though, so can't give any feedback on those.
I think another poster in the CM Nightly rom thread compared his browser to his brothers 2.1 ROM phone, and the browsers were just about the same speed wise as well.
Given that feedback, I'd say for general usage a higher clock speed is better than lower clock speed and higher Mflops.

How has this thread gotten so long without the word "frequency" mentioned once? You guys are making this way too difficult. In 1 GHz, the Hz is the unit for frequency, which just means cycles per second. If you want a simple analogy, imagine a hamster running. His legs are moving up and down and forward at a certain frequency. You're running, too. Let's say that you are running at the same frequency. Who is getting somewhere quicker? Obviously you are because your legs are longer and stronger and you have a better power to weight ratio. Processors can behave the same way. Some simply get more done than others when operating at the same frequency for various reasons. This is why looking at only frequency is useless. Instead, we look at the work that it can do. Flops (floating point operations per second) is one measure of the work that a processor can do. There are many other ways to measure performance. This is just one of them.
Why do we want faster processors? It is partially so that we can be faster, but mostly so that we can do more. If you were to run the OS from phones 10 years ago on the hardware of today, most operations would be essentially instantaneous and with smart power saving features, you wouldn't need to charge it but once a week or less. But today's phones do far more. We need those higher speeds because even when you're sitting there looking at the home screen and "not doing anything", the OS is running dozens of services in the background to keep everything working correctly. Imagine if we were to take a modern engine and put it in an econo car from 30 years ago. It would go like hell and be incredibly efficient but it wouldn't have the safety, comfort, or features that we've come to expect with a modern automobile.

Sprockethead said:
Quick off-topic question, then we'll get back on topic. Does the CyanogenMod build have the FPS broken?
Click to expand...
Click to collapse
Yes. I avg 50-55 fps.
Sent from my EVO using xda App

jasecloud4 said:
This thread is comparing Apples to Oranges. If the number of waves per second on a processor is increased, then the number of floating point calculations will increase, if every other factor remains the same.
It stands to reason that when two systems, one at 500MC/psec is pitted against another at 1000MC/psec with both systems running the same OS and JIT enabled, the one running at 1000MC/psec will have a higher number of floating points calculated.
~Jasecloud4
Click to expand...
Click to collapse
um yea, but have you ever OC a video card for example?
lets take my old nVidia 8800gtx...
just because I overclock my core speeds doesnt mean that my memory bus will also be up'd, (of course the option is there but for the sake of the thread we'll ignore that)
Sure, now itll be able to process things much faster, but it cannot render as quickly as its ciphering, buffering, processing... etc...
like biles said, up the CPU for snappier user interfacing, up the flops for lets say, vb compiling ...
im not at my most sober points right now, so if you cant comprehend what im saying, think of the 'core' speed as the CPU, and the 'bus' speed as mFLOPS ...
and well gaming and rendering effects can see an improvement through JIT, but only if the said app or whatnot was built with JIT. otherwise it would be like upscaling a standard DVD to 720p. and seeing as how 3d rendering is after all native, how much more gfx tweaks do we need?

Dualcore processor processing

Hi,
I was wondering if the 2 CPU's are working simultaneously together? or I'st just 1?., I'm using FLEXREAPER X10 ICS 4.0.3 . Sometimes I get screen glitches .... when My tab is trying to sleep and I touched the screen. Also...when I try the benchmark it only say's the CPU1 processing speed... & etc. Also when I'm browsing in the Playstore the screen animation is a bit lag... Can some1 enlighten me...or is there an app for this? than can force 2 cpu to work all the time together.?

Yes, both cores are enabled at all times. But no, you cannot make an application use both cores unless the application was designed to do so.

FLEXREAPER X10 ICS 4.0.3 base a leak rom ICS, not a stable rom, so it has some problems.

Your benchmark is correct.
There are NOT 2 CPU's. There is only one CPU, with 2 cores. It doesn't process two applications at once, it CAN process two threads of the same application at the same time. Think of it as this: two CPUs would be two people writing on different pieces of paper.A single CPU with two cores would be one person writing with both hands at the same time. He can only write on the same piece of paper, but it's faster then it would be if he was writing with only one hand.
Note: this is not related to multi-task. Multi-tasking works based on processing a little bit of each app at a time, so altough it may seen that both are running at the same time, it is not.
Most apps are not designed to work with threads though, so there's your (actually, our) problem. But this is not an A500 problem, it applies to any multi-core processor based devices ou there (including desktops).

danc135 said:
There are NOT 2 CPU's. There is only one CPU, with 2 cores
Click to expand...
Click to collapse
Essentially true, but...
It doesn't process two applications at once
Click to expand...
Click to collapse
False. Two cores is just two CPUs on the same die.

Thanks for the response guys... I'm getting bit confused with this "multi-core processor".... I was expecting that it is fast to no lag, during browsing apps in my lib,switching application, even browsing in The PlAYSTORE". So It's correct to say that multi-core processor is a bit of a waste if an app can't use it's full/all cores potential? Also if the UI of an OS can't use all cores at the same time?

Dual Core, Dual CPU....
Not entirely, because if the kernel is capable of multi-threading, then it can use one core to run services while another is running the main application. The UI is only another application running on top of the kernel...
The only difference between a dual core Intel cpu and a dual core tegra 2 is the instruction set and basic capabilities, otherwise they can be thought of as essentially the same animal. The kernel, which is the core of the OS, handles the multi-tasking, but android has limited multi-tasking capabilities for Applications. Even so, services that run in the background are less of a hindrance on a dual core cpu than a single core one, and more and more applications are being written to take advantage of multiple cores.
Just have a bunch of widgets running on your UI, and you are looking at multi-tasking and multi-threading. Which are both better on multi-core processors.

A multiple core cpu are not more then one processor stacked on one die. They thread and load balance thru software.Applications MUST BE AWARE Of multi core cpus to take advantage of the dual cores.
A multiple Processor computer has a 3rd processor chip on the main board. this chip balances the load on hardware. this does not add over head on the processors. as on a Dual multi CORE CHIP. has a much higher load overhead.
SO Many people confuse the two. This is due to how the companies market the muticore cpu devices .
So a application that can not thread itself on a multi core chip will run in one of the cpu cores. a threaded app can well guess?
a dual Processor computer can run non multi thread aware app or program on two cores..
Its quite simply complicated..

You can throw all the hardware you want at a system. In the end, if the software sucks (not multi-threaded, poorly optimized, bad at resource management, etc...), it's still going to perform bad.
Dual core doesn't mean it can run one applicaton at twice speed, it means that it can run two applications at full speed, given that they're not threaded. Android's largely meant to run one application foregrounded, and since they can't magically make every application multi-threaded, you won't be seeing the benefits of multiple cores as much as you will on a more traditional platform.
Also, a dual-core tegra 2 is good, but only in comparison to other ARM processors (and even then, it's starting to show its age.) It's going to perform poorly compared to a full x86 computer, even one that's older.

netham45 said:
You can throw all the hardware you want at a system. In the end, if the software sucks (not multi-threaded, poorly optimized, bad at resource management, etc...), it's still going to perform bad.
Dual core doesn't mean it can run one applicaton at twice speed, it means that it can run two applications at full speed, given that they're not threaded. Android's largely meant to run one application foregrounded, and since they can't magically make every application multi-threaded, you won't be seeing the benefits of multiple cores as much as you will on a more traditional platform.
Also, a dual-core tegra 2 is good, but only in comparison to other ARM processors (and even then, it's starting to show its age.) It's going to perform poorly compared to a full x86 computer, even one that's older.
Click to expand...
Click to collapse
This is so true . With the exception of a TRUE Server dual OR Quad processor computer.. There is a special on board chip that will thread application calls to balance the load for non threaded programs and games..My first dual processor computer was a amd MP3000 back when dual cpu computers started to be within user price ranges. Most applications/programs did not multi thread .
And yes as far as computer speed and performance you will not gain any from this. but only will feel less lag when running several programs at once.a 2.8 ghz dual processor computer still runs at 2.8 not double that.

erica_renee said:
With the exception of a TRUE Server dual OR Quad processor computer.. There is a special on board chip that will thread application calls to balance the load for non threaded programs and games..
Click to expand...
Click to collapse
Actually this is incorrect. All such decisions are left to the OS's own scheduler, for multiple reasons: the CPU cannot know what kind of tasks it is to run, what should be given priority under which conditions and so on, like e.g. on a desktop PC interactive, user-oriented and in-focus applications and tasks are usually given more priority than background-tasks, whereas on a server one either gives all tasks similar priority or handles tasks priorities based on task-grouping. Not to mention realtime operating system which have entirely different requirements altogether.
If it was left to the CPU the performance gains would be terribly limited and could not be adjusted for different kinds of tasks and even operating systems.
(Not that anyone cares, I just thought to pop in and rant a little...)

Self correction
I said a multi-core processor only runs threads from the same process. That is wrong (thanks to my Computer Architecture professor for misleading me). It can run multiple threads from different processes, which would constitute true parallel processing. It's just better to stick with same process threads because of shared memory within the processor. Every core has its own cache memory (level 1 caches), and shared, on-die level 2 caches.
It all depends on the OS scheduler, really.
With ICS (and future Android versions), I hope the scheduler will improve to get the best of multi-core.
In the end though, it won't matter if applications aren't multi-thread (much harder to code). What I mean is, performance will be better, but not as better as it could be if developers used a lot of multi-threading.
To answer hatyrei's question, yes, it is a waste, in the sense that it has too much untapped potential.

AMD!

Hello!
This isn't relevant to hacking but I need to know about the AMD 8120 CPU, as if you guys are hacking windows 8 hopefully you'll be able to help me out here.
I'm building a new pc system but cannot seem to find anywhere on the internet if the 8120 has any sort of intergrated graphics?

Definitely not the right place to ask, but what the hell... the FX 8xxx series does not have any built-in graphics. There may be a low-end graphics chip built into the motherboard, however. Alternatively, AMD does have a line of CPU+GPU combined chips. They run a little underpowered as CPUs (even for AMD), being equivalent to Intel's i3 chips at best and usually not even that. However, they come with quite respectable middle-of-the-line GPUs, and for most games, that's what you need.
If you just need *some* sort of graphics and don't need it to be really gaming-quality, though, then you probably don't need one of those higher-end hybrids. I'd suggest that you look at the products on AMD.com, and do a search for motherboards with integrated graphics on your favorite product-comparison site (Newegg is my usual go-to, but I haven't bought much PC hardware in the last few years).

Adarzannh said:
Hello!
This isn't relevant to hacking but I need to know about the AMD 8120 CPU, as if you guys are hacking windows 8 hopefully you'll be able to help me out here.
I'm building a new pc system but cannot seem to find anywhere on the internet if the 8120 has any sort of intergrated graphics?
Click to expand...
Click to collapse
I am an owner of an FX-8120. I can tell you like the last guy did that it doesn't have integrated graphics. It's an 8-core chip clocked at 3.2Ghz stock. Now granted, it may not have an GPU processor on the chip, but you can customize graphic settings to allow the chip to process all of the video rendering. Usually this results in poor performance as GPU chips are alot more efficient when processing graphics. I have a 560gtx and the 8120 clocked at 3.8ghz. I use the GPU to render. Honestly though, you should get a 2500k or an 2600k. I've had nothing but headaches with my 8120. It sucks alot of power, it gets really hot and it locks up quite a bit.

Will it be possible to have 2 cpus ?

Will it be possible to have 2 cpus on the Ara.. It will be a beast if it could .. ( p.s. sorry if i have mistakes! )

51r said:
Will it be possible to have 2 cpus on the Ara.. It will be a beast if it could .. ( p.s. sorry if i have mistakes! )
Click to expand...
Click to collapse
I highly doubt it, I reckon the device would heat up so much and consume so much battery. Plus I think it will take a much longer time for two mobile cpu's to play nice with each other

I doubt it. It'd be cool if you could though but I still see no point as to why.

Yes, you could. The problem is that Android is not written to really use those two processors (its only recently getting support to use dual cores, much less quad) so it would just be a waste of energy and space.

good post
riahc3 said:
Yes, you could. The problem is that Android is not written to really use those two processors (its only recently getting support to use dual cores, much less quad) so it would just be a waste of energy and space.
Click to expand...
Click to collapse
I was going to suggest dual core. You beat me to it. Your post is good info; just like not jumping on a 64 bit bandwagon before devices have 8 or more GB of ram [not storage].

im sure it would be great to have two cpus but i feel like all that power would go to waste im sure it could bring more development but still what are you going to do with two cpu's at the current clock speeds we have now? the newest kindle fire is more powerful than my computer im sure quad cores are quite enough for phones cant believe they make octacores its a huge waste.

Dual processors in Project Ara devices.
Actually, from a functional standpoint, I see no reason to have dual CPUs. Android can't make use of a dual processor system, and if it could, what benefit would it provide in real time?
The system as it is, is too inefficient to handle the CPU commands, support the current demand of a dual CPU device.
With a dual CPU device, you also need to design additional power control regulation and filtering, additional battery support and ASIC devices to control the processor when demands are not being called upon, this adds a lot to the base architecture, and not really a financial benefit for a healthy profit margin. When you have finite board real estate for each individual module, you can't simply 'design-in' additional power control circuitry and maintain the same, or similar board dimensions, something has to give.
If we had everything we desired in a single device, I guarantess that device would be dimensionally unusable, the form factor would grow, costs would multiply, and with every feature added as 'standard', you would need to drag around a automotive-sized battery to operate all the options and features.
Personally, I prefer a robust Rf section, and then a modular antenna system that uses PIN diodes so I can select internal or external antennas if I desire. Next, I would like to have Bluetooth access to the entire phone system and file structure, so I can, in essence, 'clone' my phones parameters in a lab environment for testing applications and RF system compatibility.
The RF module should come standard with ALL known and used modulations, bands and coding, such as CDMA, GSM, WCDMA2000, TDMA, CQPSK and even 450 bands for Euro networks. Heck, I'd even like to see P25 thrown in for good measure, along with LTR and EDACS and OpenSky! ( I work with a LOT of RF radio networks, including trunked systems, so of course, I would love to have them all at my fingertips.
Off-Network communications is always a desire when you are in areas not served by cell sites, and point to point comms. is always useful.
Instead of sacrificing capabilities, how about increasing usefulness instead?

dual, quad, octa or more cpu cores are fit in one module i guess and yes android can't make use of dual cpu like servers.

2 cpus 1 phone
Sent from my Nexus 5 using Tapatalk

Maybe utilize a 4.0 GHz overclocked x64 cpu?

Since Google just helped develop a new CPU for Ara this may be possible now

I could see 2 cpus as like an either or situation. Heavy load. Use the one for performance. Screen off or battery saving mode. Use a decent single core thats geared towards battery life.

The thing about Project Ara is the aim seems to be to bring smartphones to the level of customization that we see in PCs. We could very well see some manufacturers who get on board with Ara eventually make SoCs that support dual processors if they feel there is a demand for it. Another interesting thought is if there comes about a project where we could design our own SoCs. Technically it's already possible if you are a hardware developer. I looked into what it would take to do it once, and from what I found it looks like you have to be a hardware developer, own your own company, and form a partnership with a chipset maker(I.E. Intel).

Current apps don't even use all 4 cores properly let alone adding a second cpu
Sent from my GT-N7100 using XDA Premium 4 mobile app

Perhaps software in the system settings could detect the second cpu and allow you to allocate more/less power to separate processes and assign different apps to different cpus.
Sent from my GT-S7560M using XDA Free mobile app

I think that 2 cores is possible. 2 CPU depends on whether android can run it
------------------------------------------------
Projectaratalk.com - a forum for google project ara users and developers

Since the Ara use Tegra x1 ,there's a great chance it has 2 cores.

Imagine how powerfull this phone will get in 1-2 years .. :thumbup::thumbup:
Sent from my GT-I8730 using XDA Free mobile app

CPU core assigning: modem, gpu, etc.

With the availability of rooting the SM-N900V along with flashing Custom ROMs and Kernels, has anyone attempted to assign specific hardware tasks to the CPU cores?
The Snapdragon processor uses asynchronous core processing to allow tasks to be ran on any or all cores, which is great for general use. However, with viewing how battery saving and performance modes control ramping, it is my viewpoint that having a core focus on a specific function, (ie computes for the modem or gpu) instead of anything and everything possible, would increase RAM efficiency as well as increasing stability. The cores, in theory, would ramp indepently of each other, instead of having a single core being maxed out before it triggers others to come online.
I know that Linux systems have the isolcpu command to assign processes this way, but as involved as Android is, as well as being a POSIX system, it may be ridiculous to try to assign each and every process this way. Perhaps even more so with user apps being added and removed frequently.
I would love to hear insight as to whether this idea has any benefit to implementing, as well as reasons why it might be worse than the methods currently in place.