What's the difference between mobile and desktop processors?

Question

I just read about the new Samsung Galaxy Note Edge having a 2.7 GHz quad-core processor and 3GB of RAM.

The laptop I bought last year by HP is 4 GB of RAM and 2.3 GHz quad-core and my iMac is even older and is 2.5 GHz i5.

Does this mean that the new Samsung gadget is more powerful than my desktop?

Is the 2.7 GHz the same kind of GHz as non-mobile devices (is it scaled up, or compared, etc.)?

Why, in terms of power, do modern computers not have two of those Samsung quad-core processors running in parallel pushing out 5.4 GHz processing power for the amount of electrical energy as two Galaxy Note batteries?

Answer 1

---

Note: This answer is written with the assumption that the CPUs being compared consist of commercially-available Intel, AMD, and ARM-based SoCs from approximately 2006 to 2015. Any set of comparison measurements will be invalid given a wide enough scope; I wanted to provide a very specific and "tangible" answer here while also covering the two most widely used types of processor, so I made a bunch of assumptions that may not be valid in the absolutely general case of CPU design. If you have nitpicks, please keep this in mind before you share them. Thanks!

---

Let's get one thing straight: MHz / GHz and number of cores are no longer a reliable indicator of the relative performance of any two arbitrary processors.

They were dubious numbers at best even in the past, but now that we have mobile devices, they are absolutely terrible indicators. I'll explain where they can be used later in my answer, but for now, let's talk about other factors.

Today, the best numbers to consider when comparing processors are Thermal Design Power (TDP), and Feature Fabrication Size, aka "fab size" (in nanometers -- nm).

Basically: as the Thermal Design Power increases, the "scale" of the CPU increases. Think of the "scale" between a bicycle, a car, a truck, a train, and a C-17 cargo airplane. Higher TDP means larger scale. The MHz may or may not be higher, but other factors like the complexity of the microarchitecture, the number of cores, the branch predictor's performance, the amount of cache, the number of execution pipelines, etc. all tend to be higher on larger-scale processors.

Now, as the fab size decreases, the "efficiency" of the CPU increases. So, if we assume two processors which are designed exactly the same except that one of them is scaled down to 14nm while the other is at 28nm, the 14nm processor will be able to:

• Perform at least as fast as the higher fab size CPU;
• Do so using less power;
• Do so while dissipating less heat;
• Do so using a smaller volume in terms of the physical size of the chip.

Generally, when companies like Intel and the ARM-based chip manufacturers (Samsung, Qualcomm, etc) decrease fab size, they also tend to ramp up the performance a bit. This puts a hamper on exactly how much power efficiency they can gain, but everyone likes their stuff to run faster, so they design their chips in a "balanced" way, so that you get some power efficiency gains, and some performance gains. On the other extremes, they could keep the processor exactly as power-hungry as the previous generation, but ramp up the performance a lot; or, they could keep the processor exactly at the same speed as the previous generation, but reduce the power consumption by a lot.

The main point to consider is that the current generation of tablet and smartphone CPUs has a TDP around 2 to 4 Watts and a fab size of 28 nm. A low-end desktop processor from 2012 has a TDP of at least 45 Watts and a fab size of 22 nm. Even if the tablet's System On Chip (SoC) were connected to an A/C mains power source so it doesn't have to worry about power sipping (to save battery), a quad-core tablet SoC would completely lose every single CPU benchmark to a 2012 low-end "Core i3", dual-core processor running at perhaps lower GHz.

The reasons:

• The Core i3/i5/i7 chips are MUCH larger (in terms of number of transistors, physical die area, power consumption, etc.) than a tablet chip;
• Chips that go into desktops care MUCH less about power savings. Software, hardware and firmware combine to severely cut down to performance on mobile SoCs in order to give you long battery life. On desktops, these features are only implemented when they do not significantly impact the top-end performance, and when top-end performance is requested by an application, it can be given consistently. On a mobile processor, they often implement many little "tricks" to drop frames here and there, etc. (in games, for example) which are mostly imperceptible to the eye but save battery life.

One neat analogy I just thought of: you could think of a processor's "MHz" like the "RPMs" meter on a vehicle's internal combustion engine. If I rev up my motorcycle's engine to 6000 RPM, does that mean it can pull more load than a train's 16-cylinder prime mover at 1000 RPM? No, of course not. A prime mover has around 2000 to 4000 horsepower (example here), while a motorcycle engine has around 100 to 200 horsepower (example here of the highest horsepower motorcycle engine ever just topping 200 hp).

TDP is closer to horsepower than MHz, but not exactly.

A counterexample is when comparing something like a 2014-model "Haswell" (4th Generation) Intel Core i5 processor to something like a high-end AMD processor. These two CPUs will be close in performance, but the Intel processor will use 50% less energy! Indeed, a 55 Watt Core i5 can often outperform a 105 Watt AMD "Piledriver" CPU. The primary reason here is that Intel has a much more advanced microarchitecture that has pulled away from AMD in performance since the "Core" brand started. Intel has also been advancing their fab size much faster than AMD, leaving AMD in the dust.

Desktop/laptop processors are somewhat similar in terms of performance, until you get down to tiny Intel tablets, which have similar performance to ARM mobile SoCs due to power constraints. But as long as desktop and "full scale" laptop processors continue to innovate year over year, which it seems likely they will, tablet processors will not overtake them.

I'll conclude by saying that MHz and # of Cores are not completely useless metrics. You can use these metrics when you are comparing CPUs which:

• Are in the same market segment (smartphone/tablet/laptop/desktop);
• Are in the same CPU generation (i.e. the numbers are only meaningful if the CPUs are based on the same architecture, which usually means they'd be released around the same time);
• Have the same fab size and similar or identical TDP;
• When comparing all of their specs, they differ primarily or solely in the MHz (clock speed) or number of cores.

If these statements are true of any two CPUs -- for instance, the Intel Xeon E3-1270v3 vs. the Intel Xeon E3-1275v3 -- then comparing them simply by MHz and/or # of Cores can provide you a clue of the difference in performance, but the difference will be much smaller than you expect on most workloads.

Here's a little chart I did up in Excel to demonstrate the relative importance of some of the common CPU specs (note: "MHz" actually refers to "clock speed", but I was in a hurry; "ISA" refers to "Instruction Set Architecture", i.e. the actual design of the CPU)

Note: These numbers are approximate/ballpark figures based on my experience, not any scientific research.

Answer 2

Hm.. This is a good question.

The answer is NO, Samsung Galaxy is most likely not as powerful as your Desktop PC. And this would be obvious if you would run a comprehensive CPU benchmark test.

I will try to put together the answer the way I see it. Other, more experienced members will probably add more details and value later.

First of all, due to the difference in CPU architecture, mobile device processors and desktop PC processor support different instruction sets. As you have probably guessed, the instruction set is larger for PCs.

Another thing is false advertising. The speed advertised for PC CPU is often achieved and, CPU can run at that speed for long periods of time. This is possible because of excessive power supply from the mains, and decent cooling system that allows to remove the heat from the core. This is not the case for mobile devices. Advertised speed is maximal possible speed but it is much higher than the average speed. Mobile devices will often slow down their CPU, because of overheating and to save battery.

And the last but not the least is the availability of additional components like main memory (RAM), cache memory, etc. The amount of RAM is not the only criteria. There is also RAM clock speed that defines how quickly can data be stored and retrieved in/from RAM. These parameters also vary between mobile devices and PCs.

You could come up with more differences but the root cause is power consumption and size requirements. PCs can afford to draw more power from the mains and can also afford to be bigger, so they will always deliver higher processing power.

For additional reading I recommend: Processors: Computer vs Mobile

Answer 3

Actually MHz rating has little relevance between different manufacturers processors. It only has some relevance to CPU's in exactly the same family. While phone processors are becoming pretty fast and might well beat the pants off those old Pentium 4's, you still cant compare them to even a low end core i3.

You should be aware that there are quite a number of factors that influence overall performance and not just from the CPU. For example,

• CPU clock speed
• Number of processor cores
• Number of instructions per cycle
• Branch prediction
• Instruction set
• Instruction width
• Bus width
• Memory Speed
• Cache size
• Cache design
• Silicon layout
• Software optimisation
• etc

So the clock speed or MHz rating is just one part of a number of different things that you can use to gauge performance. An AMD processor is rather a different kettle of fish than one from Intel or ARM. It's long been known that an AMD CPU at 3GHz and the same core count does not perform as well as an Intel CPU with the same core count and similar spec and GHz rating.

And you'll also note that memory speed affects performance too as well as cache. Noting that server processors have large L1 caches compared to desktop counterparts and those you'll find in your phone. So they spend less time waiting for data than what a phone CPU might.

The reason I've added instruction set and software optimisation is that some software can algorithms run better one one chip than another because they can make use of special instructions to speed up certain operations that might otherwise take dozens of instructions. This should not be underestimated.

It should be pointed out the TPD has nothing to do with performance. An identical CPU build with a smaller manufacturing process, e.g. going from 32 to 22nm for example will result in a lower TDP in the 22nm vs the 32nm die. But has performance decreased? no, quite the opposite. There does exist cross platform measurements that attempt to gauge relative performance such as the Linpack benchmark. But these are artificial measures and rarely are benchmarks a good indicator of performance for a particular application.

Answer 4

allquixotic's answer gives you the practical side of things very well. I think it'd also be useful to have a short bit on the specifics of a 'clock' is and why all clocks are not created equal. And unless I err, this should hold true across all microprocessors real or theoretical.

5 GHz means 5 billion cycles or clocks per second. But what happens in a cycle is not represented in the frequency 5 GHz. If a wheel turns 25 times per second, how far does it travel? It depends on the circumference of course.

With a processor, the amount of possible work that can be achieved would be the cycles multiplied by the work per cycle (minus limitations and waiting times).

The maximum amount of work done per cycle can be any amount (theoretically). And historically, CPUs have been increasing the amount of work they can do in a cycle. They can do this in a number of ways:

• When the instruction set's size is increased, they are capable of solving a larger variation of problems in a single cycle.
• More complex instructions allow for solving more complex problems.
• Logical optimization allow for solving problems with less steps.

These optimization have led to and been made possible by adding hardware to the CPU's cores. Certain mathematical operations become more efficient when you have specialized hardware for them. For instance, working with decimal numbers is quite different from working with integers so modern CPUs have a specialized part of each core to deal with each type of number.

Since the cores have become complex, not all parts are used in every cycle, so a recent trend has been to implement some type of "hyper-threading" that combines two completely separate operations into a single cycle since both operations mainly use different parts of the core.

As you can see, this makes CPU frequency a very poor indicator of performance. This is also why benchmarks are used in almost any comparison between them since calculating the theoretical performance per cycle is a complicated mess at best.

Summary

Since the definition of a "core" is arbitrary and varies hugely from processor to processor, the amount of work done per cycle of said core is also arbitrary.

Answer 5

What's the difference between mobile and desktop processors?

The salient differences between mobile and desktop processors are:

• power comsumption: The mobile processor has to powered from small batteries of low voltage and small capacity. Therefore power efficient is a major concern for operational performance and marketing claims. For desktop processor power efficiency is a minor concern. For the gaming segment of the market, power efficiency is practically irrelevant.

• physical dimension factors: The mobile processor has to be physically small and light as possible. For a desktop processor, size and weight are essentially irrelevant, and have no design targets except for perhaps manufacturing and cost issues.

• I/O expansion: The mobile processor is for a single-board computer with well-defined and a limited number of peripherals, ports and essentially no expansion capability (i.e. no PCIe bus). Even its main memory capacity is likely to be constrained to a few GiB to minimize the MMU requirements. A desktop processor, on the other hand, has to be capable of large installable main memory, and expansion capability for adapters and peripherals using the (high speed) PCIe and USB buses.

The computational power of a mobile processor is severely constrained by these design goals. Fortunately semiconductor/processor technology is advancing so that the latest mobile processors can compare favorably with the computational power of older desktop processors.
But for any given point in time, the "best" mobile processor will not computationally outperform the "best" desktop processor. Combined with the restricted I/O expansion, the more-expensive mobile processor would probably only be used in a self-contained all-in-one "desktop" system.

My question is does this mean that the new Samsung gadget is more powerful than my desktop?

You have to define "powerful" and chose metrics. Almost any single metric (which marketing types like to use) can be manipulated to produce bogus comparisons. Some computers have been known to have been redesigned solely to perform well for specific benchmarks (e.g. measuring FLOPS) while their overall performance may be no better than the competition.
A single metric such a CPU clock speed (i.e. GHz) or TDP or fab size can become less relevant and not comparable for evaluating performance as technology changes.

Answer 6

Power vs Performance Mobile processors must conserve power (a lot of it) and generate a lot less heat than desktop processors. To serve such a requirement, mobile processors ALWAYS use a much simpler architecture (ARM) than desktop processors (x86/AMD64/x86_64) of the same generation. Indeed, the most useful metric to compare CPUs is the underlying architecture. All the MHz, feature size and number of cores may help only if you are comparing CPUs with similar or related architectures.

The CPU architecture/micro-architecture The architecture of a CPU decides how it executes programs and what algorithms it uses to perform computation and also how it accesses cache and RAM. The architecture also includes the "language"(instructions) the CPU understands. A desktop processor understands language is much more complex than what a mobile processor can understand. Desktop processors understand the complex x86/x86_64 language while mobile processors understand the ARM32/64/Thumb2 language which is a lot simpler so requires more "words" to describe an algorithm and is size inefficient when compared to x86. The reason mobile chips understand simple language is because there is an area and power constraint on the number of transistors that can go into it.

A typical desktop processor might execute 8+ CISC(Complex) instructions in parallel and in an out-of-order fashion to offer high performance at the cost of increased power dissipation while a mobile processor might execute only 2 RISC(Simple) instructions out-of-order to conserve power. Desktop processors have a lot more cache (6MB+) than mobile devices(1MB) giving a large performance boost. Further, CISC architectures (Intel x86_64 used in desktops and laptops) offer high code density allowing a larger amounts of information to be packed into a smaller space while RISC architectures (ARM64 used in mobiles) use uncompressed instructions that tend to put more pressure on memory bandwidth since more space is required to convey the same meaning. What I mean is that a 1MB CISC program conveys more information that a 1MB RISC program requiring the RISC program of similar function to perform more memory transfers causing a performance loss.

As a general rule, desktop architectures are performance oriented. For example, an SIMD operation on a modern intel processor (desktop) takes only 25% of the time a typical ARM processor (mobile) takes due to the fact that desktops can stuff in more transistors into the CPU since area and power are not constrained.

Effect of feature size As a general rule, if a processor of architecture A is ported to a lower technology (say, 22nm to 12nm), its performance improves while its power consumption reduces due to improved transistor performance and efficiency. Thus, for example, a typical ARM Cortex A-5 fabricated at 12nm will offer a higher performance and will run cooler than an ARM Cortex A-5 fabricated at 28nm. However, an ARM Cortex A-15 (a better micro-architecture than the A-5) fabricated at 32nm will run a lot faster than the A-5 at 12nm (it will consume more power, though). Thus, while feature size is an important metric, it sort of loses footing when comparing different micro-architectures/architectures especially when one is far better than the other.

Effect of cores Do not get fooled by the core count. They are terrible indicators of CPU performance. Comparing CPUs on the basis of core counts is only useful when they are of the same micro-architecture. Of course, a faster micro-architecture with more cores beats a slower micro-arch with fewer cores. However, a slow quad core will most likely offer worse performance than a high performance dual core processor. A weak quad core may be good at handling 4 simple tasks in time T while a strong (4x faster per core) dual core might be able to handle 4 simple tasks in half the time frame (T/2) since it should be able to process 2 of them in T/4 other 2 for the other T/4 (T/4 + T/4 = T/2). Also beware of quasi-octa cores(most mobiles are quasi in the sense that only 4 cores may be active at any time to save power). Desktops typically offer complete cores with little sharing of resources to enable higher performance at the cost of high power consumption.

Effect of Clock Frequency This heavily depends on the micro-architecture of the processor.

To illustrate this, consider the following problem, 3 * 3.

Say processor A converts the problem into 3+3+3 and takes 3 clock cycles to execute the problem while processor B directly performs 3*3 using a look-up-table and gives the result in 1 clock cycle. If manufacturer A says the processor frequency (clock cycle) is 1GHz while B says it is 500MHz, B is faster than A since A takes 3ns to complete 3*3 while B takes only 2ns (B is 33% faster than A even though B is running at a 50% slower in clock). Thus, clock speeds are good comparisons only when comparing similar micro-architectures. A better uarch with a lower clock speed might beat an older uarch with a much higher clock speed. Also low clock speeds save power. A high performance uarch at a higher clock speed surely will beat a lower performing uarch with a similar or lower clock speed (sometimes higher as well). So clock speed is not at all a good measure of CPU performance just like core count. Note that mobile processors implement simpler and slower algorithms to compute than desktop processors in order to save power and area. Desktop processors often feature algorithms that are almost two to four times (or more) as fast as their mobile counterparts giving them a distinct edge in performance over mobile processors.

** Effect of cache ** Cache plays a major role in processor performance than the core speed itself. Cache is high speed RAM inside the processor to reduce requests to RAM. Desktop caches are bigger and faster (there is no restriction on size or power for desktops) than mobile caches thus giving desktops an edge over mobile CPUs. Add the CISC efficiency and desktop caches have an advantage over mobile caches. A 2MB desktop cache beats 2 MB mobile cache simply by instruction density itself (more information in the same space). Caches are very important in determining CPU performance. A processor with a big fast cache will outperform a processor with a small slow cache. However, there is a trade off between speed and size of cache which is why systems have levels of cache. As technology shrinks, caches become a lot faster and more efficient. Of course, the cache architecture also plays a very important role in this regard. It simply isn't that simple to compare caches but cache comparisons are a LOT less perverse than comparisons involving cores or clock speeds.

Thus, assuming a constant generation, desktop processors will almost always outperform mobile processors in terms of raw performance while mobile processors almost always consume less power to make up for their relatively poor performance.

Answer 7

Lets use a loose analogy to think of and understand the characteristics of a CPU.

Imagine that a CPU is a factory assembling cars. Parts (data) come in, gets sent on conveyer belts where they are assembled. Finally a completed car rolls out the other end (processed data).

A simple group of parts like a door might move forward on one step, get a new part added on the next and so on. One process might be used for more than one group so for example the line that makes the door handle assembly would pass on door handle to both the front and rear doors. A more complex group like an engine goes on a longer conveyer route and might take several steps to gather all the parts, more than a single step to put them in a complex arrangment, etc. So in your CPU different commands take a different number of clock cycles to complete and use different parts of the CPU that are dedicated to a task (but might be used as part of more than one type of command).

clock speed might be the speed of your conveyer. On every tick the conveyer moves forward to the next step. Running a conveyer faster gets more cars through but you can't do this any faster than the tasks take to complete (in the CPU the limit is the electrical properties of a transistor)

die size is the size of your factory (chip). A bigger one can have more going on at once and so get more done.

fab size is how big are the assembly robots/people (transistors). When they are smaller you can fit more into the same space. Smaller transistors can run faster and use less power/give off less heat.

TDP is how much power your factory can use when running at full capacity. In a CPU this is important because it indicates how much power the CPU will use under full usage but also how much heat it will generate. You can see this only gives a rough indication that there is something going on, TDP can't be used as any indication of performance because the efficiency is dependant on all the other variables. This is common sense really because otherwise how could your PC today be thousands of times faster than one from 5 or 10 years ago without using thousands of times more electricity.

When I can't optimize or make my assembly line any quicker, I can simply have another one running alongside, this is like your number of cores. In the same way a factory might share the same access roads/delivery bay cores of a cpu share access to memory, etc.

All of these are measurable but there is one fundamental factor left that is not so easy to put a figure on, architecture. My car factory can't easily make a truck, and even less so a boat. The assembly lines are setup for one thing and to make another can still be done but means moving parts from one line to another in a way that is not optimal, wasting a lot of time. Processors are designed for specific tasks, the main CPU in your PC is quite generalised but even so has quite specialised optimisations such as multimedia extensions. One CPU might be able to do a command in 2 steps that another has to split down to 20 basic operations. Architecture can be THE most important factor in determining performance

So comparing even very similar CPUs on the same platform is quite difficult. An AMD FX and Intel i7 are better at different tasks for any given clock or TDP. A mobile PC processor like an Atom already even harder to compare, the CPU in your phone tough to compare between an ARM cortex and a Qualcomm Snapdragon let alone with a desktop processor.

So to conclude, none of these stats let you compare the performance of different types of processor. The only way is to take benchmarks based on particular tasks you are concerned about and running them on each to compare. (Bearing in mind that each platform is very good at specific ones, there is often no clear 'fastest')

Answer 8

As others stated MHz and GHz should not be used to compare CPU's with each others. They can be used to compare processors with the same architecture or family (you can actually compare i3 4000m with i3 4100m GHz wise because they share same architecture). CPU performance in modern processors is average of factors like die size, architecture, number of cores and frequency. All of those factors taken into account togheter can allow you to position CPU's in terms od performance. Desktop and mobile processors however should not be compared directly.

Because they are different on many levels. They have different architecture, different instruction set, mobile processors are much smaller in size and they have to work in different circumstances. Which means that power usage and working temperatures are also important as they are mainly used in mobile devices that have limited supply of power. Also GHz in most of high end mobile processors are empty values. You can't use their full potential for long (in most of the cases) because they tend to throttle (Nexsus 5 is a great example of this, it spots Snapdragon 800 which is throttling even in benchmarks) a lot and MHz and voltage are getting reduced to save chip from getting damaged because of overheating.

If you really want to compare them, the most reliable way would be to use linpack (compared to some silly multiplatform benchmarks), refer to this site: Linpack Still this should be used as a resource for sheer curiosity rather than educational purposes as being most reliable doesn't mean being reliable in general.

My question is does this mean that the new Samsung gadget is more powerful than my desktop?

No and it won't be for many years propably as mobile processors are still very weak compared to desktop ones.

Answer 9

When processors run they generate heat. Lots of heat. Because mobile devices are considerably smaller than computers, the heat generated by a running mobile processor is often amplified and can seriously harm components, or even melt them. Therefore, the developers and designers of the devices limit, or throttle, the speed at which a mobile processor can run. This means that if a processor is getting hot, it will limit its speed, which equates to slower performance.

Because of this throttling, the processor on many phones will actually run slower than the advertised speed. In fact, the advertised speed of mobile processors is normally the maximum. Compare this to most computer processors, where the advertised speed is usually the average running speed, and you begin to see why computers are more powerful.

Source

Answer 10

My question is does this mean that the new Samsung gadget is more powerful than my desktop?

Is the 2.7GHz the same kind of GHz as non-mobile devices (is it scaled up, or compared etc)?

For answer of this I will ask a question.

Will Intel dual core cpu with 2.7 GHz is more powerful then the Intel core I3 cpu( 2 cores) 2.7 ghz.

absolutely not na.....!!!

So there are lot of differences in Desktop cpu's only with reference to there cache, size, speed, heat, power , cores etc...

Hence The Mobile and Desktop CPU are also be different ...

Desktop CPUs are made with considering different requirements as compared to mobile.

Answer 11

all answer is good but a question not answered ! why seemed a desktop cpu cycle is More power than mobile cpu cycle ? The answer is : Desktop cpu use a More Transistor than Mobile cpu Intel Core = 600000000 ~ 1200000000 Arm Base = 20000 ~ 40000

why ? Because a Desktop cpu Process More Instructions than a Mobile cpu Therefore : More Transistor =More Instructions = More Performance

ARM Cortex A7 (4 Core at 1.5 ghz) =2,850 MIPS(million instructions per second)=2850000000 instructions

AMD E-350 (Dual core at 1.6 ghz) = 10,000 MIPS(million instructions per second)=10000000000 instructions

Tianhe-1A (186,368 cores at 2ghz)=2,670,000,000 MIPS = 2670000000000000

You Can Calc instruction Per Cycle or CPI for more help : http://meseec.ce.rit.edu/eecc550-winter2011/550-12-6-2011.pdf

and The next important : a Mobile Cpu like a SnapDragon 801 Max frequence is UP TO 2.2 GHZ this mean frequence not stable at 2.2 GHZ and it started (500 mhz ~ 2.2 ghz) It was decided to HEAT OF CPU