Core i7 vs. Core i5: Understanding the Power Story

Between generations Apple constantly struggles between squeezing every last ounce of max performance out of silicon and reducing system temperatures. I believe Apple's philosophy here is that most of the time your CPU should be running at relatively low utilization and as a result offering the full dynamic range of CPU performance is preferred to clamping max performance in order to preserve lower thermals. The problem is that in some cases, lazy background task management (e.g. keeping too many Safari windows open with Flash active) can drive CPU usage and thermals up even if you're actively doing nothing on the machine. This scenario coupled with Haswell ULT's excellent idle power consumption I believe are primary motivators for Mavericks' App Nap and occluded window slumber features.

 

 

To understand the impact on thermals (and battery life) of the Core i7-4650U on the 13-inch MacBook Air you need to understand what's going on under the hood. To hit higher frequencies, the i7-4650U generally requires a higher voltage. Power consumption (and thus thermal dissipation) can scale linearly with frequency, but it scales quadratically with voltage. The combination of the two is quite possibly the worst case scenario from a power consumption standpoint. This is why it's generally always best to increase performance via process shrinks or architectural enhancements vs. simply scaling frequency. In the case of the i7-4650U we're not talking about huge frequency/voltage scaling here, but rather a tradeoff between added performance and increased power consumption. In the table below I noted typical CPU core voltages for a couple of different operating modes on my i5-4250U and i7-4650U samples. Several years ago Intel introduced voltage binning even at a given frequency, so the voltages you see in the table below are only applicable to my parts (or other similar parts) - you could see a range of acceptable voltages in other binned parts even carrying the same model number. The values in parantheses indicate the CPU frequency (or frequencies) observed during the workload.

13-inch MacBook Air (Mid 2013) CPU Comparison - Observed Voltages
  Idle Cinebench 11.5 (1 thread) Cinebench 11.5 (4 threads)
Intel Core i5-4250U 0.665V
(800MHz)
0.852V - 0.904V
(2.3GHz - 2.6GHz*)
0.842V
(2.3GHz)
Intel Core i7-4650U 0.655V
(800MHz)
0.949V - 1.041V
(2.9GHz - 3.3GHz*)
0.786V - 0.949V
(2.8GHz - 2.9GHz*)

There are a bunch of observations here. First off, the two parts are very comparable at idle - this is how Apple can quote all implementations of the MacBook Air as being capable of up to 12 hours of battery life. At idle large parts of the silicon are clock gated if not fully power gated. Idle voltages are extremely low (even compared to what you find in modern smartphones) and both parts run at the same 800MHz frequency at idle, so power consumption is comparable between the two at idle.

Using Cinebench 11.5, I ramped up a FP intensive single threaded workload. FP workloads tend to force a bunch of large units into switching making this a great test for voltage scaling. Here we see that the i5-4250U is capable of hitting its max turbo frequency but for the most part it hangs out around 2.3GHz. The same is true for the i7-4650U, 3.3GHz is possible but most of the time it's sitting down at 2.9GHz. The i7-4650U needs higher voltages all around to hit these higher frequencies.

Next, I cranked up the number of threads. First you'll notice a reduction in clock speeds and voltages. This is where multithreading can actually be good for power consumption. Running more cores at a lower voltage for a shorter period of time can reduce total energy consumed while performing a task. The i5-4250U has no issues running at its max DC turbo frequency (2.3GHz), while the i7-4650U mostly sticks to 2.8GHz with occasional bursts up to 2.9GHz. Note that the 4650U's min voltage at 2.8GHz is actually lower than the 4250U's here. In order to hit these higher frequencies within the same TDP, Intel does have to bin for parts that do a bit better at higher frequencies whereas to make the cut for a 4250U the leakage requirements aren't as severe.

There shouldn't be any surprises thus far, but this data should give us an indication of what we can expect in terms of battery life and thermals. Where the i7 vs i5 comparison becomes tricky is if you look at workloads that can complete quick enough due to the faster performance in order to offset any additional power consumption.

CPU Performance Battery Life & Thermals
Comments Locked

127 Comments

View All Comments

  • KoolAidMan1 - Sunday, July 7, 2013 - link

    Your post is filled with angry rhetoric. It is hard to take any of that seriously
  • asianwolf - Sunday, July 7, 2013 - link

    what an amazing amount of drivel from a single post. Let's look at the one word you have used against this product 'innovation'. Prey tell please any other manufacturer in this sector that has 'innovated' in any way using the same standard Intel/hardware components?

    I'm not saying that Apple have 'innovated' in any particular way in this product as opposed to the original MBA introduction, this is just another internal upgrade...like all of the followers around them.

    Back up your thoughts with what you expect to see, rather than deriding a product that still excels amongst many of it's peers...not perfect...but neither are the components that its built from.
  • therodt - Thursday, July 18, 2013 - link

    Guys he is completely right. Its not innovating if it is not new. Refining the same thing and calling it new does it make it innovative.
  • pav1 - Sunday, January 19, 2014 - link

    The trouble is there is a conflict between innovation & pricing/value. Innovation is costly, and may not be included for low end products. You'll find innovation at the low end only for competitive reasons. Apple has significant mind and marketshare.
  • whosjohnny - Monday, September 23, 2013 - link

    dsumanik - you're a cancer, stfu man. you know NOTHING about innovation. something as good as macbook air single body design and you're like what? "release this same junk!!!" go f die you imbecile!
  • hasten - Thursday, July 11, 2013 - link

    Unfortunately everything you have written is wrong. You are the problem - fanboys that believe anything they read on the internet. Apple has not "innovated" since the early 90s. They have done nothing but taken someone else's innovation and repackaged it in a well marketed shiny box. Claiming that they have "put fourth" the best hardware shows even more how little you know. Apple does not manufacture anything. They depend on true hardware companies to create for them. Yes they do assist in the design of the mobile, low end processors for their mass market products, but they do not manufacture anything.

    Amazingly the shroud is coming off and investors and the general public alike are realizing the game that Apple has been playing. Stock prices plummeting, market share decreasing. I'm sure that hard statistical facts won't mean anything to you though. I'm sure you work in the industry with your commentary, brilliance is spewing from them. The only people that should have respect for Apple are marketers. The bubble is bursting and the kiddies are sad.
  • purerice - Friday, July 5, 2013 - link

    JKflipflop98, while I do not wish harm on anybody, I share your disgust with dsumanik.
    I have no inclination of getting an Apple MBA but Anandtech's MBA articles are great for comparing IVB to Haswell and i5 to i7, at least in a GPU-limited scenario.
    I am in the market for a new laptop and often see great deals on IVBs and the i7s are extremely tempting. However thanks to Anand's articles, I will wait for the full Haswell line of i3, i5, i7s to be out before deciding.
    Also, considering the meager difference between i5 and 30% higher clocked i7, unless it is to do with thermal limits, I think I will stick with an i3 or i5 based Haswell. Though I would be curious in performance difference between these 15W i7s and the 47W i7s in Toshiba's laptops in performance, battery life, and temperature.
    So yes, even if I now have no inclination of getting an Apple MBA, these 3 articles provided enough information to deduce what processor I want in a laptop. As laptop processors are not generally interchangeable, these articles have helped me to key in on which laptops to eliminate from my search. To that extent I am very grateful to Anandtech for these articles.

    Furthermore, even if you don't like Apple, Apple generally has consistent hardware from generation to generation and often gets early editions of Intel processors (great for getting rid of deep sleep USB3.0 issues). Thus, with fewer variables from generation to generation, Apple computers make great test beds for testing out those few variables which are new. It is both amazing and sad that on a website with "tech" in its name you get people who think as unscientifically and biased as dsumanik that they cannot appreciate genuine research for the name behind the research.

    Good day to you all and thank you Anand for your continued dedication to solid articles that give insight that is valuable even to those will not likely purchase the product reviewed. I salute you.
  • dsumanik - Friday, July 5, 2013 - link

    Stop turning the conversations towards apple vs whoever. My rant has nothing to do with apple being good or bad.

    Its ok for anand, you, me, or the rest of the general public to like apple.

    it's NOT ok for him to tell you apple is good when he isnt thinking that inside his own head.

    Why why... WHY would you ever tell someone to buy something you thought was inferior?

    "Oh man, the Core i7 upgraded seriously fixes everything."

    Ok so anand was thinking it was broken. Ok maybe not broken, but at the very least slow...a step down from last years performance. its plain to see in the numbers, the new proc isnt a flat win across the board.

    Yet he still gave the original MBA a glowing review....then wrote a separate article recommending its purchase. Like that was the icing....why did he write that article lol? wouldn't you write that after apple had refreshed its entire line?

    Why right now...all of a sudden do we need an article telling us to buy the only 2013 model.....no one here is stupid, we know not to buy the last years model of anything!!!!!

    its so LOL wtf obvious if you just take a step back and ask why, especially that second "article", why it was written.....*advertising* cough cough cough

    his true feelings were NOT reflected in the original article. End of story.

    he WANTS apple to be viewed in a positive light, even if he isn't feeling it inside himself.

    This isn't an isolated incident its been slowly happening for about 3-4 years now.

    He is writing articles telling you to buy something, that in his mind he felt was subpar.

    like seriously guys, don't you see a problem with that?

    ask yourself why someone would make that recommendation?

    Hate me all you want but the question still needs answering....why is it of PERSONAL interest for him to paint apple as rosey a picture as possible.

    It has nothing to do with me, my attitude, my love or hate of apple, Microsoft, chocolate, vanilla, titty bars, democrats, gun laws, religion, or the color of your skin.
  • biasuz - Friday, July 5, 2013 - link

    I'm sorry sir, but your premise is false.

    I know nothing about Anand besides what's resides inside this website. That accompanied to a review of intel's pentium IV a real while ago turned me into a regular visitor.

    On both of the very well written articles relating this subject matter, Anand has been clear to accurately explain the DESIGN CHOICES Apple took, when building a computer whose main focus is not a performance crowd.

    Such design choices are:
    - use of slower frequency CPU would for sure impact raw processing power, as has been perceived by the reviewer, who in fact went to the trouble of quantifying how much less raw power would you get when comparing a previous model. Now please, kindly take into consideration what sort of gains in term of battery life were achieved, WITH LITTLE TO NO IMPACT in consumer experience, because of such DESIGN CHOICES.

    - The same philosophy can also be observed in using a lesser frequency in a MUCH LARGER GPU, demoed similar to superior performance with noticeable gains in used wattage.

    This computer is all about mobility, no raw power.
    In it's premise of existing, a mobile computer, this ones generation seriously outperforms it's previous generation.

    Kind regards.
  • vFunct - Saturday, July 6, 2013 - link

    lol.

    You DO know that Apple makes the best computers in the industry, and everything else is largely garbage, right?

    THAT is objective fact. Do not attempt to spin it with your bias.

Log in

Don't have an account? Sign up now