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
POST A COMMENT

127 Comments

View All Comments

  • eanazag - Friday, July 05, 2013 - link

    Zero innovation? I am neither for or against. Though how often do companies release a new product missing features that they had enough time to roll out. Apple is fairly consistent at rolling out products with a technology first. Name another laptop with a PCIe SSD. There are a handful with AC WiFi. And Apple is on the front end of anyone releasing a design with Haswell. I am not going to ignore that the fact is the chassis is the same, but they weren't doing bad with it to begin with. The reality is that to hit 12 hours of battery life the performance was about the same as last year's model. The question was for someone buying a Mac, was there even an option that didn't destroy the battery life gains.
    The "best Mac laptop" article was geared towards consumers buying a Mac. It wasn't for everyone. I would not buy a Mac today. Gaming is not adequate for me and buying a title that can still run on my Windows desktop at the same time is a better choice.

    I would only buy Macs for specific use cases. Maybe editing media. Though I do like Sony Vegas on the PC.

    Finally, there are articles that I routinely skip because the topic doesn't interest me much at all. I would suggest you develop that skill as it will likely help you in life more than being a complainer.
    Reply
  • jack daniels esq - Friday, July 05, 2013 - link

    God - I love this f**cking site Reply
  • negativeions - Saturday, July 06, 2013 - link

    It's amazing how many anandtech and apple losers post on here. Don't you morons know that these people are just company PR. Apple rips people off blind. Are their computers nice to use. Sure. I love them. But Apple are goons. Reply
  • antonio22m - Wednesday, August 14, 2013 - link

    Macbook Air is undoubtedly a very good notebook
    Price and lack of optical drive can affect a large number of users whose decision during the judgment can be negative so that they can decide to choose another manufacturer.
    Air is perfect and the best "second computer" that you can wish for.
    His task was not to be the main and only computer we can possess.
    If you want excellent laptop computer that will be able to carry it with you wherever you go, the Air is an excellent choice for perfectly reasonable size and more pronounced weight that barely exceeds one kilo.
    Take a look at this comparison at http://www.squidoo.com/apple-macbook-air-133 and You will see comparison to the another Apple laptops.Anyone considering purchasing this laptop needs to see the information in this chart.
    Reply
  • helloworldv2 - Thursday, July 04, 2013 - link

    In my opinion, your light workload battery life test doesn't represent real life. Under my perceived light load usage (Word open, a few tabs in Firefox, running a few algorithms in terminal), I've seen 7-8 h battery life with the maxed out 13" model.. Reply
  • DanNeely - Thursday, July 04, 2013 - link

    Everyone's idea about what is a light workload is different. A few years ago when my Laptop of the time was benched on AT, I was able to beat their light load numbers by about 10-15% on a test that was much less demanding than the current one. Reply
  • melgross - Thursday, July 04, 2013 - link

    We all have our own workloads. Anand, and other testing sites make these loads up to represent what they think is approximately the average for light, medium and heavy workloads. For your usage, you seem to fall to the medium workload, even though you call it light.

    For others, light is just using a browser with a handful of tabs.

    The poi t to their workloads is to have a standard that they can compare machine to machine. Don't take it as more than that, and for somethi g that people can look at and figure where their workload falls within the least and the max tests.
    Reply
  • FwFred - Thursday, July 04, 2013 - link

    What is your screen brightness? A few algorithms? Is this code which continuously runs (not good for CPU power management)? If anything, Anand is getting on the lower end of the range others are seeing, primarily because he sets his screen to 200 nits which is higher than others. Reply
  • helloworldv2 - Thursday, July 04, 2013 - link

    Brightness is on auto. A few algorithms might be anything between querying a sequence database and making multiple sequence alignments or whatever, utilizing both cores 100% for a brief period. Nothing too heavy (that's what ssh and clusters are for). Reply
  • FwFred - Thursday, July 04, 2013 - link

    I have a 2011 MBA, and while the brightness is using the 'auto' selection, you can still set the percentage. Which percentage do you have it? The auto setting will vary the backlight based on the ambient light, but the percentage still affects the result. I am at ~70%, and I can say that 100% is very noticeably brighter. Reply

Log in

Don't have an account? Sign up now