Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
I don't know the TDP of the M1 yet.
Edit: But so far appears to be winning if the above "10W" estimate is correct.
So far nobody except Apple (and its manufacturing partners) knows what the “TDP” of these chips really is. 10W is just a guess.

My guess is it is probably higher, but not too much higher, but it is still just a guess.

Battery life is not a good gauge IMO because TDP isn’t directly related to battery life. For example, you could theoretically build a CPU with say 24 performance cores and just 4 efficiency cores where the performance cores would be shut off if they weren’t needed. However, if you had a heavy workload, you could run all 28 cores simultaneously, with a TDP of say 250 Watts. But what if you just wanted the computer to periodically check email on the efficiency cores? Perhaps in that case it only needs 15 Watts to run. That 250 W TDP CPU might last longer on battery than say an old school 90 Watt TDP CPU. This is a hypothetical situation but it does illustrate what I’m talking about.

That’s one of the benefits of Apples big.LITTLE design.

To make a long story short, you cannot necessarily equate long battery life with low TDP.
 
You are literally making up your own rules, with a bunch of different artificial qualifiers that suit the M1.

I'm comparing it to laptop chips that are found in similarly priced machines.

I disagree. Apple has never been similarly priced to anyone else, even when in the identical class with the exact same chip. Comparing price from one brand to another doesn't change the class of device. The MacBook Air is in a very specific class of devices, just because it costs more than the competitors doesn't make it comparable to a high end gaming laptop from Dell.
 
According to the interviews, M1 will doesn't have strict TDP, it all depends on where you put it. So in Air it might as well be 10w, but thermal capacity of single fan MPB is at very least 15W, possibly more.
Even so, the Macbook air's Geekbench single core score handily beats the R7 4800U and is on par with multi core and as we know the MBA chassis is only 10w TDP capable. Still impressive imo.
 
The 4800U scores over 10,000 in multicore compared to the M1's 7500. That's 33% faster. I don't care at all about TDP.
You are comparing an 8-core, 16-thread 4800U to a 8-core, 8-thread M1 (actually 4-cores+4-little cores (25% SPEC2006 of a big core each) that with very likely has half the TDP. If you don't think about TDP that would be like comparing a 3800X's 13000 score to your 4800U's 10000 score and saying the 4800U is nothing worth writing home about because it doesn't score as well as the 3800X with its 4-fold higher TDP. The fact that the 4800U does so well within a 25W TDP, even with a built-in GPU, is what makes the 4800U so amazing. That the M1 is only 25% slower while running half the number of threads with a quarter of the resources on half of them, while essentially incorporating the chipset as well, and doing it within half the TDP of the 4800U is at least as amazing to me.
 
I disagree. Apple has never been similarly priced to anyone else, even when in the identical class with the exact same chip. Comparing price from one brand to another doesn't change the class of device. The MacBook Air is in a very specific class of devices, just because it costs more than the competitors doesn't make it comparable to a high end gaming laptop from Dell.
OK, so then "class of device" is just a subjective, mostly meaningless term.

Now that Apple is making it's own chips, they are going to be compared to AMD and Intel.
 
You are comparing an 8-core, 16-thread 4800U to a 8-core, 8-thread M1 (actually 4-cores+4-little cores (25% SPEC2006 of a big core each) that with very likely has half the TDP. If you don't think about TDP that would be like comparing a 3800X's 13000 score to your 4800U's 10000 score and saying the 4800U is nothing worth writing home about because it doesn't score as well as the 3800X with its 4-fold higher TDP. The fact that the 4800U does so well within a 25W TDP, even with a built-in GPU, is what makes the 4800U so amazing. That the M1 is only 25% slower while running half the number of threads with a quarter of the resources on half of them, while essentially incorporating the chipset as well, and doing it within half the TDP of the 4800U is at least as amazing to me.
No, I'm comparing one mobile chip to another found in similarly-priced laptops. And the 4800U's TDP is only 15W. We don't even know what the TDP is for the M1 in the Macbook Pro.

Apple decided to prioritize battery life over performance with the M1 chip design. Fair enough. But you don't get to crow about battery life without acknowledging other mobile chips pummel the M1 into the dirt in multicore performance.
 
OK, so then "class of device" is just a subjective, mostly meaningless term.

Now that Apple is making it's own chips, they are going to be compared to AMD and Intel.
I think this is fair; however, if comparisons are to be made, we should still compare like for like as far as we are able. Power requirements, # of cores (including scales for efficiency cores), etc. should be taken into account.
 
  • Like
Reactions: amartinez1660
No, I'm comparing one mobile chip to another found in similarly-priced laptops. And the 4800U's TDP is only 15W. We don't even know what the TDP is for the M1 in the Macbook Pro.

Apple decided to prioritize battery life over performance with the M1 chip design. Fair enough. But you don't get to crow about battery life without acknowledging other mobile chips pummel the M1 into the dirt in multicore performance.
MC performance at the same wattage is essentially a function of the number of cores you're running. 4 performance cores + 4 efficiency cores doesn't trump 8 performance cores. OK?
 
The 4800U scores over 10,000 in multicore compared to the M1's 7500. That's 33% faster. I don't care at all about TDP.
The 4800U on Geekbench is not scoring 10,000 on muliticore, the highest I have seen is 7229. It also has 8 cores, while the M1 is 4 cores, unless the efficiency cores are being utilized as well under Geekbench. The TDPs are somewhat similar. I don’t see how the M1 is anything other than a huge win for Apple compared to AMD and Intel.

TDP is relevant in every single instance when comparing CPUs. Comparing a 10-15w CPU to a 28w or 45w TDP CPU is simply not a credible way to discredit or minimize what Apple has created.

I’m also seeing the Apple M1 outperforming Intel Xe in OpenCL tests and I’m not seeing the Radeon GPU in the 4800U beating either the M1 or the Xe ever.
 
No, I'm comparing one mobile chip to another found in similarly-priced laptops. And the 4800U's TDP is only 15W. We don't even know what the TDP is for the M1 in the Macbook Pro.

Apple decided to prioritize battery life over performance with the M1 chip design. Fair enough. But you don't get to crow about battery life without acknowledging other mobile chips pummel the M1 into the dirt in multicore performance.
Multicore is for gaming, single core is for internet surfing and watching movies.
 
  • Haha
Reactions: PickUrPoison
The 4800U on Geekbench is not scoring 10,000 on muliticore, the highest I have seen is 7229. It also has 8 cores, while the M1 is 4 cores, unless the efficiency cores are being utilized as well under Geekbench. The TDPs are somewhat similar. I don’t see how the M1 is anything other than a huge win for Apple compared to AMD and Intel.

TDP is relevant in every single instance when comparing CPUs. Comparing a 10-15w CPU to a 28w or 45w TDP CPU is simply not a credible way to discredit or minimize what Apple has created.

I’m also seeing the Apple M1 outperforming Intel Xe in OpenCL tests and I’m not seeing the Radeon GPU in the 4800U beating either the M1 or the Xe ever.
Robospungo is referring to Cinebench R23 results, although your other criticisms are valid.
 
  • Like
Reactions: Zdigital2015
Remember that the M1 has four high-performance cores and four efficiency cores. Comparing it to an octa-core where the cores are running at mostly full performance, the M1 would lag between compared to other octa-core processors.
Expect the higher end chips to have 8 performance cores and 16 GPU cores.

so 8/4/16 vs 4/4/8

It will be insanely powerful for professional apps. Not sure about high end games but is anyone going to compile and optimize them AS anyway.
 
No, I'm comparing one mobile chip to another found in similarly-priced laptops. And the 4800U's TDP is only 15W. We don't even know what the TDP is for the M1 in the Macbook Pro.

Apple decided to prioritize battery life over performance with the M1 chip design. Fair enough. But you don't get to crow about battery life without acknowledging other mobile chips pummel the M1 into the dirt in multicore performance.
Little nitpick, but at 15W the 4800U only does 9600 in Cinebench. The 10000 score requires 25W. Apart from that, "similarly priced laptop" is probably the silliest criterion to choose processors for a benchmarking comparison I have ever heard. Thanks for the laughs!
 
To be honest, if the M1 turns out to be this amazing thing for Macs, it's going to be hard not to go out and buy one! I know many are against launch/first-gen products, but I'm a sucker when it comes to these things in that if I like what I see, I'm going to buy it! So far, I haven't been burned *knocks on wood*.
I bought a TRS-80 in the late 70’s, an Apple 2 early 80’s, an Amiga 1000 followed by a 2000 in 1984-1989, plus all sorts of early audio and video equipment (CD player in 81, a Laserdisc in 82, Sony 8mm video camera,a big screen (40 inch) tube tv in 93, custom built 5 ft tall speakers in the 90’s......... have fun guys, my early adopter days are long over. If in a couple of years the iMac is on its way and all of the earlier Macs A) worked out the bugs and B) are still near the top performance wise, I may get an early 27+ inch iMac but that’s as early as I’m going to be. And it’s still an “if”.
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.