News Apple M4 benchmarks suggest it is the new single-core performance champ, beating Intel's Core i9-14900KS — incredible results of 3,800+ posted

[skiwi44]

Just based of the 13900k

die shot and the M3 die shot

It's pretty obvious Intel has more space dedicated to the CPU than than Apple Silicon does. The 13900K P cores alone take up at least 30% of the die, with e cores it's about 50%. Apple Silicon of the base M line is about 20ish%.

Also, it looks like Intel actually has a larger die. From what I can find the 13900K has a die size of 257 mm2 and M3 has 146 mm2. If we want to argue node size just rough scaling gives 146 * 2.34 = 341 which would be 32% larger. 50% of 257 is 128 mm2 for the 13900K. 20% of 341 is 68.2 mm2 would be dedicated to CPU on an M3 (TSMC N3 to Intel 7 rough scaling). This is all speculation and density scaling guesses, but it's hard to make an argument on the evidence we have that Intel is using less transistors for their CPU clusters.

You need to be careful as you're likely confusing TheHerald with facts....

 

[skiwi44]

Man, you didn't even make the effort to type the k ,the non-k 14900 is a 65W base power CPU, that will suck at warming your room and can be cooled with passive cooling.
A little more effort in your trolling would be much appreciated.

Oh please -the 14900K is a 125w part and has a 265w turbo mode - to say nothing of the system. And those are Intel "watts"

and get a sense of humour. please.

 

[skiwi44]

Completely and utterly wrong. Number of cores is irrelevant. The M4 is a bigger chip than their 14900k. It's made of 28 billion transistors vs 25 billion of the 14900k. It should be beating the crap out of the 14900k in both ST and MT performance (since each core is much bigger in transistor size) but it doesn't.

State your sources. And your logic is obviously flawed. Given the 14900K has 25bn transistors in a much less efficient process node, it is likely larger than the 28bn chip of the base M4 which is on a 2nd gen 3nm process node, so it is highly likely that the Intel is bigger than the M4.

The M4 is likely the same size (or very similar) the the M3 (3bn more transistors offset by a more efficient process node).

The 14900K has a 257mm^2 die size.

 

[TheHerald]

Just based of the 13900k

die shot and the M3 die shot

It's pretty obvious Intel has more space dedicated to the CPU than than Apple Silicon does. The 13900K P cores alone take up at least 30% of the die, with e cores it's about 50%. Apple Silicon of the base M line is about 20ish%.

Also, it looks like Intel actually has a larger die. From what I can find the 13900K has a die size of 257 mm2 and M3 has 146 mm2. If we want to argue node size just rough scaling gives 146 * 2.34 = 341 which would be 32% larger. 50% of 257 is 128 mm2 for the 13900K. 20% of 341 is 68.2 mm2 would be dedicated to CPU on an M3 (TSMC N3 to Intel 7 rough scaling). This is all speculation and density scaling guesses, but it's hard to make an argument on the evidence we have that Intel is using less transistors for their CPU clusters.

The m3 is smaller than the m4 and it gets blasted by the 13900k in MT, at least in GB6

 

[TheHerald]

State your sources. And your logic is obviously flawed. Given the 14900K has 25bn transistors in a much less efficient process node, it is likely larger than the 28bn chip of the base M4 which is on a 2nd gen 3nm process node, so it is highly likely that the Intel is bigger than the M4.

The M4 is likely the same size (or very similar) the the M3 (3bn more transistors offset by a more efficient process node).

The 14900K has a 257mm^2 die size.

The die size is irrelevant, transistor count is what matters. A CPU with 120b tranistors should be faster than one with 10b transistors, regardless of the die size.

 

[palladin9479]

The die size is irrelevant, transistor count is what matters. A CPU with 120b tranistors should be faster than one with 10b transistors, regardless of the die size.

Define "faster". An ASIC with less then 1bn transistors will smoke both of those larger CPU's at AES encryption and SHA/MD5 hashing, like by 1,000 to 10,000 percent. These are specialized chips that are responsible for running 160~240GB/s + of real time encrypted traffic and exist in many newer products. Of course those chip couldn't possibly run an OS or play video games.

It's all about the needed scenarios we are targeting. If its' gaming, then we look at benchmarks for those games we play, if it's for media encoding then we target that and so forth.