Hacker News Reader

Comment by didgetmaster | Hacker News Reader

Both AMD and Intel are competing for bragging rights, but they are both pushing the power envelope to accomplish it. The Raptor Lake processors take it to the next level. The law of diminishing returns kicks in whenever a new version is something like 20% faster but requires 25% more power in order to do it.

There are times when I will certainly sacrifice cost for speed, but most of the time I want my CPU to churn out pretty good performance while being frugal on the power budget.

View on HN

I do think TechSpot[0] (aka Hardware Unboxed) has a good chart[1] that highlights some differences in power consumption utilized to achieve performance.

Notice at 185W, the Ryzen 9 7950X is churning out about 36% higher performance than the Core i9 13900K. The Intel CPU, however, is then able to continue drawing up to 335W!

At their respective peak scores, the i9 is using over 70% more power.

[0] https://www.techspot.com/review/2552-intel-core-i9-13900k/

[1] https://static.techspot.com/articles-info/2552/bench/Power_S...

but I do think Raptor lake consunes less power than Zen4 when idling e.g. web browsing, code editing etc. I would want to see power usage for VS code + Firefox etc.

I use high performance only for seconds when compiling.

Zen's idle performance is absolutely atrocious due to the I/O die that constantly draws 20 watts. Pretty sure Intel's stuff in total draws less than half that.

Intel invested a crapload of money in laptop CPU's and low idle which is one of the reason they dominated that market for so long - I would guess that it bled over into desktop as well.

Are you talking about last years zen3? That was a common complaint.

From https://www.tweaktown.com/reviews/10195/amd-ryzen-5-7600x-ze...

"Power consumption is measured directly from the dual eight-pin connections. At peak, the 7600X pulls an impressive 130W, and during idle, it was down to 18w."

Sounds pretty good, especially considering its at the "dual eight-pin" power supply connection. Not laptop class, but pretty good for a high performance desktop.

Anecdotally, my Zen 3 5900X rated at 105W TDP, sitting kind of idle (with a dozen or so programs open, task manager showing 1% usage) is drawing about 11W.

I do seem to recall a AGESA update (motherboard firmware) that did managed to reduce the IOD power usage when idle. Sad that it was months after most of the reviews came out.

12900K idles at 8.5 watts. 18 watts is awful.

Measured where? At the power supply?

Not sure what exactly is included in the 18 watts via the power supply connector. Wasn't sure if it was all CPU, or CPU+Dimms, or maybe the entire motherboard.

The 8 pin connector goes to the CPU. The big ATX 12V connector goes to everything else.

For idle power consumption, watt usage from wall is better measurement.

I'm mostly interested in numbers under 100W, maybe even 65W, since I plan to down-clock my (future) Zen 4 machine.

AMD is killing it with efficiency there.

Yes - comparing the above 65W score from AMD to Intel's 145W score highlights the stark difference!

I've seen several posts showing that the most minor of underclocks and undervolts produce substantial power savings and minimal performance differences.

Apparently Intel's trying really hard on an old process to get the performance crown, forcing AMD to clock higher than they'd like to compete. It's ridiculous that they double the power for 10% performance. But the nice thing is you can half the power and take the 10% hit.

Also note that the 7900/7900X are dual chiplet design that has a significant power impact. The 7700x and below have a single chiplet and saves power, and also increases single thread perf. If you look at the gaming benchmarks the 7700x is often better than the 7900x, not to mention all the Intel chips except the top of the line i9.

So if you buy the 7700x and underclock just a bit you should have a very efficient desktop.

> the 7900/7900X are dual chiplet design

This is a minor terminology mix-up. The term you want here is "CCX". Each CCX holds multiple chiplets.

See https://www.tomshardware.com/reviews/amd-ccx-definition-cpu-... for more details.

EDIT: It does look like my own information on this was rusty.

A "chiplet" is not an individual core, but a trimmed down die that does not have a memory controller. A "CCX" contains cores (within a chiplet) and L3 cache.

https://www.hardwaretimes.com/amd-ccd-and-ccx-in-ryzen-proce...

> The basic unit of a Ryzen processor is a CCX or Core Complex, a quad-core/octa-core CPU chiplet with a shared L3 cache.

> For the Ryzen 3000-series processors, CCX refers to a four-core grouping inside of each core chiplet die (CCD). For example, an AMD CPU with 8 cores will have a CCD with two 4-core CCXs.

From that link, your statement does not appear accurate. Multiple CCX's appear on a given Core Chiplet Die. There are indeed two vs one core chiplets on different Ryzen designs (plus the IOD).

check out https://arstechnica.com/gadgets/2022/10/intel-i9-13900k-and-... - they power limited both 7000 and raptor lake models and surprisingly, amd doesn't respect the power limits - at 65W it's burning 90W and intel is respecting the 65W limit, 7.868Whr vs 8.58Whr to complete the same task (h264 encoding in handbrake), so interestingly intel on a 2 node disadvantage is more power efficient if you set your power limits.

That techspot review triggers me. Why does the guy go on and on about how impractical the 13900 is compared to the 12900, since the 13900 is "throttling"? Yeah, the 13900K hits a steady state of 5300MHz with all cores active and stays that way forever, which is great! The apparently "more practical" 12900K hits 4900MHz on all cores and does the job slower but it's "not throttling". This makes zero sense.

The popular tech press understanding of how closed-loop control systems work is just REALLY annoying.

And it is important to remember the AMD IOD is still on N6 or similar to current Intel 7 2nd gen. ( i.e On I/O level AMD and Intel are on the same Node ) Even if Intel was on Intel 5 or TSMC N5 equivalent it still likely wouldn't be using similar power as AMD.

So I am actually surprised at how well AMD Zen 4 is doing. It used to be if you want MT you go with AMD, at the expense of ST. Now this is no longer the case.

If you care about energy efficiency, just buy AMD Zen 4.

I think this mix of processes is testament to the fact analog is not scaling, and high speed IO has a lot of analog/phys. So having an IOD on 3nm would cost more and probably consume similar power, at least for the phys. Of course you will always get sub systems on that die that would benefit, but overall its likely a net loss.

Benchmark with same power limit like this is what I'd like to know. I also want to know wall watt usage for them, to verify it's limited correctly, and how much chipset/other components uses power.

See this comment: https://news.ycombinator.com/item?id=33278470

Not sure if it gets closer to the testing approach you're looking for?

This is great but I also want kill-a-watt measurement

how costly is in the US that diference (of power consumption) in a year?

> The law of diminishing returns kicks in whenever a new version is something like 20% faster but requires 25% more power in order to do it.

How often do you run your CPU at 100% load across all cores? For me, idle power draw dominates my overall power consumption. The difference between a 100W peak CPU and a 300W peak CPU basically doesn’t matter across the course of my day, because even compiling large codebases doesn’t last very long.

I say this because I bought into the AMD efficiency hype a few years ago, ditching my Intel workstation for an AMD workstation. Yet according to my home energy monitor, my office circuit consumption actually went up, not down.

Further investigation revealed that my AMD desktop had significantly higher idle power than the old Intel one. Given that most of my day is spent typing, not pegging the CPU at full load, this nets out to higher overall power consumption.

So I’m back to not caring about peak power consumption. If the Intel CPU wants to pull 300W for the 60 seconds that my compile takes, go for it. What I’ll really be looking at is the idle power usage.

Yes.

For my desktop, I only care if it's possible to make it quiet overall.

For a laptop, I care about performance given the more restrictive cooling restraints of the form factor, and battery life (but that's secondary since I can usually use it plugged in anyway.)

So efficiency matters (including under load), but it can't be your only deciding factor in deciding what to buy and use.

If you play any game then it's really not 60 seconds.

And then having a processor drawing this kind of power has impact on you PDU, cooling system, case...

mATX for instance makes nearly no sense with that kind of power use. But who wants a huge tower on their desk anymore?

Gamers love BIG RGB TOWER on the desk, isn't it?

If you play games, your room gets very noticeably hotter because on a high end pc you'll be at 500w while gaming. And this could be hours long.

Yea this generation power limiting in bios will be a must for high end.

Both 7950X and 13900k don't lose much performance from limiting power to "reasonable" wattage.

Seeing what the 7950X does even when limited to 65W is pretty exciting, and it will be very interesting to see what AMD does with their mobile line of processors come January!

What does limiting the power usage do to the single core performance?

It's a desktop chip, why do we care? If I need the compute power I couldn't care less about power consumption or heat. The thing will mostly sit idle anyway and sip a tiny fraction of that.

It seems to me like people only care about peak power consumption when AMD and Apple win those benchmarks.

GPUs are doing the same thing. Every generation does bring more efficiency, but also includes an increase of power consumption. I'd like to see a line that aims to reduce power consumption by a meager amount (1-5%) each generation, while continuing to push performance higher and just be an "Energy Efficient" model. Like here's our baseline.. 6 core, 12 threads @ 5.2GHz, let's see how power efficient we can get those specs over the next 5 generations, and how much performance increase we can also squeeze without drawing more power or making it bigger.

I've been thinking about these tradeoffs lately. There's an argument one hears that you can "future proof" by buying top of the line and then not having to upgrade as often. I think that's always been a bit flawed, but it feels like with the massive thermal tradeoffs these top end parts are making it less true than ever.

Heh, don't think that ever made sense. When a machine is 5 years old you don't particularly care if it's the low, mid, or high end CPU, they are all slow. However not buying ram is a killer and often results in replacing a perfectly good machines.

I don't fully agree. My 9-year-old 3rd gen Xeon is still plenty usable, barely slower than a "normal" i5 10th gen for doing Rust dev.

My work PC with a 4th gen i5 has been unusable even for basic tasks for a few years, despite the 16 GB of RAM and SSD drive. Even moving windows around and stuff is sluggish.

> Both AMD and Intel are competing for bragging rights, but they are both pushing the power envelope to accomplish it.

Yes and no. AMD just released the 5800X3D which is just a teensy bit slower than Intel's top-dog...but it uses a bit more than one third the power the I9-12900KS and 13900K do.

Right now you can get a blisteringly-fast (for gaming and other certain specific workloads) AMD CPU with power consumption a skooch over 100W. It yields a nearly 25% increase in framerate on some games, which is huge, and does it at less power usage than the non-stacked-cache variant: https://youtu.be/hBFNoKUHjcg?t=515

You're right about the next generation of Ryzen processors using more power, but nobody knows how much, partly because AMD using some silly nonsense to calculate "TDP", and review units aren't out yet: https://youtu.be/hVnJbiYOCq4?t=363

The Ryzen 7 5800X3D was released in early April 2022. It's rated for a 105W TDP, and draws up to about 190-195W depending on workload[0].

In 1080p gaming (useful for exaggerating the CPU bottleneck), the 13900K outperforms the 5800X3D by about 11%[1].

Review units of "next generation of Ryzen processors" have been out since late September when they became available to buy, so you can read reviews and find out their actual power usage[2]. The Ryzen 9 7950X is shown to push system power consumption up to 355W while running Blender.

(TechSpot reviews linked simply because they include power consumption in their reviews.)

[0] https://www.techspot.com/review/2449-amd-ryzen-5800x3D/

[1] https://www.techspot.com/review/2552-intel-core-i9-13900k/

[2] https://www.techspot.com/review/2535-amd-ryzen-7950x/

if youre buying a 13900 for 1080p gaming youre throwing away money anyways. ltt includes the 5800x3d in their numbers for comparisons at resolutions people buying super high end cpus actully want to drive.

At idle, where the cpu spends most of it's time, the Intel chips are winning significantly.

>At idle, where the cpu spends most of it's time, the Intel chips are winning significantly.

Well, by 3W for an entire system. Which isn't worth worrying about in my opinion.

So personally, I'd be looking at other specs to help me decide between them.

https://www.guru3d.com/articles_pages/intel_core_i9_13900k_r...

I put a 5800X3D in my gaming PC. It actually runs kind of hot and draws more power than I expected from the reviews, especially at idle.

For day to day use (including non-gaming work) my old Intel CPU consumes less power overall because the idle power was so much lower.

Peak TDP isn’t everything.

Reply on news.ycombinator.com