Live data from Hacker News

AMD's Strix Point: Zen 5 Hits Mobile

chipsandcheese.com

171–180 of 241 posts

Re: AMD's Strix Point: Zen 5 Hits Mobile

#171
post #161
post #149

Earlier quoted context omitted.

Function arguments and return values already are effectively special use, and should frequently be on par if not much more frequent than the couple x86 instructions with fixed registers. Both clang and gcc support calls having differing used calling conventions within one function, which ends up effectively exactly identical to fixed-register instructions (i.e. an x86 'imul r64' can be done via a pseudo-function wher…

Unlike x86, none of this is strictly necessary. As long as you put things back as expected, you may use all the registers however you like.

The option of not needing any fixed register usage would apply to, what, optimizing compilers without support for function calls (at least via passing arguments/results via registers)? That's a very tiny niche to use as an argument for having simplified compiler behavior.

And good register allocation is still pretty important on RISC-V - using more registers, besides leading to less compressed instruction usage, means more non-volatile register spilling/restoring in function prologue/epilogue, which on current compilers (esp. clang) happens at the start & end of functions, even in paths that don't need the registers.

That said, yes, RISC-V still indeed has much saner baseline behavior here and allows for simpler basic register allocation, but for non-trivial compilers the actual set of useful optimizations isn't that different.

Re: AMD's Strix Point: Zen 5 Hits Mobile

#172

Earlier quoted context omitted.

The M1 was made on 5nm which have long been available to AMD and other competitors in volume.

Fast is relative. The Ryzen HX 370 has a TDP configurable down to 15W and at that power level it could be run fanless and would be faster than the M1, but it's still faster yet if you give it 54W and raise the clock speed.

I'm going to need source on that.

What does HX 370 score at 10w?

Re: AMD's Strix Point: Zen 5 Hits Mobile

#173

One of these has to be true (or both true): 1. ARM is inherently more efficient than x86 CPUs in most tasks 2. Nuvia and Apple are better CPU designers than AMD and Intel Here are results from Notebookcheck: Cinebench R24 ST perf/watt * M3: 12.7 points/watt * X Elite: 9.3 points/watt * AMD HX 370: 3.74 points/watt * AMD 8845HS: 3.1 points/watt * Intel 155H: 3.1 points/watt In ST, Apple is 3.4x more efficient than Zen…

Performance per watt is a bad metric. You want instead performance for a given power budget (eg, how much performance can I get at 15w? 30w? etc...) Otherwise you can trivially win 100% of performance/watt comparisons by just setting clocks to the limit of the lowest usable voltage level. For example compare the 7950X to the 7950X@65w using the officially supported eco mode option: https://www.anandtech.com/show/1758…

>Performance per watt is a bad metric.

It isn't. It needs context.

Sure, you can get an Intel Celeron to have more perf/watt than an M1 if you give the Celeron low enough wattage.

The key here is the absolute performance.

In this case, both the M3 and the X Elite are not only significantly more efficient than both Zen4 and Zen5 in ST, they are also straight up faster while being more efficient.

Re: AMD's Strix Point: Zen 5 Hits Mobile

#174
post #163

Earlier quoted context omitted.

Anandtech shows[0] that M3 is massively ahead in integer performance, but slightly behind in float performance on Spec 2017. Integer workloads are by far the most common, but they tend to not scale to multiple cores very well. Most workloads that scale well across cores also benefit from big FP/SIMD units too. Put another way, the real issue with R24 is that it makes HX370 look better than it would look in more norma…

> that M3 is massively ahead in integer performance The M3 is certainly an impressive chip, but note that it's only massively ahead in some of the int tests. It's not a consistent gap. > Integer workloads are by far the most common, but they tend to not scale to multiple cores very well. The HX370 does better than the Me in specint MT though. But regardless the anandtech results paint a much closer picture than the s…

The HX370 should win in SPECINT MT. It has 12 cores to the M3's 8 cores and it runs at significantly higher power.

Compare HX370 SPECINT MT To an M3 Pro and let's see the results.

Re: AMD's Strix Point: Zen 5 Hits Mobile

#175
post #136

Earlier quoted context omitted.

Laptops vastly outsell desktops, so this tradeoff means hurting the majority of your customers to please a small minority. Servers also care about perf/watt a LOT and they are the highest profit margin segment. Why would AMD choose a target that hurts the majority of their market unless there wasn't another good option available?

The architecture started in desktop space and data center/mobile was an afterthought up until Intel shitting the bed repeatedly. If they redesigned from ground up they could probably get better instructions/watt but that would look terrible if it wasn't accompanied by a perf boost over previous generation. Just like Apple doesn't seem to scale well with more power.

> Just like Apple doesn't seem to scale well with more power.

How do you know this? When has Apple ever given 400w to the M3 Max like the 14900KS can get up to?

PS. An M4 running at 7w is faster in ST than a 14900KS running in 250w+.

Re: AMD's Strix Point: Zen 5 Hits Mobile

#176
post #64
post #62

Earlier quoted context omitted.

https://www.notebookcheck.net/AMD-Zen-5-Strix-Point-CPU-anal... They got those kinds of numbers across multiple systems. You can take it up with them I guess. I didn't even mention one of these systems was peaking at 59w on single-core workloads.

I see what's going on, they have two HX370 laptops: Laptop MC score Avg Power P16 1213 113 W S16 921 29 W M3 Pro 1059 (30 W?) They don't have M3 Pro power numbers, but I assume it is somewhere around 30W, seems like S16 has similar power efficiency as HX 370 at 30 W. Any more power, and the CPU is much less power efficient, 300% increase in power for 30% increase in performance.

This is true for every CPU. Past a certain point power consumption scales quadratically with performance.

Re: AMD's Strix Point: Zen 5 Hits Mobile

#177

Earlier quoted context omitted.

The M1 was made on 5nm which have long been available to AMD and other competitors in volume.

Fast is relative. The Ryzen HX 370 has a TDP configurable down to 15W and at that power level it could be run fanless and would be faster than the M1, but it's still faster yet if you give it 54W and raise the clock speed.

Is that the chip AMD just released? Isn't the M1 about 4 years old?

Re: AMD's Strix Point: Zen 5 Hits Mobile

#178
post #32

Earlier quoted context omitted.

> But with the sole exception of the Steam deck Uuh wut? The Steam Deck is like 3-generation-old hardware in mobile Ryzen terms. In a lot of ways it's similar to a pared-back 4800u with fewer (and older) cores, and a slightly bumped up GPU. To me it's kinda the opposite. Excluding the Steam Deck, I think most of AMD's Ultrabook APUs have been very close to the products Apple's made on the equivalent nodes. Even on 7n…

Steam Deck might be behind in terms of hardware but in terms of software it's way beyond your typical x86 linux system power efficiency, and dare I say it's doing better than windows machines with the typical shoddy bioses and drivers, specially when you consider all the extraneous services constantly sapping varying amounts of cpu time. All that contributes to make the SD punch well above its weight.

My Alienware M15 Ryzen edition gets 7-8W power consumption by just running "sudo powertop --autotune". Basically all of the power efficiency stuff in the Steam Deck apply to other Ryzen systems and are in the mainline kernel.

Re: AMD's Strix Point: Zen 5 Hits Mobile

#179

One of these has to be true (or both true): 1. ARM is inherently more efficient than x86 CPUs in most tasks 2. Nuvia and Apple are better CPU designers than AMD and Intel Here are results from Notebookcheck: Cinebench R24 ST perf/watt * M3: 12.7 points/watt * X Elite: 9.3 points/watt * AMD HX 370: 3.74 points/watt * AMD 8845HS: 3.1 points/watt * Intel 155H: 3.1 points/watt In ST, Apple is 3.4x more efficient than Zen…

Why are you comparing a chip optimized for performance with a chip optimized for efficiency? Take an Ultrabook Zen5, not the HX370.

Re: AMD's Strix Point: Zen 5 Hits Mobile

#180
post #7

Earlier quoted context omitted.

ARM got a lot of hype since the release of the M1, but most users only compared it to the terrible Intel MBPs. Ryzen mobile has been consistently close to Apple silicon perf/watt for 5 years. But got little press coverage. Hype can be really decorrelated from real world performance.

I think that's because all the press talks about actual battery life per laptop and the Apple Silicone laptops ship with literally double the size battery of any AMD based laptop without a discrete GPU. So while the efficiency may be close, actually perceived battery life of the Mac will he more than double when you also consider the priority Apple puts into their power control combined with a larger overall battery.

[dead]
Post reply on HN