Oh dear. This is going to push up wafer costs even further. People still expecting GPUs to return to pre-pandemic price scales won't be happy about this.
With more expensive wafers exerting further downward pressure on die sizes, we could see core counts start to level off and per-core generational performance improvements dropping back down into the single-digit %'s.
The future of computing feels hot & loud, as we increasingly resort to frequency as a means of extracting every last drop of performance from ever smaller and more expensive chips.
Haven't we been having "hotter and louder chips as we increasingly resort to frequency as a means of extracting every last drop of performance from ever smaller and more expensive chips," since CPUs first existed? The 8080 was 2Mhz.
To some extent I agree. But we also saw "good enough" performance allow for different form factors. I'm thinking of smartphones, tablets, but also hybrids (thinking of the surface that I daily drive). So while high performance desktop power has increased, it feels like power consumption has decreased (or at least efficiency has increased--thinking of race to idle).
The "race to idle" hypothesis is a fallacy. Chips & Cheese looked at the Joules consumed during completion of two workload classes, across multiple different types of cores and clock speeds.
The faster cores nearly always used more power, except when the E-cores were at the edge of their operating window. And, except for a couple slight bumps, all cores used more power to complete the workload faster. The other exception to that was at the very bottom of the frequency range, where it seems you need to run fast enough to overcome what are probably some fixed overheads.
I think the "race to idle" notion probably dates back to an era when CPUs weren't nearly as good at power-scaling.
It only shows it's a hit and miss on Alder Lake, which was their first beta of the new architecture, it's been shown to be true on other architectures.
No, look more closely. It's a bit confusing because the article contains a mix of different metrics - both performance and energy. The "race to idle" question is addressed by the energy graphs, so make sure you're looking at the plots labeling the Y-axis is in Joules.
Now that we're looking at the right plots, you can see that not only are the Gracemont and Golden Cove cores benchmarked, but also Skylake, and two different incarnations of Zen 2. In every case, we see higher clockspeeds consistently resulting in consuming more energy to complete the workload, with one notable exception.
The notable exception is the chiplet-based of Zen 2 CPU, which has a very slightly negative slope before it turns sharply upward. Because the monolithic Zen 2 APU doesn't exhibit the same properties, we can say this is more likely an artifact of the chiplet implementation than anything about the Zen 2 microarchitecture.
Let's put the shoe on the other foot: how about you show us a modern CPU where "race to idle" *does* apply. I doubt you can.
For about a decade, Intel's CPUs had pretty monotonic generational decreases in TDPs. Once Zen launched, Intel reversed course and each new generation has been at least as hot as the one prior.
If dies become smaller and more expensive, that only increases the incentives to juice them harder. Even "efficiency" cores will tend to be optimized more for area-efficiency than power-efficiency
Only those on the left side of the demand curve aka latest and greatest. For everyone else there's enough in the pipeline, new and used to keep people happy.
It seems to me that *everything* will get more expensive. The cutting-edge is the most affected, but even mid-range, trailing-edge, and the used market won't be unaffected.
Let's all ignore the multiple trillions of dollars the Democrats pumped into the economy including handing out thousands of dollars to most Americans in early 2021! The effects this would have were obvious at the time (especially if you listen to Ben Shapiro's podcast!). And here we are 2 years later, and articles just point to Russia and supply chains.
Inflation has hit nearly all countries. Inflation in the US has actually been *lower* than in most.
If you look at the *data* on inflation, you can clearly see the sharp uptick, in countries around the world, at the point where Russia launched its invasion.
My advice: stop getting your news from sources with a clear political agenda.
Do you think handing thousands of dollars to nearly everyone will have no effect? Come on. Inflation is too much money chasing too few goods. Why would you ignore the "too much money" portion? And where's the political agenda.
If it helps you understand, imagine a more extreme example: $50k is handed out to every American household. People would be buying new cars left and right and dealers would raise prices drastically, and people would still pay it. People would also buy new computers, video cards, and all sorts of other stuff. Companies would easily jack up their prices since people have so much cash. People's buying power would be really high initially, but much worse in the longer run when their short-term cash runs out and prices stay inflated. That's where we are now. A bag of Doritos costs nearly 5 bucks and you get 2/3rds the amount. Home prices are up 50% where I live. RTX4070's sell for $800. If you like this, vote accordingly (Democrat).
We're not *in* that imaginary world. Real-world macroeconomics typically defies thought experiments. It's a complex system, a bit like biology. You need to be data-driven, if you want to have any chance at understanding what are truly the dominant factors.
I'm not defending government handouts, but I think some of the pandemic assistance was justified. The main thing that bothers me is motivated reasoning. And I see a lot of that going on, trying to leverage public dissatisfaction with high inflation to support a political agenda.
If you take the hypothesis: "inflation was caused by too much government government handouts", then you should test that against other countries with more and less government support. You should find a very direct correlation between the amount of handouts and the inflation rate. Yet, the data doesn't align with this, at all. The countries currently suffering the highest inflation often had little or no government support.
The other thing you can do is test the hypothesis that Russia's invasion of Ukraine is contributing to inflation, and look at the inflation rate shortly before & after, in a variety of different countries. Those most heavily dependent on Russia or Ukraine for food, fuel, or fertilizer suffered the greatest shocks, but the effects of global trade meant these commodities got more expensive everywhere. There are other key raw materials & industrial components that were also disrupted by the war, such as helium, which is a critical input for chip manufacturing.
This is definitely a complex problem and not obvious to understand cause-and-effect. Now, regarding your comment "The countries currently suffering the highest inflation often had little or no government support." - I'm sure it depends on how much is imported and exported, and how much new loose cash enters the market.
It seems to me that covid shutdowns impacted supplies of many things, and then the federal government injecting trillions including literally handing thousands to everyone just increased the numerator of the simple inflation equation. I suspect the effect propagated worldwide due to the global economy.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
15 Comments
Back to Article
mode_13h - Thursday, March 16, 2023 - link
Oh dear. This is going to push up wafer costs even further. People still expecting GPUs to return to pre-pandemic price scales won't be happy about this.With more expensive wafers exerting further downward pressure on die sizes, we could see core counts start to level off and per-core generational performance improvements dropping back down into the single-digit %'s.
The future of computing feels hot & loud, as we increasingly resort to frequency as a means of extracting every last drop of performance from ever smaller and more expensive chips.
ballsystemlord - Thursday, March 16, 2023 - link
Haven't we been having "hotter and louder chips as we increasingly resort to frequency as a means of extracting every last drop of performance from ever smaller and more expensive chips," since CPUs first existed? The 8080 was 2Mhz.ingwe - Thursday, March 16, 2023 - link
To some extent I agree. But we also saw "good enough" performance allow for different form factors. I'm thinking of smartphones, tablets, but also hybrids (thinking of the surface that I daily drive). So while high performance desktop power has increased, it feels like power consumption has decreased (or at least efficiency has increased--thinking of race to idle).mode_13h - Friday, March 17, 2023 - link
The "race to idle" hypothesis is a fallacy. Chips & Cheese looked at the Joules consumed during completion of two workload classes, across multiple different types of cores and clock speeds.https://chipsandcheese.com/2022/01/28/alder-lakes-...
The faster cores nearly always used more power, except when the E-cores were at the edge of their operating window. And, except for a couple slight bumps, all cores used more power to complete the workload faster. The other exception to that was at the very bottom of the frequency range, where it seems you need to run fast enough to overcome what are probably some fixed overheads.
I think the "race to idle" notion probably dates back to an era when CPUs weren't nearly as good at power-scaling.
Zoolook - Friday, March 17, 2023 - link
It only shows it's a hit and miss on Alder Lake, which was their first beta of the new architecture, it's been shown to be true on other architectures.mode_13h - Friday, March 17, 2023 - link
No, look more closely. It's a bit confusing because the article contains a mix of different metrics - both performance and energy. The "race to idle" question is addressed by the energy graphs, so make sure you're looking at the plots labeling the Y-axis is in Joules.Now that we're looking at the right plots, you can see that not only are the Gracemont and Golden Cove cores benchmarked, but also Skylake, and two different incarnations of Zen 2. In every case, we see higher clockspeeds consistently resulting in consuming more energy to complete the workload, with one notable exception.
The notable exception is the chiplet-based of Zen 2 CPU, which has a very slightly negative slope before it turns sharply upward. Because the monolithic Zen 2 APU doesn't exhibit the same properties, we can say this is more likely an artifact of the chiplet implementation than anything about the Zen 2 microarchitecture.
Let's put the shoe on the other foot: how about you show us a modern CPU where "race to idle" *does* apply. I doubt you can.
mode_13h - Friday, March 17, 2023 - link
> Haven't we been having "hotter and louder chipsFor about a decade, Intel's CPUs had pretty monotonic generational decreases in TDPs. Once Zen launched, Intel reversed course and each new generation has been at least as hot as the one prior.
If dies become smaller and more expensive, that only increases the incentives to juice them harder. Even "efficiency" cores will tend to be optimized more for area-efficiency than power-efficiency
Threska - Thursday, March 16, 2023 - link
Only those on the left side of the demand curve aka latest and greatest. For everyone else there's enough in the pipeline, new and used to keep people happy.mode_13h - Friday, March 17, 2023 - link
It seems to me that *everything* will get more expensive. The cutting-edge is the most affected, but even mid-range, trailing-edge, and the used market won't be unaffected.AnnonymousCoward - Monday, March 27, 2023 - link
Let's all ignore the multiple trillions of dollars the Democrats pumped into the economy including handing out thousands of dollars to most Americans in early 2021! The effects this would have were obvious at the time (especially if you listen to Ben Shapiro's podcast!). And here we are 2 years later, and articles just point to Russia and supply chains.mode_13h - Tuesday, March 28, 2023 - link
OMG, this again.Inflation has hit nearly all countries. Inflation in the US has actually been *lower* than in most.
If you look at the *data* on inflation, you can clearly see the sharp uptick, in countries around the world, at the point where Russia launched its invasion.
My advice: stop getting your news from sources with a clear political agenda.
AnnonymousCoward - Tuesday, March 28, 2023 - link
Do you think handing thousands of dollars to nearly everyone will have no effect? Come on. Inflation is too much money chasing too few goods. Why would you ignore the "too much money" portion? And where's the political agenda.AnnonymousCoward - Wednesday, March 29, 2023 - link
If it helps you understand, imagine a more extreme example: $50k is handed out to every American household. People would be buying new cars left and right and dealers would raise prices drastically, and people would still pay it. People would also buy new computers, video cards, and all sorts of other stuff. Companies would easily jack up their prices since people have so much cash. People's buying power would be really high initially, but much worse in the longer run when their short-term cash runs out and prices stay inflated. That's where we are now. A bag of Doritos costs nearly 5 bucks and you get 2/3rds the amount. Home prices are up 50% where I live. RTX4070's sell for $800. If you like this, vote accordingly (Democrat).mode_13h - Thursday, March 30, 2023 - link
> imagine a more extreme exampleWe're not *in* that imaginary world. Real-world macroeconomics typically defies thought experiments. It's a complex system, a bit like biology. You need to be data-driven, if you want to have any chance at understanding what are truly the dominant factors.
I'm not defending government handouts, but I think some of the pandemic assistance was justified. The main thing that bothers me is motivated reasoning. And I see a lot of that going on, trying to leverage public dissatisfaction with high inflation to support a political agenda.
If you take the hypothesis: "inflation was caused by too much government government handouts", then you should test that against other countries with more and less government support. You should find a very direct correlation between the amount of handouts and the inflation rate. Yet, the data doesn't align with this, at all. The countries currently suffering the highest inflation often had little or no government support.
The other thing you can do is test the hypothesis that Russia's invasion of Ukraine is contributing to inflation, and look at the inflation rate shortly before & after, in a variety of different countries. Those most heavily dependent on Russia or Ukraine for food, fuel, or fertilizer suffered the greatest shocks, but the effects of global trade meant these commodities got more expensive everywhere. There are other key raw materials & industrial components that were also disrupted by the war, such as helium, which is a critical input for chip manufacturing.
AnnonymousCoward - Friday, March 31, 2023 - link
Thanks for your thoughtful insight.This is definitely a complex problem and not obvious to understand cause-and-effect. Now, regarding your comment "The countries currently suffering the highest inflation often had little or no government support." - I'm sure it depends on how much is imported and exported, and how much new loose cash enters the market.
It seems to me that covid shutdowns impacted supplies of many things, and then the federal government injecting trillions including literally handing thousands to everyone just increased the numerator of the simple inflation equation. I suspect the effect propagated worldwide due to the global economy.