Hacker News Reader

I don't disagree with the wider point but

> I could replace my 6-year old Intel i7-3770 desktop with 32GB of RAM, but what's out there that's significantly better at a reasonable cost?

AMD Ryzen 7 1700 for $200. ~10% faster single core and you get 8C/16T. DDR4 RAM is quite expensive, though.

(closest available benchmarks, 1700 is about 3% slower than 2700) [0]: https://www.anandtech.com/bench/product/2111 [1]: https://www.anandtech.com/bench/product/551

The Ryzen is better, as another commenter pointed out with the passmark scores. Is it better enough for me to actually go out and buy it?

The system the i7-3770 replaced was a 4 year old dual-core, with (IIRC) just 1GB of RAM. The i7 was a dramatic improvement, but I don't feel that the Ryzen would be a dramatic improvement.

And that's the issue. It is not just me being a little unimpressed with current offerings, or me just being cheap. The issue is that there is even a valid discussion about replacing a 6 year old desktop. In the past, in the 1990's and 2000's, it wasn't a question. You had to upgrade because you wanted to run Windows XP decently, for example.

do keep in mind though there is the perspective that we're heading back into the 70s phase where the end user owns dumb terminals and connect into semi-centralized servers. The place where performance is going to be killer is in the server space, which clearly amd is starting to get the jump on intel again, and you are (presumably, don't know what you do as a dev) not the target market. Heck, even if you're a hyperscaler, you might not be the target market, since it might be the likes of AWS.

Growth in demand for compute will continue to drive sales for the foreseeable future.

In the "old days", there was also demand from upgrades, but we're seeing that tapering off. And that should be a big concern for the investors.

> DDR4 RAM is quite expensive, though.

True, but it is a major upgrade.

The i7-3770 supports two channels of DDR3-1600 memory, or 25.6 GB/s of memory bandwidth. A Ryzen processor (or other recent generation) supports DDR4-3200, which literally doubles your memory bandwidth. Fortunately or unfortunately, we now have much faster PCIe SSDs so memory bandwidth isn't as crucial for normal use, but a 100% improvement is a much better reason to upgrade than a measly 10% bump.

Single core speed is near equal on 3770 and 1700 but you get 2x the cores with 1700.

So if you can benefit from 8Cores (ie compiling for one) then it is a nice upgrade.

If you rarely utilize all 4 cores on your 3770 then it is a pointless upgrade.

That is the thing, going from a single core to 2 core pretty much benefited everyone. Heck PentiumHT was a big thing.

Going from 2 core to 4 cores took longer to show benefits and 4 cores to 8 cores is going to be slower still to show benefits for most users.

At the end of the day single core speed has been stagnating for the last 6 years every since Sandy Bridge which was the last big jump.

I mean I plan on buying AMDs ThreadRipper 2 32 core chip since it will be of benefit to me for running 100 copies of the same program.

Still those 32 cores will not help with regular computing.

Newegg had the 1700 for an insane $159 today.

Intel i7-3770 Passmark Score (~6yrs old, was ~$320): 9300 [1]

AMD Ryzen 7 2700 Passmark Score (<1yr old, ~$290): 15382 [2]

That's a 65% improvement in benchmark performance. So not the "doubling" trend I was used to growing up, but not insignificant.

[1] https://www.cpubenchmark.net/cpu.php?cpu=Intel+Core+i7-3770+...

[2] https://www.cpubenchmark.net/cpu.php?cpu=AMD+Ryzen+7+2700&id...

If you look at the smaller print on those two pages, the Ryzen 7's single core performance is a little under the I7's, meaning if your workload doesn't take advantage of the extra cores then this only roughly an equal move.

I too have a i7-3770 and it runs fantastic. I've only just realised that it is actually 6 years old, theres just not the incentive to upgrade that there once was.

It's even faster than the newest I7 8650U

That is true for general purpose computing. However, AMD has been diversifying away from client (laptops, desktops). There is a large and growing market for semi-custom designs: game consoles, CPU+GPU cloud computing, DaaS virtualization, embedded systems. Since these are markets with large companies competing against each other there will be continual demand for incremental power and performance improvements that an individual consumer may not care about. A company that can rapidly mix and match IP to customer needs will have an advantage.

Have you looked at the price and performance for AMD's threadripper and epyc series? I agree that we're nearing the end of shrinking process nodes, but their architecture is incredibly innovative

We may discover the stagnant generation-to-generation performance uplift over the past ~10 years was mostly due to lack of competition in the market.

I don't think that has been the case.

The stuff I've read about the new process nodes from the last decade indicate that moving to those hasn't been easy. And the chip designers haven't had it easy either, with each new process comes a longer and longer list of restrictions and other difficulties.

Transitioning an existing CPU design (for example) to a new process node was never easy per se, but it has never been harder than it is these days. That's part of the slowdown.

That's why AMD innovated on a new CPU design, because what we've been using doesn't cut it anymore. Look at their CCX architecture and infinity fabric

I'm hoping that we'll see innovations such as Mill Computing's CPU get to the market, and it should provide a dramatic improvement in efficiency / performance for a given die area.

And that's great. But that'll also be a one-time thing in a sense. After it has moved to the latest process node, it will be on the same trajectory as other architectures.

Intel has a lot of interesting stuff outside of CPU area, for example NVM

Advancement of that is also dependent on silicon lithography.

Again, what's the valuation of Intel if (in the future) we see them churning out the same 1GB NVMe cards at the same cost with the same performance? The valuation of Intel and every other tech company is based on future growth potential.

Neither modern NAND (3D) nor 3D XPoint are directly dependent on planar silicon scaling.

That's true. 3D won't help with processors as much, because of heat dissipation issues, but storage will benefit.

However, the planar silicon scaling is what primarily enables cost reduction for production. I expect the (total device) density to continue to increase with the 3D tech, but cost will go up with capacity increases. Maybe not linearly though, because you don't have to pay for extra packaging.

I would not rule out 3D from processors yet. Such an invention would be able to reduce die size and likely cost. Heat density is probably the real problem and may need some additional inventions.

The 3D memories will probably see some planar (x-y) scaling, they just don't need all of their scaling from it. 3D scaling will still increase bits/die area, and thus reduce $/bit. If doubling the stacking height doubles capacity but adds 30% to wafer cost with extra processing steps, its still much more efficient than 100% cost for two wafers of the previous design.

Scaling efficiency shouldn't be too dissimilar from planar scaling, at least until the next wall is hit.