Hacker News Reader

Comment by savant_penguin | Hacker News Reader

Really curious, why is 4% improvement huge?

"Huge" means different things in different contexts. A compiler optimisation that delivered a 4% increase in speed for a whole class of well-tuned C programs would be regarded as huge by people who follow compiler technology, but would not strike most users of computers as a big deal. I take it "huge" is meant in this sense of extraordinary within a class of potential improvements.

If you can accumulate a series of 4% improvements, then even the computer consumer will start to see the significance.

A 4% improvement of the 100m dash world record would have been considered phenomenal, I imagine.

This reminded me of the 4 minute mile. The first 4 minute mile was a 3:59 run by Roger Bannister in 1954. Prior to that, the record was a 4:01 run in 1945.

A 4% improvement on the 4:01 would be a 3:51. A 3:51 wasn't achieved until 1966, about 20 years later.

So 4% can be quite a jump!

Extending your point, 4% more would go down to just under 3:42.... which has not yet happened, over a half century later.

To put that into context, Bolt's 9.58s (current WR, considered phenomenal in and of itself, I think?) is about 1.7% faster than Powell's 9.74s (last pre-Bolt WR).

A 4% improvement on Bolt's 9.58s would be about 9.19s - probably not something we'll see for several decades, if ever.

I wonder if I’ll ever see a Bolt again in my lifetime.

Such dominance and grace.

He jogged over the line with that record too.

I can’t find where the 4% number comes from, but I expect that it comes from a micro benchmark that does little more than futex calls. Reason: if it is from a benchmark that represents real-world use, real-world use must spend at least 4% of its time in futex calls. If that were the case, somebody would have seen that, and work would have been spent on this.

So no, this won’t give you 4% in general.

> If that were the case, somebody would have seen that, and work would have been spent on this.

I would think that the linked patch is good evidence that work is being spent on this.

The microbenchmark part is part of the article, no idea why the downvotes here.

Because the benchmark isn't doing what GP days it does.

From the lkml post, it's neither from a real-world case nor from an especially constructed futex benchmark, but from an existing kernel benchmark where it was thought it would be interesting to see how it performed with the new call.

Because you don't have to change one line of your previously running software to get this benefit or replace your hardware. Of course, will need a new version of the kernel and wine, but that is a matter of time to hit distro repositories. Also, consider that this will accumulate when combined with new user space libs, servers, compilers, drivers... Software will improve without any change just by keeping your distro updated.

Yes, a 4% improvement is huge.

Well, it's a relative measure. There's been a ton of optimization already. All the low-hanging fruit is gone. It's probably been a long time since a single optimization gained 4%.

I don't know much about Wine, but I'm speaking in generalities, but I've worked jobs where we spend weeks to get <10% performance increases. Very often that last bit of optimization is the hardest part.

Intel Xeons have huge price differences at the top tier for relatively minor performance differences.

So if you get 4% for free here, that could mean hundreds of dollars savings compared to having to buy the next tier hardware. Multiplied by the number of Intel customers.

4% could mean the difference between "I can still use my old computer" and "I need to buy an upgrade".

The price difference is due to artificial market segmentation, for example only xeons support ecc. It is not due to performance.

(consumer chips are usually basically identical, just with functionality disabled)

This is interesting. Does anyone know of previous figures on Windows virtualization improvement?

It's not 4% improvement for the wine use case, it's 4% improvement in existing synthetic benchmarks for the futex syscall. And a 21% regression in performance in another synthetic benchmark.

It's likely the wine WMO implementation is getting a much more significant increase in performance than 4%, but the patch description doesn't provide numbers.

Reply on news.ycombinator.com