11–20 of 234 posts
A lot of the pthreads books I see are from the late 90s. Is there a more recent reference? What's the best way to write cross-platform (e.g. not Grand Central Dispatch) multithreaded apps with these new chip architectures?
After upgrading our app's dependency chain to run native arm64 builds (which took a bit of googling) webpack's incremental build time on our app is down to 116ms from 983ms on my 2016 Macbook Pro. Over 8x faster.
Our Tensorflow.js (webgl) models that previously ran about 8fps in the browser are now running at the camera's native 30fps framerate. (Similar to my desktop 2080ti.)
Earlier quoted context omitted.
Like sibling comment says, it’s more efficient. It allows those cores to sort of pretend they’re ECs. It also reserves those PCs for bursty workloads which would otherwise be contentious for cache and memory bandwidth in an evenly balanced scheduler.
Is it basically giving programs some automatic core affinity or are the unused cores meant to be unused until the first set are saturated? I guess also, are the 4 unused cores always the same?
As far as which cores are demoted… I definitely don’t know enough to speculate. If favoring the same set would affect longevity of the device, they’d rotate. If not it’s simpler not to do that. I have no idea which is more likely.
I am curious, since Intel is relying more and more on P and E cores as well, is there any reference or research available for optimizing multithreaded userland process tasks with varying QoS? A lot of the pthreads books I see are from the late 90s. Is there a more recent reference? What's the best way to write cross-platform (e.g. not Grand Central Dispatch) multithreaded apps with these new chip architectures?
I am curious, since Intel is relying more and more on P and E cores as well, is there any reference or research available for optimizing multithreaded userland process tasks with varying QoS? A lot of the pthreads books I see are from the late 90s. Is there a more recent reference? What's the best way to write cross-platform (e.g. not Grand Central Dispatch) multithreaded apps with these new chip architectures?
I think people are just now starting that research and blog posts like this one are all we have so far.
https://scholar.google.com/scholar?hl=en&as_sdt=0%2C33&q=asy...
I am curious, since Intel is relying more and more on P and E cores as well, is there any reference or research available for optimizing multithreaded userland process tasks with varying QoS? A lot of the pthreads books I see are from the late 90s. Is there a more recent reference? What's the best way to write cross-platform (e.g. not Grand Central Dispatch) multithreaded apps with these new chip architectures?
I am curious, since Intel is relying more and more on P and E cores as well, is there any reference or research available for optimizing multithreaded userland process tasks with varying QoS? A lot of the pthreads books I see are from the late 90s. Is there a more recent reference? What's the best way to write cross-platform (e.g. not Grand Central Dispatch) multithreaded apps with these new chip architectures?
For the Mac, I believe you have equivalent access for scheduling between posix and GCD, but the scheduling configuration is likely way more approachable in GCD.
Also: On M1, there is an added capability to run in a stricter memory model to speed up x86_64 emulation. This only is available on the performance cores, which is one of the reasons people observe non-native code draining the battery quicker.
In my usage, which is game development with Unity, I haven't really been particularly impressed with the performance improvements on my 10-core M1 Pro machine. I'm sure most of the blame is due to Unity (the app is a buggy mess), but it definitely took the initial "wow this is magic" down to reality very quickly for me.
With that said, there is a huge M1 hype on HN. It reminds me of the 64-bit ARM hype when someone benchmaked encryption (because ARMv8 has AES instructions) and everyone were made to belive that the new iPhone would be 3-4 times faster.