Sign in

forked-franz.bsky.social

@forked-franz.bsky.social
89 followers 35 following 9 posts
PostsRepliesMedia
Reposted by @forked-franz.bsky.social
Brice Dutheil @bricedutheil.bsky.social · 26/02/2026
More hot bytecode! `jctools-core-jdk11` 4.0.6 is now out. This contains `VarHandle` queues generated from `Unsafe` queues to provide similar performance but within JDK APIs. Thanks to github.com/amarziali @datadoghq.com for the huge contribution, and @forked-franz.bsky.social for helping to land!
github.com
amarziali - Overview
amarziali has 29 repositories available. Follow their code on GitHub.
131
Reposted by @forked-franz.bsky.social
Brice Dutheil @bricedutheil.bsky.social · 03/06/2025
github.com/netty/netty/... This is only needed for 4.1.x, in 4.2.x we are able to fix this in another way that does not require the usage of sun.misc.Unsafe
github.com
Re-enable sun.misc.Unsafe by default on Java 24+ by chrisvest · Pull Request #15296 · netty/netty
See https://github.com/netty/netty/wiki/Java-24-and-sun.misc.Unsafe for more information. Motivation: In #14943 we disabled Unsafe by default on Java 24+, to avoid producing warnings from the JVM. ...
022
Reposted by @forked-franz.bsky.social
Devoxx Belgium @devoxx.com · 02/06/2025
The Devoxx Belgium 2025 CFP is now OPEN! ➡️https://dvbe25.cfp.dev This year we’re zooming in on Java 25 & AI Agents🤖 Got insights, hacks, or bold ideas? Share them with the dev community at #Devoxx 🔥
23422
Reposted by @forked-franz.bsky.social
Brice Dutheil @bricedutheil.bsky.social · 31/05/2025
From @forked-franz.bsky.social : These days, lot of @openjdk.org loom fun: github.com/franz1981/Ne... Do you know that VT schedulers are inherited? Which means that if you have your own and clinit some Key OpenJDK class, u risk to make your scheduler to leak into some JDK class (!)
github.com
011
Reposted by @forked-franz.bsky.social
Brice Dutheil @bricedutheil.bsky.social · 30/05/2025
Today I learned that in IBM J9 not all classes are the same: > "A ROM Class roughly corresponds to the contents of a .class file; it is not a complete class because it only references its superclass and implemented interfaces by name." blog.openj9.org/2018/11/08/a... github.com/eclipse-open...
blog.openj9.org
Ahead Of Time Compilation: Validation
This post finally gets to the much alluded to topic of Validation. As mentioned in a previous post, Validation is one of the two actions the JVM must perform to generate and execute AOT code; …
031
Reposted by @forked-franz.bsky.social
Sy Brand @tartanllama.xyz · 19/05/2025
❌ printf debugging ✅ segfault debugging
2581
Reposted by @forked-franz.bsky.social
Quarkus @quarkus.io · 19/05/2025
⏰ Starting soon! Join us for Quarkus Insights Ep. #206 as Andrea Peruffo & Hiram Chirino join us to talk about WebAssembly (WASM) & how it powers a wide range of apps & reveals potential for unique integrations & performance gains, in Java & Quarkus. bit.ly/quarkusinsig...
002
Reposted by @forked-franz.bsky.social
Jean-Philippe Bempel @jpbempel.bsky.social · 13/05/2025
TIL: since jdk22 you can use the JVM option -XX:LogClassLoadingCauseFor=com.mycompany.MyClass in conjunction with -Xlog:class+load+cause* to find out the stacktrace that triggers the load of the specify class. see github.com/openjdk/jdk/...
github.com
8193513: add support for printing a stack trace on class loading by dougxc · Pull Request #14553 · openjdk/jdk
In the development of libgraal, it has been very useful to see why a given class is loaded (e.g., trying to reduce startup time by avoiding unnecessary eager class loading). One way to do this is t...
11910
Reposted by @forked-franz.bsky.social
Jean-Philippe Bempel @jpbempel.bsky.social · 13/05/2025
Was fighting a "LinkageError: attempted duplicate class definition" for 3 days... took me 2 seconds with that option!
111
Reposted by @forked-franz.bsky.social
Iker Jiménez @ijimenez.bsky.social · 11/05/2025
The podcast episodes by @adambien.blog and @forked-franz.bsky.social talking low level Java performance stuff are 🙌🏻🙌🏻 I hope they do more airhacks.fm#episode_343 airhacks.fm#episode_340
airhacks.fm
airhacks.fm podcast
podcast with adam bien
143
Reposted by @forked-franz.bsky.social
Sy Brand @tartanllama.xyz · 04/05/2025
Showing kiddo Porco Rosso
An anthropomorphic pig in a trench coat telling a man in military garb "I'd rather be a pig than a fascist"
3481
Reposted by @forked-franz.bsky.social
Sy Brand @tartanllama.xyz · 03/05/2025
A modified version of this: github.com/rigtorp/MPMC...
github.com
GitHub - rigtorp/MPMCQueue: A bounded multi-producer multi-consumer concurrent queue written in C++11
A bounded multi-producer multi-consumer concurrent queue written in C++11 - rigtorp/MPMCQueue
112
Reposted by @forked-franz.bsky.social
Sy Brand @tartanllama.xyz · 03/05/2025
(We need the queue to be lock-free even though the kernel is single-threaded because we may want to schedule a task from an interrupt handler, and if the interrupt fires during a task schedule that held a lock on the queue, the kernel would deadlock)
161
Reposted by @forked-franz.bsky.social
Sy Brand @tartanllama.xyz · 03/05/2025
The idea is that I have a cooperatively-scheduled single-threaded OS kernel that uses C++20 coroutines as its means of expressing tasks. I want to be able to await on asynchronous tasks, and also manually yield back to the scheduler in the case of long-running computations. Some examples:
// memcpy that yields intermittently to avoid blocking the kernel thread
task<std::size_t> async_memcpy(void* destination, const void* source, std::size_t size) {
    constexpr std::size_t chunk_size = 4096;
    for (std::size_t offset = 0; offset < size; offset += chunk_size) {
        //copy a chunk of data, then...
        co_await reschedule; //reschedule the coroutine
    }
    co_return size;
}

task<unique_ptr<fat32>> fat32::mount(
  		driver::block_device& device, std::string_view mount_point) {
    auto fs = unique_ptr<fat32>(new fat32());
    // this should suspend fat32::mount until the read is complete
    auto boot_sector = co_await device.read(0, 1); //this eventually calls async_memcpy
    // etc.
}

task<> mount_initramfs() {
    // find initramfs memory, then...
    // this should suspend mount_initramfs until the mount is complete
    auto initramfs = co_await fat32::mount(initramfs_mem, "/");
    if (!initramfs) {
        com1.write("Failed to mount initramfs\n");
        co_return;
    }
    com1.write("Initramfs mounted at /\n");
}
171
Reposted by @forked-franz.bsky.social
Taki Udon @takiudon.bsky.social · 30/04/2025
CRT support The performance is great and this is very easy to use for younger kids.
101247
Reposted by @forked-franz.bsky.social
Sy Brand @tartanllama.xyz · 02/05/2025
If anyone knows of resources for this, I am very much interested, as I am more or less fumbling around. Getting a simple scheduler based on a lock free MPMC queue that works for basic coroutines was pretty straightforward, but as soon as those coroutines nest it becomes very headache-inducing.
4111
Reposted by @forked-franz.bsky.social
Sy Brand @tartanllama.xyz · 02/05/2025
Trying to implement an OS-level scheduler for C++20 coroutines that supports symmetric transfer and my brain is melting
4353
Reposted by @forked-franz.bsky.social
chipsandcheese.bsky.social @chipsandcheese.bsky.social · 30/04/2025
Hello you fine Internet folks, Today's article we are deep-diving into the architecture of Zhaoxin's latest CPU series, the KX-7000. We compare the KX-7000 to the KX-6000 along with some older x86 CPUs. Hope y'all enjoy! open.substack.com/pub/chipsand... old.chipsandcheese.com/2025/04/30/z...
open.substack.com
Zhaoxin’s KX-7000
Zhaoxin is a Chinese x86 CPU designer.
071
Reposted by @forked-franz.bsky.social
Edoardo Vacchi @evacchi.dev · 30/04/2025
I finally got my hard copy of @tartanllama.xyz's Building a Debugger and boy is it a treat! Not only is it a missing guide to DWARF for dummies like me, but it is also a gentle introduction to x64 ASM. Highly recommended! Kudos to @nostarchpress.bsky.social really my fav tech publisher :chefkiss:
2142
Reposted by @forked-franz.bsky.social
Brice Dutheil @bricedutheil.bsky.social · 22/04/2025
github.com/JCTools/JCTo... by @forked-franz.bsky.social need to spend some time at this work 🤯 #jdk24 #jctools
github.com
JCtools vs JDK 24: to VarHandle or not VarHandle? · JCTools JCTools · Discussion #397
Since JDK 24 is coming I would like to assests the current level of performance of one of the most delicate and simple Q we offer: the spsc array q. This is the first stepping stone to decide if, d...
021
Reposted by @forked-franz.bsky.social
Per Minborg @pminborg.bsky.social · 22/04/2025
We just integrated a performance improvement to Java String that will provide a ~10x performance boost in some applications where Strings are used as keys and where the associated values are constant foldable. This will make JDK 25 faster. github.com/openjdk/jdk/...
27721
Reposted by @forked-franz.bsky.social
Wasm I/O @wasm.io · 07/04/2025
🧩 Are We Enterprise-Ready Yet? By @evacchi.dev & @andreatp.bsky.social @ Wasm I/O 2025 ▶️ Video: youtu.be/UyyVL-dDbCw 🔗 Slides: docs.google.com/presentation... #wasmio25
youtu.be
Are We Enterprise-Ready Yet? By Edoardo Vacchi & Andrea Peruffo @ Wasm I/O 2025
YouTube video by WASM I/O
133
Reposted by @forked-franz.bsky.social
chipsandcheese.bsky.social @chipsandcheese.bsky.social · 28/03/2025
Hello you fine Internet folks, Today we have an interview with @oxidecomputer.bsky.social's @bcantrill.bsky.social about Oxide and what hardware they are building and the reasons why. Hope y'all enjoy! open.substack.com/pub/chipsand... old.chipsandcheese.com/2025/03/27/a... youtu.be/5-nOIlrUqMM
open.substack.com
An Interview with Oxide's Bryan Cantrill
Hello you fine Internet folks,
1327
Reposted by @forked-franz.bsky.social
Sanne Grinovero @sannegrinovero.bsky.social · 20/03/2025
Rare chance to see me in person in Singapore! March 27 I'll present on an extremely interesting JVM performance topic: www.meetup.com/singadev/eve... Also looking forwards to network and discuss anything related to @quarkus.io , @hibernate.org , @commonhaus.org 😉
meetup.com
The JVM’s Secret Bottleneck & The Next Wave in Spring AI and MCP, Thu, Mar 27, 2025, 6:30 PM | Meetup
**Title: The JVM’s Secret Bottleneck by Sanne Grinovero (Lead of the opensource Hibernate project!)** This presentation will delve into a serious JVM performance issue that
2179
Reposted by @forked-franz.bsky.social
chipsandcheese.bsky.social @chipsandcheese.bsky.social · 01/03/2025
Hello you fine Internet folks, Today's article is on Zen 5's frequency behavior when dealing with AVX512 instructions and seeing just how differently Zen 5 behaves to Skylake-X. Hope y'all enjoy! open.substack.com/pub/chipsand... old.chipsandcheese.com/2025/02/28/z...
open.substack.com
Zen 5's AVX-512 Frequency Behavior
Zen 5 is AMD's first core to use full-width AVX-512 datapaths.
0275
Reposted by @forked-franz.bsky.social
Mark Hamill @markhamillofficial.bsky.social · 10/01/2025
#EmbarrassmentInChief 🤮
24748048115323
Reposted by @forked-franz.bsky.social
pleeplop.bsky.social @pleeplop.bsky.social · 26/12/2024
Here is a recent out-of-order RISC V simulator sc-nas.fit.vutbr.cz/riscv-sim/ Paper: arxiv.org/abs/2411.07721
sc-nas.fit.vutbr.cz
021
forked-franz.bsky.social @forked-franz.bsky.social · 25/12/2024
@chipsandcheese.bsky.social hi! Do you know where I can start digging into what happen, step by step, in an OOO arch like the one at i.sstatic.net/PmR2H.png I can find info on stack overflow from Peter Cordes, but never something step of step which try to show happen with some asm, by example 🙏
100
Reposted by @forked-franz.bsky.social
Luca Molteni @lucamolteni.bsky.social · 21/12/2024
I’m impressed on how good the Breath of the Wild sound track is. Each time I listen to it I discover new things i.e. this morning I realised Ganon’s tracks are based on an harmonic minor scale and that should be obvious as Ganon is a gerudo himself.
222
Reposted by @forked-franz.bsky.social
Cowtown Coder @cowtowncoder.bsky.social · 20/12/2024
UGH. And *facepalm*. It was indeed wrong process. Not because I mis-identified local service but... because client was connecting to shared test env (because I switched between scripts). So you were right indeed. No activity, no profile.
031
Reposted by @forked-franz.bsky.social
Brice Dutheil @bricedutheil.bsky.social · 14/12/2024
Now the #JDK's has a `jcmd {pid} System.map` that works and macos! After first Linux, then windows in September. github.com/openjdk/jdk/...
github.com
8319875: Add macOS implementation for jcmd System.map by stooke · Pull Request #20953 · openjdk/jdk
This is a port of #16301 to macOS. System.map and System.dump_map are implemented using the macOS API and provide roughly the same information in the same format. Most of the heavy lifting was imp...
072
Reposted by @forked-franz.bsky.social
chipsandcheese.bsky.social @chipsandcheese.bsky.social · 11/12/2024
P.S. Chester made a Video so go watch that as well! www.youtube.com/watch?v=SwlK...
youtube.com
Disabling Zen 4's Op Cache
YouTube video by lamchester1
061
Reposted by @forked-franz.bsky.social
chipsandcheese.bsky.social @chipsandcheese.bsky.social · 11/12/2024
Hello you fine Internet folks, Today we look at disabling Zen 4's op cache for fun and giggles as well as seeing just what kind of effects this would have. Hope y'all enjoy! open.substack.com/pub/chipsand... old.chipsandcheese.com/2024/12/10/t...
open.substack.com
Turning off Zen 4's Op Cache for Curiosity and Giggles
CPUs start executing instructions by fetching those instruction bytes from memory and decoding them into internal operations (micro-ops).
1192
Reposted by @forked-franz.bsky.social
chipsandcheese.bsky.social @chipsandcheese.bsky.social · 13/12/2024
Hello you fine Internet folks, Today we return to our SC24 coverage with Fujitsu's Monaka CPU which an ARMv9 based CPU with SVE2 that uses 3D stacking and is due in 2027. Hope y'all enjoy! open.substack.com/pub/chipsand... old.chipsandcheese.com/2024/12/13/f... youtube.com/shorts/9w1Tr...
open.substack.com
Fujitsu's Monaka CPU: ARMv9, SVE2, and 3D Stacking
Designed for the datacenter and due in 2027
084
Reposted by @forked-franz.bsky.social
Karin West-Weekes @karinww.bsky.social · 06/12/2024
Video game characters are not actually real. They don’t bleed, they can’t get their feelings hurt, they can’t be betrayed because they are a collection of pixels and code and words and sound files. The game devs I’m lucky to work with are real people who deserve at least basic human respect.
205101451169
Reposted by @forked-franz.bsky.social
Edoardo Vacchi @evacchi.dev · 05/12/2024
I am working on something #java #wasm
a spoof of the poster for "Breakin' 2: Electric Boogaloo" entitled "Wasm 4 the Java Geek 3: Electric Boogaloo", together with the 3 dancers of the original posters, there are the mascots for Kotlin, GraalVM and Java
082
Reposted by @forked-franz.bsky.social
Liz Edwards @lizaledwards.bsky.social · 04/12/2024
ubisoft laying off hundreds of people in *december* is just evil honestly
1674660363
Reposted by @forked-franz.bsky.social
Loïc Mathieu @loicmathieu.fr · 03/12/2024
Made some quick prototype with @quarkus.io and the new improved error message in dev is very cool. Here it clearly says: add a missing lib man!
083
Reposted by @forked-franz.bsky.social
Matt Fleming @mfleming.bsky.social · 29/11/2024
Change Point Detection for performance testing just reached a whole new level. The project behind nyrkio.com and used in companies like Confluence and DataStax just got accepted into the ASF incubator project. Aww yeah!
nyrkio.com
Nyrkiö | For Faster Software
142
Reposted by @forked-franz.bsky.social
chipsandcheese.bsky.social @chipsandcheese.bsky.social · 28/11/2024
Hello you fine Internet folks, Today we have an interview with the CEO of NextSilicon, Elad Raz, talking about why are they putting HPC first and what does the Maverick 2 do differently. Hope y'all enjoy! open.substack.com/pub/chipsand... old.chipsandcheese.com/2024/11/28/n... youtu.be/wmLfIcObDQ8
open.substack.com
NextSilicon: Putting HPC First
Not an FPGA, not a GPU, but something different!
0163
Reposted by @forked-franz.bsky.social
chipsandcheese.bsky.social @chipsandcheese.bsky.social · 25/11/2024
Hello you fine Internet folks, Today we have something new for y'all in the form of a YouTube Short about Ayar Labs and their second generation of co-packaged optics. Hope y'all enjoy! youtube.com/shorts/Kssi8... chipsandcheese.com/p/ayar-labs-... old.chipsandcheese.com/2024/11/25/a...
youtube.com
Ayar Labs at Supercomputing 2024: Making Light Move Bits
YouTube video by Chips and Cheese
062
Reposted by @forked-franz.bsky.social
chipsandcheese.bsky.social @chipsandcheese.bsky.social · 25/11/2024
Hello you fine Internet Folks, Today we are looking at what happens when you push several different generations of AMD's Infinity Fabric to its limits and how it behaves under significant load. Hope y'all enjoy! chipsandcheese.com/p/pushing-am... old.chipsandcheese.com/2024/11/24/p...
chipsandcheese.com
Pushing AMD’s Infinity Fabric to its Limits
I recently wrote code to test memory latency under load, seeking to reproduce data in various presentations with bandwidth on the X axis and latency on the Y axis.
1388
Reposted by @forked-franz.bsky.social
Carter Kozak @ckozak.net · 21/11/2024
Welcome, @forked-franz.bsky.social! I’ve really missed your high quality jvm performance insights since leaving the other site :-)
022