Java on a 1000 Cores - Tales of Hardware / Software CoDesign

Channel:Google TechTalks · Length:1:12:01 · Published:2009-09-08 · Views:23129

Watch on YouTube

Summary

Cliff Click of Azul Systems gives a Google Tech Talk on running Java business applications on a machine with about a thousand cores. He covers hardware and software codesign, including garbage collection hardware and the JIT.

Why HN recommends it

HN treats Cliff Click's talks as an excellent source on JVMs, garbage collection and hardware-assisted Java.

Anything from Cliff Click is quite good. — HN, 2013

Python, Ruby & scripting languages · Compilers, interpreters & program analysis · Computer architecture & CPUs

Subtitles (excerpt)

>> It's my pleasure to welcome today to Google, Dr, Cliff Click. He's the Chief JVM architect for Azul Systems. He's one of the lead--he was the lead architect on HotSpot server complier back in the days when he used to work at Sun. And he's here today to talk to us about Azul's experience with lots and lots of cores and hardware/software co-Design. So, here he is. >> CLICK: Thanks. Hi. So, as you can probably tell from slides, you're getting recycled slides from ECOOP key note, but I think they're very interesting. It's a very interesting talk here. So, a quick look at what Azul is and what we do in terms of what we've done. We design our own chips. They're actually fab'ed by Taiwan Semiconductor Manufacturing Company. We build our own systems out of those chips. We target the systems for running business Java. We are a very large core count, like 54 cores per die. We can make up to 16 of the die cache-coherent. So, the big box has 864 cores in it. We have a very weak memory model but it meets the Java spec when we put in the right set of memory fences. The memory speed is flat. It's uniform. It is not NUMA which you usually expect it of a high core count machine and that's because business Java is very irregular computation. So, it

On Hacker News

Probably this one: [LINK] Anything from Cliff Click is quite good. This guy has a very deep understanding of compilers, virtual-machines, CPUs, and their interactions. A JVM does that? [LINK] Java on a 1000 Cores [VIDEO] — qznc, 2013-04
Here's an excellent google tech talk by Cliff Click of Azul talking about their hardware. Among the firehose of information in that talk, he mentions that the hardware guys wanted to add directly execute JVM bytecode. He told them not to bother since he could JIT it better and they wouldn't be able to support all the bytecodes anyway. I'd love to know more about why that is. [VIDEO] — bokchoi, 2009-10
> What I can imagine is a purpose-built CPU that would make the JIT's job a lot easier and faster than compiling for x86 or ARM. Such a machine wouldn't execute raw Java bytecode, rather, something a tiny bit more low-level. This is approximately exactly what Azul Systems did, doing a bog-standard RISC with hardware GC barriers and transactional memory. Cliff Click gave an excellent talk on it [0… — hayley-patton, 2025-11
Azul Systems (who today are mainly a JVM vendor) started by building large multicore boxes (Vega) to do Java workloads - there is an interesting tech talk about it: [VIDEO] (2009) They built a "really good JIT target" rather than direct bytecode for reasons explained in the video. Curious to hear from anyone who ever used one... — mcbridematt, 2020-07
There are some interesting challenging when scaling this large with any system. Peter referenced some of Azul System's stuff and their custom GC. Cliff Click from Azul has done some great Google Tech Talks about JVM development and scaling JVM's out to really big systems.[1][2] [1] A JVM Does That? - [LINK] [2] Java on a 1000 Cores - [VIDEO] — Alupis, 2015-03

Related videos