Presentation: JIT vs AOT Performance With GraalVM

Track: Bare Knuckle Performance

Location: Pacific DEKJ

Duration: 4:10pm - 5:00pm

Day of week: Monday

Share this on:

What You’ll Learn

  1. Hear about GraalVM, what is it good for from a performance point of view.
  2. Learn how to optimize your applications for better performance.

Abstract

In this session we are going to talk about various aspects of performance, such as peak throughput, startup, memory footprint and more, and how you can optimize your applications for them with GraalVM. GraalVM is a high-performance virtual machine, bringing new performance optimizations for individual languages and seamless interoperability for polyglot applications.

In particular, we’ll discuss JIT and AOT compilation and and talk about their advantages and trade-offs. Also, we’ll go through some practical examples comparing JIT compilation with HotSpot and GraalVM, JIT and AOT, improving AOT with profile-guided optimizations and more.

Question: 

What is the work you're doing today?

Answer: 

I'm a developer advocate for GraalVM, and this means that I’m responsible for interacting with our developer community. So I help people to learn about GraalVM: what it is, what capabilities does it offer, how they can use GraalVM in various scenarios and make the most of it. 

Question: 

What are the goals you have for the talk?

Answer: 

I want to offer an additional point of view on performance. Performance is something people often talk about, but often focus on one or two metrics, and there might be more ways to look at it, and additional opportunities to optimize. We will go through some additional metrics, discuss how they are connected, and how you can optimize for each of them, specifically in the just-in-time compilation and ahead-of-time compilation modes. 

Question: 

Could you give me an example of, say, a new performance optimization that you can do in GraalVM that you can't do with the JVM C2?

Answer: 

GraalVM can offer the ability to compile Java applications ahead of time into a native binary. The reason why you might be interested in doing so is because you will get faster startup and will consume significantly less memory compared to traditional just in time (JIT) compilation setup. JIT is very good for optimizing for peak performance, but for startup and memory footprints the native images can offer very competitive advantages. This is something you might be specifically interested in if you are working with cloud and microservices, as these performance metrics may become more relevant for you.

Question: 

You optimize for a smaller or a quicker startup time vs. the longer term performance that the classic JVM has. I got that right?

Answer: 

With GraalVM you can optimize for both. With JIT and AOT modes, you can choose whatever works for you and what your priorities for a particular application are. You can really do both, and we discuss how to do this, along with benefits and trade-offs of both ways.

Question: 

What do you want people to leave the talk with?

Answer: 

The idea is to give the audience some food for thought and motivation to try some of the different ways to trade-off the performance dimensions when they go back to work, and gain performance improvements as the result.

Speaker: Alina Yurenko

Developer Advocate for GraalVM @Oracle

Alina is a Developer Advocate for GraalVM at Oracle Labs, a research and development organization at Oracle. Coming from developer relations background, Alina now has joined the GraalVM team to work with its global community. 

Find Alina Yurenko at

Similar Talks

Evolution of Edge @Netflix

Qcon

Engineering Leader @Netflix

Vasily Vlasov

Mistakes and Discoveries While Cultivating Ownership

Qcon

Engineering Manager @Netflix in Cloud Infrastructure

Aaron Blohowiak

Monitoring and Tracing @Netflix Streaming Data Infrastructure

Qcon

Architect & Engineer in Real Time Data Infrastructure Team @Netflix

Allen Wang

Future of Data Engineering

Qcon

Distinguished Engineer @WePay

Chris Riccomini

Mapping the Evolution of Socio-Technical Systems

Qcon

Agile Methods Coach & Advocate for Woman in Tech

Cat Swetel

Coding without Complexity

Qcon

CEO/Cofounder @darklang

Ellen Chisa

Tracks

Monday, 11 November

Tuesday, 12 November

Wednesday, 13 November