Why Java Benchmarks lie and what we could do about it
This talk is devoted to Java enterprise benchmarks: from naive opensource bench suites to the mighty SPECjbb2015 — the main benchmark of our time.
But how and by whom it was developed? What impacted SPECjbb2015 development process? And finally, what did it lead to?
The fact is that SPECjbb2015 being the major benchmark for HW produces irrelevant measures, as well as some other benchmarks in the industry. We will understand how to fix that and for that we’ll discuss key questions about benchmarking: latency, throughput, SLA and how to deal with all this staff.
This talk is inspired by many challenging issues met during benchmarking Azul Zing JVM.
This talk is devoted to Java enterprise benchmarks: from naive opensource bench suites to the mighty SPECjbb2015 — the main benchmark of our time.
But how and by whom it was developed? What impacted SPECjbb2015 development process? And finally, what did it lead to?
The fact is that SPECjbb2015 being the major benchmark for HW produces irrelevant measures, as well as some other benchmarks in the industry. We will understand how to fix that and for that we’ll discuss key questions about benchmarking: latency, throughput, SLA and how to deal with all this staff.
This talk is inspired by many challenging issues met during benchmarking Azul Zing JVM.
Алексей Игнатенко,
Azul Systems
Why Java Benchmarks lie and what we could do about it
Алексей Игнатенко,
Azul Systems
Azul Systems
This talk is devoted to Java enterprise benchmarks: from naive opensource bench suites to the mighty SPECjbb2015 — the main benchmark of our time.
But how and by whom it was developed? What impacted SPECjbb2015 development process? And finally, what did it lead to?
The fact is that SPECjbb2015 being the major benchmark for HW produces irrelevant measures, as well as some other benchmarks in the industry. We will understand how to fix that and for that we'll discuss key questions about benchmarking: latency, throughput, SLA and how to deal with all this staff.
This talk is inspired by many challenging issues met during benchmarking Azul Zing JVM.
But how and by whom it was developed? What impacted SPECjbb2015 development process? And finally, what did it lead to?
The fact is that SPECjbb2015 being the major benchmark for HW produces irrelevant measures, as well as some other benchmarks in the industry. We will understand how to fix that and for that we'll discuss key questions about benchmarking: latency, throughput, SLA and how to deal with all this staff.
This talk is inspired by many challenging issues met during benchmarking Azul Zing JVM.
About speaker
About speaker
2005-2016 Intel Novosibirsk branch, projects Harmony, Oracle Hotspot, x86 optimizations, performance, benchmarking, compilers
2017-nowadays - Azul Systems - manager of Performance and Compiler Teams
2017-nowadays - Azul Systems - manager of Performance and Compiler Teams
Other speakers
Other speakers
Our partners
Drop us a line to figure out about format, platform, tickets, [anything]
Looking forward to your talk submissions. Choose any submission template you like – it's the topic and story logic that matters most
Will be happy to meet new partner companies who can help with making the conference more useful and interesting
Drop us a line to figure out about format, platform, tickets, [anything]
Looking forward to your talk submissions. Choose any submission template you like – it's the topic and story logic that matters most
Will be happy to meet new partner companies who can help with making the conference more useful and interesting
«Dolgushev & Storozhilov» + JUGNsk © 2021