After all, if they’re marked as unsafe, there’s gotta be a reason, right?

If you care about tail latency in SPECjbb2015, Composite mode hides GC impact. We quantify the discrepancy and recommend Distributed or MultiJVM.

Welcome to the home page of the 2025 ACM SIGPLAN International Symposium on Memory Management (ISMM 2025)! ISMM is the premier forum dedicated to research in memory management, covering the areas of m...

Enhance the Z Garbage Collector (ZGC) to adaptively adjust the size of the heap based on the resources available, the application's needs, and the needs of neighboring applications contending for the same resources.

Improve application startup and warmup by enhancing the Z Garbage Collector to acquire and prepare physical memory more swiftly and efficiently in response to application needs.

How Claude Code hooks differ from Cursor: broader lifecycle and permission telemetry, strong native IDs, batch and compaction events, but no thought or specialized execution hooks.

Learn how the Datadog APM team improved Java startup performance by encoding a prefix trie as a JVM string constant.

Modern hard- and software systems have a lot of features, which make programs fast, but can make it difficult to understand what is going on. Let's look at some fictitious benchmark results a think th...

[Java][JVM][Tuning][Profiling][G1][JIT] Why is Arrays.fill 265 times slower on G1GC?

YouTube video by Cliff Click

YouTube video by Cliff Click

[Java][Profiling] Async-profiler + OpenTelemetry spans

From a 2007 Windows via C/C++ VMMap demo to a modern Windows 11 analyzer and its Linux /proc/smaps counterpart - and why Working Set, RSS/PSS and 'committed' memory do not mean the same thing on the t...

Modern Java profilers often rely on unsupported JVM internals for accurate CPU profiling. Here’s how engineers from Datadog, SAP, Amazon, and the OpenJDK community helped bring a new CPU profiling eve...

Summary This PR implements JDK-8326205, introducing experimental support for grouping hot code within the CodeCache. Problem Modern CPUs use the branch target buffer (BTB), part of the branch predi...

YouTube video by Cliff Click

A trip through HotSpot's C2 branch-to-cmov heuristic: it measures branch bias, not predictability, and in a tight loop that mismatch is worth up to 2.9x.

YouTube video by CppNow

How to set up a secondary profile and pinpoint the precise frames responsible for a performance change between two JFR recordings.

YouTube video by Cliff Click

Learn how intricate and amazing the JVM is and how much cognitive load that it takes on so you rarely have to think about things that steal your focus away from application logic.

YouTube video by Cliff Click

Using NativeAOT to write a .NET GC in C#. In this part, we add support for finalization.

YouTube video by Cliff Click