liveBook · Manning

CUDA event

A CUDA event is a runtime object recorded in a CUDA stream to mark a point in device execution for synchronization or elapsed-time measurement.

How 2 Manning books explain it

GPU Programming with Triton

A CUDA event is a GPU-timeline timestamp object used to record and measure points in CUDA stream execution.

How it is used
Measures GPU work on the GPU timeline when benchmarking kernel execution.
How deep it goes
Defines event timing through stream placement and GPU timestamps, without detailing event API syntax.
Examples
Places events before and after a kernel to measure elapsed GPU time.
What you can do after
Apply CUDA events to measure kernel execution on the GPU timeline.

Read how GPU Programming with Triton explains CUDA event →

CUDA for LLMs

A CUDA event is a GPU stream marker that can be recorded and queried for synchronization or elapsed-time measurement.

How it is used
Measures GPU execution accurately and orders asynchronous work across streams.
How deep it goes
Shows event creation, recording, synchronization, elapsed-time retrieval, and cleanup without descending into event internals.
Examples
Times a kernel and coordinates a multi-GPU batch pipeline; also measures components of a quantization forward pass.
What you can do after
Diagnose GPU timing and pipeline performance using event-based measurements instead of relying on host launch time.

Read how CUDA for LLMs explains CUDA event →

Related concepts

Questions about CUDA event

What is CUDA event?

A CUDA event is a runtime object recorded in a CUDA stream to mark a point in device execution for synchronization or elapsed-time measurement.

Which Manning books explain CUDA event?

GPU Programming with Triton and CUDA for LLMs.

What is the difference between CUDA event and cudaDeviceSynchronize?

A CUDA event is a runtime object recorded in a CUDA stream to mark a point in device execution for synchronization or elapsed-time measurement. cudaDeviceSynchronize is a CUDA Runtime API function that blocks the host until previously issued work on the device has completed.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.