My Journey Optimizing a CUDA Kernel with Polar Signals
A storage engineer's descent into warp stalls, memory throttles, and aligned stores
GPUDatabases+1
Author:
Alfonso Subiotto Marqués
All posts
Posts tagged 'GPU'
Open-Source Low-Overhead NVIDIA CUDA PC Sampling
And how we made it happen
GPUProfiling+2
Author:
Tommy Reilly
Python Zebra Stacks
Unwinding Deep PyTorch Training Stacks with eBPF
GPUPyTorch+2
Author:
Tommy Reilly
Profiling NVIDIA CUDA in Kubernetes
The easiest way to get started Profiling CUDA in Kubernetes
CUDANVIDIA+3
Author:
Frederic Branczyk
Continuous NVIDIA CUDA Profiling In Production
Low-Overhead Profiling of GPUs with USDT Probes and eBPF
GPUProfiling
Author:
Tommy Reilly
The MCP for performance engineering
Introducing Remote MCP Support in Polar Signals Cloud
Performance AnalysisPerformance+2
Author:
Matthias Loibl
How Continuous Profiling reduces Engineering Debt and increases Application Performance
Application Performance engineering debt could live a long time without noticed and cause a significant overhead in developing new features, performance and the cost of operation.
Continuous-ProfilingCloud Cost+2
Author:
Batuhan Uslu
Latest in Continuous Profiling for GPUs
Attending ai.engineer 2025 in San Francisco
ProfilingCorrelation+1
Authors:
Matthias L, Brennan V.
Maximize GPU Efficiency: Visualize, Analyze, and Optimize with Precision
Introducing Continuous GPU Profiling: Get Performance Insights Over Time
System-WidePython+2
Author:
Matthias Loibl
Featured posts
Autonomous Optimization with Claude Code
Optimize your infrastructure autonomously every day with Claude Code and Polar Signals
AIClaude Code+1
OpenTelemetry Profiling goes Alpha
How to use it with Polar Signals & Parca
OpenTelemetryProfiling+2
Continuous NVIDIA CUDA Profiling In Production
Low-Overhead Profiling of GPUs with USDT Probes and eBPF
GPUProfiling
Keep up with Polar Signals
Receive new posts, product updates, and insights on performance engineering straight to your inbox.