We're back with Miles and Claire Let me just share this reporting in the New York Times this week. ICE recruitment ad posted to pages for White House and DHS on Instagram, Facebook, and X reads, quote, we'll have our home again. Join ICE .gov.Times reports this. Administration social media posts echo white supremacist messaging. Quote, we'll have our home again is also the name of a song written by members of a self-described pro-white fraternal order that has been embraced by the Proud Boys and other white ...

Joining us now is the mayor of the other city in the Twin Cities, the mayor of St. Paul, Minnesota, Kaliher. Mayor, thank you for being with us. Yes, thank you so much for being with us.Your reaction to the news that Greg Bovino and some federal agents are leaving your state. I mean, I'm hopeful that this isn't just a shift in tactics to address a political perception or problem, but that it is really going to be a change in how they're going to be operating in our cities here. So all I can do is be hopeful ...

We have several reports of parents like sending messages to each other like I'm afraid to like take my kid to school. Like I don't know if I can leave my house. We're outside Braftoft Elementary as parents are walking their kids in to start the school day.This week has felt different because there's been ice activity in this neighborhood. Mount Pleasant is historically a Salvadoran neighborhood in DC and parents here say they've been worried in the morning. How does it feel bringing your kids to school here ...

GPU Profiling & Performance Optimization - The industry emphasizes improving performance and saving costs by optimizing software, potentially reducing server usage by 10% [4] - Sampled profiling is used to balance data volume and continuous monitoring, with examples of sampling 100 times per second resulting in less than 1% CPU overhead and 4MB memory overhead [5] - The industry highlights the importance of production environment profiling to observe real-world application performance with low overhead [8] - The company's solution leverages Linux EVPF, enabling profiling without application instrumentation [9] Technology & Metrics - The company's GPU profiling solution uses Nvidia NVML to extract metrics, including overall node utilization (blue line), individual process utilization (orange line), memory utilization, and clock speed [11][12] - Key metrics include power utilization (with power limit as a dashed line), temperature (important to avoid throttling at 80 degrees Celsius), and PCIe throughput (negative for receiving, positive for sending, e g 10 MB/s) [13][14] - The solution correlates GPU metrics with CPU profiles collected using EVPF to analyze CPU activity during periods of less than full GPU utilization [14] GPU Time Profiling - The company introduces GPU time profiling to measure time spent on individual CUDA functions, determining start and end times of kernels via the Linux kernel [18] - The solution displays CPU stacks with leaf nodes representing functions taking time on the GPU, with colors indicating different binaries (e g blue for Python) [19][20] Deployment & Integration - The company's solution can be deployed using a binary on Linux, Docker, or as a DaemonSet on Kubernetes, requiring a manifest YAML and token [21] - Turbo Puffer is interested in integrating the company's GPU profiling to improve the performance of their vector engine [22]