Muhammad Zubair Bin Akbar·12h agoDebugging in HPC: Understanding How to Find Bugs in Parallel and GPU ApplicationsIntroduction
Dinie humaidi·1d agoI Made a Metal Rod Run on 4 Processes (and It Got 3.5× Faster)Simulating heat diffusion with Python, NumPy, and MPI, and what I learned about making processes talk to each other.A response icon1A response icon1
Jackson Kontny·2d agoPrefix sums, from O(1) range queries to parallel scansOne row of running totals answers any range-sum question with a single subtraction. Building that row looks stubbornly sequential, yet SIMD…
CodingInAVan·6d agoNVIDIA or AMD? Try the Same GPU Optimization on BothCan the same code change make a program faster on both NVIDIA and AMD GPUs?
Ralf Becker·Oct 29Fast, parallel, low-memory — two-pass checkpointed orbit decompositionTwo-pass Hopalong map: serial pass records segment checkpoints + bounds; parallel pass replays independent segments into private…A response icon1A response icon1
Agcshubham·Oct 25Why GPU? CPU vs GPU ArchitectureCUDA Deep Dive · Helper Blogs · H-01 This post is one of a series. See the Series Map for the full plan and where this post fits. Next…
InNeo4j Developer BlogbyMaxime GUERY·Oct 23Implementation of the Neo4j Import Without Deadlock and Lock ContentionExplanation and sharing of a generic implementation of the approach enabling lock-free data import.
InLevel Up CodingbyAri Saif·Oct 8Learn CUDA Algorithms by Watching Them RunI read a great article on GPU optimization, but I couldn’t picture what the threads were doing. So I coded the steps, ran them, and built…A response icon2A response icon2
Mohana Roy Chowdhury·Oct 6Train Neural Networks without Draining your Pocket: Introduction to Latency and Overheads and…A quick walkthrough of all the essential terms you’ll need to know to learn hardware-level optimization for training Deep Learning models.
Muhammad Zubair Bin Akbar·Oct 4Why More CPU Cores Don’t Always Make an HPC Application FasterIf 1 CPU can run a program, then 8 CPUs should make it much faster.
