![[2606.05081] Graph Traversal on Tensor Cores: A BFS Framework for Modern GPUs](/static/img/curated/desks/afbytes-tech.png)
[2606.05081] Graph Traversal on Tensor Cores: A BFS Framework for Modern GPUs
Abstract page for arXiv paper 2606.05081: Graph Traversal on Tensor Cores: A BFS Framework for Modern GPUs
America Forever Bytes
GPU · AFBytes
Technology
GPU
Recent coverage
[2606.04670] Fitting scattered data with optional monotonicity constraints on GPU: LipFit package
Abstract page for arXiv paper 2606.04670: Fitting scattered data with optional monotonicity constraints on GPU: LipFit package
[2606.03335] GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization
Abstract page for arXiv paper 2606.03335: GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization
[2606.00486] Dead on Arrival: Characterizing and Protecting Against Dead-Entry TLB Misses in GPU Microarchitectures
Abstract page for arXiv paper 2606.00486: Dead on Arrival: Characterizing and Protecting Against Dead-Entry TLB Misses in GPU Microarchitectures
[2606.01852] Parallelizing Large-Scale Tensor Network Contraction on Multiple GPUs
Abstract page for arXiv paper 2606.01852: Parallelizing Large-Scale Tensor Network Contraction on Multiple GPUs
[2606.01502] Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics
Abstract page for arXiv paper 2606.01502: Move the Query, Not the Cache: Characterizing Cross-Instance Latent Attention Redistribution Across GPU Fabrics
[2606.01693] Scalable Concurrent Queues for GPU
Abstract page for arXiv paper 2606.01693: Scalable Concurrent Queues for GPU
Should You Plug Your Monitor Into A GPU Or Motherboard?
Even when a motherboard has video output, you'll rarely use it if you've built a PC with a dedicated graphics card since it's designed to render images.
[2605.30728] Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended
Abstract page for arXiv paper 2605.30728: Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended
[2605.31464] GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization
Abstract page for arXiv paper 2605.31464: GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization
FS: Cheap Ryzen 5600G, DDR4, 1TB HDD, GTX 1650 Super, Sony Pulse 3D Headset, RX 9060XT
Looking to sell some old parts. 1. ASRock RX 9060XT 16GB Challenger - I’ve owned this GPU a grand total of 2 weeks. Never been Overclocked and is still...
Vertical Or Horizontal: What's The Best Position To Mount A GPU?
Mounting a GPU vertically can cause excessive heat build-up when compared to a horizontal mount, while providing better visual appeal to display RGB lights.
The AI economy could crash on mounting chip costs — and those token costs won’t help
Soaring GPU prices, debt-funded chip deals and an agentic token explosion — the cost of the hardware and compute powering AI could be what breaks it.
GPU prices — is the worst behind us ?
A look at the current graphics card market reveals a development that can now be called clearly positive compared to two weeks ago. — as per an analysis by...