Chinese-first Ramulator2 ECC/EDC reliability research prototype for AI and HPC memory studies
-
Updated
Aug 25, 2026 - C++
#
hbm3
Here are 3 public repositories matching this topic...
Professional benchmarking guide for evaluating NVIDIA H200 GPU memory bandwidth using the STREAM Triad (FP32) benchmark with CUDA 12.x on Linux. Includes setup, execution, performance analysis, and multi-GPU benchmarking results.
performance high-performance-computing stream-benchmarks gpu-benchmarking nvidia-h200 memory-bandwidth-benchmarking cuda124 hbm3
-
Updated
Jul 25, 2026
Software-Defined PIM-HBM Bypass Infrastructure. 0ns JAX/XLA memory view fusion with real-time asynchronous NCCL collective fault-scanning & no-recompile Mux hot-swapping.
zero-copy cuda high-performance-computing gpu-acceleration pim compiler-optimization fault-tolerant distributed-training nccl jax system-software xla double-buffering branchless hardware-software-codesign llama3 hot-plugging hbm3 memory-bypass matrix-sharding
-
Updated
Jul 16, 2026 - Python
Improve this page
Add a description, image, and links to the hbm3 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the hbm3 topic, visit your repo's landing page and select "manage topics."