Pinned Loading

1. nvidia-uma-fault-probe nvidia-uma-fault-probe Public

   Cycle-accurate UMA fault latency and bandwidth measurement for NVIDIA GPUs. C and PTX. No Python. Pascal (SM 6.0) through Blackwell GB10 (SM 12.1).

   Cuda

2. sparkview sparkview Public

   Operator-grade GPU monitor for NVIDIA GPUs with native GB10 / DGX Spark coherent UMA support — PSI pressure, clock detection, ConnectX-7 network layer

   Python 11 3

3. gb10-uma-diagnostics gb10-uma-diagnostics Public

   GB10 unified memory diagnostic suite — bandwidth, contention, atomic coherence, CUPTI activity, power and thermal correlation

   Cuda

4. cupti-activity-collector cupti-activity-collector Public

   GB10-aware CUPTI Activity collector — runtime kind detection, phase management, and JSON output for hardware-coherent UMA platforms

   Cuda 1 1

5. cuda-unified-memory-analyzer cuda-unified-memory-analyzer Public

   gpu thrashingNVIDIA GPU Unified Memory diagnostic tool — architecture-aware, measurement-based, PCIe/coherent transport detection

   Cuda 2 2

6. gb10-kernel-probe gb10-kernel-probe Public

   Empirical kernel scheduling characterization for NVIDIA GB10 (SM121a). Sweeps GEMM tile configurations, classifies PTX instruction paths, captures hardware telemetry

   C++ 1