enfiskutensykkel / ssd-gpu-dma

Build userspace NVMe drivers and storage applications with CUDA support

enfiskutensykkel/ssd-gpu-dma Issues

Can not find "nvm-latency-bench" in build/bin
Closed 5 months ago4
nvm-cuda-bench failed as "an illegal memory access was encountered"
Closed 6 months ago5
ROCm support ?
Updated 2 years ago5
Unexpected error: Unexpected CUDA error: an illegal memory access was encountered
Closed 4 years ago6
nvm-identify run error
Updated 4 years ago7
Cmake output saying 'Configuring kernel module without CUDA'
Updated 4 years ago39
Invalid NSID
Updated 5 years ago29
Does CQ and SQ memory need to be contiguous
Closed 5 years ago1
nvm-cuda-bench infintiely waiting for IO completion
Closed 5 years ago1
Sperating SQ, CQ, and PRP List Memories
Closed 5 years ago2
Floating Point Exception
Updated 5 years ago16
Does --verify option works?
Updated 5 years ago11
Investigate DAX support
Closed 5 years ago
Change benchmark statistics to per command for nvm-latency-bench
Updated 5 years ago
Incorrect use of DMA API
Updated 5 years ago1
Kernel module doesn't clean up resources if program crashes or doesn't release handles
Updated 5 years ago3
Add support for larger IO queues
Closed 5 years ago3
Build and Binding the helper driver
Closed 6 years ago1
Issue when using the cuda example/benchmark
Closed 6 years ago11
Investigate P2P support in the Linux DMA API for latest kernel release
Closed 6 years ago2
Clarify use-case involving CUDA
Closed 6 years ago32
Issue with multiple queues for latency benchmark
Closed 6 years ago
Make kernel TCP version of RPC
Updated 6 years ago
Write benchmark program that memory maps a file and uses cudaMemcpy to copy into GPU memory
Closed 6 years ago
Write benchmark that uses libnvme to read data directly into GPU memory
Closed 7 years ago
Merge into master
Closed 7 years ago
Make kernel module that supports pinning RAM and GPU pages
Closed 7 years ago1