Skip to main content

KvikIO - GPUDirect Storage (C++)

Project description

KvikIO: High Performance File IO

Summary

KvikIO (pronounced "kuh-VICK-eye-oh", see here for pronunciation of kvik) is a Python and C++ library for high performance file IO. It provides C++ and Python bindings to cuFile, which enables GPUDirect Storage (GDS). KvikIO also works efficiently when GDS isn't available and can read/write both host and device data seamlessly. The C++ library is header-only making it easy to include in existing projects.

Features

  • Object oriented API of cuFile with C++/Python exception handling.
  • A Python Zarr backend for reading and writing GPU data to file seamlessly.
  • Concurrent reads and writes using an internal thread pool.
  • Non-blocking API.
  • Transparently handles reads and writes to/from memory on both host and device.
  • Provides Python bindings to nvCOMP.

Documentation

Examples

Python

import cupy
import kvikio

def main(path):
    a = cupy.arange(100)
    f = kvikio.CuFile(path, "w")
    # Write whole array to file
    f.write(a)
    f.close()

    b = cupy.empty_like(a)
    f = kvikio.CuFile(path, "r")
    # Read whole array from file
    f.read(b)
    assert all(a == b)
    f.close()

    # Use contexmanager
    c = cupy.empty_like(a)
    with kvikio.CuFile(path, "r") as f:
        f.read(c)
    assert all(a == c)

    # Non-blocking read
    d = cupy.empty_like(a)
    with kvikio.CuFile(path, "r") as f:
        future1 = f.pread(d[:50])
        future2 = f.pread(d[50:], file_offset=d[:50].nbytes)
        # Note: must wait for futures before exiting block
        # at which point the file is closed.
        future1.get()  # Wait for first read
        future2.get()  # Wait for second read
    assert all(a == d)


if __name__ == "__main__":
    main("/tmp/kvikio-hello-world-file")

C++

#include <cstddef>
#include <cuda_runtime.h>
#include <kvikio/file_handle.hpp>
using namespace std;

int main()
{
  // Create two arrays `a` and `b`
  constexpr std::size_t size = 100;
  void *a = nullptr;
  void *b = nullptr;
  cudaMalloc(&a, size);
  cudaMalloc(&b, size);

  // Write `a` to file
  kvikio::FileHandle fw("test-file", "w");
  size_t written = fw.write(a, size);
  fw.close();

  // Read file into `b`
  kvikio::FileHandle fr("test-file", "r");
  size_t read = fr.read(b, size);
  fr.close();

  // Read file into `b` in parallel using 16 threads
  kvikio::default_thread_pool::reset(16);
  {
    // FileHandles have RAII semantics
    kvikio::FileHandle f("test-file", "r");
    future<size_t> future = f.pread(b_dev, sizeof(a), 0);  // Non-blocking
    size_t read = future.get(); // Blocking
    // Notice, `f` closes automatically on destruction.
  }
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

libkvikio_cu12-24.10.0.tar.gz (2.0 kB view details)

Uploaded Source

File details

Details for the file libkvikio_cu12-24.10.0.tar.gz.

File metadata

  • Download URL: libkvikio_cu12-24.10.0.tar.gz
  • Upload date:
  • Size: 2.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.10.12

File hashes

Hashes for libkvikio_cu12-24.10.0.tar.gz
Algorithm Hash digest
SHA256 48369ebb2a45ab6b8b287c32feac809199193ff9221b3e66899f8f0903deb273
MD5 9cb7ad0ce7377eb352686c06d01d67fc
BLAKE2b-256 1665916882a1b228f15c126670aeb436cfc1b5af874ca1a4507fb43b0842666a

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page