Dev & Engineering ✓ NVIDIA · Official doca-gpunetiocudagpudirect-rdmabluefieldconnectxpersistent-kernelnetwork-programming

DOCA GPUNetIO Development Skill

Helps developers connect CUDA kernels on NVIDIA GPUs to DOCA network queues for GPU-side packet I/O and debugging.

FollowSkills review · FSRS-2.0
Not recommended
55/ 100 5-point scale 2.8 / 5
Trust18 / 25 · 3.6/5

The documentation makes permissions, CUDA/DOCA versioning, nvidia_peermem, buffer registration, lifecycle, and rollback risks visible, and it does not request credentials; however, it recommends sudo modprobe and hardware/driver access without consistently requiring user confirmation, while least-privilege and recovery verification remain incomplete, so 7 points are deducted.

Reliability8 / 20 · 2.0/5

SKILL.md, CAPABILITIES.md, and TASKS.md provide a fairly consistent configure/build/run/test/debug workflow and error taxonomy; however, operation depends on a local DOCA installation, specialized hardware, and several unbundled companion skills, with no statically verifiable key-path tests and several unverified technical assertions, so the static ceiling applies.

Adaptability10 / 15 · 3.3/5

Audience, trigger phrases, prerequisites, exclusions, and routing are clearly described, and the guidance covers C/CUDA plus some non-C host integrations; however, it is limited to a specialized Linux/NVIDIA/DOCA/NIC or DPU environment, Chinese-language support is unspecified, and some core references depend on overseas documentation, warranting a deduction.

Convention9 / 15 · 3.0/5

Information architecture, progressive loading, related skills, dependency notes, task verbs, and limitation disclosures are strong; however, author, release version, changelog, and maintenance details are incomplete, the frontmatter license says Apache-2.0 while SKILLCARD says Apache-2.0 AND CC-BY-4.0, and signature fields remain TBD, so 6 points are deducted.

Effectiveness6 / 15 · 2.0/5

The material covers configure, build, modify, run, test, and debug, with concrete commands, API symbols, termination guidance, and rollback concepts, so it plausibly addresses the core task; however, it ships no directly buildable sample or test program, and static review cannot verify outcome correctness, so the score remains below the static maximum.

Verifiability4 / 10 · 2.0/5

There is a committed benchmark report, evaluation configuration, CI regression contract, and references to local/upstream material; however, the evaluation dataset is unavailable, the reported results are largely self-described, and reproducible key-path evidence is thin, so the score is limited to 4.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 55f18499943e
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • Do not treat the PASS in BENCHMARK.md or the SKILLCARD quality fields as independent validation; the evaluation dataset is unavailable and signature/version fields remain TBD.
  • Before sudo modprobe, driver inspection, persistent-kernel, or network-queue operations, obtain explicit confirmation and establish the target device, stop signal, and recoverable rollback path.
  • License metadata is inconsistent between Apache-2.0 and Apache-2.0 AND CC-BY-4.0 and should be reconciled before publication.
  • GPUNetIO requires specialized hardware, matched CUDA/DOCA versions, and a local installation; overseas DOCA documentation may be difficult to reach from mainland-China networks.
Review evidence [1][2][3][4][5][6][7][8][9]
See the full review method →

What does this skill do, and when should you use it?

This skill provides hands-on DOCA GPUNetIO guidance for external developers building GPU-initiated networking applications with host-side C/C++ and device-side CUDA C++. It covers the per-device doca_gpu context, GPU-visible RX/TX queues, persistent CUDA kernels, capability checks, CUDA buffer registration, and layered error diagnosis. It assumes DOCA, a CUDA version matched to DOCA, underlying DOCA Ethernet queues, and the required hardware are already prepared. It is an agent-guidance loader, not a bundle of buildable application source, CUDA kernels, or standalone build manifests.

Reads the local DOCA installation through the doca-gpunetio pkg-config module and directs the agent to CAPABILITIES.md and TASKS.md. It provides configure, build, modify, run, test, debug, and rollback workflows; explains how to create doca_gpu contexts and doca_gpu_eth_rxq/doca_gpu_eth_txq handles; checks DOCA capability-query results together with cudaGetDeviceProperties; guides cudaMalloc buffer allocation and doca_buf_arr_create_* registration; diagnoses DOCA_ERROR_* returns, CUDA/DOCA version skew, missing nvidia_peermem, and persistent-kernel failures; and routes out-of-scope questions to related skills.

  1. A developer with a BlueField DPU or ConnectX NIC wants a persistent CUDA kernel to poll a GPU-visible RX queue directly.
  2. A developer with multiple NVIDIA GPUs needs to determine whether a selected CUDA device ordinal supports GPU-initiated networking.
  3. A developer whose DOCA Ethernet queues work but GPUNetIO returns DOCA_ERROR_NOT_SUPPORTED needs to isolate capability, driver, or nvidia_peermem issues.
  4. A C/CUDA developer needs to allocate buffers with cudaMalloc, register them with DOCA, and prepare them before starting the context.
  5. A developer needs to verify whether a GPUNetIO API or persistent-kernel helper is supported by the installed DOCA and CUDA combination.

What are this skill's strengths and limitations?

Pros
  • Covers device capability checks, queue integration, buffer registration, and layered error diagnosis.
  • Clearly separates GPUNetIO from DOCA Ethernet, DOCA installation, and general CUDA work.
  • Includes workflows for configure, build, modify, run, test, debug, and rollback.
  • Benefits from the NVIDIA skills catalog’s signing, evaluation, and daily synchronization process.
Limitations
  • Does not include buildable GPUNetIO application code or CUDA kernel templates.
  • Requires an existing DOCA and CUDA environment with matching DOCA and CUDA versions.
  • Requires an NVIDIA GPU, a BlueField DPU or ConnectX NIC, and nvidia_peermem; some samples also need an InfiniBand-capable RNIC.
  • Does not cover DOCA installation, underlying Ethernet queue setup, DPA, or general CUDA programming.
  • The supplied source does not show concrete automated test commands, platform test results, or performance benchmarks.

How do you install this skill?

Install the skill from the NVIDIA/skills collection with the skills CLI:

npx skills add nvidia/skills --skill doca-gpunetio --yes

The README does not provide a separate copy-only command for the skills/doca-gpunetio directory. After installation, the skill becomes available when an agent loads it for a relevant task.

How do you use this skill?

First ensure that DOCA is installed at /opt/mellanox/doca, the CUDA version matches DOCA, nvidia_peermem is loaded, and the underlying DOCA Ethernet RX/TX queues are already configured. Then ask for a concrete GPUNetIO task, such as: “How do I make a persistent CUDA kernel receive packets directly from the NIC?” For configure, build, modify, run, test, or debug work, the skill uses TASKS.md; for capability and feature questions, it uses CAPABILITIES.md.

How does this skill compare with similar options?

Unlike doca-eth, this skill focuses on creating GPU-visible queue handles over existing DOCA Ethernet RX/TX queues and using them from CUDA kernels; underlying Ethernet queue setup belongs to doca-eth. Unlike doca-setup, it does not install or prepare DOCA or CUDA. Unlike doca-debug, it specializes in GPUNetIO issues involving CUDA, GPUDirect RDMA, version matching, and persistent kernels.

FAQ

Does the skill include a runnable sample application?
No. It directs users to the installed DOCA samples under /opt/mellanox/doca/samples/doca_gpunetio/ and to the GPU Packet Processing reference application, then recommends minimum-diff sample modifications.
Does the source state whether using it costs money?
No. The supplied material does not specify the cost of the skill or the DOCA SDK.
Why can DOCA Ethernet work while GPUNetIO still fails?
The DOCA or CUDA capability check may fail, nvidia_peermem may be unloaded, the CUDA and DOCA versions may be mismatched, or GPU buffers may not have been registered correctly.
Is it suitable for general CUDA programming?
No. It is explicitly scoped to GPUNetIO work that connects DOCA network queues to CUDA kernels; general CUDA questions should be routed elsewhere.

More skills from this repository

All from NVIDIA/skills

Dev & Engineering ✓ NVIDIA · Official

DOCA GPI GPU-Initiated RDMA Skill

Helps CUDA kernels drive RDMA queues directly from GPU memory without host-CPU mediation.

Dev & Engineering ✓ NVIDIA · Official

DOCA Verbs Raw RDMA Control

Guides DOCA developers who genuinely need low-level verbs control, porting, and diagnosis.

Automation & Ops ✓ NVIDIA · Official

DOCA Bench Benchmarking Skill

Measure DOCA library throughput, latency, and bandwidth reproducibly on real NVIDIA networking hardware.

Dev & Engineering ✓ NVIDIA · Official

DOCA Flow DPA Provider

Guides developers in exporting DOCA Flow pipes and resources into BlueField DPA for direct kernel-side access and mutation.

Dev & Engineering ✓ NVIDIA · Official

DOCA Flow gRPC Remote Control

Deploy, secure, smoke-test, and troubleshoot DOCA Flow’s gRPC control plane for non-C++ clients.

Dev & Engineering ✓ NVIDIA · Official

DOCA Hardware Telemetry Counter Reader

Guides developers in reading per-domain hardware counters from BlueField and ConnectX devices.

Dev & Engineering ✓ NVIDIA · Official

DOCA Flow DPA Performance

Guides defensible measurement of DOCA Flow rule-update and disable rates on DPA-capable NVIDIA hardware.

Automation & Ops ✓ NVIDIA · Official

DOCA Capabilities Inspector

Inspect what DOCA can see on a host through a read-only device and capability CLI.

Automation & Ops ✓ NVIDIA · Official

DOCA PCC Diagnostic Counters

Read fixed firmware and hardware PCC congestion diagnostics on ConnectX and BlueField devices.

Automation & Ops ✓ NVIDIA · Official

DOCA Management Service Operations

Operate and troubleshoot NVIDIA DMS for centralized BlueField and ConnectX management.

Dev & Engineering ✓ NVIDIA · Official

DOCA Telemetry Exporter Development

Guides DOCA applications in defining, emitting, and debugging structured telemetry for external consumers.

Dev & Engineering ✓ NVIDIA · Official

DOCA Flow Performance Measurement

Guides reproducible, defensible measurements of host-side and DPU-CPU DOCA Flow control-plane rule rates.

Dev & Engineering ✓ NVIDIA · Official

DOCA Device Management Development Skill

Programmatically manage BlueField and ConnectX state through the DOCA C API.

Dev & Engineering ✓ NVIDIA · Official

DOCA SHA OpenSSL Offload Engine

Adds DOCA SHA hardware acceleration to existing OpenSSL pipelines without rewriting the application around the doca-sha C API.

Dev & Engineering ✓ NVIDIA · Official

DOCA Ethernet Queue Development

Develop and debug DOCA Ethernet RX/TX queues on BlueField DPUs and ConnectX NICs.

Dev & Engineering ✓ NVIDIA · Official

DOCA GPUNetIO WRITE Bandwidth Benchmark

Build, run, and interpret sustained RDMA WRITE bandwidth measurements driven by CUDA kernels through the DOCA GPUNetIO surface.

Dev & Engineering ✓ NVIDIA · Official

DOCA Compress Hardware Offload

Guides hands-on DEFLATE and LZ4 decompression development and debugging on BlueField and ConnectX platforms.

Dev & Engineering ✓ NVIDIA · Official

DOCA AES-GCM Acceleration

Configure, validate, and debug DOCA AES-GCM offload on BlueField DPUs and ConnectX NICs.

Dev & Engineering ✓ NVIDIA · Official

DOCA SHA Acceleration

Guidance for offloading SHA hashing to NVIDIA BlueField and ConnectX hardware.

Dev & Engineering ✓ NVIDIA · Official

DOCA Arg Parser CLI

Guides developers in building and debugging standard CLIs for DOCA applications.

Related skills