cuda

النجوم١٠

التفرعات١

آخر تحديث٤ يوليو ٢٠٢٦ في ٠٨:٣٢

NVIDIA CUDA parallel computing platform — use when writing .cu kernels, using cuBLAS/cuDNN/cuFFT/cuSPARSE/cuRAND/cuSolver, Thrust, or Cooperative Groups for GPU-accelerated computing

التثبيت

التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.

المصدر

datathings

datathings/marketplace

فتح مستودع GitHub عرض مستودعات المنشئ

تنزيل

المهن ذات الصلةSOC

استنادا إلى تصنيف SOC المهني

مطوّرو البرمجياتمهن الحاسوب والرياضيات·SOC 15-1252

مستكشف الملفات

10 ملفات

SKILL.md

readonly

name	cuda
description	NVIDIA CUDA parallel computing platform — use when writing .cu kernels, using cuBLAS/cuDNN/cuFFT/cuSPARSE/cuRAND/cuSolver, Thrust, or Cooperative Groups for GPU-accelerated computing

CUDA

Overview

CUDA is NVIDIA's parallel computing platform and programming model for GPU-accelerated applications. It provides direct access to the GPU's virtual instruction set and parallel compute elements for executing kernels in C, C++, and Fortran.

cuda-samples version: v13.3 (CUDA Toolkit 13.3) CUDALibrarySamples: main (July 2026) Language: C/C++ (.cu files) Licenses: BSD-3-Clause (cuda-samples), Apache-2.0 (CUDALibrarySamples)

v13.3 layout note: cuda-samples renamed its top-level Samples/ directory to cpp/ (Python samples now live under python/). C++ samples are grouped under cpp/0_Introduction, cpp/4_CUDA_Libraries, cpp/6_Performance, plus new cpp/9_CUDA_Tile (CUDA Tile C++) and CCCL 3.3 feature samples (cubDeviceFind, cubDeviceSegmentedScan, cubDeviceTransform, libcuxxRandom, libcuxxMdspan) under cpp/4_CUDA_Libraries/.

Quick Start

// Minimal kernel + launch
__global__ void addVectors(float *a, float *b, float *c, int n) {
    int i = blockIdx.x * blockDim.x + threadIdx.x;
    if (i < n) c[i] = a[i] + b[i];
}

int main() {
    int n = 1 << 20;
    float *d_a, *d_b, *d_c;
    cudaMalloc(&d_a, n * sizeof(float));
    cudaMalloc(&d_b, n * sizeof(float));
    cudaMalloc(&d_c, n * sizeof(float));

    int threads = 256;
    int blocks = (n + threads - 1) / threads;
    addVectors<<<blocks, threads>>>(d_a, d_b, d_c, n);
    cudaDeviceSynchronize();

    cudaFree(d_a); cudaFree(d_b); cudaFree(d_c);
    return 0;
}

Core Concepts

Kernel: __global__ function executed on GPU by many parallel threads
Grid/Block/Thread: Launch hierarchy — <<<gridDim, blockDim>>> configures parallelism
Device memory: Must be explicitly allocated with cudaMalloc and freed with cudaFree
Streams: Async execution queues; default stream is synchronous with host
Unified Memory (cudaMallocManaged): Automatically migrates data between CPU and GPU; check support with device_prop.managedMemory

API Reference

Domain	File	Description
CUDA Runtime	api-runtime.md	Device mgmt, memory, streams, events, kernel launch
cuBLAS	api-cublas.md	Dense linear algebra: GEMM, GEMV, TRSM, grouped batched ops
cuFFT	api-cufft.md	1D/2D/3D FFT and batched transforms
cuSPARSE	api-cusparse.md	Sparse matrix ops: SpMM, SpMV, format conversions
cuRAND	api-curand.md	Random number generation on GPU
cuSolver	api-cusolver.md	Dense/sparse solvers: QR, LU, eigenvalue, SVD
Thrust	api-thrust.md	STL-like GPU algorithms: sort, reduce, transform, scan
Cooperative Groups	api-cooperative-groups.md	Flexible thread synchronization beyond blocks
Workflows	workflows.md	Complete working examples

Common Workflows

See references/workflows.md for complete examples.

Quick reference:

Matrix multiply: see workflows.md — cuBLAS GEMM section
FFT: see workflows.md — cuFFT 1D section
Custom kernel: see workflows.md — Custom CUDA Kernel section
Unified memory: see workflows.md — Unified Memory section
Error-check macros: see workflows.md — Error-Checked CUDA Boilerplate

Key Considerations

Error checking: Always check return codes; use CUDA_CHECK(err) macro pattern
Synchronization: cudaDeviceSynchronize() or stream synchronize before reading results on host
Memory alignment: 128-byte alignment for coalesced global memory access
Occupancy: Use cudaOccupancyMaxPotentialBlockSize to tune block dimensions; uses uint32_t for array indexing to avoid overflow
Tensor Cores: Available on Volta+ (sm_70+); cuBLAS uses them automatically for GEMM with correct types
Column-major: cuBLAS and cuSolver use Fortran (column-major) layout — transpose row-major C arrays or swap dimensions
cuFFT normalization: cuFFT does NOT normalize inverse transforms; divide by N manually
Streams: Always use cudaStreamNonBlocking when creating non-default streams to avoid implicit synchronization with the null stream
Unified Memory support: Check device_prop.managedMemory before using cudaMallocManaged; use cudaMemPrefetchAsync to avoid page faults
Driver API cleanup: Always call cuModuleUnload before cuCtxDestroy when using the CUDA Driver API
Compile flags: Use --gpu-architecture=sm_90a for Hopper (H100), sm_80 for Ampere (A100), sm_70 for Volta (V100)
Thrust tuples: Use cuda::std::tuple, cuda::std::make_tuple, and cuda::std::get (the thrust::tuple variants are replaced)

المزيد من هذا المستودع

نفس المستودع

greycat-c

datathings/marketplace

GreyCat C API and GCL Standard Library reference. Use for: (1) Native C development with gc_machine_t context, tensors, objects, memory management, crypto, I/O; (2) GCL Standard Library modules - std::core (Date/Time/Tuple/geospatial types), std::runtime (Scheduler/Task/Logger/Identity/Security/System/License/OpenAPI/MCP), std::io (CSV/JSON/XML/HTTP/Email/FileWalker/S3), std::util (Queue/Stack/SlidingWindow/TimeWindow/Gaussian/Histogram/Quantizers/Random/Uuid/Crypto); (3) Plugin development patterns - lifecycle hooks, type configuration, nativegen, module-level and type-level function linking, global state, thread safety, conditional logging. Keywords: GreyCat, GCL, native functions, tensors, task automation, scheduler, plugin development.

2026-07-2810

greycat

datathings/marketplace

Build, run, and edit GreyCat projects. GreyCat is a statically-typed language plus runtime for graph-persistent, time-series-aware applications. Use when reading or writing `.gcl` source, when the user mentions GreyCat / project.gcl / nodeTime / nodeList / nodeIndex / nodeGeo / @expose / @library, or when the task involves running `greycat <command>`, deploying a project, or reasoning about gcdata/, lib/, files/, webroot/.

2026-07-2110

llamacpp

datathings/marketplace

Complete llama.cpp C/C++ API reference covering model loading, inference, text generation, embeddings, chat, tokenization, sampling, batching, KV cache, LoRA adapters, and state management. Triggers on: llama.cpp questions, LLM inference code, GGUF models, local AI/ML inference, C/C++ LLM integration, "how do I use llama.cpp", API function lookups, implementation questions, troubleshooting llama.cpp issues, and any llama-cpp or ggerganov/llama.cpp mentions.

2026-07-2110

vllm

datathings/marketplace

Complete vLLM v0.19.0 Python API reference for high-throughput LLM inference: offline batch generation, chat, embeddings, classification, structured outputs, LoRA adapters, multimodal inputs, and OpenAI-compatible server. Triggers on: vLLM questions, Python LLM serving, GPU inference, "how do I use vllm", batch inference, vllm serve, OpenAI-compatible API, structured JSON output, LoRA serving.

2026-07-0910

ggml

datathings/marketplace

C tensor computation library for ML inference and training. Use when working with ggml graphs, GGUF model files, backend scheduling, quantization, or implementing low-level ML ops in C/C++.

2026-07-0410

ollama

datathings/marketplace

Run and manage local LLMs via Ollama REST API — text generation, chat completions, embeddings, tool calling, structured output, and model management. Use when code imports ollama, references localhost:11434, or user asks about local LLM inference.

2026-07-0410

CUDA

Overview

cuda-samples version: v13.3 (CUDA Toolkit 13.3) CUDALibrarySamples: main (July 2026) Language: C/C++ (.cu files) Licenses: BSD-3-Clause (cuda-samples), Apache-2.0 (CUDALibrarySamples)

v13.3 layout note: cuda-samples renamed its top-level Samples/ directory to cpp/ (Python samples now live under python/). C++ samples are grouped under cpp/0_Introduction, cpp/4_CUDA_Libraries, cpp/6_Performance, plus new cpp/9_CUDA_Tile (CUDA Tile C++) and CCCL 3.3 feature samples (cubDeviceFind, cubDeviceSegmentedScan, cubDeviceTransform, libcuxxRandom, libcuxxMdspan) under cpp/4_CUDA_Libraries/.

Quick Start

// Minimal kernel + launch __global__ void addVectors(float *a, float *b, float *c, int n) { int i = blockIdx.x * blockDim.x + threadIdx.x; if (i < n) c[i] = a[i] + b[i]; } int main() { int n = 1 << 20; float *d_a, *d_b, *d_c; cudaMalloc(&d_a, n * sizeof(float)); cudaMalloc(&d_b, n * sizeof(float)); cudaMalloc(&d_c, n * sizeof(float)); int threads = 256; int blocks = (n + threads - 1) / threads; addVectors<<<blocks, threads>>>(d_a, d_b, d_c, n); cudaDeviceSynchronize(); cudaFree(d_a); cudaFree(d_b); cudaFree(d_c); return 0; }

Core Concepts

Kernel: __global__ function executed on GPU by many parallel threads

Grid/Block/Thread: Launch hierarchy — <<<gridDim, blockDim>>> configures parallelism

Device memory: Must be explicitly allocated with cudaMalloc and freed with cudaFree

Streams: Async execution queues; default stream is synchronous with host

Unified Memory (cudaMallocManaged): Automatically migrates data between CPU and GPU; check support with device_prop.managedMemory

API Reference

Domain

File

Description

CUDA Runtime

api-runtime.md

Device mgmt, memory, streams, events, kernel launch

cuBLAS

api-cublas.md

Dense linear algebra: GEMM, GEMV, TRSM, grouped batched ops

cuFFT

api-cufft.md

1D/2D/3D FFT and batched transforms

cuSPARSE

api-cusparse.md

Sparse matrix ops: SpMM, SpMV, format conversions

cuRAND

api-curand.md

Random number generation on GPU

cuSolver

api-cusolver.md

Dense/sparse solvers: QR, LU, eigenvalue, SVD

Thrust

api-thrust.md

STL-like GPU algorithms: sort, reduce, transform, scan

Cooperative Groups

api-cooperative-groups.md

Flexible thread synchronization beyond blocks

Workflows

workflows.md

Complete working examples

Common Workflows

Quick reference:

Matrix multiply: see workflows.md — cuBLAS GEMM section

FFT: see workflows.md — cuFFT 1D section

Custom kernel: see workflows.md — Custom CUDA Kernel section

Unified memory: see workflows.md — Unified Memory section

Error-check macros: see workflows.md — Error-Checked CUDA Boilerplate

Key Considerations

Error checking: Always check return codes; use CUDA_CHECK(err) macro pattern

Synchronization: cudaDeviceSynchronize() or stream synchronize before reading results on host

Memory alignment: 128-byte alignment for coalesced global memory access

Occupancy: Use cudaOccupancyMaxPotentialBlockSize to tune block dimensions; uses uint32_t for array indexing to avoid overflow

Tensor Cores: Available on Volta+ (sm_70+); cuBLAS uses them automatically for GEMM with correct types

Column-major: cuBLAS and cuSolver use Fortran (column-major) layout — transpose row-major C arrays or swap dimensions

cuFFT normalization: cuFFT does NOT normalize inverse transforms; divide by N manually

Streams: Always use cudaStreamNonBlocking when creating non-default streams to avoid implicit synchronization with the null stream

Unified Memory support: Check device_prop.managedMemory before using cudaMallocManaged; use cudaMemPrefetchAsync to avoid page faults

Driver API cleanup: Always call cuModuleUnload before cuCtxDestroy when using the CUDA Driver API

Compile flags: Use --gpu-architecture=sm_90a for Hopper (H100), sm_80 for Ampere (A100), sm_70 for Volta (V100)

Thrust tuples: Use cuda::std::tuple, cuda::std::make_tuple, and cuda::std::get (the thrust::tuple variants are replaced)