主要内容

Kernels from Library Calls

GPU Coder™ supports libraries optimized for CUDA®GPU，例如Cublas，Cusolver，Cufft，推力，Cudnn和Tensorrt库。

  • The cuBLAS library is an implementation of Basic Linear algebra Subprograms (BLAS) on top of the NVIDIA®库达运行时间。它使您可以访问NVIDIA GPU的计算资源。

  • 基于cuSOLVER库是一个高级包on the cuBLAS and cuSPARSE libraries. It provides useful LAPACK-like features, such as common matrix factorization and triangular solve routines for dense matrices, a sparse least-squares solver, and an Eigenvalue solver.

  • The cuFFT library provides a high-performance implementation of the Fast Fourier Transform (FFT) algorithm on NVIDIA GPUs. The cuBLAS, cuSOLVER, and cuFFT libraries are part of the NVIDIA CUDA Toolkit.

  • Thrust is a C++ template library for CUDA. The Thrust library is shipped with CUDA Toolkit and allows you to take advantage of GPU-accelerated primitives such as sort to implement complex high-performance parallel applications.

  • The NVIDIA CUDA Deep Neural Network library (cuDNN) is a GPU-accelerated library of primitives for deep neural networks. cuDNN provides highly tuned implementations for standard routines such as forward and backward convolution, pooling, normalization, and activation layers. The NVIDIATensorRT是高性能深度学习推理优化器和运行时库。有关更多信息，请参阅Code Generation for Deep Learning Networks by Using cuDNN和Code Generation for Deep Learning Networks by Using TensorRT.

GPU编码器不需要特殊的Pragma来生成库的内核调用。在代码生成过程中，当您选择启用CublasGPU编码器应用程序中的选项或使用config_object.GpuConfig.EnableCUBLAS = trueproperty in CLI, GPU Coder replaces some functionality with calls to the cuBLAS library. When you select theEnable cuSOLVERGPU编码器应用程序中的选项或使用config_object.gpuconfig.enablecusolver = trueproperty in CLI, GPU Coder replaces some functionality with calls to the cuSOLVER library. For GPU Coder to replace high-level math functions to library calls, the following conditions must be met:

  • GPU-specific library replacement must exist for these functions.

  • MATLAB®Coder™data size thresholds must be satisfied.

GPU编码器支持表中万博1manbetx列出的功能的Cufft，Cusolver和Cublas库替换。对于在CUDA中没有替换的功能，GPU编码器使用映射到GPU的便携式MATLAB函数。

MATLAB Function Description MATLAB CoderLAPACK Support cuBLAS, cuSOLVER, cuFFT, Thrust Support

mtimes

矩阵倍增

Yes

Yes

mldivide (‘\’)

线性方程的求解系统Ax=Bforx

Yes

Yes

鲁

lu矩阵分解

Yes

Yes

qr

正交三角分解

Yes

Partial

det

矩阵决定因素

Yes

Yes

chol

Cholesky factorization

Yes

Yes

rcond

Reciprocal condition number

Yes

Yes

linsolve

线性方程的求解系统sAx=B

Yes

Yes

eig

Eigenvalues and eigen vectors

Yes

不

schur

Schur decomposition

Yes

不

svd

Singular value decomposition

Yes

Partial

fft,fft2,fftn

Fast Fourier Transform

Yes

Yes

ifft,ifft2,ifftn

逆快速傅立叶变换

Yes

Yes

种类

Sort array elements

是的，使用gpucoder.sort

When you select theEnable cuFFTGPU编码器应用程序中的选项或使用config_object.GpuConfig.EnableCUFFT = true在CLI中的属性，GPU编码器地图fft，ifft，fft2，ifft2，fftn.ifftnfunction calls in your MATLAB code to the appropriate cuFFT library calls. For 2-D transforms and higher, GPU Coder creates multiple 1-D batched transforms. These batched transforms have higher performance than single transforms. GPU Coder only supports out-of-place transforms. IfEnable cuFFTis not selected, GPU Coder uses CFFTW可用的库或从便携式MATLAB FFT生成内核。支持单精度数据类型。万博1manbetx输入和输出可以是真实的或复杂的，但是实现的转换速度更快。Cufft库支持输入尺寸通常万博1manbetx被指定为2的功率或可以将其纳入较小素数的产品的值。通常，较小的主要因素，性能越好。

不te

使用cuda库名称，例如袖口,cublas， 和cudnnas the names of your MATLAB function results in code generation errors.

See Also

|||||

相关话题