MATLAB代码的内核创建

MATLAB代码结构和创建CUDA的模式^®GPU kernels

GPU Coder™ generates and executes optimized CUDA kernels for specific algorithm structures and patterns in your MATLAB^®代码. The generated code calls optimized NVIDIA^®CUDA libraries, including cuFFT, cuSolver, cuBLAS, cuDNN, and TensorRT. The generated code can be integrated into your project as source code, static libraries, or dynamic libraries, and can be compiled for desktops, servers, and GPUs embedded on NVIDIA Jetson, DRIVE, and other platforms. GPU Coder lets you incorporate handwritten CUDA code into your algorithms and into the generated code.

Apps

expand all

GPU Coder

GPU Coder	Generate GPU code fromMATLAB代码
GPU Environment Check	Verify and set up GPU code generation environment

Functions

expand all

Code Generation

`代码gen`	从中生成C/C ++代码MATLAB代码
`GPUCODER`	OpenGPU Coderapp
`Coder.CheckgPuinstall`	Verify GPU code generation environment
`代码r.gpuConfig`	Configuration parameters forCUDA代码generation fromMATLAB使用代码GPU Coder

代码生成编程

`half`	Construct half-precision numeric object
`代码r.gpu.kernel`	Pragma that maps`for`-loops to GPU kernels
`代码r.gpu.kernelfun`	Pragma that maps function to GPU kernels
`代码r.gpu.nokernel`	Pragma to disable kernel creation for loops
`代码r.gpu.constantMemory`	Pragma that maps a variable to the constant memory on GPU
`GPUCODER.stencilKernel`	创造CUDA代码for stencil functions
`gpucoder.matrixmatrixkernel`	Optimized GPU implementation of functions containing matrix-matrix operations
`GPUCODER.batchedMatrixMultiply`	Optimized GPU implementation of batched matrix multiply operation
`gpucoder.stridedmatrixmultiply`	Optimized GPU implementation of strided and batched matrix multiply operation
`GPUCODER.batchedMatrixMultiplyAdd`	Optimized GPU implementation of batched matrix multiply with add operation
`gpucoder.stridedmatrixmultiplyAdd`	Optimized GPU implementation of strided, batched matrix multiply with add operation
`代码r.gpu.persistentMemory`	将变量分配为GPU上的持续内存
`GPUCODER.sort`	Optimized GPU implementation of theMATLABsort function
`coder.gpu.iterations`	Pragma向代码生成器提供信息以在可变界循环上做出并行决策
`GPUCODER.transpose`	Optimized GPU implementation of theMATLABtranspose function
`GPUCODER.reduce`	Optimized GPU implementation for reduction operations
`CODER.CEVAL`	Call external C/C++ function

Objects

expand all

代码配置

`代码r.gpuConfig`	Configuration parameters forCUDA代码generation fromMATLAB使用代码GPU Coder
`Coder.CodeConfig`	Configuration parameters for C/C++ code generation fromMATLAB代码
`代码r.EmbeddedCodeConfig`	Configuration parameters for C/C++ code generation fromMATLAB代码with嵌入式编码器
`代码r.gpuEnvConfig`	创建包含传递给参数的配置对象`Coder.CheckgPuinstall`用于执行GPU代码生成环境检查

Topics

Kernels from Element-Wise Loops

创造kernels from MATLAB functions containing scalarized, element-wise math operations.

Kernels from Scatter-Gather Type Operations

创造kernels from MATLAB functions containing reduction operations.

Kernels from Library Calls

Target GPU optimized math libraries such as cuBLAS, cuSOLVER, cuFFT, and Thrust.

Support for GPU Arrays

Generate CUDA code that uses GPU arrays.

旧版代码集成

将自定义GPU代码与用于代码生成的MATLAB代码集成。

Design Patterns

创造kernels for MATLAB functions containing computational design patterns.

GPU Memory Allocation and Minimization

Memory allocation options and optimizations for GPU Coder.

Featured Examples

$Simulate Diffraction Patterns Using CUDA FFT Libraries$

Simulate Diffraction Patterns Using CUDA FFT Libraries

使用GPU CODER™利用CUDA®快速傅立叶变换库（CUFFT）来计算NVIDIA®GPU上的二维FFT。二维傅立叶变换用于计算远场衍射模式。当单色光源通过一个小光圈（例如在Young的双缝实验中）时，您可以观察到这些衍射模式。此示例还向您展示了如何在生成CUDA MEX，源代码，静态库，动态库和可执行文件时如何使用GPU指针作为入口点函数的输入。通过使用此功能，通过最小化生成的代码中的cudamcpy调用数量来提高生成代码的性能。

打开脚本

QR Decomposition on NVIDIA GPU Using cuSOLVER Libraries

创建一个独立的CUDA®可执行文件，该可执行文件利用CUDA求解器库（Cusolver）。该示例使用曲线拟合应用程序，该应用程序在道路上模仿自动车道跟踪以说明：通过使用矩阵QR分解将任意阶多项式拟合到嘈杂数据。

打开脚本

GPU上的模具处理

Generate CUDA® kernels for stencil type operations by implementing "Game of Life" by John H. Conway.

打开脚本

$使用GPU编码器基准A \ b$

使用GPU编码器基准A \ b

Benchmark solving a linear system by generating GPU code. Use matrix left division, also known asmldivide或反斜杠符(\),解决系统of linear equationsa*x = bforx(that is, computex = A\b).

打开脚本