Module loading

Function retrieval

Register count query

Shared memory query

Max threads query

CUDA context initialization

Error handling

Device initialization

Context creation

Context cleanup

Context synchronization

Device properties

PTX compilation

Linker creation

PTX addition

Module linking

Function retrieval

Kernel Compilation

Grid/Block Configuration

Kernel Invocation

Memory Transfer

Context Initialization

DeviceMemoryPool usage

PageLockedMemoryPool usage

Managed memory allocation

Pool-based allocation

Memory pool freeing

Pool statistics

Context initialization

GPUArray creation

Element-wise arithmetic

Magnitude calculation

Vector normalization

GPU-CPU transfer

Context initialization

Kernel compilation

Prepared call usage

In handler usage

Out handler usage

Grid/block configuration

Pagelocked Buffer Creation

Device Memory Allocation

Host-to-Device Transfer

Device-to-Host Transfer

Context Management

Timing Implementation

CUDA Array Creation

Texture Reference Setup

Addressing Mode Configuration

Filtering Mode Configuration

Texture Sampling in Kernel

Sparse Matrix Format

CG Solver Invocation

Preconditioner Integration

Convergence Configuration

Result Extraction