nvGRAPH API参考分析（二）
nvGRAPH API参考分析（二）
本文提供了简单的示例。
1. nvGRAPH convert topology example
void check(nvgraphStatus_t status) {
if (status != NVGRAPH_STATUS_SUCCESS) {
printf("ERROR : %d\n",status);
exit(0);
}
}
int main(int argc, char **argv) {
size_t n = 6, nnz = 10;
// nvgraph variables
nvgraphHandle_t handle;
nvgraphCSCTopology32I_t CSC_input;
nvgraphCSRTopology32I_t CSR_output;
float *src_weights_d, *dst_weights_d;
cudaDataType_t edge_dimT = CUDA_R_32F;
// Allocate source data
CSC_input = (nvgraphCSCTopology32I_t) malloc(sizeof(struct nvgraphCSCTopology32I_st));
CSC_input->nvertices = n; CSC_input->nedges = nnz;
cudaMalloc( (void**)&(CSC_input->destination_offsets), (n+1)*sizeof(int));
cudaMalloc( (void**)&(CSC_input->source_indices), nnz*sizeof(int));
cudaMalloc( (void**)&src_weights_d, nnz*sizeof(float));
// Copy source data
float src_weights_h[] = {0.333333f, 0.5f, 0.333333f, 0.5f, 0.5f, 1.0f, 0.333333f, 0.5f, 0.5f, 0.5f};
int destination_offsets_h[] = {0, 1, 3, 4, 6, 8, 10};
int source_indices_h[] = {2, 0, 2, 0, 4, 5, 2, 3, 3, 4};
cudaMemcpy(CSC_input->destination_offsets, destination_offsets_h, (n+1)*sizeof(int), cudaMemcpyDefault);
cudaMemcpy(CSC_input->source_indices, source_indices_h, nnz*sizeof(int), cudaMemcpyDefault);
cudaMemcpy(src_weights_d, src_weights_h, nnz*sizeof(float), cudaMemcpyDefault);
// Allocate destination data
CSR_output = (nvgraphCSRTopology32I_t) malloc(sizeof(struct nvgraphCSRTopology32I_st));
cudaMalloc( (void**)&(CSR_output->source_offsets), (n+1)*sizeof(int));
cudaMalloc( (void**)&(CSR_output->destination_indices), nnz*sizeof(int));
cudaMalloc( (void**)&dst_weights_d, nnz*sizeof(float));
// Starting nvgraph and convert
check(nvgraphCreate (&handle));
check(nvgraphConvertTopology(handle, NVGRAPH_CSC_32, CSC_input, src_weights_d,
&edge_dimT, NVGRAPH_CSR_32, CSR_output, dst_weights_d));
// Free memory
check(nvgraphDestroy(handle));
cudaFree(CSC_input->destination_offsets);
cudaFree(CSC_input->source_indices);
cudaFree(CSR_output->source_offsets);
cudaFree(CSR_output->destination_indices);
cudaFree(src_weights_d);
cudaFree(dst_weights_d);
free(CSC_input);
free(CSR_output);
return 0;
}
2. nvGRAPH convert graph example
void check(nvgraphStatus_t status) {
if (status != NVGRAPH_STATUS_SUCCESS) {
printf("ERROR : %d\n",status);
exit(0);
}
}
int main(int argc, char **argv) {
size_t n = 6, nnz = 10, vert_sets = 2, edge_sets = 1;
// nvgraph variables
nvgraphHandle_t handle; nvgraphGraphDescr_t src_csc_graph;
nvgraphCSCTopology32I_t CSC_input;
cudaDataType_t edge_dimT = CUDA_R_32F;
cudaDataType_t* vertex_dimT;
// Allocate host data
float *pr_1 = (float*)malloc(n*sizeof(float));
void **vertex_dim = (void**)malloc(vert_sets*sizeof(void*));
vertex_dimT = (cudaDataType_t*)malloc(vert_sets*sizeof(cudaDataType_t));
CSC_input = (nvgraphCSCTopology32I_t) malloc(sizeof(struct nvgraphCSCTopology32I_st));
// Initialize host data
float weights_h[] = {0.333333f, 0.5f, 0.333333f, 0.5f, 0.5f, 1.0f, 0.333333f, 0.5f, 0.5f, 0.5f};
int destination_offsets_h[] = {0, 1, 3, 4, 6, 8, 10};
int source_indices_h[] = {2, 0, 2, 0, 4, 5, 2, 3, 3, 4};
float bookmark_h[] = {0.0f, 1.0f, 0.0f, 0.0f, 0.0f, 0.0f};
vertex_dim[0] = (void*)bookmark_h; vertex_dim[1]= (void*)pr_1;
vertex_dimT[0] = CUDA_R_32F; vertex_dimT[1]= CUDA_R_32F, vertex_dimT[2]= CUDA_R_32F;
// Starting nvgraph
check(nvgraphCreate (&handle));
check(nvgraphCreateGraphDescr (handle, &src_csc_graph));
CSC_input->nvertices = n; CSC_input->nedges = nnz;
CSC_input->destination_offsets = destination_offsets_h;
CSC_input->source_indices = source_indices_h;
// Set graph connectivity and properties (tranfers)
check(nvgraphSetGraphStructure(handle, src_csc_graph, (void*)CSC_input, NVGRAPH_CSC_32));
check(nvgraphAllocateVertexData(handle, src_csc_graph, vert_sets, vertex_dimT));
check(nvgraphAllocateEdgeData (handle, src_csc_graph, edge_sets, &edge_dimT));
for (int i = 0; i < 2; ++i)
check(nvgraphSetVertexData(handle, src_csc_graph, vertex_dim[i], i));
check(nvgraphSetEdgeData(handle, src_csc_graph, (void*)weights_h, 0));
// Convert to CSR graph
nvgraphGraphDescr_t dst_csr_graph;
check(nvgraphCreateGraphDescr (handle, &dst_csr_graph));
check(nvgraphConvertGraph(handle, src_csc_graph, dst_csr_graph, NVGRAPH_CSR_32));
check(nvgraphDestroyGraphDescr(handle, src_csc_graph));
check(nvgraphDestroyGraphDescr(handle, dst_csr_graph));
check(nvgraphDestroy(handle));
free(pr_1); free(vertex_dim); free(vertex_dimT);
free(CSC_input);
return 0;
}
void check(nvgraphStatus_t status) {
if (status != NVGRAPH_STATUS_SUCCESS) {
printf("ERROR : %d\n",status);
exit(0);
}
}
int main(int argc, char **argv) {
size_t n = 6, nnz = 10, vert_sets = 2, edge_sets = 1;
float alpha1 = 0.9f; void *alpha1_p = (void *) &alpha1;
// nvgraph variables
nvgraphHandle_t handle; nvgraphGraphDescr_t graph;
nvgraphCSCTopology32I_t CSC_input;
cudaDataType_t edge_dimT = CUDA_R_32F;
cudaDataType_t* vertex_dimT;
// Allocate host data
float *pr_1 = (float*)malloc(n*sizeof(float));
void **vertex_dim = (void**)malloc(vert_sets*sizeof(void*));
vertex_dimT = (cudaDataType_t*)malloc(vert_sets*sizeof(cudaDataType_t));
CSC_input = (nvgraphCSCTopology32I_t) malloc(sizeof(struct nvgraphCSCTopology32I_st));
// Initialize host data
float weights_h[] = {0.333333f, 0.5f, 0.333333f, 0.5f, 0.5f, 1.0f, 0.333333f, 0.5f, 0.5f, 0.5f};
int destination_offsets_h[] = {0, 1, 3, 4, 6, 8, 10};
int source_indices_h[] = {2, 0, 2, 0, 4, 5, 2, 3, 3, 4};
float bookmark_h[] = {0.0f, 1.0f, 0.0f, 0.0f, 0.0f, 0.0f};
vertex_dim[0] = (void*)bookmark_h; vertex_dim[1]= (void*)pr_1;
vertex_dimT[0] = CUDA_R_32F; vertex_dimT[1]= CUDA_R_32F, vertex_dimT[2]= CUDA_R_32F;
// Starting nvgraph
check(nvgraphCreate (&handle));
check(nvgraphCreateGraphDescr (handle, &graph));
CSC_input->nvertices = n; CSC_input->nedges = nnz;
CSC_input->destination_offsets = destination_offsets_h;
CSC_input->source_indices = source_indices_h;
// Set graph connectivity and properties (tranfers)
check(nvgraphSetGraphStructure(handle, graph, (void*)CSC_input, NVGRAPH_CSC_32));
check(nvgraphAllocateVertexData(handle, graph, vert_sets, vertex_dimT));
check(nvgraphAllocateEdgeData (handle, graph, edge_sets, &edge_dimT));
for (int i = 0; i < 2; ++i)
check(nvgraphSetVertexData(handle, graph, vertex_dim[i], i));
check(nvgraphSetEdgeData(handle, graph, (void*)weights_h, 0));
check(nvgraphPagerank(handle, graph, 0, alpha1_p, 0, 0, 1, 0.0f, 0));
// Get result
check(nvgraphGetVertexData(handle, graph, vertex_dim[1], 1));
check(nvgraphDestroyGraphDescr(handle, graph));
check(nvgraphDestroy(handle));
free(pr_1); free(vertex_dim); free(vertex_dimT);
free(CSC_input);
return 0;
}
void check(nvgraphStatus_t status) {
if (status != NVGRAPH_STATUS_SUCCESS) {
printf("ERROR : %d\n",status);
exit(0);
}
}
int main(int argc, char **argv) {
const size_t n = 6, nnz = 10, vertex_numsets = 1, edge_numsets = 1;
float *sssp_1_h;
void** vertex_dim;
// nvgraph variables
nvgraphStatus_t status; nvgraphHandle_t handle;
nvgraphGraphDescr_t graph;
nvgraphCSCTopology32I_t CSC_input;
cudaDataType_t edge_dimT = CUDA_R_32F;
cudaDataType_t* vertex_dimT;
// Init host data
sssp_1_h = (float*)malloc(n*sizeof(float));
vertex_dim = (void**)malloc(vertex_numsets*sizeof(void*));
vertex_dimT = (cudaDataType_t*)malloc(vertex_numsets*sizeof(cudaDataType_t));
CSC_input = (nvgraphCSCTopology32I_t) malloc(sizeof(struct nvgraphCSCTopology32I_st));
vertex_dim[0]= (void*)sssp_1_h; vertex_dimT[0] = CUDA_R_32F;
float weights_h[] = {0.333333, 0.5, 0.333333, 0.5, 0.5, 1.0, 0.333333, 0.5, 0.5, 0.5};
int destination_offsets_h[] = {0, 1, 3, 4, 6, 8, 10};
int source_indices_h[] = {2, 0, 2, 0, 4, 5, 2, 3, 3, 4};
check(nvgraphCreate(&handle));
check(nvgraphCreateGraphDescr (handle, &graph));
CSC_input->nvertices = n; CSC_input->nedges = nnz;
CSC_input->destination_offsets = destination_offsets_h;
CSC_input->source_indices = source_indices_h;
// Set graph connectivity and properties (tranfers)
check(nvgraphSetGraphStructure(handle, graph, (void*)CSC_input, NVGRAPH_CSC_32));
check(nvgraphAllocateVertexData(handle, graph, vertex_numsets, vertex_dimT));
check(nvgraphAllocateEdgeData (handle, graph, edge_numsets, &edge_dimT));
check(nvgraphSetEdgeData(handle, graph, (void*)weights_h, 0));
// Solve
int source_vert = 0;
check(nvgraphSssp(handle, graph, 0, &source_vert, 0));
// Get and print result
check(nvgraphGetVertexData(handle, graph, (void*)sssp_1_h, 0));
//Clean
free(sssp_1_h); free(vertex_dim);
free(vertex_dimT); free(CSC_input);
check(nvgraphDestroyGraphDescr(handle, graph));
check(nvgraphDestroy(handle));
return 0;
}
5. nvGRAPH Semi-Ring SPMV example
void check(nvgraphStatus_t status) {
if (status != NVGRAPH_STATUS_SUCCESS) {
printf("ERROR : %d\n",status);
exit(0);
}
}
int main(int argc, char **argv) {
size_t n = 5, nnz = 10, vertex_numsets = 2, edge_numsets = 1;
float alpha = 1.0, beta = 0.0;
void *alpha_p = (void *)&alpha, *beta_p = (void *)β
void** vertex_dim;
cudaDataType_t edge_dimT = CUDA_R_32F;
cudaDataType_t* vertex_dimT;
// nvgraph variables
nvgraphStatus_t status; nvgraphHandle_t handle;
nvgraphGraphDescr_t graph;
nvgraphCSRTopology32I_t CSR_input;
// Init host data
vertex_dim = (void**)malloc(vertex_numsets*sizeof(void*));
vertex_dimT = (cudaDataType_t*)malloc(vertex_numsets*sizeof(cudaDataType_t));
CSR_input = (nvgraphCSRTopology32I_t) malloc(sizeof(struct nvgraphCSRTopology32I_st));
float x_h[] = {1.1f, 2.2f, 3.3f, 4.4f, 5.5f};
float y_h[] = {0.0f, 0.0f, 0.0f, 0.0f, 0.0f};
vertex_dim[0]= (void*)x_h; vertex_dim[1]= (void*)y_h;
vertex_dimT[0] = CUDA_R_32F; vertex_dimT[1]= CUDA_R_32F;
float weights_h[] = {1.0f, 4.0f, 2.0f, 3.0f, 5.0f, 7.0f, 8.0f, 9.0f, 6.0f, 1.5f};
int source_offsets_h[] = {0, 2, 4, 7, 9, 10};
int destination_indices_h[] = {0, 1, 1, 2, 0, 3, 4, 2, 4, 2};
check(nvgraphCreate(&handle));
check(nvgraphCreateGraphDescr(handle, &graph));
CSR_input->nvertices = n; CSR_input->nedges = nnz;
CSR_input->source_offsets = source_offsets_h;
CSR_input->destination_indices = destination_indices_h;
// Set graph connectivity and properties (tranfers)
check(nvgraphSetGraphStructure(handle, graph, (void*)CSR_input, NVGRAPH_CSR_32));
check(nvgraphAllocateVertexData(handle, graph, vertex_numsets, vertex_dimT));
for (int i = 0; i < vertex_numsets; ++i)
check(nvgraphSetVertexData(handle, graph, vertex_dim[i], i));
check(nvgraphAllocateEdgeData (handle, graph, edge_numsets, &edge_dimT));
check(nvgraphSetEdgeData(handle, graph, (void*)weights_h, 0));
// Solve
check(nvgraphSrSpmv(handle, graph, 0, alpha_p, 0, beta_p, 1, NVGRAPH_PLUS_TIMES_SR));
//Get result
check(nvgraphGetVertexData(handle, graph, (void*)y_h, 1));
//Clean
check(nvgraphDestroyGraphDescr(handle, graph));
check(nvgraphDestroy(handle));
free(vertex_dim); free(vertex_dimT); free(CSR_input);
return 0;
}
6. nvGRAPH Triangles Counting example
#include "stdlib.h"
#include "inttypes.h"
#include "stdio.h"
#include "nvgraph.h"
#define check( a ) \
{\
nvgraphStatus_t status = (a);\
if ( (status) != NVGRAPH_STATUS_SUCCESS) {\
printf("ERROR : %d in %s : %d\n", status, __FILE__ , __LINE__ );\
exit(0);\
}\
}
int main(int argc, char **argv)
{
// nvgraph variables
nvgraphHandle_t handle;
nvgraphGraphDescr_t graph;
nvgraphCSRTopology32I_t CSR_input;
// Init host data
CSR_input = (nvgraphCSRTopology32I_t) malloc(sizeof(struct nvgraphCSRTopology32I_st));
// Undirected graph:
// 0 2-------4
// \ / \ / \
// \ / \ / \
// \ / \ / \
// 1-------3-------5
// 3 triangles
// CSR of lower triangular of adjacency matrix:
const size_t n = 6, nnz = 8;
int source_offsets[] = {0, 0, 1, 2, 4, 6, 8};
int destination_indices[] = {0, 1, 1, 2, 2, 3, 3, 4};
check(nvgraphCreate(&handle));
check(nvgraphCreateGraphDescr (handle, &graph));
CSR_input->nvertices = n;
CSR_input->nedges = nnz;
CSR_input->source_offsets = source_offsets;
CSR_input->destination_indices = destination_indices;
// Set graph connectivity
check(nvgraphSetGraphStructure(handle, graph, (void*)CSR_input, NVGRAPH_CSR_32));
uint64_t trcount = 0;
check(nvgraphTriangleCount(handle, graph, &trcount));
printf("Triangles count: %" PRIu64 "\n", trcount);
free(CSR_input);
check(nvgraphDestroyGraphDescr(handle, graph));
check(nvgraphDestroy(handle));
return 0;
}
void check_status(nvgraphStatus_t status){
if ((int)status != 0) {
printf("ERROR : %d\n",status);
exit(0);
}
}
int main(int argc, char **argv){
//Example of graph (CSR format)
const size_t n = 7, nnz = 12, vertex_numsets = 2, edge_numset = 0;
int source_offsets_h[] = {0, 1, 3, 4, 6, 8, 10, 12};
int destination_indices_h[] = {5, 0, 2, 0, 4, 5, 2, 3, 3, 4, 1, 5};
//where to store results (distances from source) and where to store results (predecessors in search tree)
int bfs_distances_h[n], bfs_predecessors_h[n];
// nvgraph variables
nvgraphStatus_t status;
nvgraphHandle_t handle;
nvgraphGraphDescr_t graph;
nvgraphCSRTopology32I_t CSR_input;
cudaDataType_t* vertex_dimT;
size_t distances_index = 0;
size_t predecessors_index = 1;
vertex_dimT = (cudaDataType_t*)malloc(vertex_numsets*sizeof(cudaDataType_t));
vertex_dimT[distances_index] = CUDA_R_32I;
vertex_dimT[predecessors_index] = CUDA_R_32I;
//Creating nvgraph objects
check_status(nvgraphCreate (&handle));
check_status(nvgraphCreateGraphDescr (handle, &graph));
// Set graph connectivity and properties (tranfers)
CSR_input = (nvgraphCSRTopology32I_t) malloc(sizeof(struct nvgraphCSCTopology32I_st));
CSR_input->nvertices = n;
CSR_input->nedges = nnz;
CSR_input->source_offsets = source_offsets_h;
CSR_input->destination_indices = destination_indices_h;
check_status(nvgraphSetGraphStructure(handle, graph, (void*)CSR_input, NVGRAPH_CSR_32));
check_status(nvgraphAllocateVertexData(handle, graph, vertex_numsets, vertex_dimT));
int source_vert = 1;
//Setting the traversal parameters
nvgraphTraversalParameter_t traversal_param;
nvgraphTraversalParameterInit(&traversal_param);
nvgraphTraversalSetDistancesIndex(&traversal_param, distances_index);
nvgraphTraversalSetPredecessorsIndex(&traversal_param, predecessors_index);
nvgraphTraversalSetUndirectedFlag(&traversal_param, false);
//Computing traversal using BFS algorithm
check_status(nvgraphTraversal(handle, graph, NVGRAPH_TRAVERSAL_BFS, &source_vert, traversal_param));
// Get result
check_status(nvgraphGetVertexData(handle, graph, (void*)bfs_distances_h, distances_index));
check_status(nvgraphGetVertexData(handle, graph, (void*)bfs_predecessors_h, predecessors_index));
// expect bfs distances_h = (1 0 1 3 3 2 2147483647)
for (int i = 0; i<n; i++) printf("Distance to vertex %d: %i\n",i, bfs_distances_h[i]); printf("\n");
// expect bfs predecessors = (1 -1 1 5 5 0 -1)
for (int i = 0; i<n; i++) printf("Predecessor of vertex %d: %i\n",i, bfs_predecessors_h[i]); printf("\n");
free(vertex_dimT);
free(CSR_input);
check_status(nvgraphDestroyGraphDescr (handle, graph));
check_status(nvgraphDestroy (handle));
return 0;
}
nvGRAPH API参考分析（二）的更多相关文章
- nvGRAPH API参考分析（一）
nvGRAPH API参考分析(一) 本文通过描述nvGRAPH库函数的输入/输出参数,数据类型和错误代码来指定其行为. 1. 返回值nvgraphStatus_t 除以下内容外,所有nvGRA ...
- PJSUA2开发文档--第十二章 PJSUA2 API 参考手册
12 PJSUA2 API 参考手册 12.1 endpoint.hpp PJSUA2基本代理操作. namespace pj PJSUA2 API在pj命名空间内. 12.1.1 class En ...
- Elasticsearch Java Rest Client API 整理总结 (二) —— SearchAPI
目录 引言 Search APIs Search API Search Request 可选参数 使用 SearchSourceBuilder 构建查询条件 指定排序 高亮请求 聚合请求 建议请求 R ...
- 框架-springmvc源码分析(二)
框架-springmvc源码分析(二) 参考: http://www.cnblogs.com/leftthen/p/5207787.html http://www.cnblogs.com/leftth ...
- Vue源码分析(二) : Vue实例挂载
Vue源码分析(二) : Vue实例挂载 author: @TiffanysBear 实例挂载主要是 $mount 方法的实现,在 src/platforms/web/entry-runtime-wi ...
- SQLite入门与分析(二)---设计与概念(续)
SQLite入门与分析(二)---设计与概念(续) 写在前面:本节讨论事务,事务是DBMS最核心的技术之一.在计算机科学史上,有三位科学家因在数据库领域的成就而获ACM图灵奖,而其中之一Jim G ...
- Linux内核启动代码分析二之开发板相关驱动程序加载分析
Linux内核启动代码分析二之开发板相关驱动程序加载分析 1 从linux开始启动的函数start_kernel开始分析,该函数位于linux-2.6.22/init/main.c start_ke ...
- 透过【百度地图API】分析双闭包问题
原文:透过[百度地图API]分析双闭包问题 摘要: 有位API爱好者问到,昨天的教程里为什么不使用for循环?他使用for循环后,也发现代码无效.这是什么原因? ------------------- ...
- java微信开发API解析（二）-获取消息和回复消息
java微信开发API解析(二)-获取消息和回复消息 说明 * 本演示样例依据微信开发文档:http://mp.weixin.qq.com/wiki/home/index.html最新版(4/3/20 ...
随机推荐
- think php 5.x
# Exploit Title: thinkphp 5.X RCE # Date: 2019-1-14 # Exploit Author: vr_system # Vendor Homepage: h ...
- C/C++ 手工实现IAT导入表注入劫持
DLL注入有多种方式,今天介绍的这一种注入方式是通过修改导入表,增加一项导入DLL以及导入函数,我们知道当程序在被运行起来之前,其导入表中的导入DLL与导入函数会被递归读取加载到目标空间中,我们向导入 ...
- hdu4908 中位数子串
题意: 给你N个数字组成的数列,然后问你这里面有多少个是以M为中位数的子序列. 思路: 首先分四中简单的情况求 (1) 就是只有他自己的那种情况 那么sum+1 ...
- LA3027简单带权并查集
题意: 有n个点,一开始大家都是独立的点,然后给出一些关系,a,b表示a是b的父亲节点,距离是abs(a-b)%1000,然后有一些询问,每次询问一个节点a到父亲节点的距离是多少? 思路: ...
- [LeetCode每日一题]80. 删除有序数组中的重复项 II
[LeetCode每日一题]80. 删除有序数组中的重复项 II 问题 给你一个有序数组 nums ,请你 原地 删除重复出现的元素,使每个元素 最多出现两次 ,返回删除后数组的新长度. 不要使用额外 ...
- Junit单元测试&反射&注解
内容索引 1. Junit单元测试 2. 反射 3. 注解 Junit单元测试: * 测试分类: 1. 黑盒测试:不需要写代码,给输入值,看程序是否能够输出期望的值. 2. 白盒测试:需要写代码的.关 ...
- 2-9-9-12分页机制（xp）
10-10-12分页限制 10-10-12分页因为页表PEB只有四个字节所以只能访问2^32 = 4GB物理地址空间,现在的物理内存都大于4GB为了能访问到更多的物理内存2-9-9-12将PEB的大小 ...
- Java集合详解（三）：HashMap原理解析
概述 本文是基于jdk8_271版本进行分析的. HashMap是Map集合中使用最多的.底层是基于数组+链表实现的,jdk8开始底层是基于数组+链表/红黑树实现的.HashMap也会动态扩容,与Ar ...
- MSSQL·将一对多的数据合并为以指定分隔符的数据
阅文时长 | 0.05分钟 字数统计 | 142.4字符 主要内容 | 1.引言&背景 2.Stuff函数语法&模拟场景 3.声明与参考资料 『MSSQL·将一对多的数据合并为以指定分 ...
- [Python] RPC实现
单线程同步 使用socket传输数据 使用json序列化消息体 struct将消息编码为二进制字节串,进行网络传输 消息协议 1 // 输入 2 { 3 in: "ping", 4 ...