sppu-practical

cuda mat mul

#include <cuda_runtime.h>
#include <iostream>

__global__ void matmul(int* A, int* B, int* C, int N) {
    int Row = blockIdx.y*blockDim.y+threadIdx.y;
    int Col = blockIdx.x*blockDim.x+threadIdx.x;
    if (Row < N && Col < N) {
        int Pvalue = 0;
        for (int k = 0; k < N; k++) {
            Pvalue += A[Row*N+k] * B[k*N+Col];
        }
        C[Row*N+Col] = Pvalue;
    }
}

int main() {
    int N = 512;
    int size = N * N * sizeof(int);
    int* A, * B, * C;
    int* dev_A, * dev_B, * dev_C;
    cudaMallocHost(&A, size);
    cudaMallocHost(&B, size);
    cudaMallocHost(&C, size);
    cudaMalloc(&dev_A, size);
    cudaMalloc(&dev_B, size);
    cudaMalloc(&dev_C, size);

    // Initialize matrices A and B
    for (int i = 0; i < N; i++) {
        for (int j = 0; j < N; j++) {
            A[i*N+j] = i*N+j;
            B[i*N+j] = j*N+i;
        }
    }

    cudaMemcpy(dev_A, A, size, cudaMemcpyHostToDevice);
    cudaMemcpy(dev_B, B, size, cudaMemcpyHostToDevice);

    dim3 dimBlock(16, 16);
    dim3 dimGrid(N/dimBlock.x, N/dimBlock.y);

    matmul<<<dimGrid, dimBlock>>>(dev_A, dev_B, dev_C, N);

    cudaMemcpy(C, dev_C, size, cudaMemcpyDeviceToHost);

    // Print the result
    for (int i = 0; i < 10; i++) {
        for (int j = 0; j < 10; j++) {
            std::cout << C[i*N+j] << " ";
        }
        std::cout << std::endl;
    }

    // Free memory
    cudaFree(dev_A);
    cudaFree(dev_B);
    cudaFree(dev_C);
    cudaFreeHost(A);
    cudaFreeHost(B);
    cudaFreeHost(C);

    return 0;
}

cuda vec add

// program 2 

#include <iostream>  
#include <cuda_runtime.h>

using namespace std;

__global__ void addVectors(int* A, int* B, int* C, int n) 
{
    int i = blockIdx.x * blockDim.x + threadIdx.x; 
    if (i < n) 
    {
        C[i] = A[i] + B[I];
    }
}

int main() 
{
    int n = 1000000;  
    int* A, * B, * C;
    int size = n * sizeof(int);

    // Allocate memory on the host  
    cudaMallocHost(&A, size);  
    cudaMallocHost(&B, size);  
    cudaMallocHost(&C, size);

    // Initialize the vectors
    for (int i = 0; i < n; i++) 
    {
        A[i] = I;
        B[i] = i * 2;
    }
    // Allocate memory on the device  
    int* dev_A, * dev_B, * dev_C;  
    cudaMalloc(&dev_A, size);  
    cudaMalloc(&dev_B, size);  
    cudaMalloc(&dev_C, size);

    // Copy data from host to device
    cudaMemcpy(dev_A, A, size, cudaMemcpyHostToDevice);  
    cudaMemcpy(dev_B, B, size, cudaMemcpyHostToDevice);

    // Launch the kernel  
    int blockSize = 256;
    int numBlocks = (n + blockSize - 1) / blockSize;
    addVectors<<<numBlocks, blockSize>>>(dev_A, dev_B, dev_C, n);

    // Copy data from device to host
    cudaMemcpy(C, dev_C, size, cudaMemcpyDeviceToHost);

    // Print the results
    for (int i = 0; i < 10; i++) 
    {
        cout << C[i] << " ";
    }
    cout << endl;

    // Free memory  
    cudaFree(dev_A);  
    cudaFree(dev_B);  
    cudaFree(dev_C);  
    cudaFreeHost(A);  
    cudaFreeHost(B);  
    cudaFreeHost(C);

    return 0;
}

cpp bfs dfs

#include <iostream>
#include <vector>
#include <queue>
#include <stack>
#include <omp.h>

using namespace std;

class Graph {
    int V;
    vector<vector<int>> adjList;

public:
    Graph(int V) {
        this->V = V;
        adjList.resize(V);
    }

    void addEdge(int src, int dest) {
        adjList[src].push_back(dest);
        adjList[dest].push_back(src); // For undirected graph
    }

    vector<int> getNeighbors(int vertex) {
        return adjList[vertex];
    }
};

void parallelBFS(Graph& graph, int source, vector<bool>& visited) {
    queue<int> q;
    q.push(source);
    visited[source] = true;

    while (!q.empty()) {
        int current = q.front();
        q.pop();
        cout << "Visited: " << current << endl;

        vector<int> neighbors = graph.getNeighbors(current);
        #pragma omp parallel for
        for (int i = 0; i < neighbors.size(); ++i) {
            int neighbor = neighbors[i];
            if (!visited[neighbor]) {
                visited[neighbor] = true;
                q.push(neighbor);
            }
        }
    }
}

void parallelDFS(Graph& graph, int source, vector<bool>& visited) {
    stack<int> s;
    s.push(source);
    visited[source] = true;

    while (!s.empty()) {
        int current = s.top();
        s.pop();
        cout << "Visited: " << current << endl;

        vector<int> neighbors = graph.getNeighbors(current);
        #pragma omp parallel for
        for (int i = 0; i < neighbors.size(); ++i) {
            int neighbor = neighbors[i];
            if (!visited[neighbor]) {
                visited[neighbor] = true;
                s.push(neighbor);
            }
        }
    }
}

int main() {
    int V, E;
    cout << "Enter the number of vertices: ";
    cin >> V;
    Graph graph(V);
    cout << "Enter the number of edges: ";
    cin >> E;
    cout << "Enter the edges (src dest):" << endl;
    for (int i = 0; i < E; ++i) {
        int src, dest;
        cin >> src >> dest;
        graph.addEdge(src, dest);
    }

    vector<bool> visited(V, false);

    cout << "Parallel BFS:" << endl;
    #pragma omp parallel num_threads(2)
    {
        #pragma omp single nowait
        parallelBFS(graph, 0, visited);
    }

    // Reset visited array for DFS
    fill(visited.begin(), visited.end(), false);

    cout << "Parallel DFS:" << endl;
    #pragma omp parallel num_threads(2)
    {
        #pragma omp single nowait
        parallelDFS(graph, 0, visited);
    }

    return 0;
}

Boston

import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, Flatten
from sklearn import preprocessing

(X_train, Y_train), (X_test, Y_test) = keras.datasets.boston_housing.load_data()

print("Training data shape:", X_train.shape)
print("Test data shape:", X_test.shape)
print("Train output data shape:", Y_train.shape)
print("Actual Test output data shape:", Y_test.shape)

##Normalize the data

X_train=preprocessing.normalize(X_train)
X_test=preprocessing.normalize(X_test)

#Model Building

X_train[0].shape
model = Sequential()
model.add(Dense(128,activation='relu',input_shape= X_train[0].shape))
model.add(Dense(64,activation='relu'))
model.add(Dense(32,activation='relu'))
model.add(Dense(1))

model.summary()

model.compile(loss='mse',optimizer='rmsprop',metrics=['mae'])

history = model.fit(X_train,Y_train,epochs=100,batch_size=1,verbose=1,validation_data=(X_test,Y_test))

results = model.evaluate(X_test, Y_test)
print(results)

fashion

from tensorflow import keras
import numpy as np 
import matplotlib.pyplot as plt 

fashion_mnist = keras.datasets.fashion_mnist
(train_img, train_labels), (test_img, test_labels) = fashion_mnist.load_data()

train_img = train_img / 255.0
test_img = test_img / 255.0

model = keras.Sequential([keras.layers.Flatten(input_shape=(28, 28)), 
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10, activation='softmax')])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', 
    metrics=['accuracy'])

model.fit(train_img, train_labels, epochs=10)

test_loss, test_acc = model.evaluate(test_img, test_labels)
print("accuracy of tessting: ",test_acc)

predictions = model.predict(test_img)

predicted_labels = np.argmax(predictions, axis=1)

num_rows = 5 
num_cols = 5
num_imgs = num_rows*num_cols

plt.figure(figsize=(2*2*num_cols, 2*num_rows))
for i in range(num_imgs):
    plt.subplot(num_rows, 2*num_cols, 2*i+1)
    plt.imshow(test_img[1], cmap='gray')
    plt.axis("off")
    plt.subplot(num_rows, 2*num_cols, 2*i+2)
    plt.bar(range(10), predictions[i])
    plt.xticks(range(10))
    plt.ylim([0,1])
    plt.tight_layout()
    plt.title(f"predicted_labels: {predicted_labels[i]}")
    plt.show()

imdb

from  keras.datasets import imdb

(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)

max([max(sequence) for sequence in train_data])


word_index = imdb.get_word_index()
reverse_word_index = dict([(val, key) for (key, val) in word_index.items()])
decoded_review = ' '.join([reverse_word_index.get(i-3, '?') for i in train_data[0]])

import numpy as np

def vectorize(sequences, dimension=10000): 
        results = np.zeros((len(sequences), dimension))
        for i, sequence in enumerate(sequences):
            results[i, sequence] = 1
        return results

x_train = vectorize(train_data)
x_test = vectorize(test_data)
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')


from keras import models
from keras import layers

model = models.Sequential()
model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(16, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))


model.compile(loss = 'binary_crossentropy',optimizer='rmsprop',  metrics = ['accuracy'])


x_val = x_train[:10000]
y_val = y_train[:10000]

partial_x = x_train[10000:]
partial_y = y_train[10000:]


history = model.fit(partial_x, partial_y, epochs=20, batch_size=512, validation_data=(x_val, y_val))
results = model.evaluate(x_test, y_test)
print(results)

min-max cpp

#include <iostream>
#include <vector>
#include <omp.h>
#include <climits>

using namespace std;

void min_reduction(vector<int>& arr) {
  int min_value = INT_MAX;
  #pragma omp parallel for reduction(min: min_value)
  for (int i = 0; i < arr.size(); i++) {
    if (arr[i] < min_value) {
      min_value = arr[i];
    }
  }
  cout << "Minimum value: " << min_value << endl;
}

void max_reduction(vector<int>& arr) {
  int max_value = INT_MIN;
  #pragma omp parallel for reduction(max: max_value)
  for (int i = 0; i < arr.size(); i++) {
    if (arr[i] > max_value) {
      max_value = arr[i];
    }
  }
  cout << "Maximum value: " << max_value << endl;
}

void sum_reduction(vector<int>& arr) {
  int sum = 0;
   #pragma omp parallel for reduction(+: sum)
   for (int i = 0; i < arr.size(); i++) {
    sum += arr[i];
  }
  cout << "Sum: " << sum << endl;
}

void average_reduction(vector<int>& arr) {
  int sum = 0;
  #pragma omp parallel for reduction(+: sum)
  for (int i = 0; i < arr.size(); i++) {
    sum += arr[i];
  }
  cout << "Average: " << (double)sum / arr.size() << endl;
}

int main() {
  vector<int> arr;
  arr.push_back(5);
  arr.push_back(2);
  arr.push_back(9);
  arr.push_back(1);
  arr.push_back(7);
  arr.push_back(6);
  arr.push_back(8);
  arr.push_back(3);
  arr.push_back(4);

  min_reduction(arr);
  max_reduction(arr);
  sum_reduction(arr);
  average_reduction(arr);
}

sorting

#include <iostream>
#include <vector>
#include <cstdlib>
#include <omp.h>

// Function to perform bubble sort
void bubbleSort(std::vector<int>& arr) {
    int n = arr.size();
    for (int i = 0; i < n-1; i++) {
        for (int j = 0; j < n-i-1; j++) {
            if (arr[j] > arr[j+1]) {
                std::swap(arr[j], arr[j+1]);
            }
        }
    }
}

// Function to merge two sorted subvectors
void merge(std::vector<int>& arr, int l, int m, int r) {
    int n1 = m - l + 1;
    int n2 = r - m;

    std::vector<int> L(n1), R(n2);

    for (int i = 0; i < n1; i++)
        L[i] = arr[l + i];
    for (int j = 0; j < n2; j++)
        R[j] = arr[m + 1 + j];

    int i = 0, j = 0, k = l;
    while (i < n1 && j < n2) {
        if (L[i] <= R[j]) {
            arr[k] = L[i];
            i++;
        } else {
            arr[k] = R[j];
            j++;
        }
        k++;
    }

    while (i < n1) {
        arr[k] = L[i];
        i++;
        k++;
    }

    while (j < n2) {
        arr[k] = R[j];
        j++;
        k++;
    }
}

// Function to perform merge sort
void mergeSort(std::vector<int>& arr, int l, int r) {
    if (l < r) {
        int m = l + (r - l) / 2;

        #pragma omp parallel sections
        {
            #pragma omp section
            mergeSort(arr, l, m);
            #pragma omp section
            mergeSort(arr, m + 1, r);
        }

        merge(arr, l, m, r);
    }
}

// Function to print a vector
void printVector(const std::vector<int>& arr) {
    for (int num : arr)
        std::cout << num << " ";
    std::cout << std::endl;
}

int main() {
    int n = 10000; // Size of vector
    std::vector<int> arr(n), arr_copy(n);

    // Initialize vector with random values
    srand(42);
    for (int i = 0; i < n; i++) {
        arr[i] = rand() % 10000;
        arr_copy[i] = arr[i];
    }

    std::cout << "Original vector:" << std::endl;
    printVector(arr);

    // Sequential bubble sort
    double start = omp_get_wtime();
    bubbleSort(arr);
    double end = omp_get_wtime();
    std::cout << "\nSequential Bubble Sort: " << end - start << " seconds" << std::endl;
    //printVector(arr);

    // Parallel merge sort
    start = omp_get_wtime();
    mergeSort(arr_copy, 0, n - 1);
    end = omp_get_wtime();
    std::cout << "\nParallel Merge Sort: " << end - start << " seconds" << std::endl;
    //printVector(arr_copy);

    return 0;
}