sandeepkumar-skb

#include <chrono>
#include <iostream>
#include <vector>
#include <thread>

__global__ void do_nothing(int time_us, int clock_rate) {
  clock_t start = clock64();
  clock_t end;
  for (;;) {
    end = clock64();

sandeepkumar-skb

import torch
import torch.nn as nn


class GroupNorm(nn.Module):
    def __init__(self, num_groups, num_features, eps=1e-5):
        super(GroupNorm, self).__init__()
        self.weight = nn.Parameter(torch.ones(1,num_features,1,1))
        self.bias = nn.Parameter(torch.zeros(1,num_features,1,1))
        self.num_groups = num_groups

sandeepkumar-skb

#include <stdio.h>
#include <thread>
#include <chrono>
#include <iostream>

const int N = 1 << 20;

__global__ void kernel(float *x, int n)
{
    int tid = threadIdx.x + blockIdx.x * blockDim.x;

sandeepkumar-skb

#include <pybind11/pybind11.h>

int add(int i, int j){
    return i+j;
}

PYBIND11_MODULE(pybind11_example, m) {
    m.doc() = "pybind11 example to add 2 integers";
    m.def("add", &add, "A function to add 2 integers");
}

sandeepkumar-skb

import torch
import torch.nn as nn
import time
from torch import Tensor

class Net(nn.Module):
    def __init__(self, features):
        super().__init__()
        self.fc_layers = [nn.Linear(features, features) for _ in range(100)]
        self.layers = nn.Sequential(*self.fc_layers)

sandeepkumar-skb

#include <thread>
#include <pthread.h>
#include <iostream>
#include <cstring>

class thread : public std::thread
{
  public:
    static void setScheduling(std::thread &th, int priority) {
        sched_param sch;

sandeepkumar-skb

#include "omp.h"
#include <thread>
#include <iostream>
#include <vector>
#include <chrono>


void doNothing(){
    int count =0;
    for (int i=0; i<1000; ++i)

sandeepkumar-skb

import torch
import torch.nn as nn
import copy
import torchvision.models as models


class BN_Folder():
    def fold(self, model):
        mymodel = copy.deepcopy(model)
        mymodel.eval()

sandeepkumar-skb

inline void gpuAssert(cudaError_t err, const char *file, int line)
{
    if (err != cudaSuccess){
        printf("%s in %s at line %d\n", cudaGetErrorString(err), file, line);
        exit(EXIT_FAILURE);
    }
}
#define gpuErrchk(ans)                        \
    {                                         \
        gpuAssert((ans), __FILE__, __LINE__); \

sandeepkumar-skb

#include <iostream>
#include <stdio.h>

#define BLOCK_SIZE 16

inline void gpuAssert(cudaError_t err, const char *file, int line)
{
    if (err != cudaSuccess){
        printf("%s in %s at line %d\n", cudaGetErrorString(err), file, line);
        exit(EXIT_FAILURE);