mkolod

#!/usr/bin/python3

# Python 3 changes hash seeds upon interpreter start.
# https://docs.python.org/3/reference/datamodel.html#object.__hash__
#
# This was to fix the following vulnerability:
# http://ocert.org/advisories/ocert-2011-003.html
#
# For non-web apps, the hash non-determinism between interpreter runs
# can be fixed by setting an env var:

mkolod

mkolod

mkolod

/* Floating Point 4x4 Matrix Multiplication */

.global _start

_start:

LDR R0, =matrix0
LDR R1, =matrix1
LDR R2, =matrix2

mkolod

mkolod

class DisjointForest:
    
    class Subset:
        
        def __init__(self, elem, parent=None, rank=0):
            self.elem = elem
            self.parent = parent
            self.rank = rank
            
        def __repr__(self):

mkolod

#include <chrono>
#include <cmath>
#include <future>
#include <iostream>
#include <memory>
#include <mutex>
#include <thread>

template<typename Ret, typename Fun, typename Arg>
class ReusableWorkerThreadWithFuture {

mkolod

#include <string>
#include <unistd.h>
#include <iostream>
#include <nvml.h>

#define cudaSafeCall(call) \
do { \
    cudaError_t err = call; \
    if (cudaSuccess != err) { \
        fprintf (stderr, "Cuda error in file '%s' in line %i : %s.", \

mkolod

# NOTE: The network here is not means to make any sense. It's just for measuring perf impact.
import torch
import torch.nn.functional as F
from time import time

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        fcs = [torch.nn.Linear(10, 100)] + [torch.nn.Linear(100, 100) for _ in range(20)]
        self.fcs = torch.nn.Sequential(*fcs)

mkolod

#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;