sandeepkumar-skb

/* Floating Point 4x4 Matrix Multiplication */

.global _start

_start:

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

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

#include <limits.h>
#include <unistd.h>
#include <csignal>
#include <cstdlib>
#include <fstream>
#include <iostream>

#include <iostream>
#include <sstream>
#include <stdexcept>

sandeepkumar-skb

// Compiling and running this program:
//   nvcc -std=c++11 device-prop-test.cu && ./a.out
#include <chrono>
#include <iostream>
using namespace std;

#define CUDA_CHECK(call)                                    \
  do {                                                      \
    cudaError_t status = call;                              \
    if(status != cudaSuccess) {                             \

sandeepkumar-skb

'''
Memory profiling utilities
'''
import gc
import inspect
import linecache
import os.path
import sys
import time
import threading

sandeepkumar-skb

'''
Memory profiling utilities
'''
import gc
import inspect
import linecache
import os.path
import sys
import time
import threading

sandeepkumar-skb

import tensorrt as trt
import numpy as np
import pycuda.autoinit
import pycuda.driver as cuda 
import time

model_path = "model.onnx"
input_size = 32

TRT_LOGGER = trt.Logger(trt.Logger.WARNING)

sandeepkumar-skb

import onnx
import sys

name = sys.argv[1]
model = onnx.load(name)
onnx.checker.check_model(model)
print(onnx.helper.printable_graph(model.graph))