JasonAtNvidia

#!/bin/bash
#Jason T. 2-6-2018

# Check specifically for the run command
if [[ $# -ge 2 && $1 == "run" ]]; then
    # Tell docker to share the following folders with the base system
    # This allows the docker containers to find CUDA, cuDNN, TensorRT
    LIB_MAPS="/usr/lib/aarch64-linux-gnu \
              /usr/local/cuda \
              /usr/local/cuda/lib64"

onauparc

#include <cuda_runtime.h>

#include <cstring>
#include <cstdlib>
#include <vector>

#include <string>
#include <iostream>
#include <stdio.h>
#include "caffe/caffe.hpp"

jboner

Latency Comparison Numbers (~2012)
----------------------------------
L1 cache reference                           0.5 ns
Branch mispredict                            5   ns
L2 cache reference                           7   ns                      14x L1 cache
Mutex lock/unlock                           25   ns
Main memory reference                      100   ns                      20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy             3,000   ns        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD