petro-rudenko

In general, check the crt/host_config.h file to find out which versions are supported. Sometimes it is possible to hack the requirements there to get some newer versions working, too :)

Thrust version can be found in $CUDA_ROOT/include/thrust/version.h.

Release notes for CUDA:

• 10.2: https://docs.nvidia.com/cuda/pdf/CUDA_Toolkit_Release_Notes.pdf
• 10.1: https://developer.download.nvidia.com/compute/cuda/10.1/Prod/docs/sidebar/CUDA_Toolkit_Release_Notes.pdf
• 10.0: https://developer.download.nvidia.com/compute/cuda/10.0/Prod/docs/sidebar/CUDA_Toolkit_Release_Notes.pdf
• 9.2: https://developer.download.nvidia.com/compute/cuda/9.2/Prod/docs/sidebar/CUDA_Toolkit_Release_Notes.pdf

petro-rudenko

object RuntimeUtils {
  def requestThreadDump: String = {
    // Get the PID of the current JVM process
    val selfName = java.lang.management.ManagementFactory.getRuntimeMXBean().getName()
    val selfPid = selfName.substring(0, selfName.indexOf('@'))

    // Attach to the VM
    import com.sun.tools.attach.VirtualMachine
    import sun.tools.attach.HotSpotVirtualMachine;
    val vm = VirtualMachine.attach(selfPid);

petro-rudenko

BAD_RES_STATE       | 0x25B161 |  destroy_ctx - context doesn't exist or doesn't match type 
BAD_RES_STATE       | 0x4A6FC9 |  destroy_ctx - context in use 
BAD_RES_STATE       | 0x60DA55 |  destroy_dct - dct not in drained state 
BAD_PARAM           | 0x67A6F2 |  slrg doesnt support write; 
BAD_PARAM           | 0x0F0E35 |  ppamp doesnt support write; 
BAD_PKT             | 0x4A22F  |  access reg MAD with specified register id not supported 
BAD_PKT             | 0x16C592 |  mad_ifc: process_smp_lid mkey check failed - silently discarded 
INTERNAL_ERR        | 0x079233 |  set_get_port_info: silently discarded. 
BAD_PKT             | 0x468496 |  mad_ifc: ATTRV_SM_INFO handled by SW 
BAD_PKT             | 0x071808 |  mad_ifc: smp trap repress silently discarded after processing. 

petro-rudenko

"""Short and sweet LSTM implementation in Tensorflow.

Motivation:
When Tensorflow was released, adding RNNs was a bit of a hack - it required
building separate graphs for every number of timesteps and was a bit obscure
to use. Since then TF devs added things like `dynamic_rnn`, `scan` and `map_fn`.
Currently the APIs are decent, but all the tutorials that I am aware of are not
making the best use of the new APIs.

Advantages of this implementation:

petro-rudenko

petro-rudenko

petro-rudenko

petro-rudenko

1. General Background and Overview

• Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
• Models and Issues in Data Stream Systems
• Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
• Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
• [Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep

petro-rudenko

"""
This is a batched LSTM forward and backward pass
"""
import numpy as np
import code

class LSTM:
  
  @staticmethod
  def init(input_size, hidden_size, fancy_forget_bias_init = 3):

petro-rudenko

// Adapted from Rob Norris' post at https://tpolecat.github.io/2014/04/11/scalac-flags.html

scalacOptions ++= Seq(
  "-deprecation",           
  "-encoding", "UTF-8",       // yes, this is 2 args
  "-feature",                
  "-unchecked",
  "-Xfatal-warnings",       
  "-Xlint",
  "-Yno-adapted-args",