Running an std::async in a loop. How to get consistent results? - multithreading

I try to parallelize calculations and write the results in order to a vector.
I'm using a std::async. The program works perfectly with a short pause (ref. the commented line). Without this pause, the program crashes.
The Code ( in an online IDE to modify & test the MCVE :
class AsyncDispatcher {
public:
/* Data is a custom class with data that contains a ID.
* The object contains no
* links or pointers.*/
vector<Data> calcResult(vector<Params> params) {
vector<Data> result;
vector<std::future<NumberedData>> futures;
threadID = 0;
for (auto param : params) {
futures.push_back(((std::async(std::launch::async, [&]() {
this_thread::sleep_for(chrono::milliseconds(100)); // not workable without this command
//^^^^^^^^^^^^^^^^^^^^^^^^^
return NumberedData(filler.createData(param, threadID), threadID);
}))));
threadID++;
}
for (auto& f : futures) {
result.push_back(f.get().data);
}
return result;
}
AsyncDispatcher() : threadID(0) {}
private:
int threadID;
Filler filler;//fills an Data with numbers
};

Related

unordered_map insertion is creating bottleneck

So here I am trying to create a Graph data structure in which i have to keep track of edges according to their ids. So I am creating edge ids in string data structure as eid: sourceid_destinationid
using namespace std;
class Edge{
public:
bool operator==(const Edge* &obj) const
{
return eid==obj->eid;
}
std::string eid;
set<int> rrids;
int sourceid;
int destid;
int strength;
public:
Edge(std::string eid,int from,int to);
std::string getId();
void addRRid(int rrid);
void removeRRid(int rrid);
void setRRid(set<int> rrids);
void setId(std::string eid);
};
This is another class which I am using for adding and removing the edges.
hpp-file
using namespace std;
class RRassociatedGraph{
public:
unordered_map<int,vertex*> vertexMap;
std::unordered_map<std::string,Edge*> EdgeMap;
int noOfEdges;
public:
RRassociatedGraph();
unordered_set<vertex> getVertices();
int getNumberOfVertices();
void addVertex(vertex v);
vertex* find(int id);
Edge* findedge(std::string id);
void addEdge(int from, int to, int label);
void removeEdge(int from, int to,int rrSetID);
};
When I debugged the code I found out that in the function add edge here the place where I am doing EdgeMap.insert the execution doesn't go to next line. It remains in hashtable for loop of some bucket entry. I can't debug this code frequently because I have to wait for 3 hours to get this issue. The code is working perfectly with small graphs. But for larger graphs where edgeMap has to store 800k edges. It goes in this hashtable infinite loop. I don't get this hashtable code. But is there something wrong with my data structure of creating Edgemap?
#include "RRassociatedGraph.hpp"
RRassociatedGraph::RRassociatedGraph() {
noOfEdges=0;
}
void RRassociatedGraph::addVertex(vertex v) {
vertexMap.insert(pair<int,vertex*>(v.getId(), &v));
}
vertex* RRassociatedGraph::find(int id) {
unordered_map<int,vertex*>::const_iterator got=vertexMap.find(id);
if(got != vertexMap.end() )
return got->second;
return nullptr;
}
Edge* RRassociatedGraph::findedge(std::string id){
unordered_map<std::string,Edge*>::const_iterator got=EdgeMap.find(id);
if(got != EdgeMap.end() )
return got->second;
return nullptr;
}
void RRassociatedGraph::addEdge(int from, int to, int label) {
vertex* fromVertex = find(from);
if (fromVertex == nullptr) {
fromVertex = new vertex(from);
vertexMap.insert(pair<int,vertex*>(fromVertex->getId(), fromVertex));
}
vertex* toVertex = find(to);
if (toVertex == nullptr) {
toVertex = new vertex(to);
vertexMap.insert(pair<int,vertex*>(toVertex->getId(), toVertex));
}
if(fromVertex==toVertex){
// fromVertex->outDegree++;
//cout<<fromVertex->getId()<<" "<<toVertex->getId()<<"\n";
return;
}
std::string eid=std::to_string(from);
eid+="_"+std::to_string(to);
Edge* edge=findedge(eid);
if(edge==nullptr){
edge=new Edge(eid,from,to);
edge->addRRid(label);
fromVertex->addOutGoingEdges(edge);
EdgeMap.insert(pair<std::string,Edge*>(edge->getId(), edge));
noOfEdges++;
}
else{
edge->addRRid(label);
fromVertex->outDegree++;
}
}
void RRassociatedGraph::removeEdge(int from, int to,int rrSetID) {
vertex* fromVertex = find(from);
std::string eid=std::to_string(from);
eid+="_"+std::to_string(to);
if(EdgeMap.count(eid)==1){
Edge* e=EdgeMap.find(eid)->second;
if(fromVertex->removeOutgoingEdge(e,rrSetID)){
EdgeMap.erase(eid);
delete e;
}
}
}
this is the place where it keeps going into this for loop. The insertion time of map should be very less but this is creating bottleneck in my code.
template <class _Tp, class _Hash, class _Equal, class _Alloc>
void
__hash_table<_Tp, _Hash, _Equal, _Alloc>::__rehash(size_type __nbc)
{
#if _LIBCPP_DEBUG_LEVEL >= 2
__get_db()->__invalidate_all(this);
#endif // _LIBCPP_DEBUG_LEVEL >= 2
__pointer_allocator& __npa = __bucket_list_.get_deleter().__alloc();
__bucket_list_.reset(__nbc > 0 ?
__pointer_alloc_traits::allocate(__npa, __nbc) : nullptr);
__bucket_list_.get_deleter().size() = __nbc;
if (__nbc > 0)
{
for (size_type __i = 0; __i < __nbc; ++__i)
__bucket_list_[__i] = nullptr;
__next_pointer __pp = __p1_.first().__ptr();
__next_pointer __cp = __pp->__next_;
if (__cp != nullptr)
{
size_type __chash = __constrain_hash(__cp->__hash(), __nbc);
__bucket_list_[__chash] = __pp;
size_type __phash = __chash;
for (__pp = __cp, __cp = __cp->__next_; __cp != nullptr;
__cp = __pp->__next_)
{
__chash = __constrain_hash(__cp->__hash(), __nbc);
if (__chash == __phash)
__pp = __cp;
else
{
if (__bucket_list_[__chash] == nullptr)
{
__bucket_list_[__chash] = __pp;
__pp = __cp;
__phash = __chash;
}
else
{
__next_pointer __np = __cp;
for (; __np->__next_ != nullptr &&
key_eq()(__cp->__upcast()->__value_,
__np->__next_->__upcast()->__value_);
__np = __np->__next_)
;
__pp->__next_ = __np->__next_;
__np->__next_ = __bucket_list_[__chash]->__next_;
__bucket_list_[__chash]->__next_ = __cp;
}
}
}
}
}
}
I have many files so I can't put the whole code. I am not that good in c++. Please let me know if I have to implement it some other way. I have to use hashMap because I also need faster search.
You are probably experiencing re-hash at insert. Unordered_map has number of buckets. When they are filled worst case insert time is O(size()).
http://en.cppreference.com/w/cpp/container/unordered_map/insert
Rehashing occurs only if the new number of elements is greater than max_load_factor()*bucket_count().
What you may do with your current setup is:
1. Growth map at the init of the program, as usually number of buckets doesn't shrink.
2. Change from std::unordered_map to Boost::intrusive_map, where you can manager number of buckets manually.

How to limit the standart library thread count?

I want to limit the number of thread for a given job.
Here is a sample code of my attempts to do so:
#DEFINE MAX_THREAD_COUNT 5
Later:
void MyClass::a_method() {
unsigned thread_count = 0;
std::vector<std::thread> jobs;
std::vector<AnObject> collection;
for(auto& c : collection) {
if(thread_count >= MAX_THREAD_COUNT) {
for(auto& j : jobs) {
if(j.joinable()) {
j.join();
thread_count--;
}
}
}
thread_count++;
jobs.push_back(std::thread([=] { this->a_long_job(c); }));
}
for(auto& j : jobs) {
if(j.joinable()) {
j.join();
}
}
}
The problem is that sometimes this->a_long_job isn't call all the time, I checked this by printing a line inside the method and by printing the number of elements contained in collection.
Another idea that could work but isn't elegant would be to launch max_thread threads with c/max_thread calls of this->a_long_job(c) in each.
I don't think that I need a thread pool for this application because there's a need only in this method.
Notes:
No external libraries
C++11 and further

Wait() in Haxe?

I am getting started with Haxe and OpenFl, and have some experience with Javascript and Lua.
It was going pretty well, till I got to a point where I needed a function similar to wait() in Lua, etc, which stops the script until the number of seconds you set is over.
How would I go about doing this?
EDIT: To clarify, I am building to Flash.
Although this is old, I wanted to add another point for reference. The OP mentioned in a comment this was for a game. One method I often use is (and could probably be put in a library):
var timerCount:Float = 0;
var maxTimerCounter:Float = 5;
function update () {
timerCounter += elapsedTime;
if (timerCounter > maxTimerCounter){
onTimerComplete();
timerCount = 0;
}
}
In SYS you are looking for:
static function sleep( seconds : Float ) : Void
Suspend the current execution for the given time (in seconds).
Example: Sys.sleep(.5);
http://haxe.org/api/sys/
Edit: User is porting to flash.
So the suggestion is to use Timer
http://haxe.org/api/haxe/timer
In Timer the suggestion is to use
static function delay( f : Void -> Void, time_ms : Int ) : Timer
Someone on stack overflow has an example that looks like this: haxe.Timer.delay(callback(someFunction,"abc"), 10); located here... Pass arguments to a delayed function with Haxe
For the Flash compile target, the best you can do is use a timer, and something like this setTimeout() function.
This means slicing your function into two - everything before the setTimeout(), and everything after that, which is in a separate function that the timeout can call.
so somethine like, eg:
tooltipTimerId = GlobalTimer.setTimeout(
Tooltip.TOOLTIP_DELAY_MS,
handleTooltipAppear,
tootipParams
);
[...]
class GlobalTimer {
private static var timerList:Array<Timer>;
public static function setTimeout(milliseconds:Int, func:Dynamic, args:Array<Dynamic>=null):Int {
var timer:Timer = new Timer(milliseconds);
var id = addTimer(timer, timerList);
timer.run = function() {
Reflect.callMethod(null, func, args);
clearTimeout(id);
}
return id;
}
private static function addTimer(timer:Timer, arr:Array<Timer>):Int {
for (i in 0...arr.length) {
if (null == arr[i]) {
arr[i] = timer;
return i;
}
}
arr.push(timer);
return arr.length -1;
}
public static function clearTimeout(id:Int) {
var timers:Array<Timer> = GlobalTimer.getInstance().timerList;
try {
timers[id].stop();
timers[id] = null;
} catch(e:Error) {/* Nothing we can do if it fails, really. */}
}
}

haxe "should be int" error

Haxe seems to assume that certain things must be Int. In the following function,
class Main {
static function main() {
function mult_s<T,A>(s:T,x:A):A { return cast s*x; }
var bb = mult_s(1.1,2.2);
}
}
I got (with Haxe 3.01):
Main.hx:xx: characters 48-49 : mult_s.T should be Int
Main.hx:xx: characters 50-51 : mult_s.A should be Int
Can anyone please explain why T and A should be Int instead of Float?
A more puzzling example is this:
class Main {
public static function min<T:(Int,Float)>(t:T, t2:T):T { return t < t2 ? t : t2; }
static function main() {
var a = min(1.1,2.2); //compile error
var b = min(1,2); //ok
}
}
I can't see why t<t2 implies that either t or t2 is Int. But Haxe seems prefer Int: min is fine if called with Int's but fails if called with Float's. Is this reasonable?
Thanks,
min<T:(Int,Float)> means T should be both Int and Float. See the constraints section of Haxe Manual.
Given Int can be converted to Float implicitly, you can safely remove the constraint of Int. i.e. the following will works:
http://try.haxe.org/#420bC
class Test {
public static function min<T:Float>(t:T, t2:T):T { return t < t2 ? t : t2; }
static function main() {
var a = min(1.1,2.2); //ok
$type(a); //Float
trace(a); //1.1
var b = min(1,2); //ok
$type(b); //Int
trace(b); //1
}
}

Making Thread-Safe Calls to labels in Windows Forms Controls

I am making a small app in Visual C++ in Microsoft Visual Studio where I am collecting data in a thread and displaying the information in labels in a Windows Form. I am trying to follow this Article/Tutorial on how to make the calls to the labels thread safe: http://msdn.microsoft.com/en-us/library/ms171728(VS.90).aspx. The example shows how to output text to one text box, but I want to output to many labels. When I try I get the error:
error C3352: 'void APP::Form1::SetText(System::String ^,System::Windows::Forms::Label ^)' : the specified function does not match the delegate type 'void (System::String ^)'
Here is some of the code I am using:
private:
void ThreadProc()
{
while(!exit)
{
uInt8 data[100];
//code to get data
SetText(data[0].ToString(), label1);
SetText(data[1].ToString(), label2);
SetText(data[2].ToString(), label3);
SetText(data[3].ToString(), label4);
SetText(data[4].ToString(), label5);
SetText(data[5].ToString(), label6);
...
}
}
delegate void SetTextDelegate(String^ text);
private:
void SetText(String^ text, Label^ label)
{
// InvokeRequired required compares the thread ID of the
// calling thread to the thread ID of the creating thread.
// If these threads are different, it returns true.
if (label->InvokeRequired)
{
SetTextDelegate^ d =
gcnew SetTextDelegate(this, &Form1::SetText);
this->Invoke(d, gcnew array<Object^> { text });
}
else
{
label->Text = text;
}
}
You need to modify the delegate to take a Label in addition to the string:
delegate void SetTextDelegate(String^ text, Label^ label);
And then call it with two parameters:
void SetText(String^ text, Label^ label)
{
// InvokeRequired required compares the thread ID of the
// calling thread to the thread ID of the creating thread.
// If these threads are different, it returns true.
if (label->InvokeRequired)
{
SetTextDelegate^ d =
gcnew SetTextDelegate(this, &Form1::SetText);
this->Invoke(d, gcnew array<Object^> { text, label });
}
else
{
label->;Text = text;
}
}

Resources