Consider the following chunk of code:
int array[30000]
#pragma omp parallel
{
for( int a = 0; a < 1000; a++ )
{
#pragma omp for nowait
for( int i = 0; i < 30000; i++ )
{
/*calculations with array[i] and also other array entries happen here*/
}
}
}
Race conditions are not a concern in my application but I would like to enforce that each thread in the parallel regions takes care of exactly the same chunk of array at each run through the inner for loop.
It is my understanding that schedule(static) distributes the for-loop items based on the number of threads and the array length. However, it is not clear whether the distribution changes for different loops or different repetitions of the same loop (even when number of threads and length are the same).
What does the standard say about this? Is schedule(static) sufficient to enforce this?
I believe this quote from OpenMP Specification provides such a guarantee:
A compliant implementation of the static schedule must ensure that the same assignment of logical iteration numbers to threads will be used in two worksharing-loop regions if the following conditions are satisfied: 1) both worksharing-loop regions have the same number of loop iterations, 2) both worksharing-loop regions have the same value of chunk_size specified, or both worksharing-loop regions have no chunk_size specified, 3) both worksharing-loop regions bind to the same parallel region, and 4) neither loop is associated with a SIMD construct.
Related
I am trying to use openmp tasks to schedule a tiled execution of basic jacobi2d computation. In jacobi2d there is a dependence on A(i,j) from
A(i, j)
A(i-1, j)
A(i+1, j)
A(i, j-1)
A(i, j+1).
To my understanding of the depend clause I am declaring the dependences correctly, but they are not being respected while executing the code. I have copied the simplified code piece below. Initially my guess was that the out of bounds ranges for some tiles might be causing this issue, so I corrected that but the issue persists.(I have not copied the longer code with corrected tile ranges as that part is just a bunch of ifs + max)
int n=8,tsteps=2,b=4; //n - size of matrix, tsteps - time iterations, b - tile size or block size
#pragma omp parallel
{
#pragma omp master
for (t=0; t<tsteps; ++t)
{
for (i=0; i<n; i+=b)
for (j=0; j<n; j+=b)
{
#pragma omp task firstprivate(t,i,j) depend(in:A[i-1:b+2][j-1:b+2]) depend(out:B[i:b][j:b])
{
#pragma omp critical
printf("t-%d i-%d j-%d --A",t,i,j); //Prints out time loop, i,j
}
}
for (i=0; i<n; i+=b)
for (j=0; j<n; j+=b)
{
#pragma omp task firstprivate(t,i,j) depend(in:B[i-1:b+2][j-1:b+2]) depend(out:A[i:b][j:b])
{
#pragma omp critical
printf("t-%d i-%d j-%d --B",t,i,j); //Prints out time loop, i,j
}
}
}
}
}
So the idea with declaring dependence starting from i-1 and j-1 and the range being (b+2) is that the neighbouring tiles also affect your current tiles calculations. And similarly for the second set of loop where values in A should only be overwritten once the neighbouring tiles have used the values.
Code is being compiled using gcc 5.3 which supports openmp 4.0.
ps: the way array range is declared above denotes the starting position and the number of indices to be considered while creating the dependence graph.
edit (based on Zulan's comment) - changed the inner code to a simple print statement as this will suffice to check order of task execution. Ideally for the above values(since there are only 4 tiles) all tiles should complete the first printf and then only execute the second. But if you execute the code it will mix the order.
So I finally figured out the issue, even though OpenMP specs say that depend clause is supposed to be implemented with a starting point and range, it has not been implemented yet in gcc. So currently it only compares the starting point from the depend clause (depend(in:A[i-1:b+2][j-1:b+2])) A[i-1][j-1] in this case.
Initially I was comparing elements in different relative tile positions. Eg comparing (0,0) element with the last element of the tile, which was giving a no conflicts with dependence and hence the random order of execution of various tasks.
Current gcc implementation does not care about the range provided in the clause at all.
I'm a beginner at cuda and am having some difficulties with it
If I have an input vector A and a result vector B both with size N, and B[i] depends on all elements of A except A[i], how can I code this without having to call a kernel multiple times inside a serial for loop? I can't think of a way to paralelise both the outer and inner loop simultaneously.
edit: Have a device with cc 2.0
example:
// a = some stuff
int i;
int j;
double result = 0;
for(i=0; i<1000; i++) {
double ai = a[i];
for(j=0; j<1000; j++) {
double aj = a[j];
if (i == j)
continue;
result += ai - aj;
}
}
I have this at the moment:
//in host
int i;
for(i=0; i<1000; i++) {
kernelFunc <<<2, 500>>> (i, d_a)
}
Is there a way to eliminate the serial loop?
Something like this should work, I think:
__global__ void my_diffs(const double *a, double *b, const length){
unsigned idx = threadIdx.x + blockDim.x*blockIdx.x;
if (idx < length){
double my_a = a[idx];
double result = 0.0;
for (int j=0; j<length; j++)
result += my_a - a[j];
b[idx] = result;
}
}
(written in browser, not tested)
This can possibly be further optimized in a couple ways, however for cc 2.0 and newer devices that have L1 cache, the benefits of these optimizations might be small:
use shared memory - we can reduce the number of global loads to one per element per block. However, the initial loads will be cached in L1, and your data set is quite small (1000 double elements ?) so the benefits might be limited
create an offset indexing scheme, so each thread is using a different element from the cacheline to create coalesced access (i.e. modify j index for each thread). Again, for cc 2.0 and newer devices, this may not help much, due to L1 cache as well as the ability to broadcast warp global reads.
If you must use a cc 1.x device, then you'll get significant mileage out of one or more optimizations -- the code I've shown here will run noticeably slower in that case.
Note that I've chosen not to bother with the special case where we are subtracting a[i] from itself, as that should be approximately zero anyway, and should not disturb your results. If you're concerned about that, you can special-case it out, easily enough.
You'll also get more performance if you increase the blocks and reduce the threads per block, perhaps something like this:
my_diffs<<<8,128>>>(d_a, d_b, len);
The reason for this is that many GPUs have more than 1 or 2 SMs. To maximize perf on these GPUs with such a small data set, we want to try and get at least one block launched on each SM. Having more blocks in the grid makes this more likely.
If you want to fully parallelize the computation, the approach would be to create a 2D matrix (let's call it c[...]) in GPU memory, of square dimensions equal to the length of your vector. I would then create a 2D grid of threads, and have each thread perform the subtraction (a[row] - a[col]) and store it's result in c[row*len+col]. I would then launch a second (1D) kernel to sum the columns of c (each thread has a loop to sum a column) to create the result vector b. However I'm not sure this would be any faster than the approach I've outlined. Such a "more fully parallelized" approach also wouldn't lend itself as easily to the optimizations I discussed.
I have a clarification question.
It is my understanding, that sourceCpp automatically passes on the RNG state, so that set.seed(123) gives me reproducible random numbers when calling Rcpp code. When compiling a package, I have to add a set RNG statement.
Now how does this all work with openMP either in sourceCpp or within a package?
Consider the following Rcpp code
#include <Rcpp.h>
#include <omp.h>
// [[Rcpp::depends("RcppArmadillo")]]
// [[Rcpp::export]]
Rcpp::NumericVector rnormrcpp1(int n, double mu, double sigma ){
Rcpp::NumericVector out(n);
for (int i=0; i < n; i++) {
out(i) =R::rnorm(mu,sigma);
}
return(out);
}
// [[Rcpp::export]]
Rcpp::NumericVector rnormrcpp2(int n, double mu, double sigma, int cores=1 ){
omp_set_num_threads(cores);
Rcpp::NumericVector out(n);
#pragma omp parallel for schedule(dynamic)
for (int i=0; i < n; i++) {
out(i) =R::rnorm(mu,sigma);
}
return(out);
}
And then run
set.seed(123)
a1=rnormrcpp1(100,2,3,2)
set.seed(123)
a2=rnormrcpp1(100,2,3,2)
set.seed(123)
a3=rnormrcpp2(100,2,3,2)
set.seed(123)
a4=rnormrcpp2(100,2,3,2)
all.equal(a1,a2)
all.equal(a3,a4)
While a1 and a2 are identical, a3 and a4 are not. How can I adjust the RNG state with the openMP loop? Can I?
To expand on what Dirk Eddelbuettel has already said, it is next to impossible to both generate the same PRN sequence in parallel and have the desired speed-up. The root of this is that generation of PRN sequences is essentially a sequential process where each state depends on the previous one and this creates a backward dependence chain that reaches back as far as the initial seeding state.
There are two basic solutions to this problem. One of them requires a lot of memory and the other one requires a lot of CPU time and both are actually more like workarounds than true solutions:
pregenerated PRN sequence: One thread generates sequentially a huge array of PRNs and then all threads access this array in a manner that would be consistent with the sequential case. This method requires lots of memory in order to store the sequence. Another option would be to have the sequence stored into a disk file that is later memory-mapped. The latter method has the advantage that it saves some compute time, but generally I/O operations are slow, so it only makes sense on machines with limited processing power or with small amounts of RAM.
prewound PRNGs: This one works well in cases when work is being statically distributed among the threads, e.g. with schedule(static). Each thread has its own PRNG and all PRNGs are seeded with the same initial seed. Then each thread draws as many dummy PRNs as its starting iteration, essentially prewinding its PRNG to the correct position. For example:
thread 0: draws 0 dummy PRNs, then draws 100 PRNs and fills out(0:99)
thread 1: draws 100 dummy PRNs, then draws 100 PRNs and fills out(100:199)
thread 2: draws 200 dummy PRNs, then draws 100 PRNs and fills out(200:299)
and so on. This method works well when each thread does a lot of computations besides drawing the PRNs since the time to prewind the PRNG could be substantial in some cases (e.g. with many iterations).
A third option exists for the case when there is a lot of data processing besides drawing a PRN. This one uses OpenMP ordered loops (note that the iteration chunk size is set to 1):
#pragma omp parallel for ordered schedule(static,1)
for (int i=0; i < n; i++) {
#pragma omp ordered
{
rnum = R::rnorm(mu,sigma);
}
out(i) = lots of processing on rnum
}
Although loop ordering essentially serialises the computation, it still allows for lots of processing on rnum to execute in parallel and hence parallel speed-up would be observed. See this answer for a better explanation as to why so.
Yes, sourceCpp() etc and an instantiation of RNGScope so the RNGs are left in a proper state.
And yes one can do OpenMP. But inside of OpenMP segment you cannot control in which order the threads are executed -- so you longer the same sequence. I have the same problem with a package under development where I would like to have reproducible draws yet use OpenMP. But it seems you can't.
Which one can gain a better performance?
Example 1
#pragma omp parallel for private (i,j)
for(i = 0; i < 100; i++) {
for (j=0; j< 100; j++){
....do sth...
}
}
Example 2
for(i = 0; i < 100; i++) {
#pragma omp parallel for private (i,j)
for (j=0; j< 100; j++){
....do sth...
}
}
Follow up question Is it valid to use Example 3?
#pragma omp parallel for private (i)
for(i = 0; i < 100; i++) {
#pragma omp parallel for private (j)
for (j=0; j< 100; j++){
....do sth...
}
}
In general, Example 1 is the best as it parallelizes the outer most loop, which minimizes thread fork/join overhead. Although many OpenMP implementations pre-allocate the thread pool, there are still overhead to dispatch logical tasks to worker threads (a.k.a. a team of thread) and join them. Also note that when you use a dynamic scheduling (e.g., schedule(dynamic, 1)), then this task dispatch overhead would be problematic.
So, Example 2 may incur significant parallel overhead, especially when the trip count of for-i is large (100 is okay, though), and the amount of workload of for-j is small. Small may be an ambiguous term and depends on many variables. But, less than 1 millisecond would be definitely wasteful to use OpenMP.
However, in case where the for-i is not parallelizable and only for-j is parallelizable, then Example2 is the only option. In this case, you must consider carefully whether the amount of parallel workload can offset the parallel overhead.
Example3 is perfectly valid once for-i and for-j are safely parallelizable (i.e., no loop-carried flow dependences in each two loops, respectively). Example3 is called nested parallelism. You may take a look this article. Nested parallelism should be used with care. In many OpenMP implementations, you need to manually turn on nested parallelism by calling omp_set_nested. However, as nested parallelism may spawn huge number of threads, its benefit may be significantly reduced.
It depends on the amount your doing in the inner loop. If it's small, lauching too many threads will represent a overhead. If the work is big, I would probabaly go with option 2, depending on the number of cores your machines has.
BTW, the only place where you need to flag a variable as private is "j" in example 1. In all the other cases it's implicit.
I'm writing a program for matrix multiplication with OpenMP, that, for cache convenience, implements the multiplication A x B(transpose) rows X rows instead of the classic A x B rows x columns, for better cache efficiency. Doing this I faced an interesting fact that for me is illogic: if in this code i parallelize the extern loop the program is slower than if I put the OpenMP directives in the most inner loop, in my computer the times are 10.9 vs 8.1 seconds.
//A and B are double* allocated with malloc, Nu is the lenght of the matrixes
//which are square
//#pragma omp parallel for
for (i=0; i<Nu; i++){
for (j=0; j<Nu; j++){
*(C+(i*Nu+j)) = 0.;
#pragma omp parallel for
for(k=0;k<Nu ;k++){
*(C+(i*Nu+j))+=*(A+(i*Nu+k)) * *(B+(j*Nu+k));//C(i,j)=sum(over k) A(i,k)*B(k,j)
}
}
}
Try hitting the result less often. This induces cacheline sharing and prevents the operation from running in parallel. Using a local variable instead will allow most of the writes to take place in each core's L1 cache.
Also, use of restrict may help. Otherwise the compiler can't guarantee that writes to C aren't changing A and B.
Try:
for (i=0; i<Nu; i++){
const double* const Arow = A + i*Nu;
double* const Crow = C + i*Nu;
#pragma omp parallel for
for (j=0; j<Nu; j++){
const double* const Bcol = B + j*Nu;
double sum = 0.0;
for(k=0;k<Nu ;k++){
sum += Arow[k] * Bcol[k]; //C(i,j)=sum(over k) A(i,k)*B(k,j)
}
Crow[j] = sum;
}
}
Also, I think Elalfer is right about needing reduction if you parallelize the innermost loop.
You could probably have some dependencies in the data when you parallelize the outer loop and compiler is not able to figure it out and adds additional locks.
Most probably it decides that different outer loop iterations could write into the same (C+(i*Nu+j)) and it adds access locks to protect it.
Compiler could probably figure out that there are no dependencies if you'll parallelize the 2nd loop. But figuring out that there are no dependencies parallelizing the outer loop is not so trivial for a compiler.
UPDATE
Some performance measurements.
Hi again. It looks like 1000 double * and + is not enough to cover the cost of threads synchronization.
I've done few small tests and simple vector scalar multiplication is not effective with openmp unless the number of elements is less than ~10'000. Basically, larger your array is, more performance will you get from using openmp.
So parallelizing the most inner loop you'll have to separate task between different threads and gather data back 1'000'000 times.
PS. Try Intel ICC, it is kinda free to use for students and open source projects. I remember being using openmp for smaller that 10'000 elements arrays.
UPDATE 2: Reduction example
double sum = 0.0;
int k=0;
double *al = A+i*Nu;
double *bl = A+j*Nu;
#pragma omp parallel for shared(al, bl) reduction(+:sum)
for(k=0;k<Nu ;k++){
sum +=al[k] * bl[k]; //C(i,j)=sum(over k) A(i,k)*B(k,j)
}
C[i*Nu+j] = sum;