tocBytes

Read how many bytes have been transferred since calling ticBytes

Syntax

tocBytes(pool)

bytes = tocBytes(pool)

tocBytes(pool,startState)

bytes = tocBytes(pool,startState)

Description

tocBytes(pool) reads how many bytes have been transferred since calling ticBytes. The function displays the total number of bytes transferred to and from each of the workers in a parallel pool after the most recent execution of ticBytes.

Use the ticBytes (pool) and tocBytes (pool) functions together to measure how much data (and associated metadata) is transferred to and from the workers in a parallel pool. You can use ticBytes and tocBytes while executing parallel language constructs and functions, such as parfor, spmd, or parfeval. Use ticBytes and tocBytes to pass around less data and optimize your code.

bytes = tocBytes(pool) returns the number of bytes transferred to and from each of the workers in the parallel pool.

tocBytes(pool,startState) displays the total number of bytes transferred in the parallel pool after the ticBytes command that generated startState.

bytes = tocBytes(pool,startState) returns the number of bytes transferred to and from each of the workers in the parallel pool after the ticBytes command that generated startState.

Examples

Measure Amount of Data Transferred While Running a Simple parfor-loop

Use tocBytes(gcp,startS) to measure the amount of data (and associated metadata) transferred.

a = 0;
b = rand(100);
startS = ticBytes(gcp);
parfor i = 1:100
    a = a + sum(b(:, i));
end
tocBytes(gcp,startS)

Starting parallel pool (parpool) using the 'Processes' profile ... 
connected to 4 workers.

             BytesSentToWorkers    BytesReceivedFromWorkers
             __________________    ________________________

    1            42948              7156                   
    2            36548              7156                   
    3            27500              4500                   
    4            27500              4500                   
    Total    1.345e+05             23312                   

Workers might transfer different numbers of bytes, because each worker might carry out different numbers of loop iterations.

Measure Amount of Data Transferred While Running a Simple spmd Block

Use bytes = tocBytes(gcp) to measure the amount of data (and associated metadata) transferred.

ticBytes(gcp);
spmd
    rand(100);
end
bytes = tocBytes(gcp)

bytes =

       13448        1208
       13448        1208
       13448        1208
       13448        1208          				   

Workers transfer the same number of bytes, because each worker carries out the same number of loop iterations.

Simultaneously Measure Multiple Amounts of Data Transferred, Using Two Pairs of ticBytes and tocBytes Calls

Measure the minimum and average number of bytes transferred while running a parfor loop nested in a for loop.

REPS = 10;   
minBytes = Inf;   
ticBytes(gcp);  % ticBytes, pair 1

for ii=1:REPS
   a = 0;
   b = rand(100);
   startS = ticBytes(gcp)  % ticBytes, pair 2  
   parfor i = 1:100
       a = a + sum(b(:, i));
   end
   bytes = tocBytes(gcp, startS)  % tocBytes, pair 2  
   minBytes = min(bytes, minBytes)
end

averageBytes = tocBytes(gcp)/REPS  % tocBytes, pair 1 
          

Note that nesting a parfor-loop in a for-loop can be slow due to overhead, see Convert Nested for-Loops to parfor-Loops.

Input Arguments

pool — Parallel pool

parallel.ProcessPool object | parallel.ClusterPool object

Parallel pool, specified as a parallel.ProcessPool or parallel.ClusterPool object.

To create a process pool or cluster pool, use parpool.

Example: pool = parpool('Processes');

startState — Starting state

TicBytesResult

Starting state returned by ticBytes(pool).

Example: startState = ticBytes(gcp);

Output Arguments

bytes — Bytes transferred

tocBytes(pool)

Bytes transferred, returned as a matrix of size numWorkers x 2. This matrix contains the number of bytes transferred to and from each of the workers in the parallel pool. bytes returns values in bytes without headings. Use tocBytes(pool) without an output argument to get Sent and Received headings, worker numbers, and values in bytes in the Command Window output.

Example: bytes = tocBytes(pool);

Extended Capabilities

Thread-Based Environment

Run code in the background using MATLAB® backgroundPool or accelerate code with Parallel Computing Toolbox™ ThreadPool.

This function fully supports thread-based environments. For more information, see Run MATLAB Functions in Thread-Based Environment.

Version History

Introduced in R2016b