leak test

leaktest.c

// File:       hello.c
//
// Abstract:   A simple "Hello World" compute example showing basic usage of OpenCL which
//             calculates the mathematical square (X[i] = pow(X[i],2)) for a buffer of
//             floating point values.
//             
//
// Version:    <1.0>
//
// Disclaimer: IMPORTANT:  This Apple software is supplied to you by Apple Inc. ("Apple")
//             in consideration of your agreement to the following terms, and your use,
//             installation, modification or redistribution of this Apple software
//             constitutes acceptance of these terms.  If you do not agree with these
//             terms, please do not use, install, modify or redistribute this Apple
//             software.
//
//             In consideration of your agreement to abide by the following terms, and
//             subject to these terms, Apple grants you a personal, non - exclusive
//             license, under Apple's copyrights in this original Apple software ( the
//             "Apple Software" ), to use, reproduce, modify and redistribute the Apple
//             Software, with or without modifications, in source and / or binary forms;
//             provided that if you redistribute the Apple Software in its entirety and
//             without modifications, you must retain this notice and the following text
//             and disclaimers in all such redistributions of the Apple Software. Neither
//             the name, trademarks, service marks or logos of Apple Inc. may be used to
//             endorse or promote products derived from the Apple Software without specific
//             prior written permission from Apple.  Except as expressly stated in this
//             notice, no other rights or licenses, express or implied, are granted by
//             Apple herein, including but not limited to any patent rights that may be
//             infringed by your derivative works or by other works in which the Apple
//             Software may be incorporated.
//
//             The Apple Software is provided by Apple on an "AS IS" basis.  APPLE MAKES NO
//             WARRANTIES, EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION THE IMPLIED
//             WARRANTIES OF NON - INFRINGEMENT, MERCHANTABILITY AND FITNESS FOR A
//             PARTICULAR PURPOSE, REGARDING THE APPLE SOFTWARE OR ITS USE AND OPERATION
//             ALONE OR IN COMBINATION WITH YOUR PRODUCTS.
//
//             IN NO EVENT SHALL APPLE BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL OR
//             CONSEQUENTIAL DAMAGES ( INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
//             SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
//             INTERRUPTION ) ARISING IN ANY WAY OUT OF THE USE, REPRODUCTION, MODIFICATION
//             AND / OR DISTRIBUTION OF THE APPLE SOFTWARE, HOWEVER CAUSED AND WHETHER
//             UNDER THEORY OF CONTRACT, TORT ( INCLUDING NEGLIGENCE ), STRICT LIABILITY OR
//             OTHERWISE, EVEN IF APPLE HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Copyright ( C ) 2008 Apple Inc. All Rights Reserved.
//

////////////////////////////////////////////////////////////////////////////////

#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <CL/opencl.h>

////////////////////////////////////////////////////////////////////////////////

// Use a static data size for simplicity
//
#define DATA_SIZE (1024*128)

////////////////////////////////////////////////////////////////////////////////

// Simple compute kernel which computes the square of an input array 
//
const char *KernelSource = "\n" \
"__kernel void square(                                                       \n" \
"   __global float* input,                                              \n" \
"   __global float* output,                                             \n" \
"   const unsigned int count)                                           \n" \
"{                                                                      \n" \
"   int i = get_global_id(0);                                           \n" \
"   if(i < count)                                                       \n" \
"       output[i] = input[i] * input[i];                                \n" \
"}                                                                      \n" \
"\n";

////////////////////////////////////////////////////////////////////////////////

int main()
{
    int err;                            // error code returned from api calls
      
    float data[DATA_SIZE];              // original data set given to device
    float results[DATA_SIZE];           // results returned from device
    unsigned int correct;               // number of correct results returned

    size_t global;                      // global domain size for our calculation
    size_t local;                       // local domain size for our calculation
    int k;
    int i;
    cl_device_id device_id;             // compute device id 
    cl_context context;                 // compute context
    cl_command_queue commands;          // compute command queue
    cl_program program;                 // compute program
    cl_kernel kernel;                   // compute kernel
    
    cl_mem input;                       // device memory used for the input array
    cl_mem output;                      // device memory used for the output array
    
	cl_platform_id platforms[32];			//an array to hold the IDs of all the platforms, hopefuly there won't be more than 32
	cl_uint num_platforms;				//this number will hold the number of platforms on this machine
	char vendor[1024];				//this strirng will hold a platforms vendor

	cl_device_id devices[32];			//this variable holds the number of devices for each platform, hopefully it won't be more than 32 per platform
	cl_uint num_devices;				//this number will hold the number of devices on this machine
	char deviceName[1024];				//this string will hold the devices name
	cl_uint numberOfCores;				//this variable holds the number of cores of on a device
	cl_long amountOfMemory;				//this variable holds the amount of memory on a device
	cl_uint clockFreq;				//this variable holds the clock frequency of a device
	cl_ulong maxAlocatableMem;			//this variable holds the maximum allocatable memory
	cl_ulong localMem;				//this variable holds local memory for a device
	cl_bool	available;				//this variable holds if the device is available
    // Fill our data set with random float values
    //
    int count = DATA_SIZE;
    for(i = 0; i < DATA_SIZE; i++)
        data[i] = rand() / (float)RAND_MAX;
    
    // Connect to a compute device
    //
	clGetPlatformIDs(2, platforms, &num_platforms);
    int pid = 0;
    err = clGetDeviceIDs(platforms[pid], CL_DEVICE_TYPE_ALL, 1, &device_id, NULL);
    if (err != CL_SUCCESS)
    {
        printf("Error: Failed to create a device group!\n");
        return EXIT_FAILURE;
    }
  
	//scan in device information
	clGetDeviceInfo(device_id, CL_DEVICE_NAME, sizeof(deviceName), deviceName, NULL);
	clGetDeviceInfo(device_id, CL_DEVICE_VENDOR, sizeof(vendor), vendor, NULL);
	clGetDeviceInfo(device_id, CL_DEVICE_MAX_COMPUTE_UNITS, sizeof(numberOfCores), &numberOfCores, NULL);
	clGetDeviceInfo(device_id, CL_DEVICE_GLOBAL_MEM_SIZE, sizeof(amountOfMemory), &amountOfMemory, NULL);
	clGetDeviceInfo(device_id, CL_DEVICE_MAX_CLOCK_FREQUENCY, sizeof(clockFreq), &clockFreq, NULL);
	clGetDeviceInfo(device_id, CL_DEVICE_MAX_MEM_ALLOC_SIZE, sizeof(maxAlocatableMem), &maxAlocatableMem, NULL);
	clGetDeviceInfo(device_id, CL_DEVICE_LOCAL_MEM_SIZE, sizeof(localMem), &localMem, NULL);
	clGetDeviceInfo(device_id, CL_DEVICE_AVAILABLE, sizeof(available), &available, NULL);


	//print out device information
	printf("\tDevice: %u\n", device_id);
	printf("\t\tName:\t\t\t\t%s\n", deviceName);
	printf("\t\tVendor:\t\t\t\t%s\n", vendor);
	printf("\t\tAvailable:\t\t\t%s\n", available ? "Yes" : "No");
	printf("\t\tCompute Units:\t\t\t%u\n", numberOfCores);
	printf("\t\tClock Frequency:\t\t%u mHz\n", clockFreq);
	printf("\t\tGlobal Memory:\t\t\t%0.00f mb\n", (double)amountOfMemory/1048576);
	printf("\t\tMax Allocateable Memory:\t%0.00f mb\n", (double)maxAlocatableMem/1048576);
	printf("\t\tLocal Memory:\t\t\t%u kb\n\n", (unsigned int)localMem);
    // Create a compute context 
    //
    context = clCreateContext(0, 1, &device_id, NULL, NULL, &err);
    if (!context)
    {
        printf("Error: Failed to create a compute context!\n");
        return EXIT_FAILURE;
    }

    // Create a command commands
    //
    commands = clCreateCommandQueue(context, device_id, 0, &err);
    if (!commands)
    {
        printf("Error: Failed to create a command commands!\n");
        return EXIT_FAILURE;
    }

    // Create the compute program from the source buffer
    //
    program = clCreateProgramWithSource(context, 1, (const char **) & KernelSource, NULL, &err);
    if (!program)
    {
        printf("Error: Failed to create compute program!\n");
        return EXIT_FAILURE;
    }

    // Build the program executable
    //
    err = clBuildProgram(program, 0, NULL, NULL, NULL, NULL);
    if (err != CL_SUCCESS)
    {
        size_t len;
        char buffer[2048];

        printf("Error: Failed to build program executable!\n");
        clGetProgramBuildInfo(program, device_id, CL_PROGRAM_BUILD_LOG, sizeof(buffer), buffer, &len);
        printf("%s\n", buffer);
        exit(1);
    }

    // Create the compute kernel in the program we wish to run
    //
    kernel = clCreateKernel(program, "square", &err);
    if (!kernel || err != CL_SUCCESS)
    {
        printf("Error: Failed to create compute kernel!\n");
        exit(1);
    }
    for(k = 0; k<9999; k++){
        // Create the input and output arrays in device memory for our calculation
        //
        input = clCreateBuffer(context,  CL_MEM_READ_ONLY,  sizeof(float) * DATA_SIZE, NULL, NULL);
        output = clCreateBuffer(context, CL_MEM_WRITE_ONLY, sizeof(float) * DATA_SIZE, NULL, NULL);
        if (!input || !output)
        {
            printf("Error: Failed to allocate device memory!\n");
            exit(1);
        }    
        
        // Write our data set into the input array in device memory 
        //
        err = clEnqueueWriteBuffer(commands, input, CL_TRUE, 0, sizeof(float) * DATA_SIZE, data, 0, NULL, NULL);
        if (err != CL_SUCCESS)
        {
            printf("Error: Failed to write to source array!\n");
            exit(1);
        }

        // Set the arguments to our compute kernel
        //
        err = 0;
        err  = clSetKernelArg(kernel, 0, sizeof(cl_mem), &input);
        err |= clSetKernelArg(kernel, 1, sizeof(cl_mem), &output);
        err |= clSetKernelArg(kernel, 2, sizeof(unsigned int), &count);
        if (err != CL_SUCCESS)
        {
            printf("Error: Failed to set kernel arguments! %d\n", err);
            exit(1);
        }

        // Get the maximum work group size for executing the kernel on the device
        //
        err = clGetKernelWorkGroupInfo(kernel, device_id, CL_KERNEL_WORK_GROUP_SIZE, sizeof(local), &local, NULL);
        if (err != CL_SUCCESS)
        {
            printf("Error: Failed to retrieve kernel work group info! %d\n", err);
            exit(1);
        }

        // Execute the kernel over the entire range of our 1d input data set
        // using the maximum number of work group items for this device
        //
        global = count;
        err = clEnqueueNDRangeKernel(commands, kernel, 1, NULL, &global, &local, 0, NULL, NULL);
        if (err)
        {
            printf("Error: Failed to execute kernel!\n");
            return EXIT_FAILURE;
        }

        // Wait for the command commands to get serviced before reading back results
        //
        clFinish(commands);

        // Read back the results from the device to verify the output
        //
        err = clEnqueueReadBuffer( commands, output, CL_TRUE, 0, sizeof(float) * DATA_SIZE, results, 0, NULL, NULL );  
        if (err != CL_SUCCESS)
        {
            printf("Error: Failed to read output array! %d\n", err);
            exit(1);
        }
        
        // Validate our results
        //
        correct = 0;
        for(i = 0; i < DATA_SIZE; i++)
        {
            if(results[i] == data[i] * data[i])
                correct++;
        }
        
        // Print a brief summary detailing the results
        //
        //printf("Computed '%d/%d' correct values!\n", correct, count);
        
        // Shutdown and cleanup
        //
        clReleaseMemObject(input);
        clReleaseMemObject(output);
    }
    clReleaseProgram(program);
    clReleaseKernel(kernel);
    clReleaseCommandQueue(commands);
    clReleaseContext(context);
    printf("Normal exit atfer %u iterations over %u bytes array\n", k, count);

    return 0;
}

leaktest.py

import pyopencl as cl
from pyopencl import array
from pyopencl import clrandom
import numpy as np
from time import sleep

ctx = cl.create_some_context()
queue = cl.CommandQueue(ctx)
mf = cl.mem_flags
dtype = np.float32
DATA_SIZE = 128*1024


KernelSource = """
__kernel void square(                      
   __global float* input,                  
   __global float* output,                 
   const unsigned int count)               
{                                          
   int i = get_global_id(0);               
   if(i < count)                           
       output[i] = input[i] * input[i];    
}
"""


prg = cl.Program(ctx, KernelSource).build()

hostdata = np.random.randn(DATA_SIZE).astype(dtype)
hostres = np.empty(shape=hostdata.shape, dtype=hostdata.dtype)

for i in range(9999):
    #clresult = array.Array(queue, (DATA_SIZE,), dtype)
    clresult = cl.Buffer(ctx, mf.READ_WRITE, hostdata.dtype.itemsize*DATA_SIZE)
    cldata   = cl.Buffer(ctx, mf.READ_ONLY| mf.COPY_HOST_PTR, hostbuf=hostdata)
    prg.square(queue, (DATA_SIZE,), None, cldata, clresult, np.uint32(DATA_SIZE))
    cl.enqueue_copy(queue, hostres, clresult)
    #assert (clresult.get() == hostdata*hostdata).all(), "Got bad result on {0} iteration".format(i)
    assert (hostres == hostdata*hostdata).all(), "Got bad result on {0} iteration".format(i)
    if i%99 == 0:
        print("Iteration {0}. Still alive".format(i))

limitmemory

#!/bin/sh
# By JanKanis 
# http://unix.stackexchange.com/questions/134414/how-to-limit-the-total-resources-memory-of-a-process-and-its-children

set -eu

if [ "$#" -lt 2 ]
then
    echo Usage: `basename $0` "<limit> <command>..."
    exit 1
fi

limit="$1"
shift
cgname="limitmem_$$"
echo "limiting memory to $limit (cgroup $cgname) for command $@"

cgm create memory "$cgname" >/dev/null
cgm setvalue memory "$cgname" memory.limit_in_bytes "$limit" >/dev/null
# try also limiting swap usage, but this fails if the system has no swap
cgm setvalue memory "$cgname" memsw.limit_in_bytes "$limit" >/dev/null 2>&1 || true

# spawn subshell to run in the cgroup
set +e
(
set -e
cgm movepid memory "$cgname" `sh -c 'echo $PPID'` > /dev/null
exec "$@"
)
# grab exit code
exitcode=`echo $?`

set -e

echo -n "peak memory used: "
cgm getvalue memory "$cgname" memory.max_usage_in_bytes | tail -1 | cut -f2 -d\"

cgm remove memory "$cgname" >/dev/null
exit $exitcode