Get Started Guide

  • 2021.3
  • 10/21/2021
  • Public Content

Run Intel® oneAPI Base Toolkit Sample Applications in Docker* Container

Run the Sample Application

  1. Run the command below to start the Docker container as root:
    ./run_interactive_docker.sh amr-ubuntu2004-full-flavour-sdk:<TAG> root
  2. Inside Docker, update /etc/apt/apt.conf.d/proxy.conf with the corresponding exports, and install CUDA:
    # Send proxy exports wget -O /etc/apt/preferences.d/cuda-repository-pin-600 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin sudo apt-key adv --keyserver-options http-proxy=http://proxy-chain.intel.com:911 --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub sudo add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/ /" sudo apt-get update -y --allow-unauthenticated && DEBIAN_FRONTEND=noninteractive sudo apt-get install -y --no-install-recommends cuda-10-1 sudo rm -rf /var/lib/apt/lists/*
  3. Set up the environment for Intel® oneAPI Base Toolkit:
    source /opt/intel/oneapi/setvars.sh
  4. Using the DPC++ compiler, create a file named
    simple.cpp
    and populate it with this content using a text editor:
    #include <CL/sycl.hpp> int main() { // Creating buffer of 4 ints to be used inside the kernel code cl::sycl::buffer<cl::sycl::cl_int, 1> Buffer(4); // Creating SYCL queue cl::sycl::queue Queue; // Size of index space for kernel cl::sycl::range<1> NumOfWorkItems{Buffer.get_count()}; // Submitting command group(work) to queue Queue.submit([&](cl::sycl::handler &cgh) { // Getting write only access to the buffer on a device auto Accessor = Buffer.get_access<cl::sycl::access::mode::write>(cgh); // Executing kernel cgh.parallel_for<class FillBuffer>( NumOfWorkItems, [=](cl::sycl::id<1> WIid) { // Fill buffer with indexes Accessor[WIid] = (cl::sycl::cl_int)WIid.get(0); }); }); // Getting read only access to the buffer on the host. // Implicit barrier waiting for queue to complete the work. const auto HostAccessor = Buffer.get_access<cl::sycl::access::mode::read>(); // Check the results bool MismatchFound = false; for (size_t I = 0; I < Buffer.get_count(); ++I) { if (HostAccessor[I] != I) { std::cout << "The result is incorrect for element: " << I << " , expected: " << I << " , got: " << HostAccessor[I] << std::endl; MismatchFound = true; } } if (!MismatchFound) { std::cout << "The results are correct!" << std::endl; } return MismatchFound; }
    Run the command below and review the output binary:
    clang++ -fsycl simple.cpp -o simple ./simple
    Expected output:
    "The results are correct":
  5. Convert CUDA to DPC++ and build it.
    1. Go to CUDA code sample and convert to DPC++:
      git clone https://github.com/oneapi-src/oneAPI-samples.git cp oneAPI-samples/Tools/Migration/vector-add-dpct/src/vector_add.cu /home/eiforamr/data_samples/vector_add.cu chmod +x /home/eiforamr/data_samples /vector_add.cu dpct --in-root=/home/eiforamr/data_samples/ /home/eiforamr/data_samples /vector_add.cu
      Expected output:
      root@edgesoftware:/home/eiforamr/data_samples# chmod +x "${DATA_SAMPLES}"/vector_add.cu root@edgesoftware:/home/eiforamr/data_samples# dpct --in-root=/home/eiforamr/data_samples/ vector_add.cu NOTE: Could not auto-detect compilation database for file 'vector_add.cu' in '/home/eiforamr/data_samples' or any parent directory. The directory "dpct_output" is used as "out-root" Processing: /home/eiforamr/data_samples/vector_add.cu /home/eiforamr/data_samples/vector_add.cu:32:14: warning: DPCT1003:0: Migrated API does not return error code. (*, 0) is inserted. You may need to rewrite this code. status = cudaMemcpy(Result, d_C, VECTOR_SIZE*sizeof(float), cudaMemcpyDeviceToHost); ^ Processed 1 file(s) in -in-root folder "/home/eiforamr/data_samples" See Diagnostics Reference to resolve warnings and complete the migration: https://www.intel.com/content/www/us/en/develop/documentation/intel-dpcpp-compatibility-tool-user-guide/top/diagnostics-reference.html root@edgesoftware:/home/eiforamr/data_samples#
    2. Conversion successfully done:
      ls dpct_output vector_add.cu
    3. Go to output directory:
      cd /dpct_output
    4. Create simple Makefile with this content:
      CXX = dpcpp TARGET = vector_add SRCS = vector_add.dp.cpp # Use predefined implicit rules and add one for *.cpp files. %.o: %.cpp $(CXX) -c $(CXXFLAGS) $(CPPFLAGS) $< -o $@ all: $(TARGET) $(TARGET): $(SRCS) $(DEPS) $(CXX) $(SRCS) -o $@ run: $(TARGET) ./$(TARGET) .PHONY: clean clean: rm -f $(TARGET) *.o
    5. Run make and then the output binary named
      vector_add
      :
      make ./vector_add
    Expected output
    A block of even numbers will be listed, indicating the result of adding two vectors: [ 1..N] + [1..N].
    dpct_output$ ./vector_add2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38 40 42 44 46 48 50 52 54 56 58 60 62 64 66 68 70 72 74 76 78 80 82 84 86 88 90 92 94 96 98 100 102 104 106 108 110 112 114 116 118 120 122 124 126 128 130 132 134 136 138 140 142 144 146 148 150 152 154 156 158 160 162 164 166 168 170 172 174 176 178 180 182 184 186 188 190 192 194 196 198 200 202 204 206 208 210 212 214 216 218 220 222 224 226 228 230 232 234 236 238 240 242 244 246 248 250 252 254 256 258 260 262 264 266 268 270 272 274 276 278 280 282 284 286 288 290 292 294 296 298 300 302 304 306 308 310 312 314 316 318 320 322 324 326 328 330 332 334 336 338 340 342 344 346 348 350 352 354 356 358 360 362 364 366 368 370 372 374 376 378 380 382 384 386 388 390 392 394 396 398 400 402 404 406 408 410 412 414 416 418 420 422 424 426 428 430 432 434 436 438 440 442 444 446 448 450 452 454 456 458 460 462 464 466 468 470 472 474 476 478 480 482 484 486 488 490 492 494 496 498 500 502 504 506 508 510 512

Troubleshooting

If the following error is encountered:
$ ./run_interactive_docker.sh amr-ubuntu2004-full-flasvour-sdk:<TAG> eiforamr bash: ./run_interactive_docker.sh Permission denied
Give executable permission to the script:
$ chmod 755 run_interactive_docker.sh

Summary and Next Steps

In this tutorial, you learned how to use the DPC++ compiler, convert CUDA to DPC++, build it, and run it.

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.