Merge branch 'compile'

requirements.txt

@@ -1,3 +1,4 @@
 -e .
 
-pytest
+pytest
+ipython

setup.py

@@ -72,6 +72,12 @@ def run(self):
 
         sys.exit()
 
+extra_compile_args = ["-DSDX_PLATFORM=xilinx:aws-vu9p-f1:4ddr-xpr-2pr:4.0",
+                      "-D__USE_XOPEN2K8", "-I/opt/Xilinx/SDx/2017.1.op/runtime/include/1_2/",
+                      "-I/opt/Xilinx/SDx/2017.1.op/Vivado_HLS/include/"]
+
+extra_link_args = ["-shared", "-lxilinxopencl", "-lpthread", "-lrt",
+                    "-L/opt/Xilinx/SDx/2017.1.op/runtime/lib/x86_64", "-lstdc++", ]
 
 # Where the magic happens:
 setup(
@@ -83,7 +89,17 @@ def run(self):
     author_email=EMAIL,
     url=URL,
     packages=find_packages(exclude=('tests',)),
-    ext_modules=[Extension("_core", ["accel/_core.c", ])],
+    ext_modules=[Extension(
+        "_core",
+        ["accel/_core.c", "src/host.cpp", "src/xcl2.cpp"],
+        extra_compile_args=extra_compile_args,
+        extra_link_args=extra_link_args,
+        language='c++14',
+        runtime_library_dirs=[
+            "/opt/Xilinx/SDx/2017.1.rte/runtime/lib/x86_64/",
+        ],
+
+    )],
     # If your package is a single module, use this instead of 'packages':
     # py_modules=['slideshows'],
 

src/host.cpp

@@ -0,0 +1,149 @@
+/**********
+Copyright (c) 2017, Xilinx, Inc.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice,
+this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+this list of conditions and the following disclaimer in the documentation
+and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its contributors
+may be used to endorse or promote products derived from this software
+without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
+IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+**********/
+#include "xcl2.hpp"
+#include <vector>
+
+using std::vector;
+static const int DATA_SIZE = 256;
+static const std::string error_message =
+    "Error: Result mismatch:\n"
+    "i = %d CPU result = %d Device result = %d\n";
+
+
+
+
+vector<int, aligned_allocator<int>> vector_sub(
+	vector<int,aligned_allocator<int>> source_a,
+	vector<int,aligned_allocator<int>> source_b
+) {
+
+	size_t size_in_bytes = DATA_SIZE * sizeof(int);
+    vector<int,aligned_allocator<int>> source_results(DATA_SIZE);
+
+	// The get_xil_devices will return vector of Xilinx Devices
+	std::vector<cl::Device> devices = xcl::get_xil_devices();
+	cl::Device device = devices[0];
+
+	//Creating Context and Command Queue for selected Device
+	cl::Context context(device);
+	cl::CommandQueue q(context, device, CL_QUEUE_PROFILING_ENABLE);
+	std::string device_name = device.getInfo<CL_DEVICE_NAME>();
+	std::cout << "Found Device=" << device_name.c_str() << std::endl;
+
+	// import_binary() command will find the OpenCL binary file created using the
+	// xocc compiler load into OpenCL Binary and return as Binaries
+	// OpenCL and it can contain many functions which can be executed on the
+	// device.
+	std::string binaryFile = xcl::find_binary_file(device_name,"src/vector_subtraction");
+	cl::Program::Binaries bins = xcl::import_binary_file(binaryFile);
+	devices.resize(1);
+	cl::Program program(context, devices, bins);
+
+	// These commands will allocate memory on the FPGA. The cl::Buffer objects can
+	// be used to reference the memory locations on the device. The cl::Buffer
+	// object cannot be referenced directly and must be passed to other OpenCL
+	// functions.
+	cl::Buffer buffer_a(context, CL_MEM_USE_HOST_PTR | CL_MEM_READ_ONLY,
+			size_in_bytes, source_a.data());
+	cl::Buffer buffer_b(context, CL_MEM_USE_HOST_PTR | CL_MEM_READ_ONLY,
+			size_in_bytes, source_b.data());
+	cl::Buffer buffer_result(context, CL_MEM_USE_HOST_PTR | CL_MEM_WRITE_ONLY,
+			size_in_bytes, source_results.data());
+	//Separate Read/write Buffer vector is needed to migrate data between host/device
+	std::vector<cl::Memory> inBufVec, outBufVec;
+	inBufVec.push_back(buffer_a);
+	inBufVec.push_back(buffer_b);
+	outBufVec.push_back(buffer_result);
+
+
+	// These commands will load the source_a and source_b vectors from the host
+	// application and into the buffer_a and buffer_b cl::Buffer objects. The data
+	// will be be transferred from system memory over PCIe to the FPGA on-board
+	// DDR memory.
+	q.enqueueMigrateMemObjects(inBufVec,0/* 0 means from host*/);
+
+	// This call will extract a kernel out of the program we loaded in the
+	// previous line. A kernel is an OpenCL function that is executed on the
+	// FPGA. This function is defined in the src/vetor_addition.cl file.
+	cl::Kernel krnl_vector_sub(program,"vector_sub");
+
+	//set the kernel Arguments
+	int narg=0;
+	krnl_vector_sub.setArg(narg++,buffer_result);
+	krnl_vector_sub.setArg(narg++,buffer_a);
+	krnl_vector_sub.setArg(narg++,buffer_b);
+	krnl_vector_sub.setArg(narg++,DATA_SIZE);
+
+	//Launch the Kernel
+	q.enqueueTask(krnl_vector_sub);
+
+	// The result of the previous kernel execution will need to be retrieved in
+	// order to view the results. This call will write the data from the
+	// buffer_result cl_mem object to the source_results vector
+	q.enqueueMigrateMemObjects(outBufVec,CL_MIGRATE_MEM_OBJECT_HOST);
+	q.finish();
+
+	return source_results;
+}
+
+
+
+// This example illustrates the very simple OpenCL example that performs
+// an addition on two vectors
+int main(int argc, char **argv) {
+	if (argc != 3){
+		std::cout << "Please provide integers to add" << std::endl;
+		return 1;
+	}
+
+    // Creates a vector of DATA_SIZE elements with an initial value
+    // passed in as arguments
+    vector<int,aligned_allocator<int>> source_a(DATA_SIZE, atoi(argv[1]));
+    vector<int,aligned_allocator<int>> source_b(DATA_SIZE, atoi(argv[2]));
+    vector<int,aligned_allocator<int>> source_results(DATA_SIZE);
+
+    source_results = vector_sub(source_a, source_b);
+
+    int match = 0;
+    printf("Result = \n");
+    for (int i = 0; i < DATA_SIZE; i++) {
+        int host_result = source_a[i] - source_b[i];
+        if (source_results[i] != host_result) {
+            printf(error_message.c_str(), i, host_result, source_results[i]);
+            match = 1;
+            break;
+        } else {
+          printf("%d ", source_results[i]);
+          if (((i + 1) % 16) == 0) printf("\n");
+        }
+    }
+
+    std::cout << "TEST " << (match ? "FAILED" : "PASSED") << std::endl; 
+    return (match ? EXIT_FAILURE :  EXIT_SUCCESS);
+}

src/host.hpp

@@ -0,0 +1,9 @@
+#include <vector>
+#include "xcl2.hpp"
+
+using std::vector;
+
+vector<int, aligned_allocator<int>> vector_sub(
+	vector<int,aligned_allocator<int>> source_a,
+	vector<int,aligned_allocator<int>> source_b
+);