/usr/share/doc/libclblas-doc/examples/example_ssbmv.c is in libclblas-doc 2.12-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 | /* ************************************************************************
* Copyright 2013 Advanced Micro Devices, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
* ************************************************************************/
#include <sys/types.h>
#include <stdio.h>
#include <string.h>
/* Include CLBLAS header. It automatically includes needed OpenCL header,
* so we can drop out explicit inclusion of cl.h header.
*/
#include <clBLAS.h>
/* This example uses predefined matrices and their characteristics for
* simplicity purpose.
*/
static const clblasOrder order = clblasRowMajor;
static const clblasUplo uplo = clblasUpper;
static const size_t N = 5;
static const size_t K = 2;
static const cl_float alpha = 10;
static const cl_float A[] = {
11, 12, 13,
22, 23, 24,
33, 34, 35,
44, 45, 00,
55, 00, 00
};
static const size_t lda = 3; // lda = K + 1
static const cl_float X[] = {
11,
21,
31,
41,
51
};
static const int incx = 1;
static const cl_float beta = 20;
static cl_float Y[] = {
11,
21,
31,
41,
51
};
static const int incy = 1;
static void
printResult(const char* str)
{
size_t i;
printf("%s:\n", str);
for (i = 0; i < N; i++) {
printf("%f\n", Y[ i * incy ]);
}
}
int
main(void)
{
cl_int err;
cl_platform_id platform = 0;
cl_device_id device = 0;
cl_context_properties props[3] = { CL_CONTEXT_PLATFORM, 0, 0 };
cl_context ctx = 0;
cl_command_queue queue = 0;
cl_mem bufA, bufX, bufY;
cl_event event = NULL;
int ret = 0;
/* Setup OpenCL environment. */
err = clGetPlatformIDs(1, &platform, NULL);
if (err != CL_SUCCESS) {
printf( "clGetPlatformIDs() failed with %d\n", err );
return 1;
}
err = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, 1, &device, NULL);
if (err != CL_SUCCESS) {
printf( "clGetDeviceIDs() failed with %d\n", err );
return 1;
}
props[1] = (cl_context_properties)platform;
ctx = clCreateContext(props, 1, &device, NULL, NULL, &err);
if (err != CL_SUCCESS) {
printf( "clCreateContext() failed with %d\n", err );
return 1;
}
queue = clCreateCommandQueue(ctx, device, 0, &err);
if (err != CL_SUCCESS) {
printf( "clCreateCommandQueue() failed with %d\n", err );
clReleaseContext(ctx);
return 1;
}
/* Setup clblas. */
err = clblasSetup();
if (err != CL_SUCCESS) {
printf("clblasSetup() failed with %d\n", err);
clReleaseCommandQueue(queue);
clReleaseContext(ctx);
return 1;
}
/* Prepare OpenCL memory objects and place matrices inside them. */
bufA = clCreateBuffer(ctx, CL_MEM_READ_ONLY, N * lda * sizeof(cl_float),
NULL, &err);
bufX = clCreateBuffer(ctx, CL_MEM_READ_ONLY, N * sizeof(cl_float),
NULL, &err);
bufY = clCreateBuffer(ctx, CL_MEM_READ_WRITE, N * sizeof(cl_float),
NULL, &err);
err = clEnqueueWriteBuffer(queue, bufA, CL_TRUE, 0,
N * lda * sizeof(cl_float), A, 0, NULL, NULL);
err = clEnqueueWriteBuffer(queue, bufX, CL_TRUE, 0,
N * sizeof(cl_float), X, 0, NULL, NULL);
err = clEnqueueWriteBuffer(queue, bufY, CL_TRUE, 0,
N * sizeof(cl_float), Y, 0, NULL, NULL);
/* Call clblas function. */
err = clblasSsbmv(order, uplo, N, K, alpha, bufA, 0, lda, bufX, 0, incx,
beta, bufY, 0, incy, 1, &queue, 0, NULL, &event);
if (err != CL_SUCCESS) {
printf("clblasSsbmv() failed with %d\n", err);
ret = 1;
}
else {
/* Wait for calculations to be finished. */
err = clWaitForEvents(1, &event);
/* Fetch results of calculations from GPU memory. */
err = clEnqueueReadBuffer(queue, bufY, CL_TRUE, 0,
N * sizeof(cl_float), Y, 0, NULL, NULL);
/* At this point you will get the result of SSBMV placed in Y array. */
printResult("clblasSsbmv result");
}
/* Release OpenCL events. */
clReleaseEvent(event);
/* Release OpenCL memory objects. */
clReleaseMemObject(bufY);
clReleaseMemObject(bufX);
clReleaseMemObject(bufA);
/* Finalize work with clblas. */
clblasTeardown();
/* Release OpenCL working objects. */
clReleaseCommandQueue(queue);
clReleaseContext(ctx);
return ret;
}
|