Я немного изменил стандартный код из https://github.com/inducer/pyopencl/blob/master/examples/benchmark-all.py
Заменив на цифры, переменная zz
import pyopencl as cl
import numpy
import numpy.linalg as la
import datetime
from time import time
zz=100
a = numpy.random.rand(zz).astype(numpy.float32)
b = numpy.random.rand(zz).astype(numpy.float32)
c_result = numpy.empty_like(a)
# Speed in normal CPU usage
time1 = time()
for i in range(zz):
for j in range(zz):
c_result[i] = a[i] + b[i]
c_result[i] = c_result[i] * (a[i] + b[i])
c_result[i] = c_result[i] * (a[i] / 2)
time2 = time()
print("Execution time of test without OpenCL: ", time2 - time1, "s")
for platform in cl.get_platforms():
for device in platform.get_devices():
print("===============================================================")
print("Platform name:", platform.name)
print("Platform profile:", platform.profile)
print("Platform vendor:", platform.vendor)
print("Platform version:", platform.version)
print("---------------------------------------------------------------")
print("Device name:", device.name)
print("Device type:", cl.device_type.to_string(device.type))
print("Device memory: ", device.global_mem_size//1024//1024, 'MB')
print("Device max clock speed:", device.max_clock_frequency, 'MHz')
print("Device compute units:", device.max_compute_units)
# Simnple speed test
ctx = cl.Context([device])
queue = cl.CommandQueue(ctx,
properties=cl.command_queue_properties.PROFILING_ENABLE)
mf = cl.mem_flags
a_buf = cl.Buffer(ctx, mf.READ_ONLY | mf.COPY_HOST_PTR, hostbuf=a)
b_buf = cl.Buffer(ctx, mf.READ_ONLY | mf.COPY_HOST_PTR, hostbuf=b)
dest_buf = cl.Buffer(ctx, mf.WRITE_ONLY, b.nbytes)
prg = cl.Program(ctx, """
__kernel void sum(__global const float *a,
__global const float *b, __global float *c)
{
int loop;
int gid = get_global_id(0);
for(loop=0; loop<%s;loop++)
{
c[gid] = a[gid] + b[gid];
c[gid] = c[gid] * (a[gid] + b[gid]);
c[gid] = c[gid] * (a[gid] / 2);
}
}
""" % (zz)).build()
exec_evt = prg.sum(queue, a.shape, None, a_buf, b_buf, dest_buf)
exec_evt.wait()
elapsed = 1e-9*(exec_evt.profile.end - exec_evt.profile.start)
print("Execution time of test: %g s" % elapsed)
c = numpy.empty_like(a)
cl.enqueue_read_buffer(queue, dest_buf, c).wait()
error = 0
for i in range(zz):
if c[i] != c_result[i]:
error = 1
if error:
print("Results doesn't match!!")
else:
print("Results OK")
Если zz = 100, у меня есть:
('Execution time of test without OpenCL: ', 0.10500001907348633, 's')
===============================================================
('Platform name:', 'AMD Accelerated Parallel Processing')
('Platform profile:', 'FULL_PROFILE')
('Platform vendor:', 'Advanced Micro Devices, Inc.')
('Platform version:', 'OpenCL 1.1 AMD-APP-SDK-v2.5 (684.213)')
---------------------------------------------------------------
('Device name:', 'Cypress\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00')
('Device type:', 'GPU')
('Device memory: ', 800, 'MB')
('Device max clock speed:', 850, 'MHz')
('Device compute units:', 20)
Execution time of test: 0.00168922 s
Results OK
===============================================================
('Platform name:', 'AMD Accelerated Parallel Processing')
('Platform profile:', 'FULL_PROFILE')
('Platform vendor:', 'Advanced Micro Devices, Inc.')
('Platform version:', 'OpenCL 1.1 AMD-APP-SDK-v2.5 (684.213)')
---------------------------------------------------------------
('Device name:', 'Intel(R) Core(TM) i5 CPU 750 @ 2.67GHz\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00')
('Device type:', 'CPU')
('Device memory: ', 8183L, 'MB')
('Device max clock speed:', 3000, 'MHz')
('Device compute units:', 4)
Execution time of test: 4.369e-05 s
Results OK
У нас есть 3 раза:
normal ('Execution time of test without OpenCL: ', 0.10500001907348633, 's')
pyopencl radeon 5870: Execution time of test: 0.00168922 s
pyopencl i5 CPU 750: Execution time of test: 4.369e-05 s
Первый пакет вопросов: что такое pyopencl i5 CPU 750?почему он быстрее «нормального» ('время выполнения теста без OpenCL) в 250 раз?и почему он быстрее "pyopencl radeon 5870" в ~ 38 раз?
Если zz = 1000, то имеем:
normal ('Execution time of test without OpenCL: ', 9.05299997329712, 's')
pyopencl radeon 5870:Execution time of test: 0.0104431 s
pyopencl i5 CPU 750: Execution time of test: 0.00238112 s
i5 * 5 = radeon5870
i5 * 3800= normal
Если zz = 10000
normal its to long... comment code...
redeon58700, Execution time of test: 0.085571 s
i5, Execution time of test: 0.261854 s
Здесь мы видим, как выиграть видеокарту.
Еще очень интересно сравнить последовательность результатов.normal_stage1 * 90 = normal_stage2 normal_stage2 * ~ 95 = normal_stage3 (основано на опыте)
i5_stage1 * 52 = i5_stage2 i5_stage2 * 109 = i5_stage3
radeon5870_stage1 * 6 = radeon_s2 * radeon_s*
Может кто-нибудь объяснить, почему результаты opencl роста не были линейными?