# coding: utf-8

# # PyOpenCL Parallel Patterns: Map/Elementwise

# ## Setup code

# In[1]:

import pyopencl as cl
import pyopencl.array
import pyopencl.clrandom
import numpy as np


# In[2]:

ctx = cl.create_some_context()
queue = cl.CommandQueue(ctx)


# In[3]:

n = 10**7
a = cl.clrandom.rand(queue, n, np.float32)
b = cl.clrandom.rand(queue, n, np.float32)


# ## A simple 'target application'

# We would like to evaluate this linear combination:

# In[4]:

c1 = 5*a + 6*b


# A problem with this is that every single operator (all three of them--and easily more for complicated expressions) corresponds to a kernel call, which can lead to high overhead. Let's try and avoid that by stuffing the entire operation into one kernel, in turn saving lots of memory traffic:

# In[5]:

from pyopencl.elementwise import ElementwiseKernel


# In[6]:

lin_comb = ElementwiseKernel(ctx,

        "float a, float *x, float b, float *y, float *c",

        "c[i] = a*x[i] + b*y[i]")


# In[7]:

c2 = cl.array.empty_like(a)
lin_comb(5, a, 6, b, c2)


# In[8]:

import numpy.linalg as la
print(la.norm(c1.get() - c2.get()))


# ## Timing ElementwiseKernel
# 
# Did this optimization pay off?

# In[9]:

from time import time
queue.finish()
start_time = time()

for i in range(10):
    c1 = 5*a + 6*b
    
queue.finish()
print("elapsed: {0} s".format(time()-start_time))


# In[10]:

from time import time
queue.finish()
start_time = time()

for i in range(10):
    lin_comb(5, a, 6, b, c2)
    
queue.finish()
print("elapsed: {0} s".format(time()-start_time))


# In[ ]: