Merge branch 'master' of git.ichec.ie:training/sohpc-training-2021 into cw-python

D2-Python/03-Cython/solution/3_conways_life/job.sh

@@ -9,4 +9,4 @@
 #SBATCH --output=sohpc_test.log
 
 python setup.py build_ext --inplace
-python run.py 
\ No newline at end of file
+python run.py
\ No newline at end of file

D2-Python/03-Cython/solution/4_mandlebrotset/mandlebrot.py

+import numpy as np
+
+def kernel(zr, zi, cr, ci, radius, num_iters):
+    count = 0
+    while ((zr*zr + zi*zi) < (radius*radius)) and count < num_iters:
+        zr, zi = zr * zr - zi * zi + cr, 2 * zr * zi + ci
+        count += 1
+    return count
+
+
+def compute_mandel_py(cr, ci, N, bound, radius=1000.):
+    mandel = np.empty((N, N), dtype=int)
+    grid_x = np.linspace(-bound, bound, N)
+
+    for i, x in enumerate(grid_x):
+        for j, y in enumerate(grid_x):
+            mandel[i,j] = kernel(x, y, cr, ci, radius, N)
+    return mandel
\ No newline at end of file

D2-Python/03-Cython/solution/4_mandlebrotset/mandlebrot_cython.pyx

+# cython: boundscheck=False
+# cython: wraparound=False
+
+import numpy as np
+cimport numpy as cnp
+
+cdef int kernel(double zr, double zi, double cr, double ci, double radius, int num_iters):
+    cdef int count = 0
+    while ((zr*zr + zi*zi) < (radius*radius)) and count < num_iters:
+        zr, zi = zr * zr - zi * zi + cr, 2 * zr * zi + ci
+        count += 1
+    return count
+
+
+def compute_mandel_cyt(double cr, double ci, int N, double bound, double radius=1000.):
+    cdef cnp.ndarray[cnp.int_t, ndim=2] mandel
+
+    mandel = np.empty((N, N), dtype=int)
+    grid_x = np.linspace(-bound, bound, N)
+
+    cdef int i, j
+    cdef double x, y
+    for i, x in enumerate(grid_x):
+        for j, y in enumerate(grid_x):
+            mandel[i,j] = kernel(x, y, cr, ci, radius, N)
+    return mandel
\ No newline at end of file

D2-Python/03-Cython/solution/4_mandlebrotset/run_mandlebrot.py

+import time
+
+from mandlebrot import compute_mandel_py
+from mandlebrot_cython import compute_mandel_cyt
+
+kwargs = dict(cr=0.3852, ci=-0.2026,
+              N=400,
+              bound=1.2)
+
+t0 = time.time()
+mandel = compute_mandel_py(**kwargs)
+runtime_p = time.time() - t0
+print("Mandelbrot set generated in {} seconds\n".format(runtime_p))
+
+t0 = time.time()
+mandel = compute_mandel_cyt(**kwargs)
+runtime_c = time.time() - t0
+print("Mandelbrot set generated in {} seconds\n".format(runtime_c))
+
+print("Speed Up is: %f" % (runtime_p/runtime_c))
\ No newline at end of file

D2-Python/03-Cython/solution/4_mandlebrotset/setup.py

+from distutils.core import setup
+from Cython.Build import cythonize
+import numpy
+
+setup(ext_modules=cythonize("mandlebrot_cython.pyx"),
+      include_dirs=[numpy.get_include()]
+      )
+
+
+

D2-Python/04-Numba/big_exercises/README.md

@@ -4,5 +4,7 @@ Answer the following questions
 
 - Which version of the evolve function respond better to optimisation by Numba, the Python or the NumPy one?
 - Try eager compilation on the better function - record time
-- Try things like `parallel=True`, `prange`, `cache=True`, `fastmath=True`. What combination gave the best optimisation? Which loop is better to have the `prange` on?
-- `njit` the iterate function as well, notice anything wrong when you parallelise the iterate function?
\ No newline at end of file
+- Try things like `parallel=True` with `prange`, `cache=True`, `fastmath=True`. What combination gave the best optimisation? 
+- Which loop is better to have the `prange` on?
+- `njit` the iterate function as well, notice anything wrong when you parallelise the iterate function?
+[note - have to remove/ comment out some python-y parts]

D2-Python/04-Numba/solutions/big_exercises/README.md

@@ -4,5 +4,46 @@ Answer the following questions
 
 - Which version of the evolve function respond better to optimisation by Numba, the Python or the NumPy one?
 - Try eager compilation on the better function - record time
-- Try things like `parallel=True`, `prange`, `cache=True`, `fastmath=True`. What combination gave the best optimisation? Which loop is better to have the `prange` on?
-- `njit` the iterate function as well, notice anything wrong when you parallelise the iterate function?
\ No newline at end of file
+- Try things like `parallel=True` with `prange`, `cache=True`, `fastmath=True`. What combination gave the best optimisation? 
+- Which loop is better to have the `prange` on?
+- `njit` the iterate function as well, notice anything wrong with heat_200.png when you parallelise the iterate function?
+[note - have to remove comment out some python-y parts]
+
+
+Solutions:
+
+- Numba performed better on the python version.
+- Eager compilation gives best performance
+-  best result with prange on first loop
+
+Time for heat_equation python_njit- 2.952451
+
+Time for heat_equation numpy_njit- 5.289980
+
+Time for heat_equation eag- 1.372720
+
+Time for heat_equation cache- 2.527283
+
+Time for heat_equation cachefm- 2.196652
+
+Time for heat_equation par- 2.049756
+
+Time for heat_equation parfm- 2.130447
+
+Time for heat_equation eager & njit iterate - 1.606561
+
+Time for heat_equation eager & njit parallel iterate - 2.002234
+
+To look at heat_200.png image need to do something like - 
+
+scp course01@kay.ichec.ie:/ichec/home/users/course01/sohpc-training-2021/D2-Python/04- Numba/solutions/big_exercises/heat_200.png
+
+Needed to remove to njit the iterate function
+```
+if i % image_interval == 0:
+          write_field(field, i)
+ ```
+Parallelising the iterate function gives wrong output!- makes sense since the system evolves based on the previous iteration - therefore cannot be parallelised.
+
+
+

D3-OpenMP/01-OpenMP-Execution/exercise/pract3.slurm

+#!/bin/bash
+#SBATCH --partition=CourseDevQ
+#SBATCH --reservation=SOHPCCourse
+#SBATCH --nodes=1
+#SBATCH --time=00:10:00
+#SBATCH --account=course
+
+
+module load intel gcc
+
+cd $SLURM_SUBMIT_DIR
+
+export OMP_NUM_THREADS=20
+
+
+# Run OMP code
+./prog 
+
+
+
+