unimore/hpc-2022-g3
unimore/hpc-2022-g3
1
Fork 0
mirror of https://github.com/Steffo99/unimore-hpc-assignments.git synced 2024-11-26 10:04:23 +00:00
Code Activity

aggiunge due for parallelizzati

Browse source
This commit is contained in:
Gattopandacorno 2022-11-16 11:09:30 +01:00
parent d45d94ca91
commit 5b8b4f84b2
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
OpenMP/linear-algebra/kernels/atax/atax.c
View file

@ -31,8 +31,8 @@ static void init_array(int nx, int ny,
} }
/// Initialize the `A` matrix with [something?] /// Initialize the `A` matrix with [something?]
// Using 4 threads here slows everything down: why? // Using 3-4 threads slow down the app
// #pragma omp parallel for num_threads(4) schedule(static) #pragma omp parallel for num_threads(2) schedule(static)
for (i = 0; i < nx; i++) for (i = 0; i < nx; i++)
for (j = 0; j < ny; j++) for (j = 0; j < ny; j++)
A[i][j] = ((DATA_TYPE)i * (j + 1)) / nx; A[i][j] = ((DATA_TYPE)i * (j + 1)) / nx;
@ -70,7 +70,7 @@ static void kernel_atax(int nx, int ny,
y[i] = 0; y[i] = 0;
/// This computes... something? I guess whatever ATAX is? /// This computes... something? I guess whatever ATAX is?
// Trying to parallelize this only seems to increase the time required #pragma omp parallel for num_threads(4) schedule(static)
for (i = 0; i < _PB_NX; i++) for (i = 0; i < _PB_NX; i++)
{ {
/// Every iteration has its own tmp variable /// Every iteration has its own tmp variable