Alice/my_digital_garden
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

vault backup: 2023-10-25 12:31:34

Browse source
This commit is contained in:
Alice 2023-10-25 12:31:34 +01:00
parent e212392f9d
commit b1fc8a7ed7
3 changed files with 24 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

21
4a1s/CP/PL - Aula 7.md
View file

@ -557,7 +557,12 @@ Run \#1 (--cpus-per-task=2):
Dot is 1.2020569029595982
```
With the same cpus per task (cores), the result may vary depending on how
Run \#n (--cpus-per-task=2):
```
Dot is 0.0000000001499965
```
With the same cpus per task (cores), the result may vary depending on how each threads randomly "picks up" the iterations of the for.
Run \#2 (--cpus-per-task=4):
```
@ -569,6 +574,18 @@ Run \#3 (--cpus-per-task=6):
Dot is 0.0000000013500135
```
Run \#4 (--cpus-per-task=8):
```
Dot is 0.0000000000719980
```
Varies with the number of cpus per task (cores) because depending on the number of threads, the distribution of the instruction ```dot += a[i]*b[i];``` per thread will vary, aka the value ```i``` will constantly vary, making the memory space alternate between versions.
### c)
### c)
We can change the code to:
And the results will always be:
### d)
We can use _reduction_ to do that.