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

vault backup: 2023-10-04 12:43:31

Browse source
This commit is contained in:
Alice 2023-10-04 12:43:31 +01:00
parent ce64639d15
commit fc96b3d6bc
1 changed files with 13 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
4a1s/CP/PL - Aula 4.md
View file

@ -51,7 +51,7 @@ Ganhos de 4 vezes mais.
----
## Ex. 3 ## Ex. 3
#### a) Peak Performance #### a) Peak Performance
2 operações em FP 2 operações em FP
@ -60,6 +60,15 @@ Ganhos de 4 vezes mais.
conclusion: 20 GFlop/s conclusion: 20 GFlop/s
>[!note]- Redoing the math
>AVX -> 256b -> 4 doubles
>machine is superscalar with 2 FOP units
>4x2= 8 double-perations
>
>freq = 2.5 GHz
>8x2.5= 20 GFlop/s
> ^ cpu limitiation
#### b) #### b)
peak with vectorization: continuous 20 GFlop/s peak with vectorization: continuous 20 GFlop/s
peak without vectorization: continuous 5 GFlop/s peak without vectorization: continuous 5 GFlop/s
@ -67,8 +76,8 @@ memory bandwith limitation: ***see alinea d)***
real achievable performance:***see alinea c)*** real achievable performance:***see alinea c)***
measured performance: measured performance:
#### d) #### d) Memory bandwidth limitation
memory bandwith limitation 1 FOP -> 2B
| GFlop/s | Flop/Byte | | GFlop/s | Flop/Byte |
| ------- | --------- | | ------- | --------- |
@ -88,6 +97,4 @@ memory bandwith limitation
| ------- | --------- | | ------- | --------- |
| 0.125 | 2.5 | | 0.125 | 2.5 |
#### e)
#### d)
AVX -> 256b -> 4 doubles