derek/master-thesis
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Smaller refactorings in result chapter

Browse Source
This commit is contained in:
Derek Christ
2024-03-08 23:26:59 +01:00
parent 42ef5e7672
commit 4430c10aad
2 changed files with 12 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/chapters/conclusion.tex
View File

@@ -8,7 +8,7 @@ A working \ac{vp} of \aca{fimdram}, in the form of a software model, has been de
This made it possible to explore the performance gain of \ac{pim} for different workloads in a simple and flexible way.
It was found that \ac{pim} can provide a speedup of up to $\qty{23.9}{\times}$ for level 1 \ac{blas} vector operations and up to $\qty{62.5}{\times}$ for level 2 \ac{blas} operations.
While these results may not strictly represent a real-world system, an achievable upper bound of speedups of $\qty{17.6}{\times}$ and $\qty{9.0}{\times}$ could be determined using a hypothetical infinite compute system.
While these results may not strictly represent a real-world system, an achievable speedup of $\qty{17.6}{\times}$ and $\qty{9.0}{\times}$ could be determined using a hypothetical infinite compute system.
This achieved speedup of $\qty{9.0}{\times}$ for the \ac{gemv} routine largely matches the number of Samsung's real-world implementation of \aca{fimdram} at about $\qty{8.3}{\times}$.
In addition to the numbers presented by Samsung, the same simulation workloads were run on two real \ac{gpu} systems, both with \aca{hbm}, and their runtimes were compared.