Fastest CPU / Fastest GPU data skewed #74214
Labels
No Label
Priority
High
Priority
Low
Priority
Normal
Status
Archived
Status
Confirmed
Status
Duplicate
Status
Needs Information from Developers
Status
Needs Triage
Status
Resolved
Type
Bug
Type
Design
Type
Report
Type
To Do
No Milestone
No project
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: infrastructure/blender-open-data#74214
Loading…
Reference in New Issue
Block a user
No description provided.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Hi!
Look at the top graphs here:
https://opendata.blender.org/
From the two top lists you can get these numbers, showing that the AMD CPU is about 1.2x faster than the GeForce card:
However, if you look at benchmark numbers for these two, where both have been run on the same...
... it turns out that it's actually the GeForce card that is faster by a factor of 1.2:
https://github.com/walles/blender-opendata-comparer/tree/walles/toplist
Branch:
walles/toplist
SHA:
4fb12bb13b5e4e5a2e70862b844f76de28ae1ae9
So due to sampling bias, where not all rendering devices have been run under the same conditions, the current comparisons sometimes come out wrong.
Not entirely sure how to do better comparisons unfortunately, but this is something that you may want to think about.
Regards /Johan
Added subscriber: @Walles
Added subscriber: @SemMulder
I think this is mainly due to the CUDA vs OptiX difference (see #73322) and compare the following:
https://opendata.blender.org/benchmarks/query/?device_name=GeForce%20RTX%202080%20Ti&group_by=benchmark&group_by=device_type
https://opendata.blender.org/benchmarks/query/?device_name=Threadripper%203970X&group_by=benchmark
So I'm merging this into #73322.
Closed as duplicate of #73322