bench: don't accumulate state over runs

This commit is contained in:
Joakim Frostegård 2020-04-08 13:08:41 +02:00
parent c75e36c105
commit 2d01a34ff7
2 changed files with 22 additions and 20 deletions

View file

@ -14,7 +14,6 @@
* Run multiple threads to test performance when contested?
* Iterate over whole returned buffer and run e.g. xor on it (.iter().fold())
* Generic bench function since current functions are almost identical
* State is now accumulated over runs. Is this good?
* Performance
* cpu-target=native good?
* mialloc good?