Closed green-real closed 2 weeks ago
How was the performance measured here - what hardware was used and what benchmarks were ran?
How was the performance measured here - what hardware was used and what benchmarks were ran?
For both benchmarks, I timed a for loop with a body that simply calls the function I am benchmarking with some non-constant arguments. Both benchmarks have been ran multiple times with around 1e8 iterations and were then averaged out which is where I got the percentages from. My benchmarks were ran on i7-11700.
Since it seems that your PR contains the same vector.normalize change as my PR and a way better vector.dot optimization, it would make sense to close this one in favour of yours.
Merged PR #1512
Optimizes vector.normalize by using SIMD instructions, yielding a ~75% speed increase.
Optimizes vector.dot by reordering operations, yielding a ~20% speed increase.