Closed bernhardmgruber closed 1 year ago
Merging #653 (1ee97e4) into develop (4271b5a) will increase coverage by
0.00%
. The diff coverage is100.00%
.
Runtime difference is marginal:
layout | runtime |
---|---|
"SoA SB aligned" | 0.113894 |
"SoA SB aligned CT size" | 0.113254 |
compile time:
runtime:
layout | runtime |
---|---|
"SoA SB aligned" | 0.160085 |
"SoA SB aligned CT size" | 0.160387 |
Here, the CT variant is actually a bit slower. But the assembly is better (less instructions).
This PR improves the SoA by precomputing a compile-time only subarray offset table when the array extents are fully static.
This PR also contains an extension of the vectoradd benchmarks: