We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 7d80fa8 commit ce80a3fCopy full SHA for ce80a3f
numojo/math/linalg/matmul.mojo
@@ -64,8 +64,8 @@ fn matmul_parallelized[
64
"""Conduct `matmul` using `vectorize` and `parallelize`.
65
66
Reference: https://docs.modular.com/mojo/notebooks/Matmul
67
- Compared to the reference, this function increases the size of
68
- the SIMD vector from the default width to 16. The purpose is to
+ Compared to the reference, this function increases the size of
+ the SIMD vector from the default width to 16. The purpose is to
69
increase the performance via SIMD.
70
The function reduces the execution time by ~50 percent compared to
71
matmul_parallelized and matmul_tiled_unrolled_parallelized for large
0 commit comments