File tree 1 file changed +3
-3
lines changed
1 file changed +3
-3
lines changed Original file line number Diff line number Diff line change 1
- .. title: Optimizing chunks for matrix multiplication. A new approach to matrix processing
1
+ .. title: Optimizing chunks for matrix multiplication in Blosc2
2
2
.. author: Ricardo Sales Piquer
3
3
.. slug: optimizing-chunks-blosc2
4
4
.. date: 2025-03-12 9:00:00 UTC
@@ -54,9 +54,9 @@ The image illustrates a **blocked matrix multiplication** approach. The key idea
54
54
is to divide matrices into smaller blocks (or chunks) to optimize memory
55
55
access and computational efficiency.
56
56
57
- In the image, matrix :math: `A (M \times K`) and matrix :math: `B (K \times N`)
57
+ In the image, matrix `A (M x K) ` and matrix `B (K x N) `
58
58
are partitioned into chunks, and these are partitioned into blocks. The resulting
59
- matrix :math: `C (M \times N`) is computed as a sum of block-wise multiplication.
59
+ matrix `C (M x N) ` is computed as a sum of block-wise multiplication.
60
60
61
61
This method significantly improves cache utilization by ensuring that only the
62
62
necessary parts of the matrices are loaded into memory at any given time. In
You can’t perform that action at this time.
0 commit comments