leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 27 Packages Projects Releases Wiki Activity

fix: fig link in cute docs (#2216)

Browse Source
This commit is contained in:
Zhang_kg
2025-04-10 14:51:41 -04:00
committed by GitHub
parent b3f3c7758c
commit 5e497243f7
4 changed files with 25 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
media/docs/cpp/cute/0x_gemm_tutorial.md
+3 -3
View File
@@ -335,7 +335,7 @@ These thread layouts are then used to partition the tiles of data in global memo
where we've used the same projection-style interface to avoid applying the `N`-mode of `tC` to the `(BLK_M,BLK_K)` shape of `sA` and avoid applying the `M`-mode of `tC` to the `(BLK_N,BLK_K)` shape of `sB`.
<p align="center">
<img src="../../images/cute/tC_partitioning.png" alt="tC_partitioning.png" height="300"/>
<img src="../../../images/cute/tC_partitioning.png" alt="tC_partitioning.png" height="300"/>
</p>
This diagram shows a `tC` layout, highlights two threads in green and blue, shows the projections of the `tC` layout, and finally highlights the subtensors within `sA`, `sB`, and `gC` that `tCsA`, `tCsB`, and `tCgC` represent.
@@ -391,7 +391,7 @@ As a first example, lets look at the `TiledCopy` that `gemm_nt` generates.
```
The easiest way to see what this `TiledCopy` does is to look at the partition pattern in LaTeX.
<p align="center">
<img src="../../images/cute/TiledCopyA.png" alt="TiledCopyA.png" height="300"/>
<img src="../../../images/cute/TiledCopyA.png" alt="TiledCopyA.png" height="300"/>
</p>
On the left is the source-tensor partitioning and on the right is the destination-tensor partitioning. The partition patterns are the same for this case, but there exist PTX instructions which require different patterns in the source and destination. The diagram shows that each thread reads 4x1 `TA` elements and there are 32x8 threads. The `UniversalCopy<uint128_t>` forces the instruction to use a 128-bit copy instruction. If the partition (of `sA` or `gA` in this case) does not result in 4 `TA` elements that cannot be vectorized to a 128-bit load/store, then CuTe will statically fail with an error message to that effect.
@@ -422,7 +422,7 @@ As a first example, lets look at the `TiledMMA` that `gemm_nt` generates.
```
The easiest way to see what this `TiledMMA` does is to look at the partition pattern in LaTeX.
<p align="center">
<img src="../../images/cute/TiledMmaC.png" alt="TiledMmaC.png" height="300"/>
<img src="../../../images/cute/TiledMmaC.png" alt="TiledMmaC.png" height="300"/>
</p>
On the left is the A-tensor partitioning, on the top is the B-tensor partitioning, and in the middle is the C-tensor partitioning.Because the `UniversalFMA` is a 1x1x1 MMA instruction, a 16x16x1 tiling of them results in a 16x16x1 `TiledMMA`. Other MMA instructions will have different threads involved and have different instruction sizes. In this case, all threads will read a single element from `A`, `B`, and `C` each.