Skip to content

Commit 2561b6c

Browse files
authored
Publish post "Deep Dive on the Hopper TMA Unit for FP8 GEMMs" (#1681)
* Publish post "Deep Dive on the Hopper TMA Unit for FP8 GEMMs" Signed-off-by: Chris Abraham <[email protected]> * fix code block Signed-off-by: Chris Abraham <[email protected]> --------- Signed-off-by: Chris Abraham <[email protected]>
1 parent a7ef155 commit 2561b6c

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

_posts/2025-07-22-hopper-tma-unit.md renamed to _posts/2024-07-22-hopper-tma-unit.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -176,8 +176,8 @@ elect.sync _|%p7, 0xffffffff;
176176
add.s32 %r24, %r65, %r67;
177177
shl.b32 %r25, %r66, 7;
178178
179-
180-
{% raw %}@%p8 cp.async.bulk.tensor.2d.shared::cluster.global.mbarrier::complete_tx::bytes [%r24], [%rd26, {%r25,%r152}], [%r19];{% endraw %}
179+
@%p8
180+
{% raw %}cp.async.bulk.tensor.2d.shared::cluster.global.mbarrier::complete_tx::bytes [%r24], [%rd26, {%r25,%r152}], [%r19];{% endraw %}
181181
```
182182

183183

0 commit comments

Comments
 (0)