# \#tpus

**URL:** https://discuss.ai.google.dev/tag/tpus/33.md

[Latest](https://discuss.ai.google.dev/latest.md) · [Categories](https://discuss.ai.google.dev/categories.md) · [Tags](https://discuss.ai.google.dev/tags.md)

---

## [Is is possible to parallelize sparse-dense matrix mul on gpus and tpus?](https://discuss.ai.google.dev/t/is-is-possible-to-parallelize-sparse-dense-matrix-mul-on-gpus-and-tpus/34881)

<div class="topic-metadata">

**Author:** [@dontknow](https://discuss.ai.google.dev/u/dontknow)\
**Replies:** 2\
**Last updated:** [January 8, 2025, 11:10am UTC](https://discuss.ai.google.dev/t/is-is-possible-to-parallelize-sparse-dense-matrix-mul-on-gpus-and-tpus/34881 "2025-01-08T11:10:54Z")

</div>

Hi. a) does the following run in parallel on all available gpus?? strategy = tf.distribute.MirroredStrategy() with strategy.scope(): strategy.run(tf.sparse.sparse\_dense\_matmul, args=(sparseMat, denseVec)), axis=Non…