SOFTCON 2025, 17 October 2025
Supercharge Your ML Research with Google's TPU Research Cloud
Architecture, access, and training on TPU pods, backed by a $376K compute grant.
- Organizer
- SOFTCON 2025
- Venue
- Online
- Attendees
- 120
- Type
- Talk
- Level
- Advanced
- Duration
- 30 minutes
- TPU
- Google Cloud
- TRC
- JAX
- ML Research
Abstract
How to access and use Google's TPU Research Cloud to run serious ML research for free. Covers TPU architecture (TensorCores, MXUs, systolic arrays, ICI/OCS torus topology) versus GPUs and competitors, training with PyTorch/XLA on MNIST, the TRC application process, and a live demo spinning up a TPU VM, with the cost math behind a ~$376,000 grant.
Outline
- Tensors, operations, and matrix multiplication
- TPU architecture (TensorCores, MXUs, systolic arrays) vs GPU and competitors
- Reduced precision: bfloat16 vs float32
- Model training with PyTorch/XLA on MNIST
- TPU Research Cloud: how to apply and gain access
- Live demo: spinning up a TPU VM on GCP
Key takeaways
- TRC grants free access to 1,000+ Cloud TPUs for accepted researchers
- A v4-64 for 5 months is roughly $376K of compute
- bfloat16 for matmul plus float32 accumulation is the precision sweet spot
- You can provision a TPU VM in minutes with one gcloud command