docs(gpu): update content

Author: bene2k1

pages/gpu/reference-content/migration-h100.mdx

@@ -9,26 +9,14 @@ dates:
 
 Scaleway is optimizing its H100 GPU Instance portfolio to improve long-term availability and provide better performance for all users.
 
-## Current situation
-
-Below is an overview of the current status of each instance type:
-
-| Instance type      | Availability status     | Notes                                                                                                                                  |
-| ------------------ | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
-| H100-1-80G         | Low stock               | No additional GPUs can be added at this time.                                                                                          |
-| H100-2-80G         | Frequently out of stock | Supply remains unstable, and shortages are expected to continue.                                                                       |
-| H100-SXM-2-80G     | Good availability       | This Instance type can scale further and is ideal for multi-GPU workloads, offering NVLink connectivity and superior memory bandwidth. |
-
-In summary, while the single- and dual-GPU PCIe instances (H100-1-80G and H100-2-80G) are experiencing supply constraints, the H100-SXM-2-80G remains available in good quantity and is the recommended option for users requiring scalable performance and high-bandwidth interconnects.
-
 We recommend users to migrate their workload from PCIe-based GPU Instances to SXM GPU Instances for improvements in performance and fure-proof access to GPUs. As H100 PCIe-variants becomes increasingly scarce, migrating ensures uninterrupted access to H100-class compute.
 
 ## Benefits of the migration
 
 There are two primary scenarios: migrating **Kubernetes (Kapsule)** workloads or **standalone** workloads.
 
 <Message type="important">
-  Always ensure that your **data is backed up** before performing any operations that could affect it.
+  Always ensure that your **data is backed up** before performing any operations that could affect it. Keep in mind that **Scratch Storage** is ephemere and does not survive once the Instance is stopped: doing a full stop/start cycle will **erase the scratch data**. However, doing a simple reboot or using the stop in place function will keep the data.
 </Message>
 
 ### Migrating Kubernetes workloads (Kubernetes Kapsule)
@@ -96,12 +84,15 @@ For further information, refer to the [Instance CLI documentation](https://githu
 H100 PCIe-based GPU Instances are not End-of-Life (EOL), but due to limited availability, we recommend migrating to `H100-SXM-2-80G` to avoid future disruptions.
 
 #### Is H100-SXM-2-80G compatible with my current setup?
-Yes — it runs the same CUDA toolchain and supports standard frameworks (PyTorch, TensorFlow, etc.). However, verify that your workload does not require large system RAM or NVMe scratch space.
+Yes — it runs the same CUDA toolchain and supports standard frameworks (PyTorch, TensorFlow, etc.). No changes in your code base are required when upgrading to a SXM-based GPU Instance.
 
 #### Why is H100-SXM better for multi-GPU?
-Because of *NVLink*, which enables near-shared-memory speeds between GPUs. In contrast, PCIe-based instances like H100-2-80G have slower interconnects that can bottleneck training. Learn more: [Understanding NVIDIA NVLink](https://www.scaleway.com/en/docs/gpu/reference-content/understanding-nvidia-nvlink/)
+The NVIDIA H100-SXM outperforms the H100-PCIe in multi-GPU configurations due to its superior interconnect and higher power capacity.
+It leverages fourth-generation NVLink and NVSwitch, providing up to 900 GB/s of bidirectional bandwidth for rapid GPU-to-GPU communication, compared to the H100-PCIe's 128 GB/s via PCIe Gen 5, which creates bottlenecks in demanding workloads like large-scale AI training and HPC. 
+Additionally, the H100-SXM’s 700W TDP enables higher clock speeds and sustained performance, while the H100-PCIe’s 300-350W TDP limits its throughput.
+For high-communication, multi-GPU tasks, the H100-SXM is the optimal choice, while the H100-PCIe suits less intensive applications with greater flexibility.
 
 #### What if my workload needs more CPU or RAM?
-Let us know via [support ticket we’re evaluating options for compute-optimized configurations to complement our GPU offerings.
+Let us know via [support ticket](https://console.scaleway.com/support/tickets/create) what your specific requoirements are. Currently we are evaluating options for compute-optimized configurations to complement our GPU offerings.
 
 -