GPU: Prevent CUDA 13 from breaking the GPUbenchmark

[mconcas]

Some features are moved out from the cudaDeviceProp struct starting from CUDA 13.

[github-actions]

REQUEST FOR PRODUCTION RELEASES:
To request your PR to be included in production software, please add the corresponding labels called "async-" to your PR. Add the labels directly (if you have the permissions) or add a comment of the form (note that labels are separated by a ",")

+async-label <label1>, <label2>, !<label3> ...

This will add <label1> and <label2> and removes <label3>.

The following labels are available
async-2023-pbpb-apass4
async-2023-pp-apass4
async-2024-pp-apass1
async-2022-pp-apass7
async-2024-pp-cpass0
async-2024-PbPb-apass1
async-2024-ppRef-apass1
async-2024-PbPb-apass2
async-2023-PbPb-apass5

[Copilot]

Pull Request Overview

This PR updates the CUDA GPU benchmark code to maintain compatibility with CUDA 13, where certain properties have been removed from the cudaDeviceProp struct and must now be accessed through device attribute queries.

• Introduces conditional compilation to handle CUDA version differences
• Replaces direct property access with cudaDeviceGetAttribute calls for CUDA 13+
• Removes output for properties no longer available in newer CUDA versions

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}