fix CI failures

[bashbaug]

Looks like some of our CI configurations are failing after an environment update that occurred sometime between May 21st (when the automated testing for #251 passed) and June 11th (when the automated testing for #253 failed). Since the automated tests on the main branch are failing now too, these don't seem to be sporadic failures, and we need to fix or disable them.

[bashbaug]

CC @Beanavil @mfep @MathiasMagnus

[Beanavil]

The windows failure https://github.com/KhronosGroup/OpenCL-Headers/actions/runs/9472987725/job/26099412897?pr=253 is due to a breaking change in the MSVC versioning (see cppblog):

We have incremented the minor version number of the MSVC toolset from 19.39 (VS 2022 v17.9) to 19.40 (VS 2022 v17.10)

The fix was already added to the Update CI, CD PRs for other repos, for instance KhronosGroup/OpenCL-SDK@3a3b557

[Beanavil]

For the MacOS one, I think this is a problem with the runner image itself (see #9997). Seems to be fixable with the suggestion in this comment, or by directly disabling gcc-13/g++-13 from the CI matrix until the runner images are fixed (this was done in the OpenCL-ICD-Loader/#226). I tested both approaches and both work:

• Use compatible Xcode
• Disable gcc-13/g++-13

[Beanavil]

BTW, by the warnings in this run we should update the actions/cache@v3 to actions/cache@v4. IINM the PRs that update the CI on the other repositories (CLHPP, ICD-Loader, SDK and Layers) already include this change, so this is only an issue for the OpenCL-Headers.

[bashbaug]

Fixed by #256 - thanks!