pgorlani

Hi @sergey-semenov, here is https://github.com/intel/llvm-test-suite/pull/1094.

Hi @sergey-semenov, is it possible to merge this PR? Thanks!

Unfortunately, I realized that `FindCUDAToolkit` module was introduced in CMake 3.17, whereas the minimum version required by SYCL is 3.14. The CI seems to fail for this reason, see [logs](https://github.com/intel/llvm/runs/7113788728?check_suite_focus=true).

**Problem**: `FindCUDA` CMake module (deprecated since 3.10) fails to find the CUPTI library on some systems. There are two possible solutions. **S1**: Use `FindCUDAToolkit` module since it seems to have...

Thanks @bader for **S3**, I implemented it in the last commit and it is working. I had a look but it seems that between CMake 3.10 and 3.17 there is...

The ``500 CUDA_ERROR_NOT_FOUND`` (that turns in a ``801 CUDA_ERROR_NOT_SUPPORTED`` for CUDA toolkit 11.3 and above) is caused by the ``suq.depth`` PTX instruction in 3d sampled readings at https://github.com/intel/llvm/blob/90c8f0543a38adeda75ad2eca7e999a36a1f2697/libclc/ptx-nvidiacl/libspirv/images/image.cl#L151 https://github.com/intel/llvm/blob/90c8f0543a38adeda75ad2eca7e999a36a1f2697/libclc/ptx-nvidiacl/libspirv/images/image.cl#L158 NVIDIA...

> Recent version of `test_all` (and `test_accessor_legacy`) aborts on NVIDIA GPU. > > ``` > pi_die: PI CUDA kernels only support images with channel types int32, uint32, float, and half....

Thanks for your reviews, @steffenlarsen @aelovikov-intel! I rebased this PR onto the last refactoring of reductions, it should be fine. The unexpectedly passed test is enabled in https://github.com/intel/llvm-test-suite/pull/1097.