Earlier quoted context omitted.
CUDA Ada would be so, so nice. Especially with non-aliasing guarantees from SPARK...
NVidia is already using Ada. https://www.adacore.com/company/partners/nvidia
Yes, I want the integration to be tighter. In fact I'd really like to be able to target Ada kernels to cuda, ispc, mlir, spirv... And also have access to deep APIs for each platform. Now that gnatllvm is getting stable(r), there's a lot of opportunities opening in the Ada/SPARK world. KLEE would also be fun there.
I really wasn't a fan of the 'parallel' loop construct foreseen in Ada2020: in addition to having a 'bad' syntax ('how' instead of 'what') wasn't really well integrated in the 'control your tasking precisely' mentality that Ada provided. Having something a bit more platform-specific but still somehow portable if designed well would fit the Ada spirit far closer.