[gpderetta]

And yet the most common language used for GPU programming is a C++ dialect.

[pjmlp]

And it took 10 years for NVidia to make it match the ISO C++ memory model introduced in C++11, as per NVidia talk at CppCon 2019.

[gpderetta]

And the C++11 memory model was added so that the language would map to the execution model of the underlying hardware, not viceversa, refuting the parent.

[pjmlp]

Not really, C++11 initally got its memory model from .NET and Java memory models, two mostly hardware agnostic stacks, and then expanded on top of them.