ckotseli

TornadoVM has two distinct APIs: 1) Loop-parallel API, and 2) Kernel API. We can use one or the other or both together. The loop parallel API requires only one annotation to be placed to the induction variable of a normal Java loop.

The kernel API is the more heavy-handed API for more power users which, as you said, follows similar style to OpenCL and exposes more hardware-specific programming elements to the user.

There are some comparisons in some of our group's papers (e.g. [1] Figure 9 where we compare against optimized OpenCL kernels). In general, from our experience, TornadoVM's relative performance to optimized CUDA or OpenCL kernels depends on the kind of the kernel. Our data suggests that it can perform between 40% and 90% of the raw execution time of native kernels. With TornadoVM v1.0 and the integration with native memory via Project Panama, such performance comparisons would be more straightforward since the memory subsystem of TornadoVM can be further optimized. Of course with this performance, someone would also benefit from ease in programmability since the starting point is existing or new Java code that can be written as single-threaded.

For more power users TornadoVM offers also the Kernel API which is very comparable to OpenCL that allow users to extract more performance by using optimizations such as grid scheduling, local memory, etc.: https://tornadovm.readthedocs.io/en/latest/programming.html#...

[1] https://research.manchester.ac.uk/files/190177400/MPAPADIMIT...