Use rocprofv2 instead of rocprof.

Abstract the boilerplate for collecting results from a process.
Account for .MLIR_N_REPEATS in rocprofv2 results, which don't include it.
Account for nrepeats in a smarter way -- count the rows, while verifying.
Don't do attention perfRunner.py on gfx110x.
Don't run the CK benchmarking for gfx110x, because ck-benchmark-driver won't compile.
getFusionTestInfo and runFusionKernel turn out to be mostly the same.
Invent --rocprof-version to switch between rocprof and rocprofv2.
Change default to rocprofv2.