[FEA] Document Compilation Procedure for Generated PTX Code in UDF Unit Tests

[lamarrr]

Is your feature request related to a problem? Please describe.
Some UDF unit tests include generated PTX code compiled either by Numba or CUDA+NVCC.
A couple of them don't have their source code, compile flags, or compilation process documented, thus, making it difficult to work with for people new to them.

Some of them are:

• cudf/cpp/tests/streams/binaryop_test.cpp

  Line 96 in 428dc18

  .visible .func (.param .b32 func_retval0) _ZN8__main__7add$241Eix(

• cudf/cpp/tests/jit/parse_ptx_function.cpp

  Line 54 in 428dc18

  .visible .func (.param .b32 func_retval0) _ZN8__main__7add$241Eff(

• cudf/cpp/tests/transform/integration/unary_transform_test.cpp

  Line 79 in 428dc18

  .visible .func (.param .b32 func_retval0) _ZN8__main__7add$241Ef(

• cudf/cpp/tests/streams/transform_test.cpp

  Line 70 in 428dc18

  .visible .func (.param .b32 func_retval0) _ZN8__main__7add$241Ef(

• cudf/cpp/tests/binaryop/binop-generic-ptx-test.cpp

  Line 55 in 428dc18

  .visible .func (.param .b32 func_retval0) _ZN8__main__7add$241Eff(

• cudf/cpp/tests/binaryop/binop-generic-ptx-test.cpp

  Line 55 in 428dc18

  .visible .func (.param .b32 func_retval0) _ZN8__main__7add$241Eff(

• cudf/cpp/tests/rolling/grouped_rolling_test.cpp

  Line 67 in 428dc18

  .visible .func (.param .b32 func_retval0) _ZN8__main__7add$241E5ArrayIiLi1E1A7mutable7alignedE(

• cudf/cpp/tests/rolling/rolling_test.cpp

  Line 1244 in 428dc18

  .visible .func (.param .b32 func_retval0) _ZN8__main__7add$241E5ArrayIiLi1E1A7mutable7alignedE(

• cudf/java/src/test/java/ai/rapids/cudf/ColumnVectorTest.java

  Line 67 in 428dc18

  " .param .b64 _Z1fPii_param_0," +

Describe the solution you'd like
For the full source code, flags, and environment to be documented. Either in a separate doc and having them referenced in the source code or directly embedded as comments in the source code.