Question 1How are you going to provide language and/or library (or other?) support in Fortran, C/C++, or another language for massively parallel programming on loosely and tightly coupled cluster machines without requiring MPI, MP, or similar low level memory and thread synchronization? Any standards committees looking at this? Any ad-hoc committees looking at this?

Question 2How are you going to provide good (not perfect!) performance optimization across the full gamut of HPC machines from cheap clustered pizza boxes through powerful high end systems? Is there going to be any dynamic optimization (different optimization paths generated at compile time and chosen depending on the scope of the problem at run time)?

Question 3How are you going to support heterogeneous cores/nodes from a single compiled input stream?

Question 4What productivity tools or languages besides the Fortran and C/C++ compilers are you going to provide to enable non-cluster experts or non-cluster-ready codes to utilize a cluster with minimal expertise and minimal intrusive code (this is in addition to compiler directives that can be added to the code)? Will these tools provide information to the compiler to help with its task? How are profilers going to operate to help the non-expert user figure out where their codes are utilizing resources?

Question 5How are you going to support third-party, pre-compiled libraries (e.g. VNI, NAG) to implement on multi-core, many-core, and hybrid systems?