1 Solution
GCN can use up to 256 vgprs/thread with 4 waves per CU for full occupancy.
The maximum vgpr array size then depends on what other vgprs the compiler needs to use.
In one case, I saw the compiler wasted 74 vgprs as temporaries by loading blocks of data before writing to the array.
Even here, int array[160] was not a problem.
But beware the devil. 
When the array indices are not known at compile time, both gcn and VLIW will access registers serially one thread at a time.
gcn scans the 'lanes' for threads looking for an index. It will then read/write all threads with the same index in parallel using v_movereld/s, then repeat until all threads are processed. Worst case is all 64 indexes in a wave are different = 64 read/write loops (yes branching too). Best case, all indexes are the same and there is only one read/write. (actually that's pretty cool 
.) Although VLIW uses A0 register, it also does something similar to serially access different indices.
LDS might be faster but, there's not enough.
