…ions (pytorch#1131)

Fixes pytorch#1102 

This PR implements the second approach mentioned in pytorch#1102 For example, indexing and predicates are changed from:

```
      = T0[(((((nvfuser_index_t)blockIdx.x) * ((nvfuser_index_t)blockDim.y)) + ((nvfuser_index_t)threadIdx.y)) * T0.stride[0])]
```

to:

```
 = T0[(((((nvfuser_index_t)blockIdx.x) * 4) + ((nvfuser_index_t)threadIdx.y)) * T0.stride[0])]
```

The use of `blockDim.y` is replaced by the extent of the second axis of `T0`, which is `4` in this case. This change only matters when a parallel type is not exact (in this case `TIDy`). 

The indexing change only needed to change `getExtent` in index_compute.cpp. However, we also need to predicate `threadIdx` and `blockIdx` to be smaller than IterDomain extents. That's implemented as `ParallelizedDomainPredicate` in predicate_compute.h.

…in test-infra (pytorch#1131)

…h#1131)

Support for MIOpen immediate mode is not enabled in release/1.11 release/1.12 branches which is required
for the test_Conv2d_naive_groups test to pass - https://ontrack-internal.amd.com/browse/SWDEV-355273