[llvm] [NVPTX] Fix crash caused by ComputePTXValueVTs (PR #104524)

[Artem Belevich via llvm-commits]

================
@@ -0,0 +1,61 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 | FileCheck %s
+
+target triple = "nvptx-nvidia-cuda"
+
+define <6 x half> @half6() {
----------------
Artem-B wrote:

What I, roughly, had in mind is something like this:

```
interesting_cases = set()
for data_size in [1, 8, 16, 32, 64]:
   for pow2 in range(1,5):
      vector_size = element_count * data_size 
      if vector_size > MAX_BYTES:
          break;
      interesting_cases.add([data_size, element_count-1])
      interesting_cases.add([data_size, element_count])
      interesting_cases.add([data_size, element_count+1])
```

https://github.com/llvm/llvm-project/pull/104524