Don't segfault on unsupported mma->mma

triton-lang#4492 started causing an
issue where chained MMAs on hopper would segfault with 8 warps. It seems
that previously this was checked, but the check got removed in this PR
and it's still unsupported.

Adding back this check means these MMAs will have to go back to shared
memory, but it's better than segfaulting until it's actually supported.

Resolves openxla/xla#17356

lib/Analysis/Utility.cpp

@@ -565,6 +565,7 @@ bool matchMmaV3AndDotOperandLayout(RankedTensorType srcTy,
  srcTy.getShape(), srcTy.getElementType(), dotOperandLayout.getParent());
  auto ans = mmaLayout.getVersionMajor() == 3 &&
  dotOperandLayout.getOpIdx() == 0 &&
+ mmaLayout.getWarpsPerCTA()[1] == 1 &&
  !cvtNeedsSharedMemory(parentTy, srcTy) &&
  (elementTypeSize == 16 || elementTypeSize == 8);
  return ans;