[clang] [PowerPC][CLANG] DMF VSX Vector float GER 2x (rank-2 update) (PR #147383)

[Maryam Moghadas via cfe-commits]

================
@@ -1116,6 +1116,14 @@ UNALIASED_CUSTOM_MMA_BUILTIN(mma_xvbf16ger2, "vW512*VV",
                              "mma,paired-vector-memops")
 UNALIASED_CUSTOM_MMA_BUILTIN(mma_pmxvbf16ger2, "vW512*VVi15i15i3",
                              "mma,paired-vector-memops")
+UNALIASED_CUSTOM_MMA_BUILTIN(mma_dmxvbf16gerx2, "vW1024*W256V",
+                             "mma,isa-future-instructions")
----------------
maryammo wrote:

The paired-vector-memops target feature corresponds to PPC paired vector memory operations added in ISA 3.1. It does not seem it is related to the overlapping of the MMA registers with VSX registers.
https://reviews.llvm.org/D83722

https://github.com/llvm/llvm-project/pull/147383