[PATCH] D33938: [x86] use vperm2f128 rather than vinsertf128 when there's a chance to fold a 32-byte load

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added inline comments.


================
Comment at: test/CodeGen/X86/avx-vperm2x128.ll:55
+; ALL:       ## BB#0: ## %entry
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = mem[0,1,0,1]
+; ALL-NEXT:    retq
----------------
I wonder what's preventing this from using VBROADCASTF128 ?


https://reviews.llvm.org/D33938