[PATCH] D17630: [x86, SSE] fold 'isPositive' vector integer operations (PR26701)

[Ahmed Bougacha via llvm-commits]

ab accepted this revision.
ab added a comment.
This revision is now accepted and ready to land.

LGTM


================
Comment at: lib/Target/X86/X86ISelLowering.cpp:26802
@@ +26801,3 @@
+  // TODO: AVX2 can handle 256-bit integer vectors.
+  if (!VT.is128BitVector() || !Subtarget.hasSSE2())
+    return SDValue();
----------------
Could this miss something crazy like v128i1, or v1i128?


http://reviews.llvm.org/D17630