[llvm] [X86] Try Folding icmp of v8i32 -> fcmp of v8f32 on AVX (PR #82290)

[via llvm-commits]

================
@@ -41125,6 +41255,154 @@ static SDValue combineShuffle(SDNode *N, SelectionDAG &DAG,
   return SDValue();
 }
 
+// Simplify a decomposed (sext (setcc)). Assumes prior check that
+// bitwidth(sext)==bitwidth(setcc operands).
+static SDValue simplifySExtOfDecomposedSetCCImpl(
----------------
goldsteinn wrote:

Can do, the only issue is that basically its functionality is dependent on this pr. Otherwise we never really get the necessary floating point flags to assist with the simplifcation.

https://github.com/llvm/llvm-project/pull/82290