Auto merge of #133984 - DaniPopes:scmp-ucmp, r=scottmcm

Lower BinOp::Cmp to llvm.{s,u}cmp.* intrinsics

Lowers `mir::BinOp::Cmp` (`three_way_compare` intrinsic) to the corresponding LLVM `llvm.{s,u}cmp.i8.*` intrinsics.

These are the intrinsics mentioned in https://github.com/rust-lang/rust/pull/118310, which are now available in LLVM 19.

I couldn't find any follow-up PRs/discussions about this, please let me know if I missed something.

r? `@scottmcm`

compiler/rustc_codegen_ssa/src/mir/rvalue.rs

@@ -988,6 +988,9 @@ impl<'a, 'tcx, Bx: BuilderMethods<'a, 'tcx>> FunctionCx<'a, 'tcx, Bx> {
             mir::BinOp::Cmp => {
                 use std::cmp::Ordering;
                 assert!(!is_float);
+                if let Some(value) = bx.three_way_compare(lhs_ty, lhs, rhs) {
+                    return value;
+                }
                 let pred = |op| base::bin_op_to_icmp_predicate(op, is_signed);
                 if bx.cx().tcx().sess.opts.optimize == OptLevel::No {
                     // FIXME: This actually generates tighter assembly, and is a classic trick

compiler/rustc_codegen_ssa/src/traits/builder.rs

@@ -397,6 +397,18 @@ pub trait BuilderMethods<'a, 'tcx>:
     fn icmp(&mut self, op: IntPredicate, lhs: Self::Value, rhs: Self::Value) -> Self::Value;
     fn fcmp(&mut self, op: RealPredicate, lhs: Self::Value, rhs: Self::Value) -> Self::Value;
 
+    /// Returns `-1` if `lhs < rhs`, `0` if `lhs == rhs`, and `1` if `lhs > rhs`.
+    // FIXME: Move the default implementation from `codegen_scalar_binop` into this method and
+    // remove the `Option` return once LLVM 20 is the minimum version.
+    fn three_way_compare(
+        &mut self,
+        _ty: Ty<'tcx>,
+        _lhs: Self::Value,
+        _rhs: Self::Value,
+    ) -> Option<Self::Value> {
+        None
+    }
+
     fn memcpy(
         &mut self,
         dst: Self::Value,