Merge pull request #2278 from akirilov-arm/load_splat

Introduce the Cranelift IR instruction `LoadSplat`

cranelift/codegen/meta/src/isa/x86/legalize.rs

@@ -396,6 +396,7 @@ fn define_simd(
     let insertlane = insts.by_name("insertlane");
     let ishl = insts.by_name("ishl");
     let ishl_imm = insts.by_name("ishl_imm");
+    let load_splat = insts.by_name("load_splat");
     let raw_bitcast = insts.by_name("raw_bitcast");
     let scalar_to_vector = insts.by_name("scalar_to_vector");
     let splat = insts.by_name("splat");
@@ -820,6 +821,7 @@ fn define_simd(
     narrow.custom_legalize(fcvt_to_sint_sat, "expand_fcvt_to_sint_sat_vector");
     narrow.custom_legalize(fmin, "expand_minmax_vector");
     narrow.custom_legalize(fmax, "expand_minmax_vector");
+    narrow.custom_legalize(load_splat, "expand_load_splat");
 
     narrow_avx.custom_legalize(imul, "convert_i64x2_imul");
     narrow_avx.custom_legalize(fcvt_from_uint, "expand_fcvt_from_uint_vector");

cranelift/codegen/meta/src/shared/instructions.rs

@@ -4459,5 +4459,24 @@ pub(crate) fn define(
         .other_side_effects(true),
     );
 
+    let Offset = &Operand::new("Offset", &imm.offset32).with_doc("Byte offset from base address");
+    let a = &Operand::new("a", TxN);
+
+    ig.push(
+        Inst::new(
+            "load_splat",
+            r#"
+        Load an element from memory at ``p + Offset`` and return a vector
+        whose lanes are all set to that element.
+
+        This is equivalent to ``load`` followed by ``splat``.
+        "#,
+            &formats.load,
+        )
+        .operands_in(vec![MemFlags, p, Offset])
+        .operands_out(vec![a])
+        .can_load(true),
+    );
+
     ig.build()
 }