feat(amd64): encode legacy SSE binaries, imm8 shuffles and MOVQ xmm moves

.idea/.gitignore

@@ -0,0 +1,10 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Ignored default folder with query files
+/queries/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/gasm-devkit.iml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="WEB_MODULE" version="4">
+  <component name="GoModuleSettings" enabled="true" />
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/gasm-devkit.iml" filepath="$PROJECT_DIR$/.idea/gasm-devkit.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

asm/encode_test.go

@@ -369,3 +369,29 @@ func TestSSEShuffleGroundTruth(t *testing.T) {
 		}
 	}
 }
+
+// TestMOVQXMMGroundTruth pins the SSE2 packed-quadword move encodings:
+// loads and register moves on F3 0F 7E, stores on 66 0F D6 — the forms
+// the GPR-move fallback silently corrupted.
+func TestMOVQXMMGroundTruth(t *testing.T) {
+	cases := []struct {
+		name string
+		mnem string
+		ops  []Operand
+		want string
+	}{
+		{"MOVQ (DI),X0", "MOVQ", []Operand{Ptr(DI, 0, 8), vreg(t, "X0")}, "f30f7e07"},
+		{"MOVQ X1,X2", "MOVQ", []Operand{vreg(t, "X1"), vreg(t, "X2")}, "f30f7ed1"},
+		{"MOVQ X0,(DI)", "MOVQ", []Operand{vreg(t, "X0"), Ptr(DI, 0, 8)}, "660fd607"},
+	}
+	for _, c := range cases {
+		code, err := Encode(c.mnem, c.ops...)
+		if err != nil {
+			t.Errorf("%s: %v", c.name, err)
+			continue
+		}
+		if got := fmt.Sprintf("%x", code); got != c.want {
+			t.Errorf("%s = %s, want %s", c.name, got, c.want)
+		}
+	}
+}

asm/instrs.go

@@ -48,6 +48,31 @@ func (e *enc) encodeMov(ops []Operand, size int) error {
 	}
 	src, dst := ops[0], ops[1]
 
+	// MOVQ with an XMM operand is the SSE2 packed-quadword move, NOT a
+	// GPR move: mem→xmm and xmm↔xmm encode as F3 0F 7E (reg = dst),
+	// xmm→mem as 66 0F D6 (rm = xmm).  A GPR-move fallback would
+	// silently emit REX.W 8B with the wrong operand meaning.
+	_, srcVec := vecReg(src)
+	dstReg, dstVec := vecReg(dst)
+	if srcVec || dstVec {
+		if dstVec {
+			i := &instr{prefix: 0xF3, opcode: []byte{0x0F, 0x7E}, modrm: -1, sib: -1}
+			if err := setRM(i, dstReg, src, 8); err != nil {
+				return err
+			}
+			return e.emit(i)
+		}
+		srcXMM, srcIsXMM := src.(Reg)
+		if !srcIsXMM || !srcXMM.isVec() {
+			return fmt.Errorf("MOVQ: store needs an XMM source")
+		}
+		i := &instr{prefix: 0x66, opcode: []byte{0x0F, 0xD6}, modrm: -1, sib: -1}
+		if err := setRM(i, srcXMM, dst, 8); err != nil {
+			return err
+		}
+		return e.emit(i)
+	}
+
 	dstReg, dstIsReg := dst.(Reg)
 	switch src := src.(type) {
 	case Reg: