[SVE256] Handle SSE insertions for PMADDWD

See #3799

FEXCore/Source/Interface/Core/OpcodeDispatcher/Vector.cpp

@@ -3658,7 +3658,7 @@ void OpDispatchBuilder::PMADDWD(OpcodeArgs) {
   Ref Src2 = LoadSourceFPR(Op, Op->Src[0], Op->Flags);
 
   Ref Result = PMADDWDOpImpl(Size, Src1, Src2);
-  StoreResultFPR(Op, Result);
+  StoreResult_WithAVXInsert(VectorOpType::SSE, RegClass::FPR, Op, Result);
 }
 
 void OpDispatchBuilder::VPMADDWDOp(OpcodeArgs) {

unittests/ASM/SSELanePreservation/pmaddwd.asm

@@ -0,0 +1,28 @@
+%ifdef CONFIG
+{
+  "HostFeatures": ["AVX"],
+  "RegData": {
+    "XMM0": ["0xfaafa59a0a05f0c2", "0xee4d0958071f3be6", "0xccdbcfc31f3ff0f3", "0x108390defebac4be"],
+    "XMM1": ["0x11f46a902dd8255d", "0x2407b8d517a65424", "0", "0"],
+    "XMM2": ["0xc4be43cc1ad6970b", "0x4549bd7eb46a1278", "0xf793ef673dac6e4c", "0xbb7b5b3d85d34271"],
+    "XMM3": ["0x000043cc1ad6970b", "0x4549bd7eb46a1278", "0xf793ef673dac6e4c", "0xbb7b5b3d85d34271"]
+  }
+}
+%endif
+
+vmovaps ymm0, [rel .data]
+vmovaps ymm1, [rel .data + (1 * 32)]
+vmovaps ymm2, [rel .data + (2 * 32)]
+vmovaps ymm3, [rel .data + (3 * 32)]
+
+pmaddwd xmm0, xmm1
+vpmaddwd xmm1, xmm2, xmm3
+
+hlt
+
+align 32
+.data:
+dq 0xfdecd28fab3fa4a5, 0x7d7ccd8836d09fc2, 0xccdbcfc31f3ff0f3, 0x108390defebac4be
+dq 0x43cc1ad6970b4549, 0xbd7eb46a1278f793, 0xef673dac6e4cbb7b, 0x5b3d85d342718be9
+dq 0xc4be43cc1ad6970b, 0x4549bd7eb46a1278, 0xf793ef673dac6e4c, 0xbb7b5b3d85d34271
+dq 0x000043cc1ad6970b, 0x4549bd7eb46a1278, 0xf793ef673dac6e4c, 0xbb7b5b3d85d34271