perf(hex8): packetize ordered gradient and geometric contractions

src/fesa/elements/hex8_pair_simd.h

@@ -23,6 +23,30 @@ struct MaterialPacketInput {
   PairPacket accumulated;
   PacketPair weight;
 };
+/// @brief One owned trial point/a and four independent b gradients, raw only.
+struct GeometryPacketInput {
+  PacketPair gradient_a[3];
+  PacketPair gradient_stress[3][3];
+  PairPacket gradient_b[3];
+  PacketPair weight;
+};
+/// @brief Independent raw contractions; accumulator entries remain caller-owned.
+struct GeometryPacketOutput {
+  PairPacket gradient_dot;
+  PairPacket weighted_geometric;
+};
+using GeometryPacketEvaluator = void (*)(const GeometryPacketInput&,
+                                        GeometryPacketOutput*);
+/// @brief Baseline checked zero-start Dot3/ordered j,l Geo9 and weight products.
+/// @note Lane order is 0..3. Invalid pairs remain invalid for original gates.
+void EvaluateGeometryPacketScalar(const GeometryPacketInput& input,
+                                  GeometryPacketOutput* output);
+/// @brief Evaluates independent b lanes without horizontal reduction.
+/// @pre The material selector has admitted CPU/OS/current masked FP state.
+/// @note Keeps original zero-start, product association and j,l Add order.
+void EvaluateGeometryPacketAvx2(const GeometryPacketInput& input,
+                                GeometryPacketOutput* output);
+
 using MaterialPacketEvaluator = void (*)(const MaterialPacketInput&, PairPacket*);
 
 /// @brief Evaluates each lane's original checked material graph in order 0..3.