perf(hex8): packetize ordered gradient and geometric contractions

src/fesa/elements/hex8_pair_simd_avx2.cpp

@@ -111,6 +111,10 @@ VectorPair Load(const PairPacket& value) {
           _mm256_setr_pd(value.values[0].low, value.values[1].low,
                          value.values[2].low, value.values[3].low)};
 }
+/// @brief Replicates one raw first product without changing either component.
+VectorPair Splat(PacketPair value) {
+  return {_mm256_set1_pd(value.high), _mm256_set1_pd(value.low)};
+}
 /// @brief Stores raw high/low fields without rounding or lane reduction.
 PairPacket Store(VectorPair value) {
   double high[4];
@@ -251,6 +255,20 @@ void EvaluateMaterialPacketAvx2(const MaterialPacketInput& input,
   *output = Store(Add(Load(input.accumulated),
                       Multiply(material, Load(weight)), true));
 }
+void EvaluateGeometryPacketAvx2(const GeometryPacketInput& input,
+                                GeometryPacketOutput* output) {
+  VectorPair dot{_mm256_setzero_pd(), _mm256_setzero_pd()};
+  for (std::size_t i = 0; i < 3; ++i)
+    dot = Add(dot, Multiply(Splat(input.gradient_a[i]),
+                            Load(input.gradient_b[i])), true);
+  VectorPair geo{_mm256_setzero_pd(), _mm256_setzero_pd()};
+  for (std::size_t j = 0; j < 3; ++j)
+    for (std::size_t l = 0; l < 3; ++l)
+      geo = Add(geo, Multiply(Splat(input.gradient_stress[j][l]),
+                              Load(input.gradient_b[l])), true);
+  output->gradient_dot = Store(dot);
+  output->weighted_geometric = Store(Multiply(geo, Splat(input.weight)));
+}
 }  // namespace fesa::hex8_internal
 #else
 namespace fesa::hex8_internal {
@@ -258,5 +276,9 @@ void EvaluateMaterialPacketAvx2(const MaterialPacketInput& input,
                                 PairPacket* output) {
   EvaluateMaterialPacketScalar(input, output);
 }
+void EvaluateGeometryPacketAvx2(const GeometryPacketInput& input,
+                                GeometryPacketOutput* output) {
+  EvaluateGeometryPacketScalar(input, output);
+}
 }  // namespace fesa::hex8_internal
 #endif