interfaces/Crafter.Math-VectorF32.cppm

@@ -2136,6 +2136,28 @@ namespace Crafter {
             return sq;
         }
 
+        // Batched dot product over BatchSize (a, b) pairs: Dot(a0, b0, a1, b1,
+        // ...) returns one lane per pair. MatrixRowMajor relies on it, so
+        // without it this fallback (every target that has no intrinsic
+        // backend above) does not compile. Only the first Len lanes of each
+        // input are summed, as in the other backends.
+        template<typename... Rest>
+            requires((std::is_same_v<Rest, VectorF32<Len, Packing>> && ...) &&
+                     (1 + sizeof...(Rest) == 2 * VectorBase<Len, Packing, float>::BatchSize))
+        constexpr static auto Dot(VectorF32<Len, Packing> first, Rest... rest) {
+            constexpr std::uint8_t N = VectorBase<Len, Packing, float>::BatchSize;
+            VectorF32<1, static_cast<std::uint8_t>(Packing * N)> r;
+            std::array<VectorF32<Len, Packing>, 2 * N> args{ first, rest... };
+            for (std::uint8_t i = 0; i < N; ++i)
+                for (std::uint8_t p = 0; p < Packing; ++p) {
+                    float acc = 0.0f;
+                    for (std::uint8_t k = 0; k < Len; ++k)
+                        acc += args[2 * i].v[p * Len + k] * args[2 * i + 1].v[p * Len + k];
+                    r.v[i * Packing + p] = acc;
+                }
+            return r;
+        }
+
         template<typename... Rest>
             requires((std::is_same_v<Rest, VectorF32<Len, Packing>> && ...) &&
                      (1 + sizeof...(Rest) == VectorBase<Len, Packing, float>::BatchSize))