From ed188f207ba45014265e5a1fa4f868441fed153b Mon Sep 17 00:00:00 2001
From: Jorijn van der Graaf <jorijnvdgraaf@catcrafts.net>
Date: Tue, 6 Oct 2026 16:52:24 +0200
Subject: [PATCH] fix(vector): batched Dot in the scalar VectorF32 fallback

MatrixRowMajor calls VectorF32<Len, 1>::Dot(a0, b0, a1, b1, ...) for
its matrix-vector products and for LookAt. The x86, wasm and RISC-V
backends each define it; the scalar fallback, which every other target
gets, did not. Anything that imports Crafter.Math on such a target
failed to compile with "no member named 'Dot' in VectorF32", aarch64
included: cross-building Crafter.Graphics for a phone stopped there.

The fallback gains the same batched Dot, written like the RISC-V one:
one lane per (a, b) pair, summing only the first Len lanes of each
input.

No test exercises it: the suite builds the x86 and RISC-V tiers only.
Checked by cross-building Crafter.Graphics for aarch64-alpine-linux-musl
and running its UI on the device.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---
 interfaces/Crafter.Math-VectorF32.cppm | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/interfaces/Crafter.Math-VectorF32.cppm b/interfaces/Crafter.Math-VectorF32.cppm
index ecb91a1..6ffccc6 100755
--- a/interfaces/Crafter.Math-VectorF32.cppm
+++ b/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))
-- 
2.47.3