perf(hex8): packetize ordered gradient and geometric contractions

This commit is contained in:
KOKO\Mimi
2026-10-14 22:37:39 +09:00
parent 01590bbb0d
commit 96772651d8
5 changed files with 323 additions and 3 deletions
@@ -42,6 +42,27 @@ void ScalarPacketTwoProduct(const double left[4], const double right[4],
output->values[lane] = {value.high, value.low};
}
}
FESA_HEX8_BASELINE_NOINLINE
void EvaluateGeometryPacketScalar(const GeometryPacketInput& input,
GeometryPacketOutput* output) {
const auto value = [](PacketPair pair) {
return math_internal::HighLow{pair.high, pair.low};
};
for (std::size_t lane = 0; lane < 4; ++lane) {
math_internal::HighLow dot;
for (std::size_t i = 0; i < 3; ++i)
dot = AddPair(dot, MultiplyPair(value(input.gradient_a[i]),
value(input.gradient_b[i].values[lane])));
math_internal::HighLow geo;
for (std::size_t j = 0; j < 3; ++j)
for (std::size_t l = 0; l < 3; ++l)
geo = AddPair(geo, MultiplyPair(value(input.gradient_stress[j][l]),
value(input.gradient_b[l].values[lane])));
const auto weighted = MultiplyPair(geo, value(input.weight));
output->gradient_dot.values[lane] = {dot.high, dot.low};
output->weighted_geometric.values[lane] = {weighted.high, weighted.low};
}
}
#undef FESA_HEX8_BASELINE_NOINLINE
bool SupportsMaterialPacketInstructions(std::uint32_t leaf1_ecx,