func (u *ΔUpdater) Update() {
qin := u.in.Array()
qout := u.out.Array()
q0 := u.q0.Array()
qinMul := u.in.Multiplier()
qoutMul := u.out.Multiplier()
q0Mul := u.q0.Multiplier()
COMP := u.in.NComp()
pre := make([]float64, COMP)
for ii := 0; ii < COMP; ii++ {
qoutMul[ii] = qinMul[ii]
pre[ii] = -q0Mul[ii] / qinMul[ii] //0?
}
switch COMP {
case 1:
gpu.Madd(qout.Component(0), qin.Component(0), q0.Component(0), pre[0])
case 3:
gpu.VecMadd(qout, qin, q0, pre)
default:
panic(InputErrF("Δ is not implemented for NComp: ", COMP))
}
}
func (u *SumUpdater) addTerms() {
// TODO: optimize for 0,1,2 or more parents
sum := u.sum
parents := u.parents
if sum.IsSpaceDependent() {
for i := range parents {
parent := parents[i]
weight := u.weight[i]
parMul := make([]float64, sum.NComp())
for c := 0; c < sum.NComp(); c++ {
parMul[c] = weight * parent.Multiplier()[c] / sum.Multiplier()[c]
}
switch sum.NComp() {
case 1:
gpu.Madd(sum.array.Component(0), sum.array.Component(0), parent.array.Component(0), parMul[0])
case 3:
gpu.VecMadd(sum.Array(), sum.Array(), parent.Array(), parMul)
default:
panic(InputErr("sum is not implemented for NComp: " + fmt.Sprint(sum.NComp())))
}
}
} else {
for p, parent := range parents {
for c := range sum.multiplier {
sum.multiplier[c] += parent.multiplier[c] * u.weight[p]
}
}
}
}