func SetMFM(dst *data.Slice) {
buf := cuda.Buffer(3, Mesh().Size())
defer cuda.Recycle(buf)
if mfmconv_ == nil {
reinitmfmconv()
}
mfmconv_.Exec(buf, M.Buffer(), geometry.Gpu(), Bsat.gpuLUT1(), regions.Gpu())
cuda.Madd3(dst, buf.Comp(0), buf.Comp(1), buf.Comp(2), 1, 1, 1)
}
func SetMFM(dst *data.Slice) {
buf := cuda.Buffer(3, Mesh().Size())
defer cuda.Recycle(buf)
if mfmconv_ == nil {
reinitmfmconv()
}
msat := Msat.MSlice()
defer msat.Recycle()
mfmconv_.Exec(buf, M.Buffer(), geometry.Gpu(), msat)
cuda.Madd3(dst, buf.Comp(0), buf.Comp(1), buf.Comp(2), 1, 1, 1)
}
// Adaptive Heun method, can be used as solver.Step
func (_ *Heun) Step() {
y := M.Buffer()
dy0 := cuda.Buffer(VECTOR, y.Size())
defer cuda.Recycle(dy0)
if FixDt != 0 {
Dt_si = FixDt
}
dt := float32(Dt_si * GammaLL)
util.Assert(dt > 0)
// stage 1
torqueFn(dy0)
cuda.Madd2(y, y, dy0, 1, dt) // y = y + dt * dy
// stage 2
dy := cuda.Buffer(3, y.Size())
defer cuda.Recycle(dy)
Time += Dt_si
torqueFn(dy)
err := cuda.MaxVecDiff(dy0, dy) * float64(dt)
// adjust next time step
if err < MaxErr || Dt_si <= MinDt || FixDt != 0 { // mindt check to avoid infinite loop
// step OK
cuda.Madd3(y, y, dy, dy0, 1, 0.5*dt, -0.5*dt)
M.normalize()
NSteps++
adaptDt(math.Pow(MaxErr/err, 1./2.))
setLastErr(err)
setMaxTorque(dy)
} else {
// undo bad step
util.Assert(FixDt == 0)
Time -= Dt_si
cuda.Madd2(y, y, dy0, 1, -dt)
NUndone++
adaptDt(math.Pow(MaxErr/err, 1./3.))
}
}
// TODO: into cuda
func madd4(dst, src1, src2, src3, src4 *data.Slice, w1, w2, w3, w4 float32) {
cuda.Madd3(dst, src1, src2, src3, w1, w2, w3)
cuda.Madd2(dst, dst, src4, 1, w4)
}
func (rk *RK45DP) Step() {
m := M.Buffer()
size := m.Size()
if FixDt != 0 {
Dt_si = FixDt
}
// upon resize: remove wrongly sized k1
if rk.k1.Size() != m.Size() {
rk.Free()
}
// first step ever: one-time k1 init and eval
if rk.k1 == nil {
rk.k1 = cuda.NewSlice(3, size)
torqueFn(rk.k1)
}
// FSAL cannot be used with finite temperature
if !Temp.isZero() {
torqueFn(rk.k1)
}
t0 := Time
// backup magnetization
m0 := cuda.Buffer(3, size)
defer cuda.Recycle(m0)
data.Copy(m0, m)
k2, k3, k4, k5, k6 := cuda.Buffer(3, size), cuda.Buffer(3, size), cuda.Buffer(3, size), cuda.Buffer(3, size), cuda.Buffer(3, size)
defer cuda.Recycle(k2)
defer cuda.Recycle(k3)
defer cuda.Recycle(k4)
defer cuda.Recycle(k5)
defer cuda.Recycle(k6)
// k2 will be re-used as k7
h := float32(Dt_si * GammaLL) // internal time step = Dt * gammaLL
// there is no explicit stage 1: k1 from previous step
// stage 2
Time = t0 + (1./5.)*Dt_si
cuda.Madd2(m, m, rk.k1, 1, (1./5.)*h) // m = m*1 + k1*h/5
M.normalize()
torqueFn(k2)
// stage 3
Time = t0 + (3./10.)*Dt_si
cuda.Madd3(m, m0, rk.k1, k2, 1, (3./40.)*h, (9./40.)*h)
M.normalize()
torqueFn(k3)
// stage 4
Time = t0 + (4./5.)*Dt_si
madd4(m, m0, rk.k1, k2, k3, 1, (44./45.)*h, (-56./15.)*h, (32./9.)*h)
M.normalize()
torqueFn(k4)
// stage 5
Time = t0 + (8./9.)*Dt_si
madd5(m, m0, rk.k1, k2, k3, k4, 1, (19372./6561.)*h, (-25360./2187.)*h, (64448./6561.)*h, (-212./729.)*h)
M.normalize()
torqueFn(k5)
// stage 6
Time = t0 + (1.)*Dt_si
madd6(m, m0, rk.k1, k2, k3, k4, k5, 1, (9017./3168.)*h, (-355./33.)*h, (46732./5247.)*h, (49./176.)*h, (-5103./18656.)*h)
M.normalize()
torqueFn(k6)
// stage 7: 5th order solution
Time = t0 + (1.)*Dt_si
// no k2
madd6(m, m0, rk.k1, k3, k4, k5, k6, 1, (35./384.)*h, (500./1113.)*h, (125./192.)*h, (-2187./6784.)*h, (11./84.)*h) // 5th
M.normalize()
k7 := k2 // re-use k2
torqueFn(k7) // next torque if OK
// error estimate
Err := cuda.Buffer(3, size) //k3 // re-use k3 as error estimate
defer cuda.Recycle(Err)
madd6(Err, rk.k1, k3, k4, k5, k6, k7, (35./384.)-(5179./57600.), (500./1113.)-(7571./16695.), (125./192.)-(393./640.), (-2187./6784.)-(-92097./339200.), (11./84.)-(187./2100.), (0.)-(1./40.))
// determine error
err := cuda.MaxVecNorm(Err) * float64(h)
// adjust next time step
if err < MaxErr || Dt_si <= MinDt || FixDt != 0 { // mindt check to avoid infinite loop
// step OK
setLastErr(err)
setMaxTorque(k7)
NSteps++
Time = t0 + Dt_si
adaptDt(math.Pow(MaxErr/err, 1./5.))
data.Copy(rk.k1, k7) // FSAL
} else {
// undo bad step
//util.Println("Bad step at t=", t0, ", err=", err)
util.Assert(FixDt == 0)
Time = t0
data.Copy(m, m0)
NUndone++
adaptDt(math.Pow(MaxErr/err, 1./6.))
}
}
// TODO: into cuda
func madd5(dst, src1, src2, src3, src4, src5 *data.Slice, w1, w2, w3, w4, w5 float32) {
cuda.Madd3(dst, src1, src2, src3, w1, w2, w3)
cuda.Madd3(dst, dst, src4, src5, 1, w4, w5)
}
