sm9/bn256: also apply to 1-2-6-12 #139 #137

This commit is contained in:
Sun Yimin 2023-07-06 17:36:34 +08:00 committed by GitHub
parent 5f72151e74
commit 4755d5aa2a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
16 changed files with 543 additions and 147 deletions

View File

@ -32,19 +32,20 @@ func lineFunctionAdd(r, p, rOut *twistPoint, q *curvePoint, r2, a, b, c *gfP2) {
t2.Add(t2, t2) // t2 = 2Yr * J
rOut.y.Sub(t, t2) // rOut.y = L1*(V-rOut.x) - 2Yr*J
rOut.t.Square(&rOut.z)
rOut.t.SquareNC(&rOut.z)
t.Add(&p.y, &rOut.z).Square(t).Sub(t, r2).Sub(t, &rOut.t) // t = (Yp + rOut.Z)^2 - Yp^2 - rOut.Z^2 = 2Yp*rOut.Z
// t = (Yp + rOut.Z)^2 - Yp^2 - rOut.Z^2 = 2Yp*rOut.Z
t.Add(&p.y, &rOut.z).Square(t).Sub(t, r2).Sub(t, &rOut.t)
t2.Mul(L1, &p.x)
t2.Add(t2, t2) // t2 = 2 L1 * Xp
a.Sub(t2, t) // a = 2 L1 * Xp - 2 Yp * rOut.z
a.Sub(t2, t) // a = 2 L1 * Xp - 2 Yp * rOut.z = 2 L1 * Xp - (Yp + rOut.Z)^2 + Yp^2 + rOut.Z^2
c.MulScalar(&rOut.z, &q.y)
c.Add(c, c)
c.MulScalar(&rOut.z, &q.y) // c = rOut.z * Yq
c.Add(c, c) // c = 2 * rOut.z * Yq
b.Neg(L1)
b.MulScalar(b, &q.x).Add(b, b)
b.Neg(L1) // b= -L1
b.MulScalar(b, &q.x).Add(b, b) // b = -2 * L1 * Xq
}
func lineFunctionDouble(r, rOut *twistPoint, q *curvePoint, a, b, c *gfP2) {
@ -71,38 +72,36 @@ func lineFunctionDouble(r, rOut *twistPoint, q *curvePoint, a, b, c *gfP2) {
t.Add(t, t).Add(t, t) // t = 8 * Yr ^ 4
rOut.y.Sub(&rOut.y, t)
rOut.t.Square(&rOut.z)
rOut.t.SquareNC(&rOut.z)
t.Mul(E, &r.t).Add(t, t)
b.Neg(t)
b.MulScalar(b, &q.x)
t.Mul(E, &r.t).Add(t, t) // t = 2(E * Tr)
b.Neg(t) // b = -2(E * Tr)
b.MulScalar(b, &q.x) // b = -2(E * Tr * Xq)
a.Add(&r.x, E)
a.Square(a).Sub(a, A).Sub(a, G)
t.Add(B, B).Add(t, t)
a.Sub(a, t)
a.Add(&r.x, E) // a = Xr + E
a.Square(a).Sub(a, A).Sub(a, G) // a = (Xr + E) ^ 2 - A - G
t.Add(B, B).Add(t, t) // t = 4B
a.Sub(a, t) // a = (Xr + E) ^ 2 - A - G - 4B
c.Mul(&rOut.z, &r.t)
c.Add(c, c).MulScalar(c, &q.y)
c.Mul(&rOut.z, &r.t) // c = rOut.z * Tr
c.Add(c, c).MulScalar(c, &q.y) // c = 2 rOut.z * Tr * Yq
}
// (ret.z + ret.y*w + ret.x*w^2)* ((cv+a) + b*w^2)
func mulLine(ret *gfP12, a, b, c *gfP2) {
t1, tz, t, bz := &gfP4{}, &gfP4{}, &gfP4{}, &gfP4{}
gfp2Copy(&bz.x, c)
gfp2Copy(&bz.y, a)
tz.MulNC(&ret.z, bz)
tz, t := &gfP4{}, &gfP4{}
tz.MulNC2(&ret.z, c, a)
t.MulScalar(&ret.y, b).MulV1(t)
tz.Add(tz, t)
t1.MulNC(&ret.y, bz)
t.MulScalar(&ret.x, b).MulV1(t)
ret.y.Add(t1, t)
t.MulNC2(&ret.y, c, a)
ret.y.MulScalar(&ret.x, b).MulV1(&ret.y)
ret.y.Add(&ret.y, t)
t.MulNC2(&ret.x, c, a)
ret.x.MulScalar(&ret.z, b)
ret.x.Add(&ret.x, t)
t.MulNC(&ret.x, bz)
t1.MulScalar(&ret.z, b)
ret.x.Add(t1, t)
gfp4Copy(&ret.z, tz)
}

View File

@ -61,9 +61,9 @@ func millerB6(q *twistPoint, p *curvePoint) *gfP12b6 {
ret.Square(ret)
}
mulLineB6(ret, a, b, c)
tmpR= r
tmpR = r
r = newR
newR= tmpR
newR = tmpR
switch sixUPlus2NAF[i-1] {
case 1:
lineFunctionAdd(r, aAffine, newR, bAffine, r2, a, b, c)
@ -74,9 +74,9 @@ func millerB6(q *twistPoint, p *curvePoint) *gfP12b6 {
}
mulLineB6(ret, a, b, c)
tmpR= r
tmpR = r
r = newR
newR= tmpR
newR = tmpR
}
// In order to calculate Q1 we have to convert q from the sextic twist
@ -109,9 +109,9 @@ func millerB6(q *twistPoint, p *curvePoint) *gfP12b6 {
r2.Square(&q1.y)
lineFunctionAdd(r, q1, newR, bAffine, r2, a, b, c)
mulLineB6(ret, a, b, c)
tmpR= r
tmpR = r
r = newR
newR= tmpR
newR = tmpR
r2.Square(&minusQ2.y)
lineFunctionAdd(r, minusQ2, newR, bAffine, r2, a, b, c)
@ -144,42 +144,44 @@ func finalExponentiationB6(in *gfP12b6) *gfP12b6 {
inv.Invert(in)
t1.Mul(t1, inv)
t2 := (&gfP12b6{}).FrobeniusP2(t1)
t2 := inv.FrobeniusP2(t1) // reuse inv
t1.Mul(t1, t2)
fp := (&gfP12b6{}).Frobenius(t1)
fp2 := (&gfP12b6{}).FrobeniusP2(t1)
fp3 := (&gfP12b6{}).Frobenius(fp2)
fu := (&gfP12b6{}).Exp(t1, u)
fu2 := (&gfP12b6{}).Exp(fu, u)
fu3 := (&gfP12b6{}).Exp(fu2, u)
y0 := &gfP12b6{}
y0.MulNC(fp, fp2).Mul(y0, fp3)
// reuse fp, fp2, fp3 local variables
// [gfP12ExpU] is most time consuming operation
fu := fp.gfP12ExpU(t1)
fu2 := fp2.gfP12ExpU(fu)
fu3 := fp3.gfP12ExpU(fu2)
y3 := (&gfP12b6{}).Frobenius(fu)
fu2p := (&gfP12b6{}).Frobenius(fu2)
fu3p := (&gfP12b6{}).Frobenius(fu3)
y2 := (&gfP12b6{}).FrobeniusP2(fu2)
y0 := &gfP12b6{}
y0.Mul(fp, fp2).Mul(y0, fp3)
y1 := (&gfP12b6{}).Conjugate(t1)
y5 := (&gfP12b6{}).Conjugate(fu2)
y3.Conjugate(y3)
y4 := (&gfP12b6{}).Mul(fu, fu2p)
y4 := (&gfP12b6{}).MulNC(fu, fu2p)
y4.Conjugate(y4)
y6 := (&gfP12b6{}).Mul(fu3, fu3p)
y6 := (&gfP12b6{}).MulNC(fu3, fu3p)
y6.Conjugate(y6)
t0 := (&gfP12b6{}).Square(y6)
t0 := (&gfP12b6{}).SpecialSquareNC(y6)
t0.Mul(t0, y4).Mul(t0, y5)
t1.Mul(y3, y5).Mul(t1, t0)
t0.Mul(t0, y2)
t1.Square(t1).Mul(t1, t0).Square(t1)
t1.SpecialSquare(t1).Mul(t1, t0).SpecialSquare(t1)
t0.Mul(t1, y1)
t1.Mul(t1, y0)
t0.Square(t0).Mul(t0, t1)
t0.SpecialSquare(t0).Mul(t0, t1)
return t0
}

View File

@ -13,7 +13,7 @@ type G2 struct {
p *twistPoint
}
//Gen2 is the generator of G2.
// Gen2 is the generator of G2.
var Gen2 = &G2{twistGen}
var g2GeneratorTable *[32 * 2]twistPointTable

View File

@ -9,7 +9,6 @@ import (
type gfP [4]uint64
var genericZero = &gfP{0}
var zero = newGFp(0)
var one = newGFp(1)
var two = newGFp(2)

View File

@ -134,11 +134,6 @@ func (e *gfP12) MulGFP(a *gfP12, b *gfP) *gfP12 {
}
func (e *gfP12) Mul(a, b *gfP12) *gfP12 {
// (z0 + y0*w + x0*w^2)* (z1 + y1*w + x1*w^2)
// z0*z1 + z0*y1*w + z0*x1*w^2
// +y0*z1*w + y0*y1*w^2 + y0*x1*v
// +x0*z1*w^2 + x0*y1*v + x0*x1*v*w
//=(z0*z1+y0*x1*v+x0*y1*v) + (z0*y1+y0*z1+x0*x1*v)w + (z0*x1 + y0*y1 + x0*z1)*w^2
tmp := &gfP12{}
tmp.MulNC(a, b)
gfp12Copy(e, tmp)
@ -186,10 +181,6 @@ func (e *gfP12) MulNC(a, b *gfP12) *gfP12 {
}
func (e *gfP12) Square(a *gfP12) *gfP12 {
// (z + y*w + x*w^2)* (z + y*w + x*w^2)
// z^2 + z*y*w + z*x*w^2 + y*z*w + y^2*w^2 + y*x*v + x*z*w^2 + x*y*v + x^2 *v *w
// (z^2 + y*x*v + x*y*v) + (z*y + y*z + v * x^2)w + (z*x + y^2 + x*z)*w^2
// (z^2 + 2*x*y*v) + (v*x^2 + 2*y*z) *w + (y^2 + 2*x*z) * w^2
tmp := &gfP12{}
tmp.SquareNC(a)
gfp12Copy(e, tmp)
@ -244,6 +235,10 @@ func (e *gfP12) SpecialSquare(a *gfP12) *gfP12 {
return e
}
// Special squaring loop for use on elements in T_6(fp2) (after the
// easy part of the final exponentiation. Used in the hard part
// of the final exponentiation. Function uses formulas in
// Granger/Scott (PKC2010).
func (e *gfP12) SpecialSquares(a *gfP12, n int) *gfP12 {
// Square first round
in := &gfP12{}
@ -257,12 +252,9 @@ func (e *gfP12) SpecialSquares(a *gfP12, n int) *gfP12 {
v1.SquareNC(&a.y) // (t12, t01)
v2.SquareNC(&a.z) // (t11, t00)
tx.Add(v0, v0)
tx.Add(v0, tx)
ty.Add(v1, v1)
ty.Add(v1, ty)
tz.Add(v2, v2)
tz.Add(v2, tz)
tx.Triple(v0)
ty.Triple(v1)
tz.Triple(v2)
v0.Add(&a.x, &a.x) // (f12, f01)
v0.y.Neg(&v0.y)
@ -287,12 +279,9 @@ func (e *gfP12) SpecialSquares(a *gfP12, n int) *gfP12 {
v1.SquareNC(&in.y) // (t12, t01)
v2.SquareNC(&in.z) // (t11, t00)
tx.Add(v0, v0)
tx.Add(v0, tx)
ty.Add(v1, v1)
ty.Add(v1, ty)
tz.Add(v2, v2)
tz.Add(v2, tz)
tx.Triple(v0)
ty.Triple(v1)
tz.Triple(v2)
v0.Add(&in.x, &in.x) // (f12, f01)
v0.y.Neg(&v0.y)
@ -325,12 +314,9 @@ func (e *gfP12) SpecialSquareNC(a *gfP12) *gfP12 {
v1.SquareNC(&a.y) // (t12, t01)
v2.SquareNC(&a.z) // (t11, t00)
tx.Add(v0, v0)
tx.Add(v0, tx)
ty.Add(v1, v1)
ty.Add(v1, ty)
tz.Add(v2, v2)
tz.Add(v2, tz)
tx.Triple(v0)
ty.Triple(v1)
tz.Triple(v2)
v0.Add(&a.x, &a.x) // (f12, f01)
v0.y.Neg(&v0.y)

View File

@ -125,15 +125,25 @@ func (e *gfP12b6) Sub(a, b *gfP12b6) *gfP12b6 {
}
func (e *gfP12b6) Mul(a, b *gfP12b6) *gfP12b6 {
tmp := &gfP12b6{}
tmp.MulNC(a, b)
e.x.Set(&tmp.x)
e.y.Set(&tmp.y)
return e
}
func (e *gfP12b6) MulNC(a, b *gfP12b6) *gfP12b6 {
// "Multiplication and Squaring on Pairing-Friendly Fields"
// Section 4, Karatsuba method.
// http://eprint.iacr.org/2006/471.pdf
//(a0+a1*t)(b0+b1*t)=c0+c1*t, where
//c0 = a0*b0 +a1*b1*s
//c1 = (a0 + a1)(b0 + b1) - a0*b0 - a1*b1 = a0*b1 + a1*b0
tx, ty, v0, v1 := &gfP6{}, &gfP6{}, &gfP6{}, &gfP6{}
v0.Mul(&a.y, &b.y)
v1.Mul(&a.x, &b.x)
tx := &e.x
ty := &e.y
v0, v1 := &gfP6{}, &gfP6{}
v0.MulNC(&a.y, &b.y)
v1.MulNC(&a.x, &b.x)
tx.Add(&a.x, &a.y)
ty.Add(&b.x, &b.y)
@ -144,8 +154,6 @@ func (e *gfP12b6) Mul(a, b *gfP12b6) *gfP12b6 {
ty.MulS(v1)
ty.Add(ty, v0)
e.x.Set(tx)
e.y.Set(ty)
return e
}
@ -168,21 +176,209 @@ func (e *gfP12b6) MulGfP2(a *gfP12b6, b *gfP2) *gfP12b6 {
}
func (e *gfP12b6) Square(a *gfP12b6) *gfP12b6 {
tmp := &gfP12b6{}
tmp.SquareNC(a)
e.x.Set(&tmp.x)
e.y.Set(&tmp.y)
return e
}
func (e *gfP12b6) SquareNC(a *gfP12b6) *gfP12b6 {
// Complex squaring algorithm
// (xt+y)² = (x^2*s + y^2) + 2*x*y*t
tx, ty := &gfP6{}, &gfP6{}
tx.Square(&a.x).MulS(tx)
ty.Square(&a.y)
tx := &e.x
ty := &e.y
tx.SquareNC(&a.x).MulS(tx)
ty.SquareNC(&a.y)
ty.Add(tx, ty)
tx.Mul(&a.x, &a.y)
tx.Add(tx, tx)
e.x.Set(tx)
e.y.Set(ty)
return e
}
// Special squaring for use on elements in T_6(fp2) (after the
// easy part of the final exponentiation. Used in the hard part
// of the final exponentiation. Function uses formulas in
// Granger/Scott (PKC2010).
func (e *gfP12b6) SpecialSquare(a *gfP12b6) *gfP12b6 {
tmp := &gfP12b6{}
tmp.SpecialSquareNC(a)
e.x.Set(&tmp.x)
e.y.Set(&tmp.y)
return e
}
func (e *gfP12b6) SpecialSquareNC(a *gfP12b6) *gfP12b6 {
f02 := &e.y.x
f01 := &e.y.y
f00 := &e.y.z
f12 := &e.x.x
f11 := &e.x.y
f10 := &e.x.z
t00, t01, t02, t10, t11, t12 := &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}
gfP4Square(t11, t00, &a.x.y, &a.y.z)
gfP4Square(t12, t01, &a.y.x, &a.x.z)
gfP4Square(t02, t10, &a.x.x, &a.y.y)
f00.MulU1(t02)
t02.Set(t10)
t10.Set(f00)
f00.Add(t00, t00)
t00.Add(f00, t00)
f00.Add(t01, t01)
t01.Add(f00, t01)
f00.Add(t02, t02)
t02.Add(f00, t02)
f00.Add(t10, t10)
t10.Add(f00, t10)
f00.Add(t11, t11)
t11.Add(f00, t11)
f00.Add(t12, t12)
t12.Add(f00, t12)
f00.Add(&a.y.z, &a.y.z)
f00.Neg(f00)
f01.Add(&a.y.y, &a.y.y)
f01.Neg(f01)
f02.Add(&a.y.x, &a.y.x)
f02.Neg(f02)
f10.Add(&a.x.z, &a.x.z)
f11.Add(&a.x.y, &a.x.y)
f12.Add(&a.x.x, &a.x.x)
f00.Add(f00, t00)
f01.Add(f01, t01)
f02.Add(f02, t02)
f10.Add(f10, t10)
f11.Add(f11, t11)
f12.Add(f12, t12)
return e
}
func (e *gfP12b6) SpecialSquares(a *gfP12b6, n int) *gfP12b6 {
// Square first round
in := &gfP12b6{}
f02 := &in.y.x
f01 := &in.y.y
f00 := &in.y.z
f12 := &in.x.x
f11 := &in.x.y
f10 := &in.x.z
t00, t01, t02, t10, t11, t12 := &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}
gfP4Square(t11, t00, &a.x.y, &a.y.z)
gfP4Square(t12, t01, &a.y.x, &a.x.z)
gfP4Square(t02, t10, &a.x.x, &a.y.y)
f00.MulU1(t02)
t02.Set(t10)
t10.Set(f00)
f00.Add(t00, t00)
t00.Add(f00, t00)
f00.Add(t01, t01)
t01.Add(f00, t01)
f00.Add(t02, t02)
t02.Add(f00, t02)
f00.Add(t10, t10)
t10.Add(f00, t10)
f00.Add(t11, t11)
t11.Add(f00, t11)
f00.Add(t12, t12)
t12.Add(f00, t12)
f00.Add(&a.y.z, &a.y.z)
f00.Neg(f00)
f01.Add(&a.y.y, &a.y.y)
f01.Neg(f01)
f02.Add(&a.y.x, &a.y.x)
f02.Neg(f02)
f10.Add(&a.x.z, &a.x.z)
f11.Add(&a.x.y, &a.x.y)
f12.Add(&a.x.x, &a.x.x)
f00.Add(f00, t00)
f01.Add(f01, t01)
f02.Add(f02, t02)
f10.Add(f10, t10)
f11.Add(f11, t11)
f12.Add(f12, t12)
tmp := &gfP12b6{}
var tmp2 *gfP12b6
for i := 1; i < n; i++ {
f02 = &tmp.y.x
f01 = &tmp.y.y
f00 = &tmp.y.z
f12 = &tmp.x.x
f11 = &tmp.x.y
f10 = &tmp.x.z
gfP4Square(t11, t00, &in.x.y, &in.y.z)
gfP4Square(t12, t01, &in.y.x, &in.x.z)
gfP4Square(t02, t10, &in.x.x, &in.y.y)
f00.MulU1(t02)
t02.Set(t10)
t10.Set(f00)
f00.Add(t00, t00)
t00.Add(f00, t00)
f00.Add(t01, t01)
t01.Add(f00, t01)
f00.Add(t02, t02)
t02.Add(f00, t02)
f00.Add(t10, t10)
t10.Add(f00, t10)
f00.Add(t11, t11)
t11.Add(f00, t11)
f00.Add(t12, t12)
t12.Add(f00, t12)
f00.Add(&in.y.z, &in.y.z)
f00.Neg(f00)
f01.Add(&in.y.y, &in.y.y)
f01.Neg(f01)
f02.Add(&in.y.x, &in.y.x)
f02.Neg(f02)
f10.Add(&in.x.z, &in.x.z)
f11.Add(&in.x.y, &in.x.y)
f12.Add(&in.x.x, &in.x.x)
f00.Add(f00, t00)
f01.Add(f01, t01)
f02.Add(f02, t02)
f10.Add(f10, t10)
f11.Add(f11, t11)
f12.Add(f12, t12)
// Switch references
tmp2 = in
in = tmp
tmp = tmp2
}
e.x.Set(&in.x)
e.y.Set(&in.y)
return e
}
func gfP4Square(retX, retY, x, y *gfP2) {
retX.SquareUNC(x)
retY.SquareNC(y)
retY.Add(retX, retY)
retX.MulNC(x, y)
retX.Add(retX, retX)
}
func (c *gfP12b6) Exp(a *gfP12b6, power *big.Int) *gfP12b6 {
sum := (&gfP12b6{}).SetOne()
t := &gfP12b6{}
@ -206,8 +402,8 @@ func (e *gfP12b6) Invert(a *gfP12b6) *gfP12b6 {
t0, t1 := &gfP6{}, &gfP6{}
t0.Mul(&a.y, &a.y)
t1.Mul(&a.x, &a.x).MulS(t1)
t0.MulNC(&a.y, &a.y)
t1.MulNC(&a.x, &a.x).MulS(t1)
t0.Sub(t0, t1)
t0.Invert(t0)

View File

@ -311,3 +311,28 @@ func BenchmarkGfP12b6Frobenius(b *testing.B) {
}
}
}
func TestGfP12b6SpecialSquare(t *testing.T) {
in := &gfP12b6{
p6,
p6,
}
t1 := &gfP12b6{}
t1.x.Neg(&in.x)
t1.y.Set(&in.y)
inv := &gfP12b6{}
inv.Invert(in)
t1.Mul(t1, inv)
t2 := (&gfP12b6{}).FrobeniusP2(t1)
t1.Mul(t1, t2)
got := &gfP12b6{}
expected := &gfP12b6{}
got.SpecialSquare(t1)
expected.Square(t1)
if *got != *expected {
t.Errorf("not same got=%v, expected=%v", got, expected)
}
}

View File

@ -93,7 +93,7 @@ func BenchmarkGfP12SpecialSquare(b *testing.B) {
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
x2.Square(t1)
x2.SpecialSquare(t1)
}
}

View File

@ -0,0 +1,43 @@
package bn256
// Use special square
func (e *gfP12b6) gfP12ExpU(x *gfP12b6) *gfP12b6 {
// The sequence of 10 multiplications and 61 squarings is derived from the
// following addition chain generated with github.com/mmcloughlin/addchain v0.4.0.
//
// _10 = 2*1
// _100 = 2*_10
// _101 = 1 + _100
// _1001 = _100 + _101
// _1011 = _10 + _1001
// _1100 = 1 + _1011
// i56 = (_1100 << 40 + _1011) << 7 + _1011 + _100
// i69 = (2*(i56 << 4 + _1001) + 1) << 6
// return 2*(_101 + i69)
//
var z = e
var t0 = new(gfP12b6)
var t1 = new(gfP12b6)
var t2 = new(gfP12b6)
var t3 = new(gfP12b6)
t2.SpecialSquareNC(x)
t1.SpecialSquareNC(t2)
z.MulNC(x, t1)
t0.MulNC(t1, z)
t2.Mul(t2, t0)
t3.MulNC(x, t2)
t3.SpecialSquares(t3, 40)
t3.Mul(t2, t3)
t3.SpecialSquares(t3, 7)
t2.Mul(t2, t3)
t1.Mul(t1, t2)
t1.SpecialSquares(t1, 4)
t0.Mul(t0, t1)
t0.SpecialSquare(t0)
t0.Mul(x, t0)
t0.SpecialSquares(t0, 6)
z.Mul(z, t0)
z.SpecialSquare(z)
return e
}

View File

@ -64,13 +64,13 @@ func (e *gfP2) IsOne() bool {
func (e *gfP2) Conjugate(a *gfP2) *gfP2 {
e.y.Set(&a.y)
gfpSub(&e.x, genericZero, &a.x)
gfpSub(&e.x, zero, &a.x)
return e
}
func (e *gfP2) Neg(a *gfP2) *gfP2 {
gfpSub(&e.x, genericZero, &a.x)
gfpSub(&e.y, genericZero, &a.y)
gfpSub(&e.x, zero, &a.x)
gfpSub(&e.y, zero, &a.y)
return e
}
@ -135,14 +135,20 @@ func (e *gfP2) MulNC(a, b *gfP2) *gfP2 {
return e
}
func (e *gfP2) MulU(a, b *gfP2) *gfP2 {
tmp := &gfP2{}
tmp.MulUNC(a, b)
gfp2Copy(e, tmp)
return e
}
// MulU: a * b * u
// (a0+a1*u)(b0+b1*u)*u=c0+c1*u, where
// c1 = (a0*b0 - 2a1*b1)u
// c0 = -2 * ((a0 + a1)(b0 + b1) - a0*b0 - a1*b1) = -2 * (a0*b1 + a1*b0)
func (e *gfP2) MulU(a, b *gfP2) *gfP2 {
tmp := &gfP2{}
tx := &tmp.x
ty := &tmp.y
func (e *gfP2) MulUNC(a, b *gfP2) *gfP2 {
tx := &e.x
ty := &e.y
v0, v1 := &gfP{}, &gfP{}
gfpMul(v0, &a.y, &b.y)
@ -155,12 +161,11 @@ func (e *gfP2) MulU(a, b *gfP2) *gfP2 {
gfpSub(ty, ty, v0)
gfpSub(ty, ty, v1)
gfpAdd(ty, ty, ty)
gfpSub(ty, genericZero, ty)
gfpSub(ty, zero, ty)
gfpSub(tx, v0, v1)
gfpSub(tx, tx, v1)
gfp2Copy(e, tmp)
return e
}
@ -171,7 +176,7 @@ func (e *gfP2) MulU(a, b *gfP2) *gfP2 {
func (e *gfP2) MulU1(a *gfP2) *gfP2 {
t := &gfP{}
gfpAdd(t, &a.x, &a.x)
gfpSub(t, genericZero, t)
gfpSub(t, zero, t)
gfpCopy(&e.x, &a.y)
gfpCopy(&e.y, t)
@ -228,7 +233,7 @@ func (e *gfP2) SquareUNC(a *gfP2) *gfP2 {
gfpAdd(tx, tx, ty)
gfpAdd(ty, ty, ty)
gfpAdd(ty, ty, ty)
gfpSub(ty, genericZero, ty)
gfpSub(ty, zero, ty)
return e
}
@ -251,7 +256,7 @@ func (e *gfP2) Invert(a *gfP2) *gfP2 {
inv := &gfP{}
inv.Invert(t3) // inv = (2 * a.x ^ 2 + a.y ^ 2) ^ (-1)
gfpSub(t1, genericZero, &a.x)
gfpSub(t1, zero, &a.x)
gfpMul(&e.x, t1, inv) // x = - a.x * inv
gfpMul(&e.y, &a.y, inv) // y = a.y * inv

View File

@ -73,6 +73,12 @@ func (e *gfP4) Add(a, b *gfP4) *gfP4 {
return e
}
func (e *gfP4) Triple(a *gfP4) *gfP4 {
e.x.Triple(&a.x)
e.y.Triple(&a.y)
return e
}
func (e *gfP4) Sub(a, b *gfP4) *gfP4 {
e.x.Sub(&a.x, &b.x)
e.y.Sub(&a.y, &b.y)
@ -92,12 +98,6 @@ func (e *gfP4) MulGFP(a *gfP4, b *gfP) *gfP4 {
}
func (e *gfP4) Mul(a, b *gfP4) *gfP4 {
// "Multiplication and Squaring on Pairing-Friendly Fields"
// Section 4, Karatsuba method.
// http://eprint.iacr.org/2006/471.pdf
//(a0+a1*v)(b0+b1*v)=c0+c1*v, where
//c0 = a0*b0 +a1*b1*u
//c1 = (a0 + a1)(b0 + b1) - a0*b0 - a1*b1 = a0*b1 + a1*b0
tmp := &gfP4{}
tmp.MulNC(a, b)
gfp4Copy(e, tmp)
@ -129,6 +129,33 @@ func (e *gfP4) MulNC(a, b *gfP4) *gfP4 {
return e
}
// MulNC2 muls a with (xv+y), this method is used in mulLine function
// to avoid gfP4 instance construction.
func (e *gfP4) MulNC2(a *gfP4, x, y *gfP2) *gfP4 {
// "Multiplication and Squaring on Pairing-Friendly Fields"
// Section 4, Karatsuba method.
// http://eprint.iacr.org/2006/471.pdf
//(a0+a1*v)(b0+b1*v)=c0+c1*v, where
//c0 = a0*b0 +a1*b1*u
//c1 = (a0 + a1)(b0 + b1) - a0*b0 - a1*b1 = a0*b1 + a1*b0
tx := &e.x
ty := &e.y
v0, v1 := &gfP2{}, &gfP2{}
v0.MulNC(&a.y, y)
v1.MulNC(&a.x, x)
tx.Add(&a.x, &a.y)
ty.Add(x, y)
tx.Mul(tx, ty)
tx.Sub(tx, v0)
tx.Sub(tx, v1)
ty.MulU1(v1)
ty.Add(ty, v0)
return e
}
// MulV: a * b * v
// (a0+a1*v)(b0+b1*v)*v=c0+c1*v, where
// (a0*b0 + a0*b1v + a1*b0*v + a1*b1*u)*v

View File

@ -26,9 +26,7 @@ func (e *gfP6) String() string {
}
func (e *gfP6) Set(a *gfP6) *gfP6 {
e.x.Set(&a.x)
e.y.Set(&a.y)
e.z.Set(&a.z)
gfp6Copy(e, a)
return e
}
@ -104,15 +102,25 @@ func (e *gfP6) MulGfP(a *gfP6, b *gfP) *gfP6 {
}
func (e *gfP6) Mul(a, b *gfP6) *gfP6 {
tmp := &gfP6{}
tmp.MulNC(a, b)
gfp6Copy(e, tmp)
return e
}
func (e *gfP6) MulNC(a, b *gfP6) *gfP6 {
// (z0 + y0*s + x0*s²)* (z1 + y1*s + x1*s²)
// z0*z1 + z0*y1*s + z0*x1*s²
// +y0*z1*s + y0*y1*s² + y0*x1*u
// +x0*z1*s² + x0*y1*u + x0*x1*s*u
//=(z0*z1+y0*x1*u+x0*y1*u) + (z0*y1+y0*z1+x0*x1*u)s + (z0*x1 + y0*y1 + x0*z1)*s²
tx, ty, tz, t, v0, v1, v2 := &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}
v0.Mul(&a.z, &b.z)
v1.Mul(&a.y, &b.y)
v2.Mul(&a.x, &b.x)
tx := &e.x
ty := &e.y
tz := &e.z
t, v0, v1, v2 := &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}
v0.MulNC(&a.z, &b.z)
v1.MulNC(&a.y, &b.y)
v2.MulNC(&a.x, &b.x)
t.Add(&a.y, &a.x)
tz.Add(&b.y, &b.x)
@ -137,9 +145,6 @@ func (e *gfP6) Mul(a, b *gfP6) *gfP6 {
tx.Add(tx, v1)
tx.Sub(tx, v2)
e.x.Set(tx)
e.y.Set(ty)
e.z.Set(tz)
return e
}
@ -161,30 +166,47 @@ func (e *gfP6) MulS(a *gfP6) *gfP6 {
}
func (e *gfP6) Square(a *gfP6) *gfP6 {
tmp := &gfP6{}
tmp.SquareNC(a)
gfp6Copy(e, tmp)
return e
}
func (e *gfP6) SquareNC(a *gfP6) *gfP6 {
// (z + y*s + x*s²)* (z + y*s + x*s²)
// z^2 + z*y*s + z*x*s² + y*z*s + y^2*s² + y*x*u + x*z*s² + x*y*u + x^2 *u *s
// (z^2 + y*x*s + x*y*u) + (z*y + y*z + u * x^2)s + (z*x + y^2 + x*z)*s²
// (z^2 + 2*x*y*u) + (u*x^2 + 2*y*z) * s + (y^2 + 2*x*z) * s²
tx, ty, tz, t := &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}
// Karatsuba method
tx := &e.x
ty := &e.y
tz := &e.z
t, v0, v1, v2 := &gfP2{}, &gfP2{}, &gfP2{}, &gfP2{}
tz.Square(&a.z)
t.MulU(&a.x, &a.y)
t.Add(t, t)
tz.Add(tz, t)
v0.SquareNC(&a.z)
v1.SquareNC(&a.y)
v2.SquareNC(&a.x)
ty.SquareU(&a.x)
t.Mul(&a.y, &a.z)
t.Add(t, t)
t.Add(&a.y, &a.x)
tz.SquareNC(t)
tz.Sub(tz, v1)
tz.Sub(tz, v2)
tz.MulU1(tz)
tz.Add(tz, v0)
t.Add(&a.z, &a.y)
ty.SquareNC(t)
ty.Sub(ty, v0)
ty.Sub(ty, v1)
t.MulU1(v2)
ty.Add(ty, t)
tx.Square(&a.y)
t.Mul(&a.x, &a.z)
t.Add(t, t)
tx.Add(tx, t)
t.Add(&a.z, &a.x)
tx.SquareNC(t)
tx.Sub(tx, v0)
tx.Add(tx, v1)
tx.Sub(tx, v2)
e.x.Set(tx)
e.y.Set(ty)
e.z.Set(tz)
return e
}
@ -209,19 +231,19 @@ func (e *gfP6) Invert(a *gfP6) *gfP6 {
// See "Implementing cryptographic pairings", M. Scott, section 3.2.
// ftp://136.206.11.249/pub/crypto/pairings.pdf
t1 := (&gfP2{}).MulU(&a.x, &a.y)
A := (&gfP2{}).Square(&a.z)
t1 := (&gfP2{}).MulUNC(&a.x, &a.y)
A := (&gfP2{}).SquareNC(&a.z)
A.Sub(A, t1)
B := (&gfP2{}).SquareU(&a.x)
B := (&gfP2{}).SquareUNC(&a.x)
t1.Mul(&a.y, &a.z)
B.Sub(B, t1)
C := (&gfP2{}).Square(&a.y)
C := (&gfP2{}).SquareNC(&a.y)
t1.Mul(&a.x, &a.z)
C.Sub(C, t1)
F := (&gfP2{}).MulU(C, &a.y)
F := (&gfP2{}).MulUNC(C, &a.y)
t1.Mul(A, &a.z)
F.Add(F, t1)
t1.MulU(B, &a.x)

View File

@ -179,6 +179,22 @@ func TestInvert(t *testing.T) {
}
}
func TestGfpNeg(t *testing.T) {
x := fromBigInt(bigFromHex("9093a2b979e6186f43a9b28d41ba644d533377f2ede8c66b19774bf4a9c7a596"))
got := &gfP{}
gfpSub(got, zero, x)
expected := &gfP{}
gfpNeg(expected, x)
if *expected != *got {
t.Errorf("got %v, expected %v", got, expected)
}
gfpSub(got, zero, zero)
gfpNeg(expected, zero)
if *expected != *got {
t.Errorf("got %v, expected %v", got, expected)
}
}
func BenchmarkGfPMul(b *testing.B) {
x := fromBigInt(bigFromHex("9093a2b979e6186f43a9b28d41ba644d533377f2ede8c66b19774bf4a9c7a596"))
b.ReportAllocs()

View File

@ -97,6 +97,62 @@ copygfp4_avx2:
VZEROUPPER
RET
// func gfp6Copy(res, a *gfP6)
TEXT ·gfp6Copy(SB),NOSPLIT,$0
MOVQ res+0(FP), res_ptr
MOVQ a+8(FP), x_ptr
CMPB ·supportAVX2+0(SB), $0x01
JEQ copygfp6_avx2
MOVOU (16*0)(x_ptr), X0
MOVOU (16*1)(x_ptr), X1
MOVOU (16*2)(x_ptr), X2
MOVOU (16*3)(x_ptr), X3
MOVOU (16*4)(x_ptr), X4
MOVOU (16*5)(x_ptr), X5
MOVOU (16*6)(x_ptr), X6
MOVOU (16*7)(x_ptr), X7
MOVOU (16*8)(x_ptr), X8
MOVOU (16*9)(x_ptr), X9
MOVOU (16*10)(x_ptr), X10
MOVOU (16*11)(x_ptr), X11
MOVOU X0, (16*0)(res_ptr)
MOVOU X1, (16*1)(res_ptr)
MOVOU X2, (16*2)(res_ptr)
MOVOU X3, (16*3)(res_ptr)
MOVOU X4, (16*4)(res_ptr)
MOVOU X5, (16*5)(res_ptr)
MOVOU X6, (16*6)(res_ptr)
MOVOU X7, (16*7)(res_ptr)
MOVOU X8, (16*8)(res_ptr)
MOVOU X9, (16*9)(res_ptr)
MOVOU X10, (16*10)(res_ptr)
MOVOU X11, (16*11)(res_ptr)
copygfp6_avx2:
VMOVDQU (32*0)(x_ptr), Y0
VMOVDQU (32*1)(x_ptr), Y1
VMOVDQU (32*2)(x_ptr), Y2
VMOVDQU (32*3)(x_ptr), Y3
VMOVDQU (32*4)(x_ptr), Y4
VMOVDQU (32*5)(x_ptr), Y5
VMOVDQU Y0, (32*0)(res_ptr)
VMOVDQU Y1, (32*1)(res_ptr)
VMOVDQU Y2, (32*2)(res_ptr)
VMOVDQU Y3, (32*3)(res_ptr)
VMOVDQU Y4, (32*4)(res_ptr)
VMOVDQU Y5, (32*5)(res_ptr)
VZEROUPPER
RET
// func gfp12Copy(res, a *gfP12)
TEXT ·gfp12Copy(SB),NOSPLIT,$0
MOVQ res+0(FP), res_ptr

View File

@ -30,7 +30,7 @@ TEXT ·gfp2Copy(SB),NOSPLIT,$0
RET
/* ---------------------------------------*/
// func gfp4Copy(res, a *gfP2)
// func gfp4Copy(res, a *gfP4)
TEXT ·gfp4Copy(SB),NOSPLIT,$0
MOVD res+0(FP), res_ptr
MOVD a+8(FP), a_ptr
@ -43,6 +43,23 @@ TEXT ·gfp4Copy(SB),NOSPLIT,$0
RET
/* ---------------------------------------*/
// func gfp6Copy(res, a *gfP6)
TEXT ·gfp6Copy(SB),NOSPLIT,$0
MOVD res+0(FP), res_ptr
MOVD a+8(FP), a_ptr
VLD1.P 64(a_ptr), [V0.B16, V1.B16, V2.B16, V3.B16]
VST1.P [V0.B16, V1.B16, V2.B16, V3.B16], 64(res_ptr)
VLD1.P 64(a_ptr), [V0.B16, V1.B16, V2.B16, V3.B16]
VST1.P [V0.B16, V1.B16, V2.B16, V3.B16], 64(res_ptr)
VLD1.P 64(a_ptr), [V0.B16, V1.B16, V2.B16, V3.B16]
VST1.P [V0.B16, V1.B16, V2.B16, V3.B16], 64(res_ptr)
RET
/* ---------------------------------------*/
// func gfp12Copy(res, a *gfP12)
TEXT ·gfp12Copy(SB),NOSPLIT,$0

View File

@ -31,5 +31,8 @@ func gfp2Copy(res, in *gfP2)
//go:noescape
func gfp4Copy(res, in *gfP4)
//go:noescape
func gfp6Copy(res, in *gfP6)
//go:noescape
func gfp12Copy(res, in *gfP12)