[Beignet] [PATCH] backend: add double support to log2

[rander]

Signed-off-by: rander <rander.wang at intel.com>
---
 backend/src/libocl/tmpl/ocl_math.tmpl.cl    | 68 +++++++++++++++++++++++++++++
 backend/src/libocl/tmpl/ocl_math_20.tmpl.cl | 68 +++++++++++++++++++++++++++++
 2 files changed, 136 insertions(+)

diff --git a/backend/src/libocl/tmpl/ocl_math.tmpl.cl b/backend/src/libocl/tmpl/ocl_math.tmpl.cl
index a3428c8..f0c40fc 100644
--- a/backend/src/libocl/tmpl/ocl_math.tmpl.cl
+++ b/backend/src/libocl/tmpl/ocl_math.tmpl.cl
@@ -4103,3 +4103,71 @@ OVERLOADABLE double log(double x)
 
 }
 
+OVERLOADABLE double log2(double x)
+{
+	double ln2 = 0.69314718055994530942,
+	zero = 0,
+	two54   =  1.80143985094819840000e+16,  /* 43500000 00000000 */
+	Lg1 = 6.666666666666735130e-01,  /* 3FE55555 55555593 */
+	Lg2 = 3.999999999940941908e-01,  /* 3FD99999 9997FA04 */
+	Lg3 = 2.857142874366239149e-01,  /* 3FD24924 94229359 */
+	Lg4 = 2.222219843214978396e-01,  /* 3FCC71C5 1D8E78AF */
+	Lg5 = 1.818357216161805012e-01,  /* 3FC74664 96CB03DE */
+	Lg6 = 1.531383769920937332e-01,  /* 3FC39A09 D078C69F */
+	Lg7 = 1.479819860511658591e-01;  /* 3FC2F112 DF3E5244 */
+
+	double hfsq,f,s,z,R,w,t1,t2,dk;
+	int k,hx,i,j;
+	uint lx;
+
+	hx = __HI(x);
+	lx = __LO(x);
+
+	k=0;
+	if (hx < 0x00100000)
+	{			/* x < 2**-1022  */
+		if (((hx&0x7fffffff)|lx)==0)
+			return -two54/(x-x);		/* log(+-0)=-inf */
+
+		if (hx<0) return (x-x)/(x-x);	/* log(-#) = NaN */
+
+		k -= 54; x *= two54; /* subnormal number, scale up x */
+		hx = __HI(x);
+	}
+
+	if (hx >= 0x7ff00000) return x+x;
+	k += (hx>>20)-1023;
+	hx &= 0x000fffff;
+	i = (hx+0x95f64)&0x100000;
+	__setHigh(&x,hx|(i^0x3ff00000));	/* normalize x or x/2 */
+	k += (i>>20);
+	dk = (double) k;
+	f = x-1.0;
+
+	if((0x000fffff&(2+hx))<3)
+	{	/* |f| < 2**-20 */
+		if(f==zero) return dk;
+		R = f*f*(0.5-0.33333333333333333*f);
+		return dk-(R-f)/ln2;
+	}
+
+	s = f/(2.0+f);
+	z = s*s;
+	i = hx-0x6147a;
+	w = z*z;
+	j = 0x6b851-hx;
+	t1= w*(Lg2+w*(Lg4+w*Lg6));
+	t2= z*(Lg1+w*(Lg3+w*(Lg5+w*Lg7)));
+	i |= j;
+	R = t2+t1;
+	if(i>0)
+	{
+		hfsq=0.5*f*f;
+		return dk-((hfsq-(s*(hfsq+R)))-f)/ln2;
+	}
+	else
+	{
+		return dk-((s*(f-R))-f)/ln2;
+	}
+}
+
diff --git a/backend/src/libocl/tmpl/ocl_math_20.tmpl.cl b/backend/src/libocl/tmpl/ocl_math_20.tmpl.cl
index 0f355b1..ea2ee37 100644
--- a/backend/src/libocl/tmpl/ocl_math_20.tmpl.cl
+++ b/backend/src/libocl/tmpl/ocl_math_20.tmpl.cl
@@ -3979,5 +3979,73 @@ OVERLOADABLE double log(double x)
 
 }
 
+OVERLOADABLE double log2(double x)
+{
+	double ln2 = 0.69314718055994530942,
+	zero = 0,
+	two54   =  1.80143985094819840000e+16,  /* 43500000 00000000 */
+	Lg1 = 6.666666666666735130e-01,  /* 3FE55555 55555593 */
+	Lg2 = 3.999999999940941908e-01,  /* 3FD99999 9997FA04 */
+	Lg3 = 2.857142874366239149e-01,  /* 3FD24924 94229359 */
+	Lg4 = 2.222219843214978396e-01,  /* 3FCC71C5 1D8E78AF */
+	Lg5 = 1.818357216161805012e-01,  /* 3FC74664 96CB03DE */
+	Lg6 = 1.531383769920937332e-01,  /* 3FC39A09 D078C69F */
+	Lg7 = 1.479819860511658591e-01;  /* 3FC2F112 DF3E5244 */
+
+	double hfsq,f,s,z,R,w,t1,t2,dk;
+	int k,hx,i,j;
+	uint lx;
+
+	hx = __HI(x);
+	lx = __LO(x);
+
+	k=0;
+	if (hx < 0x00100000)
+	{			/* x < 2**-1022  */
+		if (((hx&0x7fffffff)|lx)==0)
+			return -two54/(x-x);		/* log(+-0)=-inf */
+
+		if (hx<0) return (x-x)/(x-x);	/* log(-#) = NaN */
+
+		k -= 54; x *= two54; /* subnormal number, scale up x */
+		hx = __HI(x);
+	}
+
+	if (hx >= 0x7ff00000) return x+x;
+	k += (hx>>20)-1023;
+	hx &= 0x000fffff;
+	i = (hx+0x95f64)&0x100000;
+	__setHigh(&x,hx|(i^0x3ff00000));	/* normalize x or x/2 */
+	k += (i>>20);
+	dk = (double) k;
+	f = x-1.0;
+
+	if((0x000fffff&(2+hx))<3)
+	{	/* |f| < 2**-20 */
+		if(f==zero) return dk;
+		R = f*f*(0.5-0.33333333333333333*f);
+		return dk-(R-f)/ln2;
+	}
+
+	s = f/(2.0+f);
+	z = s*s;
+	i = hx-0x6147a;
+	w = z*z;
+	j = 0x6b851-hx;
+	t1= w*(Lg2+w*(Lg4+w*Lg6));
+	t2= z*(Lg1+w*(Lg3+w*(Lg5+w*Lg7)));
+	i |= j;
+	R = t2+t1;
+	if(i>0)
+	{
+		hfsq=0.5*f*f;
+		return dk-((hfsq-(s*(hfsq+R)))-f)/ln2;
+	}
+	else
+	{
+		return dk-((s*(f-R))-f)/ln2;
+	}
+}
+
 
 
-- 
2.7.4