xtensa: add HW FPU sequences for DIV/SQRT/RECIP/RSQRT

Use new FPU instruction sequences documented in the ISA book to
implement __divsf3, __divdf3, __recipsf2, __recipdf2, __rsqrtsf2,
__rsqrtdf2 and __ieee754_sqrtf and __ieee754_sqrt.

2016-10-18  Ding-Kai Chen  <dkchen@cadence.com>
libgcc/
	* config/xtensa/ieee754-df.S (__recipdf2, __rsqrtdf2,
	__ieee754_sqrt): New functions.
	(__divdf3): Add implementation with new FPU instructions under
	#if XCHAL_HAVE_DFP_DIV.
	* config/xtensa/ieee754-sf.S (__recipsf2, __rsqrtsf2,
	__ieee754_sqrtf): New functions.
	(__divsf3): Add implementation with new FPU instructions under
	#if XCHAL_HAVE_FP_DIV.
	* config/xtensa/t-xtensa (LIB1ASMFUNCS): Add _sqrtf, _recipsf2
	_rsqrtsf2, _sqrt, _recipdf2 and _rsqrtdf2.

From-SVN: r241312

4 files changed, 348 insertions, 3 deletions

diff --git a/libgcc/ChangeLog b/libgcc/ChangeLog
index c861ca6..b98f6d4 100644
--- a/libgcc/ChangeLog
+++ b/libgcc/ChangeLog
@@ -1,3 +1,16 @@
+2016-10-18  Ding-Kai Chen  <dkchen@cadence.com>
+
+	* config/xtensa/ieee754-df.S (__recipdf2, __rsqrtdf2,
+	__ieee754_sqrt): New functions.
+	(__divdf3): Add implementation with new FPU instructions under
+	#if XCHAL_HAVE_DFP_DIV.
+	* config/xtensa/ieee754-sf.S (__recipsf2, __rsqrtsf2,
+	__ieee754_sqrtf): New functions.
+	(__divsf3): Add implementation with new FPU instructions under
+	#if XCHAL_HAVE_FP_DIV.
+	* config/xtensa/t-xtensa (LIB1ASMFUNCS): Add _sqrtf, _recipsf2
+	_rsqrtsf2, _sqrt, _recipdf2 and _rsqrtdf2.
+
 2016-10-13  Thomas Preud'homme  <thomas.preudhomme@arm.com>
 
 	* libgcov-profiler.c: Replace MEMMODEL_* macros by their __ATOMIC_*
diff --git a/libgcc/config/xtensa/ieee754-df.S b/libgcc/config/xtensa/ieee754-df.S
index 1d9ef46..a2fb166 100644
--- a/libgcc/config/xtensa/ieee754-df.S
+++ b/libgcc/config/xtensa/ieee754-df.S
@@ -1217,8 +1217,58 @@ __muldf3:
 
 #ifdef L_divdf3
 
-	.literal_position
 	/* Division */
+
+#if XCHAL_HAVE_DFP_DIV
+
+        .text
+        .align 4
+        .global __divdf3
+        .type	__divdf3, @function
+__divdf3:
+	leaf_entry	sp, 16
+
+	wfrd		f1, xh, xl
+	wfrd		f2, yh, yl
+
+	div0.d		f3, f2
+	nexp01.d	f4, f2
+	const.d		f0, 1
+	maddn.d		f0, f4, f3
+	const.d		f5, 0
+	mov.d		f7, f2
+	mkdadj.d	f7, f1
+	maddn.d		f3, f0, f3
+	maddn.d		f5, f0, f0
+	nexp01.d	f1, f1
+	div0.d		f2, f2
+	maddn.d		f3, f5, f3
+	const.d		f5, 1
+	const.d		f0, 0
+	neg.d		f6, f1
+	maddn.d		f5, f4, f3
+	maddn.d		f0, f6, f2
+	maddn.d		f3, f5, f3
+	maddn.d		f6, f4, f0
+	const.d		f2, 1
+	maddn.d		f2, f4, f3
+	maddn.d		f0, f6, f3
+	neg.d		f1, f1
+	maddn.d		f3, f2, f3
+	maddn.d		f1, f4, f0
+	addexpm.d	f0, f7
+	addexp.d	f3, f7
+	divn.d		f0, f1, f3
+
+	rfr		xl, f0
+	rfrd		xh, f0
+
+	leaf_return
+
+#else
+
+	.literal_position
+
 __divdf3_aux:
 
 	/* Handle unusual cases (zeros, subnormals, NaNs and Infinities).
@@ -1537,6 +1587,8 @@ __divdf3:
 	movi	xl, 0
 	leaf_return
 
+#endif /* XCHAL_HAVE_DFP_DIV */
+
 #endif /* L_divdf3 */
 
 #ifdef L_cmpdf2
@@ -2388,3 +2440,127 @@ __extendsfdf2:
 #endif /* L_extendsfdf2 */
 
 
+#if XCHAL_HAVE_DFP_SQRT
+#ifdef L_sqrt
+
+        .text
+        .align 4
+        .global __ieee754_sqrt
+        .type	__ieee754_sqrt, @function
+__ieee754_sqrt:
+	leaf_entry	sp, 16
+
+	wfrd		f1, xh, xl
+
+	sqrt0.d		f2, f1
+	const.d		f4, 0
+	maddn.d		f4, f2, f2
+	nexp01.d	f3, f1
+	const.d		f0, 3
+	addexp.d	f3, f0
+	maddn.d		f0, f4, f3
+	nexp01.d	f4, f1
+	maddn.d		f2, f0, f2
+	const.d		f5, 0
+	maddn.d		f5, f2, f3
+	const.d		f0, 3
+	maddn.d		f0, f5, f2
+	neg.d		f6, f4
+	maddn.d		f2, f0, f2
+	const.d		f0, 0
+	const.d		f5, 0
+	const.d		f7, 0
+	maddn.d		f0, f6, f2
+	maddn.d		f5, f2, f3
+	const.d		f3, 3
+	maddn.d		f7, f3, f2
+	maddn.d		f4, f0, f0
+	maddn.d		f3, f5, f2
+	neg.d		f2, f7
+	maddn.d		f0, f4, f2
+	maddn.d		f7, f3, f7
+	mksadj.d	f2, f1
+	nexp01.d	f1, f1
+	maddn.d		f1, f0, f0
+	neg.d		f3, f7
+	addexpm.d	f0, f2
+	addexp.d	f3, f2
+	divn.d		f0, f1, f3
+
+	rfr		xl, f0
+	rfrd		xh, f0
+
+	leaf_return
+
+#endif /* L_sqrt */
+#endif /* XCHAL_HAVE_DFP_SQRT */
+
+#if XCHAL_HAVE_DFP_RECIP
+#ifdef L_recipdf2
+	/* Reciprocal */
+
+	.align	4
+	.global	__recipdf2
+	.type	__recipdf2, @function
+__recipdf2:
+	leaf_entry	sp, 16
+
+	wfrd		f1, xh, xl
+
+	recip0.d	f0, f1
+	const.d		f2, 2
+	msub.d		f2, f1, f0
+	mul.d		f3, f1, f0
+	const.d		f4, 2
+	mul.d		f5, f0, f2
+	msub.d		f4, f3, f2
+	const.d		f2, 1
+	mul.d		f0, f5, f4
+	msub.d		f2, f1, f0
+	maddn.d		f0, f0, f2
+
+	rfr		xl, f0
+	rfrd		xh, f0
+
+	leaf_return
+
+#endif /* L_recipdf2 */
+#endif /* XCHAL_HAVE_DFP_RECIP */
+
+#if XCHAL_HAVE_DFP_RSQRT
+#ifdef L_rsqrtdf2
+	/* Reciprocal square root */
+
+	.align	4
+	.global	__rsqrtdf2
+	.type	__rsqrtdf2, @function
+__rsqrtdf2:
+	leaf_entry	sp, 16
+
+	wfrd		f1, xh, xl
+
+	rsqrt0.d	f0, f1
+	mul.d		f2, f1, f0
+	const.d		f3, 3
+	mul.d		f4, f3, f0
+	const.d		f5, 1
+	msub.d		f5, f2, f0
+	maddn.d		f0, f4, f5
+	const.d		f2, 1
+	mul.d		f4, f1, f0
+	mul.d		f5, f3, f0
+	msub.d		f2, f4, f0
+	maddn.d		f0, f5, f2
+	const.d		f2, 1
+	mul.d		f1, f1, f0
+	mul.d		f3, f3, f0
+	msub.d		f2, f1, f0
+	maddn.d		f0, f3, f2
+
+	rfr		xl, f0
+	rfrd		xh, f0
+
+	leaf_return
+
+#endif /* L_rsqrtdf2 */
+#endif /* XCHAL_HAVE_DFP_RSQRT */
diff --git a/libgcc/config/xtensa/ieee754-sf.S b/libgcc/config/xtensa/ieee754-sf.S
index 7864a74..6acad59 100644
--- a/libgcc/config/xtensa/ieee754-sf.S
+++ b/libgcc/config/xtensa/ieee754-sf.S
@@ -885,8 +885,52 @@ __mulsf3:
 
 #ifdef L_divsf3
 
-	.literal_position
 	/* Division */
+
+#if XCHAL_HAVE_FP_DIV
+
+	.align	4
+	.global	__divsf3
+	.type	__divsf3, @function
+__divsf3:
+	leaf_entry	sp, 16
+
+	wfr		f1, a2	/* dividend */
+	wfr		f2, a3	/* divisor */
+
+	div0.s		f3, f2
+	nexp01.s	f4, f2
+	const.s		f5, 1
+	maddn.s		f5, f4, f3
+	mov.s		f6, f3
+	mov.s		f7, f2
+	nexp01.s	f2, f1
+	maddn.s		f6, f5, f6
+	const.s		f5, 1
+	const.s		f0, 0
+	neg.s		f8, f2
+	maddn.s		f5, f4, f6
+	maddn.s		f0, f8, f3
+	mkdadj.s	f7, f1
+	maddn.s		f6, f5, f6
+	maddn.s		f8, f4, f0
+	const.s		f3, 1
+	maddn.s		f3, f4, f6
+	maddn.s		f0, f8, f6
+	neg.s		f2, f2
+	maddn.s		f6, f3, f6
+	maddn.s		f2, f4, f0
+	addexpm.s	f0, f7
+	addexp.s	f6, f7
+	divn.s		f0, f2, f6
+
+	rfr		a2, f0
+
+	leaf_return
+
+#else
+
+	.literal_position
 __divsf3_aux:
 
 	/* Handle unusual cases (zeros, subnormals, NaNs and Infinities).
@@ -1112,6 +1156,8 @@ __divsf3:
 	slli	a2, a2, 31
 	leaf_return
 
+#endif /* XCHAL_HAVE_FP_DIV */
+
 #endif /* L_divsf3 */
 
 #ifdef L_cmpsf2
@@ -1757,3 +1803,111 @@ __floatdisf:
 	leaf_return
 
 #endif /* L_floatdisf */
+
+#if XCHAL_HAVE_FP_SQRT
+#ifdef L_sqrtf
+	/* Square root */
+
+	.align	4
+	.global	__ieee754_sqrtf
+	.type	__ieee754_sqrtf, @function
+__ieee754_sqrtf:
+	leaf_entry	sp, 16
+
+	wfr		f1, a2
+
+	sqrt0.s		f2, f1
+	const.s		f3, 0
+	maddn.s		f3, f2, f2
+	nexp01.s	f4, f1
+	const.s		f0, 3
+	addexp.s	f4, f0
+	maddn.s		f0, f3, f4
+	nexp01.s	f3, f1
+	neg.s		f5, f3
+	maddn.s		f2, f0, f2
+	const.s		f0, 0
+	const.s		f6, 0
+	const.s		f7, 0
+	maddn.s		f0, f5, f2
+	maddn.s		f6, f2, f4
+	const.s		f4, 3
+	maddn.s		f7, f4, f2
+	maddn.s		f3, f0, f0
+	maddn.s		f4, f6, f2
+	neg.s		f2, f7
+	maddn.s		f0, f3, f2
+	maddn.s		f7, f4, f7
+	mksadj.s	f2, f1
+	nexp01.s	f1, f1
+	maddn.s		f1, f0, f0
+	neg.s		f3, f7
+	addexpm.s	f0, f2
+	addexp.s	f3, f2
+	divn.s		f0, f1, f3
+
+	rfr		a2, f0
+
+	leaf_return
+
+#endif /* L_sqrtf */
+#endif /* XCHAL_HAVE_FP_SQRT */
+
+#if XCHAL_HAVE_FP_RECIP
+#ifdef L_recipsf2
+	/* Reciprocal */
+
+	.align	4
+	.global	__recipsf2
+	.type	__recipsf2, @function
+__recipsf2:
+	leaf_entry	sp, 16
+
+	wfr		f1, a2
+
+	recip0.s	f0, f1
+	const.s		f2, 1
+	msub.s		f2, f1, f0
+	maddn.s		f0, f0, f2
+	const.s		f2, 1
+	msub.s		f2, f1, f0
+	maddn.s		f0, f0, f2
+
+	rfr		a2, f0
+
+	leaf_return
+
+#endif /* L_recipsf2 */
+#endif /* XCHAL_HAVE_FP_RECIP */
+
+#if XCHAL_HAVE_FP_RSQRT
+#ifdef L_rsqrtsf2
+	/* Reciprocal square root */
+
+	.align	4
+	.global	__rsqrtsf2
+	.type	__rsqrtsf2, @function
+__rsqrtsf2:
+	leaf_entry	sp, 16
+
+	wfr		f1, a2
+
+	rsqrt0.s	f0, f1
+	mul.s		f2, f1, f0
+	const.s		f3, 3;
+	mul.s		f4, f3, f0
+	const.s		f5, 1
+	msub.s		f5, f2, f0
+	maddn.s		f0, f4, f5
+	mul.s		f2, f1, f0
+	mul.s		f1, f3, f0
+	const.s		f3, 1
+	msub.s		f3, f2, f0
+	maddn.s		f0, f1, f3
+
+	rfr		a2, f0
+
+	leaf_return
+
+#endif /* L_rsqrtsf2 */
+#endif /* XCHAL_HAVE_FP_RSQRT */
diff --git a/libgcc/config/xtensa/t-xtensa b/libgcc/config/xtensa/t-xtensa
index ed3eb84..90df5f1 100644
--- a/libgcc/config/xtensa/t-xtensa
+++ b/libgcc/config/xtensa/t-xtensa
@@ -4,10 +4,12 @@ LIB1ASMFUNCS = _mulsi3 _divsi3 _modsi3 _udivsi3 _umodsi3 \
 	_ashldi3 _ashrdi3 _lshrdi3 \
 	_negsf2 _addsubsf3 _mulsf3 _divsf3 _cmpsf2 _fixsfsi _fixsfdi \
 	_fixunssfsi _fixunssfdi _floatsisf _floatunsisf \
+	_sqrtf _recipsf2 _rsqrtsf2 \
 	_floatdisf _floatundisf \
 	_negdf2 _addsubdf3 _muldf3 _divdf3 _cmpdf2 _fixdfsi _fixdfdi \
 	_fixunsdfsi _fixunsdfdi _floatsidf _floatunsidf \
 	_floatdidf _floatundidf \
-	_truncdfsf2 _extendsfdf2
+	_truncdfsf2 _extendsfdf2 \
+	_sqrt _recipdf2 _rsqrtdf2
 
 LIB2ADD = $(srcdir)/config/xtensa/lib2funcs.S