From 809556e60a3359f646946879dd94c4760e5b8e84 Mon Sep 17 00:00:00 2001
From: Rich Felker <dalias@aerifal.cx>
Date: Thu, 15 Mar 2012 01:29:03 -0400
Subject: [PATCH] correctly rounded sqrt() asm for x86 (i387)

the fsqrt opcode is correctly rounded, but only in the fpu's selected
precision mode, which is 80-bit extended precision. to get a correctly
rounded double precision output, we check for the only corner cases
where two-step rounding could give different results than one-step
(extended-precision mantissa ending in 0x400) and adjust the mantissa
slightly in the opposite direction of the rounding which the fpu
already did (reported in the c1 flag of the fpu status word).

this should have near-zero cost in the non-corner cases and at worst
very low cost.

note that in order for sqrt() to get used when compiling with gcc, the
broken, non-conformant builtin sqrt must be disabled.
---
 src/math/i386/sqrt.s | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/src/math/i386/sqrt.s b/src/math/i386/sqrt.s
index c6e55303..8289d094 100644
--- a/src/math/i386/sqrt.s
+++ b/src/math/i386/sqrt.s
@@ -2,4 +2,20 @@
 .type sqrt,@function
 sqrt:	fldl 4(%esp)
 	fsqrt
+	fstsw %ax
+	sub $12,%esp
+	fld %st(0)
+	fstpt (%esp)
+	mov (%esp),%ecx
+	and $0x7ff,%ecx
+	cmp $0x400,%ecx
+	jnz 1f
+	and $0x200,%eax
+	sub $0x100,%eax
+	sub %eax,(%esp)
+	fstp %st(0)
+	fldt (%esp)
+1:	add $12,%esp
+	fstpl 4(%esp)
+	fldl 4(%esp)
 	ret
-- 
2.25.1