assembly optimizations for fmod/remainder functions

src/math/i386/fmod.s

+.global fmod
+.type fmod,@function
+fmod:
+	fldl 12(%esp)
+	fldl 4(%esp)
+1:	fprem
+	fstsw %ax
+	sahf
+	jp 1b
+	fstp %st(1)
+	ret

src/math/i386/fmodf.s

+.global fmodf
+.type fmodf,@function
+fmodf:
+	flds 8(%esp)
+	flds 4(%esp)
+1:	fprem
+	fstsw %ax
+	sahf
+	jp 1b
+	fstp %st(1)
+	ret

src/math/i386/fmodl.s

+.global fmodl
+.type fmodl,@function
+fmodl:
+	fldt 16(%esp)
+	fldt 4(%esp)
+1:	fprem
+	fstsw %ax
+	sahf
+	jp 1b
+	fstp %st(1)
+	ret

src/math/i386/remainder.s

+.global remainder
+.type remainder,@function
+remainder:
+	fldl 12(%esp)
+	fldl 4(%esp)
+1:	fprem1
+	fstsw %ax
+	sahf
+	jp 1b
+	fstp %st(1)
+	ret

src/math/i386/remainderf.s

+.global remainderf
+.type remainderf,@function
+remainderf:
+	flds 8(%esp)
+	flds 4(%esp)
+1:	fprem1
+	fstsw %ax
+	sahf
+	jp 1b
+	fstp %st(1)
+	ret

src/math/i386/remainderl.s

+.global remainderl
+.type remainderl,@function
+remainderl:
+	fldt 16(%esp)
+	fldt 4(%esp)
+1:	fprem1
+	fstsw %ax
+	sahf
+	jp 1b
+	fstp %st(1)
+	ret

src/math/x86_64/fmodl.s

+.global fmodl
+.type fmodl,@function
+fmodl:
+	fldt 24(%rsp)
+	fldt 8(%rsp)
+1:	fprem
+	fstsw %ax
+	sahf
+	jp 1b
+	fstp %st(1)
+	ret

src/math/x86_64/remainderl.s

+.global remainderl
+.type remainderl,@function
+remainderl:
+	fldt 24(%rsp)
+	fldt 8(%rsp)
+1:	fprem1
+	fstsw %ax
+	sahf
+	jp 1b
+	fstp %st(1)
+	ret