public inbox for libc-hacker@sourceware.org
 help / color / mirror / Atom feed
* [PATCH] Fix i386/x86_64 log{,10,2,1p}{,f,l}
@ 2007-03-15 17:15 Jakub Jelinek
  0 siblings, 0 replies; only message in thread
From: Jakub Jelinek @ 2007-03-15 17:15 UTC (permalink / raw)
  To: Ulrich Drepper; +Cc: Glibc hackers

Hi!

As the added tests show, we had some issues in hand written log* assembly:
1) logl(NAN) on x86_64 and log{,f,l}(NAN) on i386 raised FE_INVALID, while
   it shouldn't, at least neither Domain nor Pole error is documented for
   x is NaN case in
   http://www.opengroup.org/onlinepubs/009695399/functions/logl.html
2) log{2,10}l(-HUGE_VALL) on x86_64 didn't raise FE_INVALID, while it
   was supposed to (Domain error is documented for that the same as
   it is for negative finite arguments)
3) log1pl(-HUGE_VALL) returned -HUGE_VALL instead of NAN and didn't
   raise FE_INVALID on x86_64

2) and 3) were caused by broken conversion from sahf: the original
i386 code did: sahf; jc 3f; 4: ... 3: jp 4b; (wanted to execute
code after jp only for NaN (i.e. (%ah & 0x45) == 1) and code at
4: for other cases.  This was converted to
andb $1, %ah; jnz 3f; 4: ... 3: jp 4b; but of course jp never
branched, because the result of andb was always 1.  This can be
either done as in the patch below
(testb $1, %ah; jnz 3f; 4: ... 3: testb $4, %ah; jnz 4b;)
or perhaps could be done as shorter (but more insns in the common
case) andb $0x45, %ah; cmpb $1, %ah; jz 3f; 4: ... 3:

2007-03-15  Jakub Jelinek  <jakub@redhat.com>

	[BZ #3919]
	* math/libm-test.inc (log_test): Test -Inf and NaN.
	(log10_test, log1p_test, log2_test): Test -Inf.
	* sysdeps/i386/fpu/e_log.S (__ieee754_log): Don't raise
	FE_INVALID when argument is qNaN.
	* sysdeps/i386/fpu/e_logl.S (__ieee754_logl): Likewise.
	* sysdeps/i386/fpu/e_logf.S (__ieee754_logf): Likewise.
	* sysdeps/x86_64/fpu/e_logl.S (__ieee754_logl): Likewise.
	* sysdeps/x86_64/fpu/e_log10l.S (__ieee754_log10l): Replace
	andb $1, %ah with testb $1, %ah, don't test for parity, instead
	testb $4, %ah and jump if non-zero.
	* sysdeps/x86_64/fpu/e_log2l.S (__ieee754_log2l): Likewise.
	* sysdeps/x86_64/fpu/s_log1pl.S (__log1pl): Likewise.

--- libc/math/libm-test.inc.jj	2007-03-13 17:42:15.000000000 +0100
+++ libc/math/libm-test.inc	2007-03-15 16:14:28.000000000 +0100
@@ -4127,7 +4127,9 @@ log_test (void)
   TEST_f_f (log, 1, 0);
 
   TEST_f_f (log, -1, nan_value, INVALID_EXCEPTION);
+  TEST_f_f (log, minus_infty, nan_value, INVALID_EXCEPTION);
   TEST_f_f (log, plus_infty, plus_infty);
+  TEST_f_f (log, nan_value, nan_value);
 
   TEST_f_f (log, M_El, 1);
   TEST_f_f (log, 1.0 / M_El, -1);
@@ -4157,6 +4159,7 @@ log10_test (void)
 
   /* log10 (x) == NaN plus invalid exception if x < 0.  */
   TEST_f_f (log10, -1, nan_value, INVALID_EXCEPTION);
+  TEST_f_f (log10, minus_infty, nan_value, INVALID_EXCEPTION);
 
   TEST_f_f (log10, plus_infty, plus_infty);
   TEST_f_f (log10, nan_value, nan_value);
@@ -4188,6 +4191,7 @@ log1p_test (void)
 
   TEST_f_f (log1p, -1, minus_infty, DIVIDE_BY_ZERO_EXCEPTION);
   TEST_f_f (log1p, -2, nan_value, INVALID_EXCEPTION);
+  TEST_f_f (log1p, minus_infty, nan_value, INVALID_EXCEPTION);
 
   TEST_f_f (log1p, plus_infty, plus_infty);
   TEST_f_f (log1p, nan_value, nan_value);
@@ -4218,6 +4222,7 @@ log2_test (void)
   TEST_f_f (log2, 1, 0);
 
   TEST_f_f (log2, -1, nan_value, INVALID_EXCEPTION);
+  TEST_f_f (log2, minus_infty, nan_value, INVALID_EXCEPTION);
 
   TEST_f_f (log2, plus_infty, plus_infty);
   TEST_f_f (log2, nan_value, nan_value);
--- libc/sysdeps/i386/fpu/e_log.S.jj	2005-05-04 19:45:15.000000000 +0200
+++ libc/sysdeps/i386/fpu/e_log.S	2007-03-15 17:57:18.000000000 +0100
@@ -36,11 +36,15 @@ limit:	.double 0.29
 ENTRY(__ieee754_log)
 	fldln2			// log(2)
 	fldl	4(%esp)		// x : log(2)
+	fxam
+	fnstsw
 #ifdef PIC
 	LOAD_PIC_REG (dx)
 #endif
 	fld	%st		// x : x : log(2)
-	fsubl	MO(one)		// x-1 : x : log(2)
+	sahf
+	jc	3f		// in case x is NaN or +-Inf
+4:	fsubl	MO(one)		// x-1 : x : log(2)
 	fld	%st		// x-1 : x-1 : x : log(2)
 	fabs			// |x-1| : x-1 : x : log(2)
 	fcompl	MO(limit)	// x-1 : x : log(2)
@@ -54,4 +58,9 @@ ENTRY(__ieee754_log)
 2:	fstp	%st(0)		// x : log(2)
 	fyl2x			// log(x)
 	ret
+
+3:	jp	4b		// in case x is +-Inf
+	fstp	%st(1)
+	fstp	%st(1)
+	ret
 END (__ieee754_log)
--- libc/sysdeps/i386/fpu/e_logf.S.jj	2005-05-04 19:45:15.000000000 +0200
+++ libc/sysdeps/i386/fpu/e_logf.S	2007-03-15 17:56:15.000000000 +0100
@@ -37,11 +37,15 @@ limit:	.double 0.29
 ENTRY(__ieee754_logf)
 	fldln2			// log(2)
 	flds	4(%esp)		// x : log(2)
+	fxam
+	fnstsw
 #ifdef PIC
 	LOAD_PIC_REG (dx)
 #endif
 	fld	%st		// x : x : log(2)
-	fsubl	MO(one)		// x-1 : x : log(2)
+	sahf
+	jc	3f		// in case x is NaN or +-Inf
+4:	fsubl	MO(one)		// x-1 : x : log(2)
 	fld	%st		// x-1 : x-1 : x : log(2)
 	fabs			// |x-1| : x-1 : x : log(2)
 	fcompl	MO(limit)	// x-1 : x : log(2)
@@ -55,4 +59,9 @@ ENTRY(__ieee754_logf)
 2:	fstp	%st(0)		// x : log(2)
 	fyl2x			// log(x)
 	ret
+
+3:	jp	4b		// in case x is +-Inf
+	fstp	%st(1)
+	fstp	%st(1)
+	ret
 END (__ieee754_logf)
--- libc/sysdeps/i386/fpu/e_logl.S.jj	2005-05-04 19:45:15.000000000 +0200
+++ libc/sysdeps/i386/fpu/e_logl.S	2007-03-15 17:54:29.000000000 +0100
@@ -37,11 +37,15 @@ limit:	.double 0.29
 ENTRY(__ieee754_logl)
 	fldln2			// log(2)
 	fldt	4(%esp)		// x : log(2)
+	fxam
+	fnstsw
 #ifdef PIC
 	LOAD_PIC_REG (dx)
 #endif
 	fld	%st		// x : x : log(2)
-	fsubl	MO(one)		// x-1 : x : log(2)
+	sahf
+	jc	3f		// in case x is NaN or +-Inf
+4:	fsubl	MO(one)		// x-1 : x : log(2)
 	fld	%st		// x-1 : x-1 : x : log(2)
 	fabs			// |x-1| : x-1 : x : log(2)
 	fcompl	MO(limit)	// x-1 : x : log(2)
@@ -55,4 +59,9 @@ ENTRY(__ieee754_logl)
 2:	fstp	%st(0)		// x : log(2)
 	fyl2x			// log(x)
 	ret
+
+3:	jp	4b		// in case x is +-Inf
+	fstp	%st(1)
+	fstp	%st(1)
+	ret
 END (__ieee754_logl)
--- libc/sysdeps/x86_64/fpu/s_log1pl.S.jj	2001-09-19 12:24:08.000000000 +0200
+++ libc/sysdeps/x86_64/fpu/s_log1pl.S	2007-03-15 17:47:56.000000000 +0100
@@ -45,7 +45,7 @@ ENTRY(__log1pl)
 	fxam
 	fnstsw
 	fld	%st
-	andb	$1,%ah
+	testb	$1, %ah
 	jnz	3f		// in case x is NaN or ±Inf
 4:
 	fabs
@@ -62,7 +62,8 @@ ENTRY(__log1pl)
 2:	fyl2xp1
 	ret
 
-3:	jp	4b		// in case x is ±Inf
+3:	testb	$4, %ah
+	jnz	4b		// in case x is ±Inf
 	fstp	%st(1)
 	fstp	%st(1)
 	ret
--- libc/sysdeps/x86_64/fpu/e_log10l.S.jj	2001-09-19 12:24:08.000000000 +0200
+++ libc/sysdeps/x86_64/fpu/e_log10l.S	2007-03-15 17:46:02.000000000 +0100
@@ -42,7 +42,7 @@ ENTRY(__ieee754_log10l)
 	fxam
 	fnstsw
 	fld	%st		// x : x : log10(2)
-	andb	$1,%ah
+	testb	$1, %ah
 	jnz	3f		// in case x is NaN or ±Inf
 4:	fsubl	MO(one)		// x-1 : x : log10(2)
 	fld	%st		// x-1 : x-1 : x : log10(2)
@@ -59,7 +59,8 @@ ENTRY(__ieee754_log10l)
 	fyl2x			// log10(x)
 	ret
 
-3:	jp	4b		// in case x is ±Inf
+3:	testb	$4, %ah
+	jnz	4b		// in case x is ±Inf
 	fstp	%st(1)
 	fstp	%st(1)
 	ret
--- libc/sysdeps/x86_64/fpu/e_log2l.S.jj	2001-09-19 12:24:08.000000000 +0200
+++ libc/sysdeps/x86_64/fpu/e_log2l.S	2007-03-15 17:45:27.000000000 +0100
@@ -39,7 +39,7 @@ ENTRY(__ieee754_log2l)
 	fxam
 	fnstsw
 	fld	%st		// x : x : 1
-	andb	$1,%ah
+	testb	$1, %ah
 	jnz	3f		// in case x is NaN or ±Inf
 4:	fsub	%st(2), %st	// x-1 : x : 1
 	fld	%st		// x-1 : x-1 : x : 1
@@ -56,7 +56,8 @@ ENTRY(__ieee754_log2l)
 	fyl2x			// log(x)
 	ret
 
-3:	jp	4b		// in case x is ±Inf
+3:	testb	$4, %ah
+	jnz	4b		// in case x is ±Inf
 	fstp	%st(1)
 	fstp	%st(1)
 	ret
--- libc/sysdeps/x86_64/fpu/e_logl.S.jj	2001-09-19 12:24:08.000000000 +0200
+++ libc/sysdeps/x86_64/fpu/e_logl.S	2007-03-15 17:46:16.000000000 +0100
@@ -38,8 +38,12 @@ limit:	.double 0.29
 ENTRY(__ieee754_logl)
 	fldln2			// log(2)
 	fldt	8(%rsp)		// x : log(2)
+	fxam
+	fnstsw
 	fld	%st		// x : x : log(2)
-	fsubl	MO(one)		// x-1 : x : log(2)
+	testb	$1, %ah
+	jnz	3f		// in case x is NaN or +-Inf
+4:	fsubl	MO(one)		// x-1 : x : log(2)
 	fld	%st		// x-1 : x-1 : x : log(2)
 	fabs			// |x-1| : x-1 : x : log(2)
 	fcompl	MO(limit)	// x-1 : x : log(2)
@@ -53,4 +57,10 @@ ENTRY(__ieee754_logl)
 2:	fstp	%st(0)		// x : log(2)
 	fyl2x			// log(x)
 	ret
+
+3:	testb	$4, %ah
+	jnz	4b		// in case x is +-Inf
+	fstp	%st(1)
+	fstp	%st(1)
+	ret
 END (__ieee754_logl)

	Jakub

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2007-03-15 17:15 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2007-03-15 17:15 [PATCH] Fix i386/x86_64 log{,10,2,1p}{,f,l} Jakub Jelinek

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).