about summary refs log tree commit diff
path: root/sysdeps/i386/i686
diff options
context:
space:
mode:
authorJoseph Myers <joseph@codesourcery.com>2015-09-18 21:53:22 +0000
committerJoseph Myers <joseph@codesourcery.com>2015-09-18 21:53:22 +0000
commit6f0f237bf5a3c8d29a6342cbf8b4c17b10aa1d4c (patch)
tree1e25a1ec02189868aea10af3ae026ffd3f15a545 /sysdeps/i386/i686
parent1344384b52829a4dcde51ec3a307c4b3d6a713fa (diff)
downloadglibc-6f0f237bf5a3c8d29a6342cbf8b4c17b10aa1d4c.tar.gz
glibc-6f0f237bf5a3c8d29a6342cbf8b4c17b10aa1d4c.tar.xz
glibc-6f0f237bf5a3c8d29a6342cbf8b4c17b10aa1d4c.zip
Avoid excess range in results from i386 exp, hypot, pow functions (bug 18980).
i386 exp, hypot and pow functions can return overflowing and
underflowing values with excess range and precision; ; Wilco
Dijkstra's patches to make isfinite etc. expand inline cause this
pre-existing issue to result in test failures.

This patch fixes those functions to avoid excess range and precision
in their return values.  Appropriate macros are added for the repeated
code sequences; in future I'll add more such macros and refactor
existing code forcing underflow (with or without also eliminating
excess range and precision from the return value) to use such macros.

Tested for x86.  If, after this patch, you still see x86 libm test
failures with excess range or precision, please file bugs in Bugzilla.

	[BZ #18980]
	* sysdeps/i386/fpu/i386-math-asm.h (DEFINE_FLT_MIN): New macro.
	(DEFINE_DBL_MIN): Likewise.
	(FLT_NARROW_EVAL_UFLOW_NONNEG_NAN): Likewise.
	(DBL_NARROW_EVAL_UFLOW_NONNEG_NAN): Likewise.
	(FLT_NARROW_EVAL_UFLOW_NONNEG): Likewise.
	(DBL_NARROW_EVAL_UFLOW_NONNEG): Likewise.
	* sysdeps/i386/fpu/e_exp.S: Include <i386-math-asm.h>.
	(dbl_min): Replace with use of DEFINE_DBL_MIN.
	(__ieee754_exp): Use DBL_NARROW_EVAL_UFLOW_NONNEG_NAN.
	(__exp_finite): Use DBL_NARROW_EVAL_UFLOW_NONNEG.
	* sysdeps/i386/fpu/e_exp10.S: Include <i386-math-asm.h>.
	(dbl_min): Replace with use of DEFINE_DBL_MIN.
	(__ieee754_exp10): Use DBL_NARROW_EVAL_UFLOW_NONNEG_NAN.
	* sysdeps/i386/fpu/e_exp10f.S: Include <i386-math-asm.h>.
	(flt_min): Replace with use of DEFINE_FLT_MIN.
	(__ieee754_exp10f): Use FLT_NARROW_EVAL_UFLOW_NONNEG_NAN.
	* sysdeps/i386/fpu/e_exp2.S: Include <i386-math-asm.h>.
	(dbl_min): Replace with use of DEFINE_DBL_MIN.
	(__ieee754_exp2): Use DBL_NARROW_EVAL_UFLOW_NONNEG_NAN.
	* sysdeps/i386/fpu/e_exp2f.S: Include <i386-math-asm.h>.
	(flt_min): Replace with use of DEFINE_FLT_MIN.
	(__ieee754_exp2f): Use FLT_NARROW_EVAL_UFLOW_NONNEG_NAN.
	* sysdeps/i386/fpu/e_expf.S: Include <i386-math-asm.h>.
	(flt_min): Replace with use of DEFINE_FLT_MIN.
	(__ieee754_expf): Use FLT_NARROW_EVAL_UFLOW_NONNEG_NAN.
	(__expf_finite): Use FLT_NARROW_EVAL_UFLOW_NONNEG.
	* sysdeps/i386/fpu/e_hypot.S: Include <i386-math-asm.h>.
	(__ieee754_hypot): Use DBL_NARROW_EVAL.
	* sysdeps/i386/fpu/e_hypotf.S: Include <i386-math-asm.h>.
	(__ieee754_hypotf): Use FLT_NARROW_EVAL.
	* sysdeps/i386/fpu/e_pow.S: Include <i386-math-asm.h>.
	(__ieee754_pow): Use DBL_NARROW_EVAL.
	* sysdeps/i386/fpu/e_powf.S: Include <i386-math-asm.h>.
	(__ieee754_powf): Use FLT_NARROW_EVAL.
	* sysdeps/i386/i686/fpu/multiarch/e_expf-sse2.S
	(__ieee754_expf_sse2): Convert double-precision result to single
	precision.
	* sysdeps/i386/fpu/libm-test-ulps: Update.
Diffstat (limited to 'sysdeps/i386/i686')
-rw-r--r--sysdeps/i386/i686/fpu/multiarch/e_expf-sse2.S9
1 files changed, 5 insertions, 4 deletions
diff --git a/sysdeps/i386/i686/fpu/multiarch/e_expf-sse2.S b/sysdeps/i386/i686/fpu/multiarch/e_expf-sse2.S
index be3b145e0f..2e2359508b 100644
--- a/sysdeps/i386/i686/fpu/multiarch/e_expf-sse2.S
+++ b/sysdeps/i386/i686/fpu/multiarch/e_expf-sse2.S
@@ -113,11 +113,12 @@ ENTRY(__ieee754_expf_sse2)
 	mulsd	MO2(DP_T,%eax,8), %xmm0	/* DP P(y)*T[j] */
 	addsd	MO2(DP_T,%eax,8), %xmm0	/* DP T[j]*(P(y)+1) */
 	mulsd	%xmm1, %xmm0		/* DP result=2^n*(T[j]*(P(y)+1)) */
+	cvtsd2ss	%xmm0, %xmm1
 
-	lea	-8(%esp), %esp		/* Borrow 8 bytes of stack frame */
-	movsd	%xmm0, 0(%esp)		/* Move result from sse... */
-	fldl	0(%esp)			/* ...to FPU. */
-	lea	8(%esp), %esp		/* Return back 8 bytes of stack frame */
+	lea	-4(%esp), %esp		/* Borrow 4 bytes of stack frame */
+	movss	%xmm1, 0(%esp)		/* Move result from sse... */
+	flds	0(%esp)			/* ...to FPU. */
+	lea	4(%esp), %esp		/* Return back 4 bytes of stack frame */
 	ret
 
 	.p2align	4