about summary refs log tree commit diff
path: root/sysdeps/i386/fpu
diff options
context:
space:
mode:
authorH.J. Lu <hjl.tools@gmail.com>2017-10-22 07:58:54 -0700
committerH.J. Lu <hjl.tools@gmail.com>2017-10-22 08:00:18 -0700
commit7eda65f69e0e4533b76ca4614fe516de03fe2b3a (patch)
tree0b81497d81ea5be20c8a130f92c62f245a4e2089 /sysdeps/i386/fpu
parent5d15c9697577d2c342b5ade820bfd7b84a736b23 (diff)
downloadglibc-7eda65f69e0e4533b76ca4614fe516de03fe2b3a.tar.gz
glibc-7eda65f69e0e4533b76ca4614fe516de03fe2b3a.tar.xz
glibc-7eda65f69e0e4533b76ca4614fe516de03fe2b3a.zip
i386: Replace assembly versions of e_exp2f with generic e_exp2f.c
This patch replaces i386 assembly versions of e_exp2f with generic
e_exp2f.c.  For workload-spec2017.wrf, on Nehalem, it improves
performance by:

                           Before            After     Improvement
reciprocal-throughput      112.996          40.0454       182%
latency                    126.581          54.4479       132%

On Skylake, it improves performance by:

                           Before            After     Improvement
reciprocal-throughput      113.14           39.447        186%
latency                    136.068          55.684        144%

On IvyBridge with --disable-multi-arch, it improves performance by:

                           Before            After     Improvement
reciprocal-throughput      132.521          40.3759       228%
latency                    145.791          58.4587       149%

	* sysdeps/i386/fpu/e_exp2f.S: Removed.
	* sysdeps/i386/fpu/w_exp2f.c: Likewise.
	* sysdeps/i386/fpu/libm-test-ulps: Updated for generic e_exp2f.c.
	* sysdeps/i386/i686/fpu/multiarch/libm-test-ulps: Likewise.
	* sysdeps/i386/i686/fpu/multiarch/Makefile (libm-sysdep_routines):
	Add e_exp2f-sse2.
	(CFLAGS-e_exp2f-sse2.c): New.
	* sysdeps/i386/i686/fpu/multiarch/e_exp2f-sse2.c: New file.
	* sysdeps/i386/i686/fpu/multiarch/e_exp2f.c: Likewise.
Diffstat (limited to 'sysdeps/i386/fpu')
-rw-r--r--sysdeps/i386/fpu/e_exp2f.S52
-rw-r--r--sysdeps/i386/fpu/libm-test-ulps2
-rw-r--r--sysdeps/i386/fpu/w_exp2f.c1
3 files changed, 2 insertions, 53 deletions
diff --git a/sysdeps/i386/fpu/e_exp2f.S b/sysdeps/i386/fpu/e_exp2f.S
deleted file mode 100644
index 30623cd850..0000000000
--- a/sysdeps/i386/fpu/e_exp2f.S
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Written by J.T. Conklin <jtc@netbsd.org>.
- * Adapted for exp2 by Ulrich Drepper <drepper@cygnus.com>.
- * Public domain.
- */
-
-#include <machine/asm.h>
-#include <i386-math-asm.h>
-
-DEFINE_FLT_MIN
-
-#ifdef PIC
-# define MO(op) op##@GOTOFF(%ecx)
-#else
-# define MO(op) op
-#endif
-
-	.text
-ENTRY(__ieee754_exp2f)
-#ifdef  PIC
-	LOAD_PIC_REG (cx)
-#endif
-	flds	4(%esp)
-/* I added the following ugly construct because exp(+-Inf) resulted
-   in NaN.  The ugliness results from the bright minds at Intel.
-   For the i686 the code can be written better.
-   -- drepper@cygnus.com.  */
-	fxam				/* Is NaN or +-Inf?  */
-	fstsw	%ax
-	movb	$0x45, %dh
-	andb	%ah, %dh
-	cmpb	$0x05, %dh
-	je	1f			/* Is +-Inf, jump.  */
-	fld	%st
-	frndint				/* int(x) */
-	fsubr	%st,%st(1)		/* fract(x) */
-	fxch
-	f2xm1				/* 2^(fract(x)) - 1 */
-	fld1
-	faddp				/* 2^(fract(x)) */
-	fscale				/* e^x */
-	fstp	%st(1)
-	FLT_NARROW_EVAL_UFLOW_NONNEG_NAN
-	ret
-
-1:	testl	$0x200, %eax		/* Test sign.  */
-	jz	2f			/* If positive, jump.  */
-	fstp	%st
-	fldz				/* Set result to 0.  */
-2:	ret
-END (__ieee754_exp2f)
-strong_alias (__ieee754_exp2f, __exp2f_finite)
diff --git a/sysdeps/i386/fpu/libm-test-ulps b/sysdeps/i386/fpu/libm-test-ulps
index c826b29c2c..0aa18ea9b7 100644
--- a/sysdeps/i386/fpu/libm-test-ulps
+++ b/sysdeps/i386/fpu/libm-test-ulps
@@ -1921,7 +1921,9 @@ ildouble: 1
 ldouble: 1
 
 Function: "exp2_upward":
+float: 1
 float128: 2
+ifloat: 1
 ifloat128: 2
 ildouble: 1
 ldouble: 1
diff --git a/sysdeps/i386/fpu/w_exp2f.c b/sysdeps/i386/fpu/w_exp2f.c
deleted file mode 100644
index 583065d12a..0000000000
--- a/sysdeps/i386/fpu/w_exp2f.c
+++ /dev/null
@@ -1 +0,0 @@
-#include <sysdeps/../math/w_exp2f.c>