about summary refs log tree commit diff
path: root/sysdeps/i386/i686/fpu/multiarch/Makefile
diff options
context:
space:
mode:
authorH.J. Lu <hjl.tools@gmail.com>2017-10-22 08:11:15 -0700
committerH.J. Lu <hjl.tools@gmail.com>2017-10-22 08:12:41 -0700
commit5313581cb52fd5d3d2cf222ddb6f8f86f090974f (patch)
treee2ec5d944c1089cec1de29c5c72c3fb600a8c3fb /sysdeps/i386/i686/fpu/multiarch/Makefile
parent6089a3ee24cede17e9443aef0aa72fa1a0ba1548 (diff)
downloadglibc-5313581cb52fd5d3d2cf222ddb6f8f86f090974f.tar.gz
glibc-5313581cb52fd5d3d2cf222ddb6f8f86f090974f.tar.xz
glibc-5313581cb52fd5d3d2cf222ddb6f8f86f090974f.zip
i386: Replace assembly versions of e_powf with generic e_powf.c
This patch replaces i386 assembly versions of e_powf with generic
e_powf.c.  For workload-spec2017.wrf, on Nehalem, it improves
performance by:

                           Before            After     Improvement
reciprocal-throughput      230.855          78.3358       194%
latency                    231.685          94.1259       146%

On Skylake, it improves performance by:

                           Before            After     Improvement
reciprocal-throughput      239.858          47.4713       405%
latency                    247.57           93.8798       163%

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

                           Before            After     Improvement
reciprocal-throughput      269.078          63.3758       324%
latency                    271.473          102.091       165%

	* sysdeps/i386/fpu/e_powf.S: Removed.
	* sysdeps/i386/fpu/e_powf_log2_data.c: Likewise.
	* sysdeps/i386/fpu/w_powf.c: Likewise.
	* sysdeps/i386/fpu/libm-test-ulps: Updated for generic e_powf.c.
	* sysdeps/i386/i686/fpu/multiarch/libm-test-ulps: Likewise.
	* sysdeps/i386/i686/fpu/multiarch/Makefile (libm-sysdep_routines):
	Add e_powf-sse2.
	(CFLAGS-e_powf-sse2.c): New.
	* sysdeps/i386/i686/fpu/multiarch/e_powf-sse2.c: New file.
	* sysdeps/i386/i686/fpu/multiarch/e_powf.c: Likewise.
Diffstat (limited to 'sysdeps/i386/i686/fpu/multiarch/Makefile')
-rw-r--r--sysdeps/i386/i686/fpu/multiarch/Makefile3
1 files changed, 2 insertions, 1 deletions
diff --git a/sysdeps/i386/i686/fpu/multiarch/Makefile b/sysdeps/i386/i686/fpu/multiarch/Makefile
index eee3b8b1fd..c0fa9761d3 100644
--- a/sysdeps/i386/i686/fpu/multiarch/Makefile
+++ b/sysdeps/i386/i686/fpu/multiarch/Makefile
@@ -1,9 +1,10 @@
 ifeq ($(subdir),math)
 libm-sysdep_routines += e_exp2f-sse2 e_expf-sse2 e_logf-sse2 e_log2f-sse2 \
-			s_sinf-sse2 s_cosf-sse2 s_sincosf-sse2
+			e_powf-sse2 s_sinf-sse2 s_cosf-sse2 s_sincosf-sse2
 
 CFLAGS-e_exp2f-sse2.c = -msse2 -mfpmath=sse
 CFLAGS-e_expf-sse2.c = -msse2 -mfpmath=sse
 CFLAGS-e_log2f-sse2.c = -msse2 -mfpmath=sse
 CFLAGS-e_logf-sse2.c = -msse2 -mfpmath=sse
+CFLAGS-e_powf-sse2.c = -msse2 -mfpmath=sse
 endif