From 43705eb7fef0bb994d0770e8e246c3c1cd39a2cd Mon Sep 17 00:00:00 2001 From: vangyzen Date: Mon, 26 Oct 2015 16:21:56 +0000 Subject: [PATCH] Disable SSE in libthr Clang emits SSE instructions on amd64 in the common path of pthread_mutex_unlock. If the thread does not otherwise use SSE, this usage incurs a context-switch of the FPU/SSE state, which reduces the performance of multiple real-world applications by a non-trivial amount (3-5% in one application). Instead of this change, I experimented with eagerly switching the FPU state at context-switch time. This did not help. Most of the cost seems to be in the read/write of memory--as kib@ stated--and not in the #NM handling. I tested on machines with and without XSAVEOPT. One counter-argument to this change is that most applications already use SIMD, and the number of applications and amount of SIMD usage are only increasing. This is absolutely true. I agree that--in general and in principle--this change is in the wrong direction. However, there are applications that do not use enough SSE to offset the extra context-switch cost. SSE does not provide a clear benefit in the current libthr code with the current compiler, but it does provide a clear loss in some cases. Therefore, disabling SSE in libthr is a non-loss for most, and a gain for some. I refrained from disabling SSE in libc--as was suggested--because I can't make the above argument for libc. It provides a wide variety of code; each case should be analyzed separately. https://lists.freebsd.org/pipermail/freebsd-current/2015-March/055193.html Suggestions from: dim, jmg, rpaulo Sponsored by: Dell Inc. git-svn-id: svn://svn.freebsd.org/base/stable/10@290014 ccf9f872-aa2e-dd11-9fc8-001c23d0bc1f --- lib/libthr/arch/amd64/Makefile.inc | 6 ++++++ lib/libthr/arch/i386/Makefile.inc | 6 ++++++ libexec/rtld-elf/amd64/Makefile.inc | 2 +- libexec/rtld-elf/i386/Makefile.inc | 2 +- share/mk/bsd.cpu.mk | 21 +++++++++++++++++++++ 5 files changed, 35 insertions(+), 2 deletions(-) diff --git a/lib/libthr/arch/amd64/Makefile.inc b/lib/libthr/arch/amd64/Makefile.inc index e6d99ec0f..0ae764c32 100644 --- a/lib/libthr/arch/amd64/Makefile.inc +++ b/lib/libthr/arch/amd64/Makefile.inc @@ -1,3 +1,9 @@ #$FreeBSD$ SRCS+= pthread_md.c _umtx_op_err.S + +# With the current compiler and libthr code, using SSE in libthr +# does not provide enough performance improvement to outweigh +# the extra context switch cost. This can measurably impact +# performance when the application also does not use enough SSE. +CFLAGS+=${CFLAGS_NO_SIMD} diff --git a/lib/libthr/arch/i386/Makefile.inc b/lib/libthr/arch/i386/Makefile.inc index 01290d5dd..81fb6bb4a 100644 --- a/lib/libthr/arch/i386/Makefile.inc +++ b/lib/libthr/arch/i386/Makefile.inc @@ -1,3 +1,9 @@ # $FreeBSD$ SRCS+= pthread_md.c _umtx_op_err.S + +# With the current compiler and libthr code, using SSE in libthr +# does not provide enough performance improvement to outweigh +# the extra context switch cost. This can measurably impact +# performance when the application also does not use enough SSE. +CFLAGS+=${CFLAGS_NO_SIMD} diff --git a/libexec/rtld-elf/amd64/Makefile.inc b/libexec/rtld-elf/amd64/Makefile.inc index 7528dbe1e..a09db6f60 100644 --- a/libexec/rtld-elf/amd64/Makefile.inc +++ b/libexec/rtld-elf/amd64/Makefile.inc @@ -1,6 +1,6 @@ # $FreeBSD$ -CFLAGS+= -mno-mmx -mno-3dnow -mno-sse -mno-sse2 -mno-sse3 -msoft-float +CFLAGS+= ${CFLAGS_NO_SIMD} -msoft-float # Uncomment this to build the dynamic linker as an executable instead # of a shared library: #LDSCRIPT= ${.CURDIR}/${MACHINE_CPUARCH}/elf_rtld.x diff --git a/libexec/rtld-elf/i386/Makefile.inc b/libexec/rtld-elf/i386/Makefile.inc index 7528dbe1e..a09db6f60 100644 --- a/libexec/rtld-elf/i386/Makefile.inc +++ b/libexec/rtld-elf/i386/Makefile.inc @@ -1,6 +1,6 @@ # $FreeBSD$ -CFLAGS+= -mno-mmx -mno-3dnow -mno-sse -mno-sse2 -mno-sse3 -msoft-float +CFLAGS+= ${CFLAGS_NO_SIMD} -msoft-float # Uncomment this to build the dynamic linker as an executable instead # of a shared library: #LDSCRIPT= ${.CURDIR}/${MACHINE_CPUARCH}/elf_rtld.x diff --git a/share/mk/bsd.cpu.mk b/share/mk/bsd.cpu.mk index 5453bd4b3..f0da4aeb8 100644 --- a/share/mk/bsd.cpu.mk +++ b/share/mk/bsd.cpu.mk @@ -267,6 +267,27 @@ _CPUCFLAGS += -mfloat-abi=softfp CFLAGS += ${_CPUCFLAGS} .endif +# +# Prohibit the compiler from emitting SIMD instructions. +# These flags are added to CFLAGS in areas where the extra context-switch +# cost outweighs the advantages of SIMD instructions. +# +# gcc: +# Setting -mno-mmx implies -mno-3dnow +# Setting -mno-sse implies -mno-sse2, -mno-sse3, -mno-ssse3 and -mfpmath=387 +# +# clang: +# Setting -mno-mmx implies -mno-3dnow and -mno-3dnowa +# Setting -mno-sse implies -mno-sse2, -mno-sse3, -mno-ssse3, -mno-sse41 and +# -mno-sse42 +# (-mfpmath= is not supported) +# +.if ${MACHINE_CPUARCH} == "i386" || ${MACHINE_CPUARCH} == "amd64" +CFLAGS_NO_SIMD.clang= -mno-avx +CFLAGS_NO_SIMD= -mno-mmx -mno-sse +.endif +CFLAGS_NO_SIMD += ${CFLAGS_NO_SIMD.${COMPILER_TYPE}} + # Add in any architecture-specific CFLAGS. # These come from make.conf or the command line or the environment. CFLAGS += ${CFLAGS.${MACHINE_ARCH}} -- 2.42.0