Hi Cyril,
On 03/03/2016 11:06 PM, Cyril Bur wrote:
Currently it doesn't appear the resulting binary actually uses any Altivec
or VSX instructions the solution is to explicitly tell GCC to use vector
instructions and use vector types in the code.
Part of this this issue can be GCC version specific:
GCC 4.9.x is happy to use Altivec and VSX instructions if altivec.h is
includedi (and possibly if vector types are used), this also means that
4.9.x will use VSX instructions even if only -maltivec is passed. It is
also possible that Altivec instructions will be used even without -maltivec
or -mabi=altivec.
GCC 5.2.x complains about the lack of -maltivec parameter if altivec.h is
included and will not use VSX unless -mvsx is present on commandline.
GCC 5.3.0 has a regression that means __attribute__((__target__("no-vsx"))
fails to build. A fix is targeted for 5.4.
Furthermore LTO (Link Time Optimisation) doesn't play well with
__attribute__((__target__("no-vsx")), LTO can cause GCC to forget about the
attribute and compile with VSX instructions regardless. Be weary when
enabling -flfo for this test.
Signed-off-by: Cyril Bur <cyril...@gmail.com>
This patch breaks the build on my setup:
ppc-linux-gcc -std=gnu99 -O2 -Wall -Werror
-DGIT_VERSION='"v5.0-rc3-560-ge0ce62731d77"'
-I/root/linux-powerpc/tools/testing/selftests/powerpc/include -O2
-maltivec -mvsx -mabi=altivec context_switch.c ../harness.c
../utils.c -lpthread -o
/root/linux-powerpc/tools/testing/selftests/powerpc/benchmarks/context_switch
context_switch.c:1:0: error: -mvsx requires hardware floating point
[-Werror]
/*
^
cc1: all warnings being treated as errors
../harness.c:1:0: error: -mvsx requires hardware floating point [-Werror]
/*
^
cc1: all warnings being treated as errors
../utils.c:1:0: error: -mvsx requires hardware floating point [-Werror]
/*
^
cc1: all warnings being treated as errors
make[1]: ***
[/root/linux-powerpc/tools/testing/selftests/powerpc/benchmarks/context_switch]
Error 1
By removing the -mvsx option, it compiles just fine.
Is that option really required ? According to gcc doc, it is
automatically selected when compiling for cpus that support it.
I'm using:
[root@po16846vm linux-powerpc]# ppc-linux-gcc -v
Using built-in specs.
COLLECT_GCC=ppc-linux-gcc
COLLECT_LTO_WRAPPER=/opt/cldk-1.4.0/libexec/gcc/ppc-linux/5.4.0/lto-wrapper
Target: ppc-linux
Configured with: /root/cldk/gcc-5.4.0/configure --target=ppc-linux
--with-headers=yes --with-cpu=860 --prefix=/opt/cldk-1.4.0
--bindir=/opt/cldk-1.4.0/bin --sbindir=/opt/cldk-1.4.0/sbin
--libexecdir=/opt/cldk-1.4.0/libexec --datadir=/opt/cldk-1.4.0/share
--sysconfdir=/opt/cldk-1.4.0/etc --libdir=/opt/cldk-1.4.0/lib
--includedir=/opt/cldk-1.4.0/usr/include
--oldincludedir=/opt/cldk-1.4.0/usr/include
--infodir=/opt/cldk-1.4.0/share/info --mandir=/opt/cldk-1.4.0/share/man
--with-glibc-version=2.18 --enable-languages=c,c++
Thread model: posix
gcc version 5.4.0 (GCC)
Christophe
---
tools/testing/selftests/powerpc/benchmarks/Makefile | 1 +
tools/testing/selftests/powerpc/benchmarks/context_switch.c | 11 ++++++++---
2 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile
b/tools/testing/selftests/powerpc/benchmarks/Makefile
index 912445f..6816fc2 100644
--- a/tools/testing/selftests/powerpc/benchmarks/Makefile
+++ b/tools/testing/selftests/powerpc/benchmarks/Makefile
@@ -7,6 +7,7 @@ all: $(TEST_PROGS)
$(TEST_PROGS): ../harness.c
context_switch: ../utils.c
+context_switch: CFLAGS += -maltivec -mvsx -mabi=altivec
context_switch: LDLIBS += -lpthread
include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/benchmarks/context_switch.c
b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
index e6af382..a36883a 100644
--- a/tools/testing/selftests/powerpc/benchmarks/context_switch.c
+++ b/tools/testing/selftests/powerpc/benchmarks/context_switch.c
@@ -25,7 +25,9 @@
#include <sys/types.h>
#include <sys/shm.h>
#include <linux/futex.h>
-
+#ifdef __powerpc__
+#include <altivec.h>
+#endif
#include "../utils.h"
static unsigned int timeout = 30;
@@ -37,12 +39,15 @@ static int touch_fp = 1;
double fp;
static int touch_vector = 1;
-typedef int v4si __attribute__ ((vector_size (16)));
-v4si a, b, c;
+vector int a, b, c;
#ifdef __powerpc__
static int touch_altivec = 1;
+/*
+ * Note: LTO (Link Time Optimisation) doesn't play well with this function
+ * attribute. Be very careful enabling LTO for this test.
+ */
static void __attribute__((__target__("no-vsx"))) altivec_touch_fn(void)
{
c = a + b;
