[dpdk-dev] [PATCH v2] ACL: fix build for native-icc target on haswell fails

Konstantin Ananyev konstantin.ananyev at intel.com
Fri Nov 20 16:38:50 CET 2015


On HSW box with icc 16.0.0 build for x86_64-native-linuxapp-icc fails with:
icc: command line warning #10120: overriding '-march=native' with '-msse4.1'
...
dpdk.org/x86_64-native-linuxapp-icc/include/rte_memcpy.h(96): error: identifier "__m256i" is undefined

The reason is that icc treats "-march=native ... -msse4.1"
in a different way, then gcc and clang.
For icc it means override all flags enabled with
'-march=native' with '-msse4.1'.
Even when '-march=native' is a superset for '-msse4.1'.
To overcome the problem add a check is SSE4.1 compilation flag already enabled.
If yes, then no need to add '-msse4.1'
Similar change for avx2 compilation option.

Fixes: 074f54ad03ee ("acl: fix build and runtime for default target")

Reported-by: Declan Doherty <declan.doherty at intel.com>
Reported-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy at intel.com>
Signed-off-by: Konstantin Ananyev <konstantin.ananyev at intel.com>
---
 lib/librte_acl/Makefile | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

v2 changes:
- merged with latest mainline

diff --git a/lib/librte_acl/Makefile b/lib/librte_acl/Makefile
index 27f91d5..897237d 100644
--- a/lib/librte_acl/Makefile
+++ b/lib/librte_acl/Makefile
@@ -48,31 +48,42 @@ SRCS-$(CONFIG_RTE_LIBRTE_ACL) += rte_acl.c
 SRCS-$(CONFIG_RTE_LIBRTE_ACL) += acl_bld.c
 SRCS-$(CONFIG_RTE_LIBRTE_ACL) += acl_gen.c
 SRCS-$(CONFIG_RTE_LIBRTE_ACL) += acl_run_scalar.c
+
 ifeq ($(CONFIG_RTE_ARCH_ARM64),y)
 SRCS-$(CONFIG_RTE_LIBRTE_ACL) += acl_run_neon.c
+CFLAGS_acl_run_neon.o += -flax-vector-conversions -Wno-maybe-uninitialized
 else
 SRCS-$(CONFIG_RTE_LIBRTE_ACL) += acl_run_sse.c
+#check if flag for SSE4.1 is already on, if not set it up manually
+	ifeq ($(findstring RTE_MACHINE_CPUFLAG_SSE4_1,$(CFLAGS)),)
+		CFLAGS_acl_run_sse.o += -msse4.1
+	endif
 endif
 
-CFLAGS_acl_run_sse.o += -msse4.1
-CFLAGS_acl_run_neon.o += -flax-vector-conversions -Wno-maybe-uninitialized
-
 #
 # If the compiler supports AVX2 instructions,
 # then add support for AVX2 classify method.
 #
 
-CC_AVX2_SUPPORT=$(shell $(CC) -march=core-avx2 -dM -E - </dev/null 2>&1 | \
-grep -q AVX2 && echo 1)
+#check if flag for AVX2 is already on, if not set it up manually
+ifeq ($(findstring RTE_MACHINE_CPUFLAG_AVX2,$(CFLAGS)),RTE_MACHINE_CPUFLAG_AVX2)
+	CC_AVX2_SUPPORT=1
+else
+	CC_AVX2_SUPPORT=\
+	$(shell $(CC) -march=core-avx2 -dM -E - </dev/null 2>&1 | \
+	grep -q AVX2 && echo 1)
+	ifeq ($(CC_AVX2_SUPPORT), 1)
+		ifeq ($(CC), icc)
+		CFLAGS_acl_run_avx2.o += -march=core-avx2
+		else
+		CFLAGS_acl_run_avx2.o += -mavx2
+		endif
+	endif
+endif
 
 ifeq ($(CC_AVX2_SUPPORT), 1)
 	SRCS-$(CONFIG_RTE_LIBRTE_ACL) += acl_run_avx2.c
 	CFLAGS_rte_acl.o += -DCC_AVX2_SUPPORT
-	ifeq ($(CC), icc)
-	CFLAGS_acl_run_avx2.o += -march=core-avx2
-	else
-	CFLAGS_acl_run_avx2.o += -mavx2
-	endif
 endif
 
 # install this header file
-- 
1.8.5.3



More information about the dev mailing list