[dpdk-dev] [PATCH v2] arm: detect NEON by RTE_MACHINE_CPUFLAG_NEON flag only

Jan Viktorin viktorin at rehivetech.com
Sat Mar 19 10:26:30 CET 2016


The RTE_MACHINE_CPUFLAG_NEON was only a result of the gcc testing. However,
the target CPU may not support NEON or the user can disable to use it (as it
does not always improve the performance).

The RTE_MACHINE_CPUFLAG_NEON detection is now based on both, the __ARM_NEON_FP
feature from gcc and CONFIG_RTE_ARCH_ARM_NEON from the .config. The memcpy
implemention is driven by RTE_MACHINE_CPUFLAG_NEON, so the reason to disable
NEON is hidden for the actual code.

Signed-off-by: Jan Viktorin <viktorin at rehivetech.com>
---
v2: fix l3fwm_em.c to refer RTE_MACHINE_CPUFLAG_NEON instead of __ARM_NEON
---
 examples/l3fwd/l3fwd_em.c                              | 2 +-
 lib/librte_eal/common/include/arch/arm/rte_memcpy_32.h | 4 ++--
 mk/machine/armv7a/rte.vars.mk                          | 2 +-
 mk/rte.cpuflags.mk                                     | 2 ++
 4 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/examples/l3fwd/l3fwd_em.c b/examples/l3fwd/l3fwd_em.c
index 0adf8f4..4983eed 100644
--- a/examples/l3fwd/l3fwd_em.c
+++ b/examples/l3fwd/l3fwd_em.c
@@ -250,7 +250,7 @@ em_mask_key(void *key, xmm_t mask)
 
 	return _mm_and_si128(data, mask);
 }
-#elif defined(__ARM_NEON)
+#elif defined(RTE_MACHINE_CPUFLAG_NEON)
 static inline xmm_t
 em_mask_key(void *key, xmm_t mask)
 {
diff --git a/lib/librte_eal/common/include/arch/arm/rte_memcpy_32.h b/lib/librte_eal/common/include/arch/arm/rte_memcpy_32.h
index df47c0d..ad8bc65 100644
--- a/lib/librte_eal/common/include/arch/arm/rte_memcpy_32.h
+++ b/lib/librte_eal/common/include/arch/arm/rte_memcpy_32.h
@@ -42,7 +42,7 @@ extern "C" {
 
 #include "generic/rte_memcpy.h"
 
-#ifdef __ARM_NEON_FP
+#ifdef RTE_MACHINE_CPUFLAG_NEON
 
 /* ARM NEON Intrinsics are used to copy data */
 #include <arm_neon.h>
@@ -325,7 +325,7 @@ rte_memcpy_func(void *dst, const void *src, size_t n)
 	return memcpy(dst, src, n);
 }
 
-#endif /* __ARM_NEON_FP */
+#endif /* RTE_MACHINE_CPUFLAG_NEON */
 
 #ifdef __cplusplus
 }
diff --git a/mk/machine/armv7a/rte.vars.mk b/mk/machine/armv7a/rte.vars.mk
index 48d3979..7a167c1 100644
--- a/mk/machine/armv7a/rte.vars.mk
+++ b/mk/machine/armv7a/rte.vars.mk
@@ -62,6 +62,6 @@ ifdef CONFIG_RTE_ARCH_ARM_TUNE
 MACHINE_CFLAGS += -mtune=$(CONFIG_RTE_ARCH_ARM_TUNE)
 endif
 
-ifeq ($(CONFIG_RTE_ARCH_ARM_NEON),y)
+ifdef $(RTE_MACHINE_CPUFLAG_NEON)
 MACHINE_CFLAGS += -mfpu=neon
 endif
diff --git a/mk/rte.cpuflags.mk b/mk/rte.cpuflags.mk
index 19a3e7e..1947511 100644
--- a/mk/rte.cpuflags.mk
+++ b/mk/rte.cpuflags.mk
@@ -111,9 +111,11 @@ CPUFLAGS += VSX
 endif
 
 # ARM flags
+ifeq ($(CONFIG_RTE_ARCH_ARM_NEON),y)
 ifneq ($(filter $(AUTO_CPUFLAGS),__ARM_NEON_FP),)
 CPUFLAGS += NEON
 endif
+endif
 
 ifneq ($(filter $(AUTO_CPUFLAGS),__ARM_FEATURE_CRC32),)
 CPUFLAGS += CRC32
-- 
2.7.0



More information about the dev mailing list