When choosing a vector path to take, an extra condition must be
satisfied to ensure the max SIMD bitwidth allows for the CPU enabled
path.
Cc: Byron Marohn <byron.mar...@intel.com>
Cc: Yipeng Wang <yipeng1.w...@intel.com>
Signed-off-by: Ciara Power <ciara.po...@intel.com>
Acked-by: Yipeng Wang <yipeng1.w...@intel.com>
---
v4: Updated enum name.
---
lib/librte_efd/rte_efd.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/lib/librte_efd/rte_efd.c b/lib/librte_efd/rte_efd.c
index 6a799556d4..e925b73a9c 100644
--- a/lib/librte_efd/rte_efd.c
+++ b/lib/librte_efd/rte_efd.c
@@ -645,7 +645,9 @@ rte_efd_create(const char *name, uint32_t max_num_rules,
uint32_t key_len,
* For less than 4 bits, scalar function performs better
* than vectorised version
*/
- if (RTE_EFD_VALUE_NUM_BITS > 3 &&
rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2))
+ if (RTE_EFD_VALUE_NUM_BITS > 3
+ && rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2)
+ && rte_get_max_simd_bitwidth() >= RTE_SIMD_256)
table->lookup_fn = EFD_LOOKUP_AVX2;
else
#endif
@@ -655,7 +657,8 @@ rte_efd_create(const char *name, uint32_t max_num_rules,
uint32_t key_len,
* than vectorised version
*/
if (RTE_EFD_VALUE_NUM_BITS > 16 &&
- rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON))
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON) &&
+ rte_get_max_simd_bitwidth() >= RTE_SIMD_128)
table->lookup_fn = EFD_LOOKUP_NEON;
else
#endif
--
2.22.0
