sched: add NEON optimizations

* Removed setting CONFIG_RTE_SCHED_VECTOR=n from armv8a config
  so that the setting from common_base is taken as the default
  setting for armv8a
* Verified the changes with sched_autotest unit test case

Signed-off-by: Ashwin Sekhar T K <ashwin.sekhar@caviumnetworks.com>
Acked-by: Jianbo Liu <jianbo.liu@linaro.org>

diff --git a/config/defconfig_arm64-armv8a-linuxapp-gcc b/config/defconfig_arm64-armv8a-linuxapp-gcc
index 9f32766..749b007 100644 (file)
--- a/config/defconfig_arm64-armv8a-linuxapp-gcc
+++ b/config/defconfig_arm64-armv8a-linuxapp-gcc
@@ -52,5 +52,3 @@ CONFIG_RTE_EAL_IGB_UIO=n
 CONFIG_RTE_LIBRTE_FM10K_PMD=n
 CONFIG_RTE_LIBRTE_SFC_EFX_PMD=n
 CONFIG_RTE_LIBRTE_AVP_PMD=n
-
-CONFIG_RTE_SCHED_VECTOR=n

diff --git a/lib/librte_sched/rte_sched.c b/lib/librte_sched/rte_sched.c
index 614705d..4ba476a 100644 (file)
--- a/lib/librte_sched/rte_sched.c
+++ b/lib/librte_sched/rte_sched.c
@@ -58,6 +58,8 @@
 
 #if defined(__SSE4__)
 #define SCHED_VECTOR_SSE4
+#elif defined(RTE_MACHINE_CPUFLAG_NEON)
+#define SCHED_VECTOR_NEON
 #endif
 
 #endif
@@ -1732,6 +1734,26 @@ grinder_pipe_exists(struct rte_sched_port *port, uint32_t base_pipe)
        return 1;
 }
 
+#elif defined(SCHED_VECTOR_NEON)
+
+static inline int
+grinder_pipe_exists(struct rte_sched_port *port, uint32_t base_pipe)
+{
+       uint32x4_t index, pipes;
+       uint32_t *pos = (uint32_t *)port->grinder_base_bmp_pos;
+
+       index = vmovq_n_u32(base_pipe);
+       pipes = vld1q_u32(pos);
+       if (!vminvq_u32(veorq_u32(pipes, index)))
+               return 1;
+
+       pipes = vld1q_u32(pos + 4);
+       if (!vminvq_u32(veorq_u32(pipes, index)))
+               return 1;
+
+       return 0;
+}
+
 #else
 
 static inline int