'__sync' built-in functions are deprecated, should use the '__atomic'
built-in instead. the sync built-in functions are full barriers, while
atomic built-in functions offer less restrictive one-way barriers,
which help performance.

Here is the example test result on TX2:
sudo ./arm64-armv8a-linuxapp-gcc/app/test -l 112-139 \
-n 4 --socket-mem=1024,1024 -- -i
RTE>>distributor_perf_autotest

*** distributor_perf_autotest without this patch ***
==== Cache line switch test ===
Time for 33554432 iterations = 1519202730 ticks
Ticks per iteration = 45

*** distributor_perf_autotest with this patch ***
==== Cache line switch test ===
Time for 33554432 iterations = 1251715496 ticks
Ticks per iteration = 37

Less ticks needed for the cache line switch test. It got 17% of
performance improvement.

Signed-off-by: Phil Yang <phil.y...@arm.com>
Reviewed-by: Gavin Hu <gavin...@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.w...@arm.com>
Reviewed-by: Joyce Kong <joyce.k...@arm.com>
Reviewed-by: Dharmik Thakkar <dharmik.thak...@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagaraha...@arm.com>
---
 app/test/test_distributor.c      | 7 ++++---
 app/test/test_distributor_perf.c | 2 +-
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/app/test/test_distributor.c b/app/test/test_distributor.c
index 98919ec..0364637 100644
--- a/app/test/test_distributor.c
+++ b/app/test/test_distributor.c
@@ -62,7 +62,7 @@ handle_work(void *arg)
        struct worker_params *wp = arg;
        struct rte_distributor *db = wp->dist;
        unsigned int count = 0, num = 0;
-       unsigned int id = __sync_fetch_and_add(&worker_idx, 1);
+       unsigned int id = __atomic_fetch_add(&worker_idx, 1, __ATOMIC_RELAXED);
        int i;
 
        for (i = 0; i < 8; i++)
@@ -270,7 +270,7 @@ handle_work_with_free_mbufs(void *arg)
        unsigned int count = 0;
        unsigned int i;
        unsigned int num = 0;
-       unsigned int id = __sync_fetch_and_add(&worker_idx, 1);
+       unsigned int id = __atomic_fetch_add(&worker_idx, 1, __ATOMIC_RELAXED);
 
        for (i = 0; i < 8; i++)
                buf[i] = NULL;
@@ -343,7 +343,8 @@ handle_work_for_shutdown_test(void *arg)
        unsigned int total = 0;
        unsigned int i;
        unsigned int returned = 0;
-       const unsigned int id = __sync_fetch_and_add(&worker_idx, 1);
+       const unsigned int id = __atomic_fetch_add(&worker_idx, 1,
+                       __ATOMIC_RELAXED);
 
        num = rte_distributor_get_pkt(d, id, buf, buf, num);
 
diff --git a/app/test/test_distributor_perf.c b/app/test/test_distributor_perf.c
index edf1998..89b28f0 100644
--- a/app/test/test_distributor_perf.c
+++ b/app/test/test_distributor_perf.c
@@ -111,7 +111,7 @@ handle_work(void *arg)
        unsigned int count = 0;
        unsigned int num = 0;
        int i;
-       unsigned int id = __sync_fetch_and_add(&worker_idx, 1);
+       unsigned int id = __atomic_fetch_add(&worker_idx, 1, __ATOMIC_RELAXED);
        struct rte_mbuf *buf[8] __rte_cache_aligned;
 
        for (i = 0; i < 8; i++)
-- 
2.7.4

Reply via email to