With the removal of the separate block for 16B-descriptors, we can
remove the superfluous braces and dedent the code a bit. This allows us
to reduce overall number of lines, since we can merge quite a number of
lines together.
Signed-off-by: Bruce Richardson <bruce.richard...@intel.com>
---
drivers/net/iavf/iavf_rxtx_vec_avx2.c | 67 ++++++++++-----------------
1 file changed, 24 insertions(+), 43 deletions(-)
diff --git a/drivers/net/iavf/iavf_rxtx_vec_avx2.c
b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
index 3cec1eef9d..49d41af953 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_avx2.c
+++ b/drivers/net/iavf/iavf_rxtx_vec_avx2.c
@@ -193,49 +193,30 @@ _iavf_recv_raw_pkts_vec_avx2(struct iavf_rx_queue *rxq,
_mm256_loadu_si256((void *)&sw_ring[i + 4]));
#endif
- __m256i raw_desc0_1, raw_desc2_3, raw_desc4_5, raw_desc6_7;
- {
- const __m128i raw_desc7 =
- _mm_load_si128((void *)(rxdp + 7));
- rte_compiler_barrier();
- const __m128i raw_desc6 =
- _mm_load_si128((void *)(rxdp + 6));
- rte_compiler_barrier();
- const __m128i raw_desc5 =
- _mm_load_si128((void *)(rxdp + 5));
- rte_compiler_barrier();
- const __m128i raw_desc4 =
- _mm_load_si128((void *)(rxdp + 4));
- rte_compiler_barrier();
- const __m128i raw_desc3 =
- _mm_load_si128((void *)(rxdp + 3));
- rte_compiler_barrier();
- const __m128i raw_desc2 =
- _mm_load_si128((void *)(rxdp + 2));
- rte_compiler_barrier();
- const __m128i raw_desc1 =
- _mm_load_si128((void *)(rxdp + 1));
- rte_compiler_barrier();
- const __m128i raw_desc0 =
- _mm_load_si128((void *)(rxdp + 0));
-
- raw_desc6_7 =
- _mm256_inserti128_si256
- (_mm256_castsi128_si256(raw_desc6),
- raw_desc7, 1);
- raw_desc4_5 =
- _mm256_inserti128_si256
- (_mm256_castsi128_si256(raw_desc4),
- raw_desc5, 1);
- raw_desc2_3 =
- _mm256_inserti128_si256
- (_mm256_castsi128_si256(raw_desc2),
- raw_desc3, 1);
- raw_desc0_1 =
- _mm256_inserti128_si256
- (_mm256_castsi128_si256(raw_desc0),
- raw_desc1, 1);
- }
+ const __m128i raw_desc7 = _mm_load_si128((void *)(rxdp + 7));
+ rte_compiler_barrier();
+ const __m128i raw_desc6 = _mm_load_si128((void *)(rxdp + 6));
+ rte_compiler_barrier();
+ const __m128i raw_desc5 = _mm_load_si128((void *)(rxdp + 5));
+ rte_compiler_barrier();
+ const __m128i raw_desc4 = _mm_load_si128((void *)(rxdp + 4));
+ rte_compiler_barrier();
+ const __m128i raw_desc3 = _mm_load_si128((void *)(rxdp + 3));
+ rte_compiler_barrier();
+ const __m128i raw_desc2 = _mm_load_si128((void *)(rxdp + 2));
+ rte_compiler_barrier();
+ const __m128i raw_desc1 = _mm_load_si128((void *)(rxdp + 1));
+ rte_compiler_barrier();
+ const __m128i raw_desc0 = _mm_load_si128((void *)(rxdp + 0));
+
+ const __m256i raw_desc6_7 =
+
_mm256_inserti128_si256(_mm256_castsi128_si256(raw_desc6), raw_desc7, 1);
+ const __m256i raw_desc4_5 =
+
_mm256_inserti128_si256(_mm256_castsi128_si256(raw_desc4), raw_desc5, 1);
+ const __m256i raw_desc2_3 =
+
_mm256_inserti128_si256(_mm256_castsi128_si256(raw_desc2), raw_desc3, 1);
+ const __m256i raw_desc0_1 =
+
_mm256_inserti128_si256(_mm256_castsi128_si256(raw_desc0), raw_desc1, 1);
if (split_packet) {
int j;
--
2.40.1
