With the removal of the #ifdef block for 16-byte descriptor loads, the
do { } while(0) around the descriptor load block becomes unnecessary.
Removing that do-while allows us to reduce indentation level of the code
by one tab, and makes the function that little cleaner and clearer to
read.
Signed-off-by: Bruce Richardson <bruce.richard...@intel.com>
---
drivers/net/i40e/i40e_rxtx_vec_avx2.c | 51 +++++++++++++--------------
1 file changed, 24 insertions(+), 27 deletions(-)
diff --git a/drivers/net/i40e/i40e_rxtx_vec_avx2.c
b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
index ce87e185f0..19cf0ac718 100644
--- a/drivers/net/i40e/i40e_rxtx_vec_avx2.c
+++ b/drivers/net/i40e/i40e_rxtx_vec_avx2.c
@@ -276,33 +276,30 @@ _recv_raw_pkts_vec_avx2(struct i40e_rx_queue *rxq, struct
rte_mbuf **rx_pkts,
_mm256_loadu_si256((void *)&sw_ring[i + 4]));
#endif
- __m256i raw_desc0_1, raw_desc2_3, raw_desc4_5, raw_desc6_7;
- do {
- 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);
- } while (0);
+ 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
