The ixgbe pmd currently can't be built without enabling sse instructions at
compile time. While sse extensions provide better performance, theres no reason
that we can't still create builds to run on systems that don't support sse. If
we modify the ixgbe code to use the __builtin_shuffle and __builtin_popcountll
functions, I've confirmed that the gcc compiler emits the appropriate sse
instructions when the provided -march parameter indicates a machine that
includes sse support, and emits generic code when see isn't available.
Signed-off-by: Neil Horman <nhorman at tuxdriver.com>
CC: Thomas Monjalon <thomas.monjalon at 6wind.com>
---
lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
index 09e19a3..5747072 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
+++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
@@ -38,8 +38,6 @@
#include "ixgbe_ethdev.h"
#include "ixgbe_rxtx.h"
-#include <nmmintrin.h>
-
#ifndef __INTEL_COMPILER
#pragma GCC diagnostic ignored "-Wcast-qual"
#endif
@@ -294,8 +292,8 @@ ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf
**rx_pkts,
rte_compiler_barrier();
/* D.1 pkt 3,4 convert format from desc to pktmbuf */
- pkt_mb4 = _mm_shuffle_epi8(descs[3], shuf_msk);
- pkt_mb3 = _mm_shuffle_epi8(descs[2], shuf_msk);
+ pkt_mb4 = __builtin_shuffle(descs[3], shuf_msk);
+ pkt_mb3 = __builtin_shuffle(descs[2], shuf_msk);
/* C.1 4=>2 filter staterr info only */
sterr_tmp2 = _mm_unpackhi_epi32(descs[3], descs[2]);
@@ -310,8 +308,8 @@ ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf
**rx_pkts,
pkt_mb3 = _mm_add_epi16(pkt_mb3, in_port);
/* D.1 pkt 1,2 convert format from desc to pktmbuf */
- pkt_mb2 = _mm_shuffle_epi8(descs[1], shuf_msk);
- pkt_mb1 = _mm_shuffle_epi8(descs[0], shuf_msk);
+ pkt_mb2 = __builtin_shuffle(descs[1], shuf_msk);
+ pkt_mb1 = __builtin_shuffle(descs[0], shuf_msk);
/* C.2 get 4 pkts staterr value */
zero = _mm_xor_si128(dd_check, dd_check);
@@ -338,7 +336,7 @@ ixgbe_recv_pkts_vec(void *rx_queue, struct rte_mbuf
**rx_pkts,
pkt_mb1);
/* C.4 calc avaialbe number of desc */
- var = _mm_popcnt_u64(_mm_cvtsi128_si64(staterr));
+ var = __builtin_popcountll(_mm_cvtsi128_si64(staterr));
nb_pkts_recd += var;
if (likely(var != RTE_IXGBE_DESCS_PER_LOOP))
break;
--
1.8.3.1
