X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=app%2Ftest-pmd%2Fmacswap_sse.h;h=223f87a53946fca3985c45eafd6cbd00e1f1d0b1;hb=965b3127d4259c25c61eefefb082c042f3c87142;hp=79c7e9883d7ef4e9c835fcc5c137a80dbd090635;hpb=a68b61687af0fc8c6c3ce6ae4e82286d58d6d56b;p=dpdk.git diff --git a/app/test-pmd/macswap_sse.h b/app/test-pmd/macswap_sse.h index 79c7e9883d..223f87a539 100644 --- a/app/test-pmd/macswap_sse.h +++ b/app/test-pmd/macswap_sse.h @@ -11,11 +11,12 @@ static inline void do_macswap(struct rte_mbuf *pkts[], uint16_t nb, struct rte_port *txp) { - struct ether_hdr *eth_hdr; - struct rte_mbuf *mb; + struct rte_ether_hdr *eth_hdr[4]; + struct rte_mbuf *mb[4]; uint64_t ol_flags; int i; - __m128i addr; + int r; + __m128i addr0, addr1, addr2, addr3; /** * shuffle mask be used to shuffle the 16 bytes. * byte 0-5 wills be swapped with byte 6-11. @@ -30,19 +31,63 @@ do_macswap(struct rte_mbuf *pkts[], uint16_t nb, vlan_qinq_set(pkts, nb, ol_flags, txp->tx_vlan_id, txp->tx_vlan_id_outer); - for (i = 0; i < nb; i++) { - if (likely(i < nb - 1)) - rte_prefetch0(rte_pktmbuf_mtod(pkts[i+1], void *)); - mb = pkts[i]; + i = 0; + r = nb; + + while (r >= 4) { + if (r >= 8) { + rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 4], void *)); + rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 5], void *)); + rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 6], void *)); + rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 7], void *)); + } + + mb[0] = pkts[i++]; + eth_hdr[0] = rte_pktmbuf_mtod(mb[0], struct rte_ether_hdr *); + addr0 = _mm_loadu_si128((__m128i *)eth_hdr[0]); + + mb[1] = pkts[i++]; + eth_hdr[1] = rte_pktmbuf_mtod(mb[1], struct rte_ether_hdr *); + addr1 = _mm_loadu_si128((__m128i *)eth_hdr[1]); + + + mb[2] = pkts[i++]; + eth_hdr[2] = rte_pktmbuf_mtod(mb[2], struct rte_ether_hdr *); + addr2 = _mm_loadu_si128((__m128i *)eth_hdr[2]); - eth_hdr = rte_pktmbuf_mtod(mb, struct ether_hdr *); + mb[3] = pkts[i++]; + eth_hdr[3] = rte_pktmbuf_mtod(mb[3], struct rte_ether_hdr *); + addr3 = _mm_loadu_si128((__m128i *)eth_hdr[3]); + + addr0 = _mm_shuffle_epi8(addr0, shfl_msk); + addr1 = _mm_shuffle_epi8(addr1, shfl_msk); + addr2 = _mm_shuffle_epi8(addr2, shfl_msk); + addr3 = _mm_shuffle_epi8(addr3, shfl_msk); + + _mm_storeu_si128((__m128i *)eth_hdr[0], addr0); + _mm_storeu_si128((__m128i *)eth_hdr[1], addr1); + _mm_storeu_si128((__m128i *)eth_hdr[2], addr2); + _mm_storeu_si128((__m128i *)eth_hdr[3], addr3); + + mbuf_field_set(mb[0], ol_flags); + mbuf_field_set(mb[1], ol_flags); + mbuf_field_set(mb[2], ol_flags); + mbuf_field_set(mb[3], ol_flags); + r -= 4; + } + + for ( ; i < nb; i++) { + if (i < nb - 1) + rte_prefetch0(rte_pktmbuf_mtod(pkts[i+1], void *)); + mb[0] = pkts[i]; + eth_hdr[0] = rte_pktmbuf_mtod(mb[0], struct rte_ether_hdr *); /* Swap dest and src mac addresses. */ - addr = _mm_loadu_si128((__m128i *)eth_hdr); - addr = _mm_shuffle_epi8(addr, shfl_msk); - _mm_storeu_si128((__m128i *)eth_hdr, addr); + addr0 = _mm_loadu_si128((__m128i *)eth_hdr[0]); + addr0 = _mm_shuffle_epi8(addr0, shfl_msk); + _mm_storeu_si128((__m128i *)eth_hdr[0], addr0); - mbuf_field_set(mb, ol_flags); + mbuf_field_set(mb[0], ol_flags); } }