DPDK patches and discussions
 help / color / mirror / Atom feed
From: Lance Richardson <lance.richardson@broadcom.com>
To: Bruce Richardson <bruce.richardson@intel.com>,
	Konstantin Ananyev <konstantin.ananyev@intel.com>,
	Ajit Khaparde <ajit.khaparde@broadcom.com>,
	Somnath Kotur <somnath.kotur@broadcom.com>
Cc: dev@dpdk.org, stable@dpdk.org
Subject: [PATCH 2/2] net/bnxt: remove software prefetches from AVX2 Rx path
Date: Mon, 15 Nov 2021 13:24:10 -0500	[thread overview]
Message-ID: <20211115182410.5545-3-lance.richardson@broadcom.com> (raw)
In-Reply-To: <20211115182410.5545-1-lance.richardson@broadcom.com>

[-- Attachment #1: Type: text/plain, Size: 1849 bytes --]

Testing has shown no performance benefit from software prefetching
of receive completion descriptors in the AVX2 burst receive path,
and slightly better performance without them on some CPU families,
so this patch removes them.

Fixes: c4e4c18963b0 ("net/bnxt: add AVX2 RX/Tx")
Cc: stable@dpdk.org
Signed-off-by: Lance Richardson <lance.richardson@broadcom.com>
---
 drivers/net/bnxt/bnxt_rxtx_vec_avx2.c | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_rxtx_vec_avx2.c b/drivers/net/bnxt/bnxt_rxtx_vec_avx2.c
index 54e3af22ac..34bd22edf0 100644
--- a/drivers/net/bnxt/bnxt_rxtx_vec_avx2.c
+++ b/drivers/net/bnxt/bnxt_rxtx_vec_avx2.c
@@ -92,12 +92,6 @@ recv_burst_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 	cons = raw_cons & (cp_ring_size - 1);
 	mbcons = (raw_cons / 2) & (rx_ring_size - 1);
 
-	/* Prefetch first four descriptor pairs. */
-	rte_prefetch0(&cp_desc_ring[cons + 0]);
-	rte_prefetch0(&cp_desc_ring[cons + 4]);
-	rte_prefetch0(&cp_desc_ring[cons + 8]);
-	rte_prefetch0(&cp_desc_ring[cons + 12]);
-
 	/* Return immediately if there is not at least one completed packet. */
 	if (!bnxt_cpr_cmp_valid(&cp_desc_ring[cons], raw_cons, cp_ring_size))
 		return 0;
@@ -136,14 +130,6 @@ recv_burst_vec_avx2(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 		_mm256_storeu_si256((void *)&rx_pkts[i + 4], t0);
 #endif
 
-		/* Prefetch eight descriptor pairs for next iteration. */
-		if (i + BNXT_RX_DESCS_PER_LOOP_VEC256 < nb_pkts) {
-			rte_prefetch0(&cp_desc_ring[cons + 16]);
-			rte_prefetch0(&cp_desc_ring[cons + 20]);
-			rte_prefetch0(&cp_desc_ring[cons + 24]);
-			rte_prefetch0(&cp_desc_ring[cons + 28]);
-		}
-
 		/*
 		 * Load eight receive completion descriptors into 256-bit
 		 * registers. Loads are issued in reverse order in order to
-- 
2.25.1


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4221 bytes --]

  parent reply	other threads:[~2021-11-15 18:24 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-15 18:24 [PATCH 0/2] net/bnxt: minor performance fixes for AVX2 Rx Lance Richardson
2021-11-15 18:24 ` [PATCH 1/2] net/bnxt: avoid unnecessary work in AVX2 Rx path Lance Richardson
2021-11-15 18:24 ` Lance Richardson [this message]
2021-11-17  3:59 ` [PATCH 0/2] net/bnxt: minor performance fixes for AVX2 Rx Ajit Khaparde

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211115182410.5545-3-lance.richardson@broadcom.com \
    --to=lance.richardson@broadcom.com \
    --cc=ajit.khaparde@broadcom.com \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=konstantin.ananyev@intel.com \
    --cc=somnath.kotur@broadcom.com \
    --cc=stable@dpdk.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).