DPDK patches and discussions
 help / color / mirror / Atom feed
From: Yoan Picchi <yoan.picchi@arm.com>
To: Yipeng Wang <yipeng1.wang@intel.com>,
	Sameh Gobriel <sameh.gobriel@intel.com>,
	Bruce Richardson <bruce.richardson@intel.com>,
	Vladimir Medvedkin <vladimir.medvedkin@intel.com>
Cc: dev@dpdk.org, nd@arm.com, Yoan Picchi <yoan.picchi@arm.com>,
	Harjot Singh <harjot.singh@arm.com>,
	Nathan Brown <nathan.brown@arm.com>,
	Ruifeng Wang <ruifeng.wang@arm.com>
Subject: [PATCH v9 4/4] hash: add SVE support for bulk key lookup
Date: Tue, 30 Apr 2024 16:27:43 +0000	[thread overview]
Message-ID: <20240430162743.1525484-5-yoan.picchi@arm.com> (raw)
In-Reply-To: <20240430162743.1525484-1-yoan.picchi@arm.com>

- Implemented SVE code for comparing signatures in bulk lookup.
- New SVE code is ~5% slower than optimized NEON for N2 processor for
128b vectors.

Signed-off-by: Yoan Picchi <yoan.picchi@arm.com>
Signed-off-by: Harjot Singh <harjot.singh@arm.com>
Reviewed-by: Nathan Brown <nathan.brown@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
 lib/hash/arch/arm/compare_signatures.h | 58 ++++++++++++++++++++++++++
 lib/hash/rte_cuckoo_hash.c             |  7 +++-
 lib/hash/rte_cuckoo_hash.h             |  1 +
 3 files changed, 65 insertions(+), 1 deletion(-)

diff --git a/lib/hash/arch/arm/compare_signatures.h b/lib/hash/arch/arm/compare_signatures.h
index 72bd171484..b4b4cf04e9 100644
--- a/lib/hash/arch/arm/compare_signatures.h
+++ b/lib/hash/arch/arm/compare_signatures.h
@@ -47,6 +47,64 @@ compare_signatures_dense(uint16_t *hitmask_buffer,
 		*hitmask_buffer = vaddvq_u16(hit2);
 		}
 		break;
+#endif
+#if defined(RTE_HAS_SVE_ACLE)
+	case RTE_HASH_COMPARE_SVE: {
+		svuint16_t vsign, shift, sv_matches;
+		svbool_t pred, match, bucket_wide_pred;
+		int i = 0;
+		uint64_t vl = svcnth();
+
+		vsign = svdup_u16(sig);
+		shift = svindex_u16(0, 1);
+
+		if (vl >= 2 * RTE_HASH_BUCKET_ENTRIES && RTE_HASH_BUCKET_ENTRIES <= 8) {
+			svuint16_t primary_array_vect, secondary_array_vect;
+			bucket_wide_pred = svwhilelt_b16(0, RTE_HASH_BUCKET_ENTRIES);
+			primary_array_vect = svld1_u16(bucket_wide_pred, prim_bucket_sigs);
+			secondary_array_vect = svld1_u16(bucket_wide_pred, sec_bucket_sigs);
+
+			/* We merged the two vectors so we can do both comparisons at once */
+			primary_array_vect = svsplice_u16(bucket_wide_pred,
+				primary_array_vect,
+				secondary_array_vect);
+			pred = svwhilelt_b16(0, 2*RTE_HASH_BUCKET_ENTRIES);
+
+			/* Compare all signatures in the buckets */
+			match = svcmpeq_u16(pred, vsign, primary_array_vect);
+			if (svptest_any(svptrue_b16(), match)) {
+				sv_matches = svdup_u16(1);
+				sv_matches = svlsl_u16_z(match, sv_matches, shift);
+				*hitmask_buffer = svorv_u16(svptrue_b16(), sv_matches);
+			}
+		} else {
+			do {
+				pred = svwhilelt_b16(i, RTE_HASH_BUCKET_ENTRIES);
+				uint16_t lower_half = 0;
+				uint16_t upper_half = 0;
+				/* Compare all signatures in the primary bucket */
+				match = svcmpeq_u16(pred, vsign, svld1_u16(pred,
+							&prim_bucket_sigs[i]));
+				if (svptest_any(svptrue_b16(), match)) {
+					sv_matches = svdup_u16(1);
+					sv_matches = svlsl_u16_z(match, sv_matches, shift);
+					lower_half = svorv_u16(svptrue_b16(), sv_matches);
+				}
+				/* Compare all signatures in the secondary bucket */
+				match = svcmpeq_u16(pred, vsign, svld1_u16(pred,
+							&sec_bucket_sigs[i]));
+				if (svptest_any(svptrue_b16(), match)) {
+					sv_matches = svdup_u16(1);
+					sv_matches = svlsl_u16_z(match, sv_matches, shift);
+					upper_half = svorv_u16(svptrue_b16(), sv_matches)
+						<< RTE_HASH_BUCKET_ENTRIES;
+				}
+				hitmask_buffer[i / 8] = upper_half | lower_half;
+				i += vl;
+			} while (i < RTE_HASH_BUCKET_ENTRIES);
+		}
+		}
+		break;
 #endif
 	default:
 		for (unsigned int i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
diff --git a/lib/hash/rte_cuckoo_hash.c b/lib/hash/rte_cuckoo_hash.c
index 0697743cdf..75f555ba2c 100644
--- a/lib/hash/rte_cuckoo_hash.c
+++ b/lib/hash/rte_cuckoo_hash.c
@@ -450,8 +450,13 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		h->sig_cmp_fn = RTE_HASH_COMPARE_SSE;
 	else
 #elif defined(RTE_ARCH_ARM64)
-	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON))
+	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON)) {
 		h->sig_cmp_fn = RTE_HASH_COMPARE_NEON;
+#if defined(RTE_HAS_SVE_ACLE)
+		if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SVE))
+			h->sig_cmp_fn = RTE_HASH_COMPARE_SVE;
+#endif
+	}
 	else
 #endif
 		h->sig_cmp_fn = RTE_HASH_COMPARE_SCALAR;
diff --git a/lib/hash/rte_cuckoo_hash.h b/lib/hash/rte_cuckoo_hash.h
index a528f1d1a0..01ad01c258 100644
--- a/lib/hash/rte_cuckoo_hash.h
+++ b/lib/hash/rte_cuckoo_hash.h
@@ -139,6 +139,7 @@ enum rte_hash_sig_compare_function {
 	RTE_HASH_COMPARE_SCALAR = 0,
 	RTE_HASH_COMPARE_SSE,
 	RTE_HASH_COMPARE_NEON,
+	RTE_HASH_COMPARE_SVE,
 	RTE_HASH_COMPARE_NUM
 };
 
-- 
2.25.1


  parent reply	other threads:[~2024-04-30 16:28 UTC|newest]

Thread overview: 73+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-20 16:51 [PATCH v2 0/4] " Yoan Picchi
2023-10-20 16:51 ` [PATCH v2 1/4] hash: pack the hitmask for hash in bulk lookup Yoan Picchi
2023-10-20 16:51 ` [PATCH v2 2/4] hash: optimize compare signature for NEON Yoan Picchi
2023-10-20 16:51 ` [PATCH v2 3/4] test/hash: check bulk lookup of keys after collision Yoan Picchi
2023-10-20 16:51 ` [PATCH v2 4/4] hash: add SVE support for bulk key lookup Yoan Picchi
2024-02-27 17:41 ` [PATCH v5 0/4] " Yoan Picchi
2024-02-27 17:42   ` [PATCH v5 1/4] hash: pack the hitmask for hash in bulk lookup Yoan Picchi
2024-02-27 17:42   ` [PATCH v5 2/4] hash: optimize compare signature for NEON Yoan Picchi
2024-02-27 17:42   ` [PATCH v5 3/4] test/hash: check bulk lookup of keys after collision Yoan Picchi
2024-02-27 17:42   ` [PATCH v5 4/4] hash: add SVE support for bulk key lookup Yoan Picchi
2024-02-28 10:56     ` Konstantin Ananyev
2024-02-28 14:48       ` Yoan Picchi
2024-03-04 13:35         ` Konstantin Ananyev
2024-03-05 15:36           ` Yoan Picchi
2024-03-11 23:21 ` [PATCH v6 0/4] " Yoan Picchi
2024-03-11 23:21   ` [PATCH v6 1/4] hash: pack the hitmask for hash in bulk lookup Yoan Picchi
2024-03-11 23:21   ` [PATCH v6 2/4] hash: optimize compare signature for NEON Yoan Picchi
2024-03-11 23:21   ` [PATCH v6 3/4] test/hash: check bulk lookup of keys after collision Yoan Picchi
2024-03-11 23:21   ` [PATCH v6 4/4] hash: add SVE support for bulk key lookup Yoan Picchi
2024-03-12  3:57     ` fengchengwen
2024-03-12 15:08       ` Yoan Picchi
2024-03-12 15:42 ` [PATCH v7 0/4] " Yoan Picchi
2024-03-12 15:42   ` [PATCH v7 1/4] hash: pack the hitmask for hash in bulk lookup Yoan Picchi
2024-03-19 10:41     ` Konstantin Ananyev
2024-03-19 13:09       ` Yoan Picchi
2024-03-19 13:25         ` Konstantin Ananyev
2024-03-19 16:09     ` Stephen Hemminger
2024-03-12 15:42   ` [PATCH v7 2/4] hash: optimize compare signature for NEON Yoan Picchi
2024-03-20  7:37     ` [EXTERNAL] " Pavan Nikhilesh Bhagavatula
2024-04-11 13:32       ` Yoan Picchi
2024-03-12 15:42   ` [PATCH v7 3/4] test/hash: check bulk lookup of keys after collision Yoan Picchi
2024-03-12 15:42   ` [PATCH v7 4/4] hash: add SVE support for bulk key lookup Yoan Picchi
2024-04-17 16:08 ` [PATCH v8 0/4] " Yoan Picchi
2024-04-17 16:08   ` [PATCH v8 1/4] hash: pack the hitmask for hash in bulk lookup Yoan Picchi
2024-04-17 18:12     ` Stephen Hemminger
2024-04-17 16:08   ` [PATCH v8 2/4] hash: optimize compare signature for NEON Yoan Picchi
2024-04-17 16:08   ` [PATCH v8 3/4] test/hash: check bulk lookup of keys after collision Yoan Picchi
2024-04-17 16:08   ` [PATCH v8 4/4] hash: add SVE support for bulk key lookup Yoan Picchi
2024-04-30 16:27 ` [PATCH v9 0/4] " Yoan Picchi
2024-04-30 16:27   ` [PATCH v9 1/4] hash: pack the hitmask for hash in bulk lookup Yoan Picchi
2024-06-14 13:42     ` David Marchand
2024-04-30 16:27   ` [PATCH v9 2/4] hash: optimize compare signature for NEON Yoan Picchi
2024-04-30 16:27   ` [PATCH v9 3/4] test/hash: check bulk lookup of keys after collision Yoan Picchi
2024-04-30 16:27   ` Yoan Picchi [this message]
2024-06-14 13:42     ` [PATCH v9 4/4] hash: add SVE support for bulk key lookup David Marchand
2024-06-14 13:43   ` [PATCH v9 0/4] " David Marchand
2024-06-18 15:55     ` Konstantin Ananyev
2024-06-27 14:48   ` Thomas Monjalon
2024-07-03 17:13 ` [PATCH v10 " Yoan Picchi
2024-07-03 17:13   ` [PATCH v10 1/4] hash: pack the hitmask for hash in bulk lookup Yoan Picchi
2024-07-04 20:31     ` David Marchand
2024-07-05 17:43       ` Yoan Picchi
2024-07-07 12:08         ` Thomas Monjalon
2024-07-03 17:13   ` [PATCH v10 2/4] hash: optimize compare signature for NEON Yoan Picchi
2024-07-03 17:13   ` [PATCH v10 3/4] test/hash: check bulk lookup of keys after collision Yoan Picchi
2024-07-03 17:13   ` [PATCH v10 4/4] hash: add SVE support for bulk key lookup Yoan Picchi
2024-07-05 17:45 ` [PATCH v11 0/7] " Yoan Picchi
2024-07-05 17:45   ` [PATCH v11 1/7] hash: make compare signature function enum private Yoan Picchi
2024-07-05 17:45   ` [PATCH v11 2/7] hash: split compare signature into arch-specific files Yoan Picchi
2024-07-05 17:45   ` [PATCH v11 3/7] hash: add a check on hash entry max size Yoan Picchi
2024-07-05 17:45   ` [PATCH v11 4/7] hash: pack the hitmask for hash in bulk lookup Yoan Picchi
2024-07-05 17:45   ` [PATCH v11 5/7] hash: optimize compare signature for NEON Yoan Picchi
2024-07-05 17:45   ` [PATCH v11 6/7] test/hash: check bulk lookup of keys after collision Yoan Picchi
2024-07-05 17:45   ` [PATCH v11 7/7] hash: add SVE support for bulk key lookup Yoan Picchi
2024-07-08 12:14 ` [PATCH v12 0/7] " Yoan Picchi
2024-07-08 12:14   ` [PATCH v12 1/7] hash: make compare signature function enum private Yoan Picchi
2024-07-08 12:14   ` [PATCH v12 2/7] hash: split compare signature into arch-specific files Yoan Picchi
2024-07-08 12:14   ` [PATCH v12 3/7] hash: add a check on hash entry max size Yoan Picchi
2024-07-08 12:14   ` [PATCH v12 4/7] hash: pack the hitmask for hash in bulk lookup Yoan Picchi
2024-07-08 12:14   ` [PATCH v12 5/7] hash: optimize compare signature for NEON Yoan Picchi
2024-07-08 12:14   ` [PATCH v12 6/7] test/hash: check bulk lookup of keys after collision Yoan Picchi
2024-07-08 12:14   ` [PATCH v12 7/7] hash: add SVE support for bulk key lookup Yoan Picchi
2024-07-09  4:48   ` [PATCH v12 0/7] " David Marchand

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=20240430162743.1525484-5-yoan.picchi@arm.com \
    --to=yoan.picchi@arm.com \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=harjot.singh@arm.com \
    --cc=nathan.brown@arm.com \
    --cc=nd@arm.com \
    --cc=ruifeng.wang@arm.com \
    --cc=sameh.gobriel@intel.com \
    --cc=vladimir.medvedkin@intel.com \
    --cc=yipeng1.wang@intel.com \
    /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).