[PATCH v2 1/4] hash: pack the hitmask for hash in bulk lookup

[Yoan Picchi <yoan.picchi@arm.com>]

Current hitmask includes padding due to Intel's SIMD
implementation detail. This patch allows non Intel SIMD
implementations to benefit from a dense hitmask.

Signed-off-by: Yoan Picchi <yoan.picchi@arm.com>
---
 .mailmap                   |   2 +
 lib/hash/rte_cuckoo_hash.c | 118 ++++++++++++++++++++++++++-----------
 2 files changed, 86 insertions(+), 34 deletions(-)

diff --git a/.mailmap b/.mailmap
index 3f5bab26a8..b9c49aa7f6 100644
--- a/.mailmap
+++ b/.mailmap
@@ -485,6 +485,7 @@ Hari Kumar Vemula <hari.kumarx.vemula@intel.com>
 Harini Ramakrishnan <harini.ramakrishnan@microsoft.com>
 Hariprasad Govindharajan <hariprasad.govindharajan@intel.com>
 Harish Patil <harish.patil@cavium.com> <harish.patil@qlogic.com>
+Harjot Singh <harjot.singh@arm.com>
 Harman Kalra <hkalra@marvell.com>
 Harneet Singh <harneet.singh@intel.com>
 Harold Huang <baymaxhuang@gmail.com>
@@ -1602,6 +1603,7 @@ Yixue Wang <yixue.wang@intel.com>
 Yi Yang <yangyi01@inspur.com> <yi.y.yang@intel.com>
 Yi Zhang <zhang.yi75@zte.com.cn>
 Yoann Desmouceaux <ydesmouc@cisco.com>
+Yoan Picchi <yoan.picchi@arm.com>
 Yogesh Jangra <yogesh.jangra@intel.com>
 Yogev Chaimovich <yogev@cgstowernetworks.com>
 Yongjie Gu <yongjiex.gu@intel.com>
diff --git a/lib/hash/rte_cuckoo_hash.c b/lib/hash/rte_cuckoo_hash.c
index 19b23f2a97..2aa96eb862 100644
--- a/lib/hash/rte_cuckoo_hash.c
+++ b/lib/hash/rte_cuckoo_hash.c
@@ -1850,8 +1850,50 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 
 }
 
+#if defined(__ARM_NEON)
+
+static inline void
+compare_signatures_dense(uint32_t *prim_hash_matches, uint32_t *sec_hash_matches,
+			const struct rte_hash_bucket *prim_bkt,
+			const struct rte_hash_bucket *sec_bkt,
+			uint16_t sig,
+			enum rte_hash_sig_compare_function sig_cmp_fn)
+{
+	unsigned int i;
+
+	/* For match mask every bits indicates the match */
+	switch (sig_cmp_fn) {
+	case RTE_HASH_COMPARE_NEON: {
+		uint16x8_t vmat, vsig, x;
+		int16x8_t shift = {0, 1, 2, 3, 4, 5, 6, 7};
+
+		vsig = vld1q_dup_u16((uint16_t const *)&sig);
+		/* Compare all signatures in the primary bucket */
+		vmat = vceqq_u16(vsig,
+			vld1q_u16((uint16_t const *)prim_bkt->sig_current));
+		x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x0001)), shift);
+		*prim_hash_matches = (uint32_t)(vaddvq_u16(x));
+		/* Compare all signatures in the secondary bucket */
+		vmat = vceqq_u16(vsig,
+			vld1q_u16((uint16_t const *)sec_bkt->sig_current));
+		x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x0001)), shift);
+		*sec_hash_matches = (uint32_t)(vaddvq_u16(x));
+		}
+		break;
+	default:
+		for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
+			*prim_hash_matches |=
+				((sig == prim_bkt->sig_current[i]) << i);
+			*sec_hash_matches |=
+				((sig == sec_bkt->sig_current[i]) << i);
+		}
+	}
+}
+
+#else
+
 static inline void
-compare_signatures(uint32_t *prim_hash_matches, uint32_t *sec_hash_matches,
+compare_signatures_sparse(uint32_t *prim_hash_matches, uint32_t *sec_hash_matches,
 			const struct rte_hash_bucket *prim_bkt,
 			const struct rte_hash_bucket *sec_bkt,
 			uint16_t sig,
@@ -1878,25 +1920,7 @@ compare_signatures(uint32_t *prim_hash_matches, uint32_t *sec_hash_matches,
 		/* Extract the even-index bits only */
 		*sec_hash_matches &= 0x5555;
 		break;
-#elif defined(__ARM_NEON)
-	case RTE_HASH_COMPARE_NEON: {
-		uint16x8_t vmat, vsig, x;
-		int16x8_t shift = {-15, -13, -11, -9, -7, -5, -3, -1};
-
-		vsig = vld1q_dup_u16((uint16_t const *)&sig);
-		/* Compare all signatures in the primary bucket */
-		vmat = vceqq_u16(vsig,
-			vld1q_u16((uint16_t const *)prim_bkt->sig_current));
-		x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)), shift);
-		*prim_hash_matches = (uint32_t)(vaddvq_u16(x));
-		/* Compare all signatures in the secondary bucket */
-		vmat = vceqq_u16(vsig,
-			vld1q_u16((uint16_t const *)sec_bkt->sig_current));
-		x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)), shift);
-		*sec_hash_matches = (uint32_t)(vaddvq_u16(x));
-		}
-		break;
-#endif
+#endif /* defined(__SSE2__) */
 	default:
 		for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
 			*prim_hash_matches |=
@@ -1907,6 +1931,8 @@ compare_signatures(uint32_t *prim_hash_matches, uint32_t *sec_hash_matches,
 	}
 }
 
+#endif /* defined(__ARM_NEON) */
+
 static inline void
 __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 		const struct rte_hash_bucket **primary_bkt,
@@ -1921,18 +1947,30 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 	uint32_t sec_hitmask[RTE_HASH_LOOKUP_BULK_MAX] = {0};
 	struct rte_hash_bucket *cur_bkt, *next_bkt;
 
+#if defined(__ARM_NEON)
+	const int hitmask_padding = 0;
+#else
+	const int hitmask_padding = 1;
+#endif
+
 	__hash_rw_reader_lock(h);
 
 	/* Compare signatures and prefetch key slot of first hit */
 	for (i = 0; i < num_keys; i++) {
-		compare_signatures(&prim_hitmask[i], &sec_hitmask[i],
+#if defined(__ARM_NEON)
+		compare_signatures_dense(&prim_hitmask[i], &sec_hitmask[i],
+			primary_bkt[i], secondary_bkt[i],
+			sig[i], h->sig_cmp_fn);
+#else
+		compare_signatures_sparse(&prim_hitmask[i], &sec_hitmask[i],
 			primary_bkt[i], secondary_bkt[i],
 			sig[i], h->sig_cmp_fn);
+#endif
 
 		if (prim_hitmask[i]) {
 			uint32_t first_hit =
 					__builtin_ctzl(prim_hitmask[i])
-					>> 1;
+					>> hitmask_padding;
 			uint32_t key_idx =
 				primary_bkt[i]->key_idx[first_hit];
 			const struct rte_hash_key *key_slot =
@@ -1946,7 +1984,7 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 		if (sec_hitmask[i]) {
 			uint32_t first_hit =
 					__builtin_ctzl(sec_hitmask[i])
-					>> 1;
+					>> hitmask_padding;
 			uint32_t key_idx =
 				secondary_bkt[i]->key_idx[first_hit];
 			const struct rte_hash_key *key_slot =
@@ -1963,7 +2001,7 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 		while (prim_hitmask[i]) {
 			uint32_t hit_index =
 					__builtin_ctzl(prim_hitmask[i])
-					>> 1;
+					>> hitmask_padding;
 			uint32_t key_idx =
 				primary_bkt[i]->key_idx[hit_index];
 			const struct rte_hash_key *key_slot =
@@ -1985,13 +2023,13 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 				positions[i] = key_idx - 1;
 				goto next_key;
 			}
-			prim_hitmask[i] &= ~(3ULL << (hit_index << 1));
+			prim_hitmask[i] &= ~(1 << (hit_index << hitmask_padding));
 		}
 
 		while (sec_hitmask[i]) {
 			uint32_t hit_index =
 					__builtin_ctzl(sec_hitmask[i])
-					>> 1;
+					>> hitmask_padding;
 			uint32_t key_idx =
 				secondary_bkt[i]->key_idx[hit_index];
 			const struct rte_hash_key *key_slot =
@@ -2014,7 +2052,7 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 				positions[i] = key_idx - 1;
 				goto next_key;
 			}
-			sec_hitmask[i] &= ~(3ULL << (hit_index << 1));
+			sec_hitmask[i] &= ~(1 << (hit_index << hitmask_padding));
 		}
 next_key:
 		continue;
@@ -2069,6 +2107,12 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 	struct rte_hash_bucket *cur_bkt, *next_bkt;
 	uint32_t cnt_b, cnt_a;
 
+#if defined(__ARM_NEON)
+	const int hitmask_padding = 0;
+#else
+	const int hitmask_padding = 1;
+#endif
+
 	for (i = 0; i < num_keys; i++)
 		positions[i] = -ENOENT;
 
@@ -2082,14 +2126,20 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare signatures and prefetch key slot of first hit */
 		for (i = 0; i < num_keys; i++) {
-			compare_signatures(&prim_hitmask[i], &sec_hitmask[i],
+#if defined(__ARM_NEON)
+			compare_signatures_dense(&prim_hitmask[i], &sec_hitmask[i],
 				primary_bkt[i], secondary_bkt[i],
 				sig[i], h->sig_cmp_fn);
+#else
+			compare_signatures_sparse(&prim_hitmask[i], &sec_hitmask[i],
+				primary_bkt[i], secondary_bkt[i],
+				sig[i], h->sig_cmp_fn);
+#endif
 
 			if (prim_hitmask[i]) {
 				uint32_t first_hit =
 						__builtin_ctzl(prim_hitmask[i])
-						>> 1;
+						>> hitmask_padding;
 				uint32_t key_idx =
 					primary_bkt[i]->key_idx[first_hit];
 				const struct rte_hash_key *key_slot =
@@ -2103,7 +2153,7 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 			if (sec_hitmask[i]) {
 				uint32_t first_hit =
 						__builtin_ctzl(sec_hitmask[i])
-						>> 1;
+						>> hitmask_padding;
 				uint32_t key_idx =
 					secondary_bkt[i]->key_idx[first_hit];
 				const struct rte_hash_key *key_slot =
@@ -2119,7 +2169,7 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 			while (prim_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(prim_hitmask[i])
-						>> 1;
+						>> hitmask_padding;
 				uint32_t key_idx =
 				__atomic_load_n(
 					&primary_bkt[i]->key_idx[hit_index],
@@ -2145,13 +2195,13 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 					positions[i] = key_idx - 1;
 					goto next_key;
 				}
-				prim_hitmask[i] &= ~(3ULL << (hit_index << 1));
+				prim_hitmask[i] &= ~(1 << (hit_index << hitmask_padding));
 			}
 
 			while (sec_hitmask[i]) {
 				uint32_t hit_index =
 						__builtin_ctzl(sec_hitmask[i])
-						>> 1;
+						>> hitmask_padding;
 				uint32_t key_idx =
 				__atomic_load_n(
 					&secondary_bkt[i]->key_idx[hit_index],
@@ -2178,7 +2228,7 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 					positions[i] = key_idx - 1;
 					goto next_key;
 				}
-				sec_hitmask[i] &= ~(3ULL << (hit_index << 1));
+				sec_hitmask[i] &= ~(1 << (hit_index << hitmask_padding));
 			}
 next_key:
 			continue;
-- 
2.25.1