- 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.pic...@arm.com>
Signed-off-by: Harjot Singh <harjot.si...@arm.com>
Reviewed-by: Nathan Brown <nathan.br...@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.w...@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 2601ed68b3..140ff97b1d 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
