bug-bounty528
xss284
rce158
google121
bragging-post120
exploit100
account-takeover99
open-source91
microsoft87
csrf78
facebook78
privilege-escalation76
authentication-bypass75
cve72
stored-xss72
malware68
access-control65
ai-agents63
reflected-xss61
writeup56
ssrf53
input-validation53
web-security53
sql-injection49
cross-site-scripting48
smart-contract46
tool46
defi45
ethereum45
privacy44
web-application43
apple43
phishing42
cloudflare41
browser40
information-disclosure39
dos38
web337
llm37
responsible-disclosure37
lfi36
burp-suite35
opinion35
api-security35
oauth34
automation34
vulnerability-disclosure34
reverse-engineering34
idor32
machine-learning32
0
4/10
This article explores optimizing prefix sum (scan) operations on ARM NEON SIMD instructions, demonstrating how to process multiple integer values in parallel using vector operations and interleaved load/store techniques to achieve speeds up to tens of gigabytes per second compared to scalar loop approaches.
performance-optimization
simd
arm-neon
algorithm-optimization
prefix-sum
vectorization
cpu-optimization
Daniel Lemire
ARM NEON
0
4/10
Benchmark comparison of vector search performance across MariaDB 11.8, MariaDB 12.3, and Postgres 18.2 with pgvector, showing MariaDB 12.3 achieves superior recall/precision and lower CPU usage per query on datasets ranging from 100k to 1M vectors.
vector-search
database-performance
benchmarking
mariadb
postgres
ann-benchmarks
indexing
cpu-optimization
MariaDB
MariaDB 11.8.5
MariaDB 12.3.0
Postgres 18.2
pgvector 0.8.1
Small Datum LLC
MariaDB Foundation
Mark Callaghan
Hetzner ax162-s