Andrew Zonenberg on Nostr: After another round of tuning to remove some expensive barriers and optimize memory ...
After another round of tuning to remove some expensive barriers and optimize memory access patterns, the CDR PLL on this benchmark went from 13.6 ms baseline down to 4.5 on the AMD R9700.
The 3070 Ti is still faster, but by a much smaller margin: 7.8 ms on the original code down to 4.2 on the newly optimized.
Published at
2026-08-01 06:28:43 UTCEvent JSON
{
"id": "a7efbe4dca672fbd572af10b94961c7f7595fce460c33714ea126dbea39f163d",
"pubkey": "c35a8fae05a838b863707803bb1fdfcfcbb39adcf01ee1a9fc52ef44998ce4c0",
"created_at": 1785565723,
"kind": 1,
"tags": [
[
"proxy",
"https://ioc.exchange/users/azonenberg/statuses/117018835251819741",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub"
]
],
"content": "After another round of tuning to remove some expensive barriers and optimize memory access patterns, the CDR PLL on this benchmark went from 13.6 ms baseline down to 4.5 on the AMD R9700.\n\nThe 3070 Ti is still faster, but by a much smaller margin: 7.8 ms on the original code down to 4.2 on the newly optimized.",
"sig": "7e55871a3b07e22050057088c83df63ad82f3b76269da1c869efc54bcf5795cb57318c8a838f7bb970589d812fc8a83d43dfa35f220ccb82248be0d044041be1"
}
