Gets new blocks from daemon immediately without polling, saving ~0.5 seconds on average when daemon gets new block from the network. Also saves some CPU cycles because it doesn't need to poll daemon every second.
Testing: add "daemon-zmq-port": 28083 to xmrig's pool config in config.json and run ./monerod --testnet --zmq-pub tcp://127.0.0.1:28083
With `self-select` mode enabled, the `submit-to-origin` config option
will let the `SelfSelectClient` submit the solution to both
the daemon where it got the template from as well as to
the connected pool, for miners that want to do pool minining
with Monero and solo mining with an altcoin (merged mining variant).
Thank you and special credit to @StriderDM (https://github.com/StriderDM)!
- Use only steady timestamp counters to guarantee correctness
- CPU backend: directly measure total hashrate using raw hash counters from each thread; update data more often on ARM CPUs because they're slower
- GPU backends: directly measure total hashrate too, but use interpolator with 4 second lag to fix variance from batches of hashes
Total hashrate is now measured directly (realtime for CPU, 4 seconds lag for GPU), so it might differ a bit from the sum of all thread hashrates because data points are taken at different moments in time.
Overhead is reduced a lot since it doesn't have to go through all threads to calculate max total hashrate on every timer tick (2 times a second).
Set to false by default, gives 0.2% boost on Ryzen 7 3700X with 16 threads, but hashrate might be unstable on Ryzen between launches. Use with caution.
`scratchpad_prefetch_mode` can have 4 values:
0: off
1: use `prefetcht0` instruction (default, same as previous XMRig versions)
2: use `prefetchnta` instruction (faster on Coffee Lake and a few other CPUs)
3: use `mov` instruction
