 Pelle Nilsson
|
ff1becce3a
Bugfix: First core in each die got too big nonce area to work on
|
11 years ago |
 Vitalii Demianets
|
162207d2e6
Titan: Submit stale shares while doing flushes
|
11 years ago |
|
Vitalii Demianets
|
9957145695
Typo in comment
|
11 years ago |
|
Vitalii Demianets
|
0770a46363
Increase die inactivity timeout to 20 secs
|
11 years ago |
|
Vitalii Demianets
|
a2fa9d4e1e
Slightly improve some debug messages
|
11 years ago |
|
Vitalii Demianets
|
318850075e
Use multi-part batched SPI transfers for flushes (saves 2 secs on each flush)
|
11 years ago |
|
Vitalii Demianets
|
f6c6f331f7
titan: Increase queue prefill value up to 20
|
11 years ago |
|
Vitalii Demianets
|
46fc0033c8
Whitespaces
|
11 years ago |
|
Vitalii Demianets
|
d90a9b5cfb
Do not return error on RECONFIGURE command
|
11 years ago |
|
Vitalii Demianets
|
0b8548c604
Flag for fast broadcast flushes. Not enabled: DC/DCs trip off easily!
|
11 years ago |
|
Vitalii Demianets
|
59e91fa7ac
Monitor die health, reconfigure it if no shares in 10 seconds
|
11 years ago |
|
Vitalii Demianets
|
7d42273f77
Work assignment and flushing is per-die, not per-ASIC
|
11 years ago |
|
Vitalii Demianets
|
014dcae797
Set flush flag after re-configuring the die.
|
11 years ago |
|
Vitalii Demianets
|
0f30d086bc
Refactoring: intermediate variables for first_proc and repr
|
11 years ago |
|
Vitalii Demianets
|
f1ac6e85ac
Flush cores one-by-one right before reconfiguring them
|
11 years ago |
|
Vitalii Demianets
|
a6c6b24e45
Define for the broadcast core address
|
11 years ago |
|
Vitalii Demianets
|
31264eb7c2
Don't forget to setup minerloop locking ("control_request") mechanism
|
11 years ago |
|
Vitalii Demianets
|
2b79bfe93e
First clumsy attempt to reconfigure die
|
11 years ago |
|
Vitalii Demianets
|
6d5dd3a39c
titan: configure_one_die func for configuring single die
|
11 years ago |
|
Vitalii Demianets
|
4d3d71b2e2
titan: fill all non-found ASIC structs with the same (invalid) data
|
11 years ago |
|
Vitalii Demianets
|
a1ee4dcfbf
titan: stubs for re-configuring dies through API command "procset"
|
11 years ago |
|
Vitalii Demianets
|
5e472f6a41
Core init parameters (nonce range) independent of number of found dies.
|
11 years ago |
 Luke Dashjr
|
4d6024c868
extra_work_queue so devices can influence their effect on the central work queue somewhat (titan needs less than 1-per-proc)
|
11 years ago |
|
Vitalii Demianets
|
028cf30ceb
titan: Do not fill up next slot immediately after urgent setwork
|
11 years ago |
|
Vitalii Demianets
|
91c9bf837c
titan: Pre-fill work queue so that all ASICs have fresh jobs after a flush
|
11 years ago |
|
Vitalii Demianets
|
fe130f1a8c
titan: Subdivide full nonce range only between cores in one ASIC (because works are now distributed per-ASIC too)
|
11 years ago |
|
Vitalii Demianets
|
e6c129d420
titan: DC/DCs does not like broadcast flushes (urgent setwork). Do not do it!
|
11 years ago |
|
Vitalii Demianets
|
12b289873f
titan: Preparation to setting threads-per-core externally, by user
|
11 years ago |
|
Vitalii Demianets
|
748dd115bb
titan: Re-flush cores in case of slot number collision
|
11 years ago |
|
Vitalii Demianets
|
de50f70e37
titan: Per-ASIC flush, per-ASIC work management
|
11 years ago |
