mirrors/hekate
1
0
Fork 0
mirror of https://github.com/CTCaer/hekate.git synced 2024-12-23 16:36:03 +00:00
Code Issues Releases Activity
1011 commits 2 branches 75 tags 5.5 MiB
Commit graph

16 commits

Author SHA1 Message Date
CTCaer
05833bb38c minerva: update to v1.4 
- Correct Zqlatch period checks
- Update periodic training
- Simplify some logic
- Fix some mr13 values
- Separate EMC channel enums from macros
- Add extra reg flushes
- Fix tree margin comparison signedness
 By using incorrect signedness on tree margins the delta taps would always apply.
 By casting margins to integer it now properly checks if it should apply delta taps on the new trimmers.
 This fixes a bug that exists in every Nvidia emc dvfs code.
 2021-05-11 10:23:08 +03:00
CTCaer
07d1982abf minerva: add compile time sdram voltage change 2021-04-11 10:31:57 +03:00
CTCaer
faf5651607 minerva: more accurate clock tree delays 
Additionally, do not restore source DPD ctrl when switching frequencies or training is not needed.
 2021-04-11 09:50:06 +03:00
CTCaer
8ce5d55eb8 mtc: Confine RAM OC completely inside minerva 
Enabling OVERCLOCK_FREQ takes care of everything without the need of changing minerva caller.
 2021-01-03 14:37:39 +02:00
CTCaer
afb749560a mtc: Fix temperature deltas for clk tree delays when negative 2021-01-03 14:35:21 +02:00
CTCaer
7a66e0298a mtc: Refactor various types 2021-01-03 14:33:56 +02:00
CTCaer
dfcdb2e1e6 mtc: Update minerva to simplify some logic 2020-12-26 17:28:49 +02:00
CTCaer
d37fe213d7 mtc: Name sdram ids 2020-06-14 17:39:39 +03:00
CTCaer
6e256d29c7 Utilize hekate's BDK for hekate main and Nyx 2020-06-14 16:45:45 +03:00
CTCaer
84328aa676 minerva: Make use of new minerva 
- Training and switch is now faster
- Compatibility checks: New Minerva does not allow old binaries. New binaries do not allow old Minerva
- MTC table is now in a safe region
- Periodic training period increased to every 250ms
 2019-12-04 21:56:45 +02:00
CTCaer
66c4f30bdf minerva: Update to v1.2 and use only integers 
Additionally remove support for DRAM types that Switch platform does not have.

This will reduce periodic training cost to 30us from 6ms.
 2019-12-04 21:46:33 +02:00
Kostas Missos
7c42f72b8a refactor: Remove all unwanted whitespace 2019-10-18 18:02:06 +03:00
ctcaer@gmail.com
52478833de [MTC] Utilize Minerva Training Cell 2019-06-30 03:49:33 +03:00
Kostas Missos
cfef8b4f72 Update libminerva to v1.1 2018-11-10 13:30:17 +02:00
Kostas Missos
ec1bb508b3 Fix minerva build 
This is still for testing it out.
The real usage will come later.
 2018-11-05 10:54:31 +02:00
Kostas Missos
cae9044c17 Minerva our DRAM trainer 
Supports up to 1600MHz and periodic training.

For more check here: https://github.com/CTCaer/minerva_tc
 2018-11-04 03:15:32 +02:00