|
fa4ce8da
|
2012-02-18T22:29:12
|
|
Keep track of intended engine clock speed and only adjust up if it's higher than the last intended speed. This avoids setting the clock speed to one
relative to a lower profile one by mistake.
|
|
|
d1cf80a5
|
2012-02-18T19:49:52
|
|
Use gpu-memdiff on startup if an engine clockspeed is set and a memdiff value is set.
|
|
|
66ea9304
|
2012-02-18T19:43:23
|
|
Revert "Adjust engine speed up according to performance level engine setting, not the current engine speed."
This reverts commit 68217ef6eed95f37da9024f96d098a3114e75c75.
This did not have the desired effect and only added complexity.
|
|
|
c4270974
|
2012-02-18T19:43:17
|
|
Revert "Logic fail on engine multiplier."
This reverts commit b0787e07c88cc5ae9a5a23bbcc004e180e4a24a5.
2nd of 3.
|
|
|
eb5dcc60
|
2012-02-18T19:42:56
|
|
Revert "Correct yet more logic fail :("
This reverts commit 83b76da2c659bbff8d17236ef1b3e69a0ce6228a.
First of 3.
|
|
|
83b76da2
|
2012-02-13T10:53:03
|
|
Correct yet more logic fail :(
|
|
|
b0787e07
|
2012-02-13T10:47:05
|
|
Logic fail on engine multiplier.
|
|
|
68217ef6
|
2012-02-13T10:37:35
|
|
Adjust engine speed up according to performance level engine setting, not the current engine speed.
|
|
|
07c2ee53
|
2012-02-12T17:00:44
|
|
Put win32 equivalents of nanosleep and sleep into compat.h fixing sleep() for adl.c.
|
|
|
405a2120
|
2012-02-11T20:11:18
|
|
Remove unnecessary check for opt_debug on every invocation of applog at LOG_DEBUG and place the check in applog().
|
|
|
2b61d973
|
2012-02-11T19:54:15
|
|
Remove the test for whether the device is on the highest profil level before raising the GPU speed as it is ineffectual and may prevent raising the GPU
speed.
|
|
543265d6
|
2012-01-24T14:34:17
|
|
Generalize --temp-cutoff and implement support for reading temperature from BitFORCE FPGAs
|
|
|
c72a8b8c
|
2012-02-05T22:41:37
|
|
Silence ADL warnings.
|
|
|
23685aa4
|
2012-02-05T17:28:53
|
|
Continue auto-management of fan and engine speeds even if a device is disabled for safety reasons.
|
|
|
f8fed37e
|
2012-02-05T17:24:26
|
|
No need to check we're highest performance level when throttling GPU engine speed.
|
|
|
af5aaece
|
2012-01-30T21:15:47
|
|
Revert "Pass the correct GPU from the menu to the adl code."
This reverts commit 7bcda9a28fcaff801ed9ee9e0b6613cbdb3be646.
Corrected for virtual device twice by mistake.
|
|
|
94059c06
|
2012-01-30T21:07:16
|
|
Ensure all virtual_gpu entries are set when the number of ADL devices does not match the number of OpenCL devices.
|
|
|
c9404f4d
|
2012-01-30T15:33:55
|
|
Make sure to set virtual adapters if --dev-reorder is not enabled or device numbers don't match.
|
|
|
5a14ec53
|
2012-01-30T15:21:14
|
|
Add a --dev-reorder option to only reorder devices according to PCI Bus ID when requested.
|
|
|
7bcda9a2
|
2012-01-30T12:42:43
|
|
Pass the correct GPU from the menu to the adl code.
|
|
|
a73156ac
|
2012-01-30T10:02:51
|
|
Display GPU number and device name when ADL is successfully enabled on it.
|
|
|
176bbcbc
|
2012-01-30T09:44:19
|
|
Display GPU ordering remapping in verbose mode.
|
|
|
89196038
|
2012-01-30T09:15:20
|
|
Don't fail in the case the number of ADL and OpenCL devices do not match, and do not attempt to reorder devices unless they match.
Instead give a warning about the likely cause and the potential consequence of it - Hardware monitoring may NOT match up with devices.
|
|
|
f0746f0b
|
2012-01-30T08:18:50
|
|
Display error codes should ADL not return ADL_OK in the more critical function calls.
|
|
|
cdcaaba6
|
2012-01-30T08:06:23
|
|
Revert "Add ADL_Overdrive5_ThermalDevices_Enum interface."
This reverts commit 1e1519e93ec6a3de432dd0b34504675f037c3542.
|
|
|
430a1954
|
2012-01-30T08:06:00
|
|
Revert "Read off lpThermalControllerInfo from each ADL device."
This reverts commit 2d29cdb6117be29ff6353d94a6be0784a588fdb6.
|
|
|
4ae0aad1
|
2012-01-30T08:05:36
|
|
Revert "Set iSize for thermal device enum first."
This reverts commit 990bb4a994261fb0aca8a6bd1b324a3007583207.
Thermal devices is not used. 1st of 3 reverts.
|
|
|
82af288e
|
2012-01-29T22:57:29
|
|
Revert "Fix various harmless warnings."
This reverts commit a4b67f030fc0c7e2b18e79114a441c1e1617d5f8.
|
|
|
a4b67f03
|
2012-01-29T21:06:17
|
|
Fix various harmless warnings.
|
|
|
a8e46a07
|
2012-01-29T20:47:08
|
|
Add extensive ADL based device info in debug mode.
|
|
|
83a83676
|
2012-01-29T13:49:08
|
|
Linux's ADL uses a busnumber in descending order for devices so enumerate them in the opposite order to windows.
|
|
|
4bf01f01
|
2012-01-28T12:08:55
|
|
Fix potential overflow.
|
|
|
05970127
|
2012-01-28T11:26:56
|
|
Carry virtual gpu number across.
|
|
|
3bc05834
|
2012-01-28T11:19:28
|
|
Iterate and change virtual device order instead of shuffling ram.
|
|
|
371e5f68
|
2012-01-28T09:22:33
|
|
Reorder displayed devices to map to physical locations and initialise according to logical location instead.
|
|
|
5a0b4f62
|
2012-01-28T01:56:12
|
|
Map GPU devices to virtual devices in their true physical order based on BusNumber.
|
|
|
06fd9c4a
|
2012-01-26T23:27:10
|
|
Detect dual GPU cards by iterating through all GPUs, finding ones without fanspeed and matching twins with fanspeed one bus ID apart.
|
|
487327f8
|
2012-01-26T14:06:31
|
|
Remove compile warning
|
|
|
4995b7c2
|
2012-01-25T16:34:39
|
|
On dual GPUs, only autotune the shared fan once per gpu autotune cycle.
|
|
|
c009c6cd
|
2012-01-25T16:16:28
|
|
Don't try to explicitly drift to exactly the target temperature, aim for just below it.
|
|
|
312724ce
|
2012-01-25T15:48:28
|
|
Adjust fan speed gently while in the optimal range when temperature is drifting to minimise overshoot in either direction.
|
|
|
9549dacf
|
2012-01-25T01:19:58
|
|
Detect dual GPU cards via the indirect information of - 1st card has a fan controller. 2nd card does not have a fan controller, cards share the same
device name, and are one bus ID apart. Use this information to create paired devices, displaying the fan speed on both devices and using the hottest
temperature from either GPU to control the overall fanspeed.
|
|
|
990bb4a9
|
2012-01-23T10:54:21
|
|
Set iSize for thermal device enum first.
|
|
|
2d29cdb6
|
2012-01-23T09:25:53
|
|
Read off lpThermalControllerInfo from each ADL device.
|
|
|
1e1519e9
|
2012-01-23T09:20:21
|
|
Add ADL_Overdrive5_ThermalDevices_Enum interface.
|
|
|
ec2c0b78
|
2012-01-22T18:24:55
|
|
Add API commands: config, switchpool, gpu settings, save
|
|
|
845961af
|
2012-01-05T19:26:01
|
|
Refactor to abstract device-specific code
|
|
|
400cb21d
|
2011-12-24T08:06:53
|
|
Off by one error in performance level.
|
|
|
f4d657ee
|
2011-12-24T07:35:42
|
|
Only adjust gpu engine speed in autotune mode if the gpu is currently at the performance level of that being adjusted.
|
|
|
8c63061e
|
2011-10-23T20:50:52
|
|
Allow a fixed speed difference between memory and GPU clock speed that will change memory speed when GPU speed is changed in autotune mode.
|
|
|
5976f6b3
|
2011-10-14T21:51:55
|
|
Get rid of unused variable.
|
|
|
0ae3f718
|
2011-09-23T10:45:43
|
|
Check last temperature we reached and don't change fan speed if it's already correcting.
|
|
|
b8ea0dd1
|
2011-09-17T13:23:58
|
|
Update curses logging to allow LOG_WARNING and LOG_ERR messages to still go through while within the menu, and drop share message to LOG_NOTICE.
|
|
|
5a24c282
|
2011-09-16T16:46:14
|
|
Try to set temperature regardless of whether get fanspeed fails. This may need to be reverted if it causes problems.
|
|
|
12e99c83
|
2011-09-16T16:42:11
|
|
Initialise all the iSizes of the ADL structures for completeness.
|
|
|
07c21bcb
|
2011-09-16T10:40:58
|
|
Don't forget to set the actual fanspeed too!
|
|
|
3c38adc9
|
2011-09-16T10:27:36
|
|
Only set the speed once, but set it only if fanspeed get says the card is ok and ready.
|
|
|
67fe6ab7
|
2011-09-16T10:26:25
|
|
Don't both with adapter speed set as it has no effect on mining speed.
|
|
|
92e1ffd3
|
2011-09-16T08:31:27
|
|
Store the targetfan even if the later getfanspeed fails in case it's temporary.
|
|
|
8feb661d
|
2011-09-15T20:46:39
|
|
Set the fanspeed in coarse rounded up values and then ever finer grained values in case the card does not support fine values.
|
|
|
3f10e80a
|
2011-09-15T12:18:30
|
|
If the user defined flag is not set on fanspeed, set the fanspeed with it first.
|
|
|
87ec3f47
|
2011-09-15T11:21:54
|
|
Convert fanspeed management to default on exit.
|
|
|
918ec7b0
|
2011-09-14T23:01:07
|
|
Enable adl earlier to allow values to be set in init_adl or they're silently ignored!
|
|
|
1db6ab0b
|
2011-09-14T22:18:49
|
|
Set targetfan when fanspeed is set on parameters.
|
|
|
2e09eee7
|
2011-09-14T21:45:04
|
|
Use the gpu_fan set value as the starting fan speed.
Don't try and change the value if get() doesn't match as it's unreliable, just save the reentrant value.
Limit fanspeeds to reported iMax and iMin.
|
|
|
88eb514c
|
2011-09-11T11:57:08
|
|
Only display supported values from fanspeed on change settings.
|
|
|
b4009ada
|
2011-09-11T11:47:22
|
|
Remove redundant check.
|
|
|
ebae03f2
|
2011-09-11T11:38:02
|
|
Do not bother resetting values to old ones if changes to GPU parameters report failure, instead returning a failure code only if the return value from get() differs.
|
|
|
dff1a81d
|
2011-09-11T11:25:28
|
|
Use a re-entrant value to store what fanspeed we're trying to set in case the card doesn't support small changes.
Force it to a multiple of 10% if it fails on trying to speed up the fan.
|
|
|
076677dd
|
2011-09-11T11:08:01
|
|
Flag any devices with autofan or autogpu as being managed.
|
|
|
a602f4e5
|
2011-09-11T11:06:52
|
|
Only force the adapter speed to high if we've flagged this device as being managed.
|
|
|
25c77ae8
|
2011-09-09T11:53:45
|
|
Only display values in the log if they're supported and standardise device log line printing.
|
|
|
2fafdab9
|
2011-09-09T10:03:10
|
|
Allow adapterid 0 cards to enumerate as a device as they will be non-AMD cards, and enable ADL on any AMD card.
|
|
|
b7d81781
|
2011-09-08T14:10:55
|
|
Setting the hysteresis is unlikely to be useful on the fly and doesn't belong in the per-gpu submenu.
|
|
|
0e1c2916
|
2011-09-08T14:05:41
|
|
Display fan range in autofan status.
|
|
|
e0a9f1aa
|
2011-09-08T13:53:10
|
|
Allow temperature targets to be set on a per-card basis on the command line.
|
|
|
d6f3bd05
|
2011-09-08T13:33:24
|
|
Display which GPU has overheated in warning message.
|
|
|
b50041c8
|
2011-09-08T13:29:13
|
|
Allow per-device fan ranges to be set and use them in auto-fan mode.
|
|
|
9b5cd618
|
2011-09-08T13:04:39
|
|
Implement accepting a range of engine speeds as well to allow a lower limit to be specified on the command line.
|
|
|
7ea7f5f3
|
2011-09-08T10:51:32
|
|
Allow temperatures greater than 100 degrees.
|
|
|
4628db5b
|
2011-09-07T10:44:57
|
|
Change the fan speed by only 5% if it's over the target temperature but less than the hysteresis value to minimise overshoot down in temperature.
|
|
|
3997f308
|
2011-09-07T10:43:26
|
|
Add a thermal cutoff option as well and set it to 95 degrees by default.
|
|
|
311420db
|
2011-09-07T10:03:06
|
|
Flag adl as active if any card is successfully activated.
|
|
|
058303bc
|
2011-09-07T10:00:10
|
|
Only reset values on exiting if we've ever modified them.
|
|
|
b8be1e6c
|
2011-09-07T09:17:51
|
|
Ignore whether the display is active or not since only display enabled devices work this way, and we skip over repeat entries anwyay.
|
|
|
f89c032d
|
2011-09-06T12:04:23
|
|
The ° character is not reliably shown on all platforms so remove it.
|
|
|
fd23532b
|
2011-09-06T09:41:58
|
|
Make adl attempt to compile only on win32 or linux since there is no support for it on onther platforms, and fix sleep() definition on win32.
|
|
|
16aff37c
|
2011-09-06T09:36:42
|
|
Fix compilation errors on mingw32 to do with order of pulling in headers, curses.h and definition of bool.
|
|
|
9f618f4a
|
2011-09-05T17:14:09
|
|
Lower profile settings cannot be higher than higher profile ones so link any drops in settings.
|
|
|
ca379355
|
2011-09-05T16:14:43
|
|
Ramp up the fan more if we're over target temperature.
|
|
|
bc972440
|
2011-09-05T16:05:04
|
|
Provide locking around all adl calls to prevent races.
|
|
|
666d724b
|
2011-09-05T13:48:06
|
|
Set a safe starting fan speed if we're automanaging the speeds.
|
|
|
5fc56a45
|
2011-09-05T09:36:43
|
|
Force the speed to high on startup and restore it to whatever the setting was on exit.
|
|
|
cb29fb7d
|
2011-09-05T09:04:15
|
|
Remove the safety checks in speed setting since confirmation is done first in the menu, then show the new current values after a short pause.
|
|
|
ee06a3ba
|
2011-09-05T08:33:00
|
|
Limit fanspeed to 85% properly when temperature is below overheat levels.
|
|
|
40491cd5
|
2011-09-05T08:32:31
|
|
Change default hysteresis to 3 degrees for lower average fanspeeds.
|
|
|
47f1a759
|
2011-09-04T23:23:31
|
|
Implement setting the GPU powertune value of all devices or each device as a comma separated value.
|
|
|
656bacc5
|
2011-09-04T23:14:36
|
|
Get the value of powertune in get_stats.
|
|
|
7711c6fb
|
2011-09-04T23:10:57
|
|
Implement changing of powertune value from the GPU change settings menu.
|
|
|
bd292258
|
2011-09-04T22:56:19
|
|
Add support for monitoring powertune setting.
|