It's observed that most GPU jobs utilize less than one server, typically
with each GPU being used by an independent job. If a job consumed poisoned
data, a SIGBUS signal will be sent to terminate it. Meanwhile, the
gpu_recovery parameter is set to -1 by default, the amdgpu driver resets
all GPUs on
Hi,
i noticed in drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c that
arcturus never reclocks its memory, allways keeping it at the boot up
default of 1200 Mhz regardless of load.
This is despite teh fact the vbios on my m100 devices contain other
uclk states too:
FreqTableUclk:
FreqTable
This patch checks and handles the return code of the called function.
Signed-off-by: Andrew Martin
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 2 ++
drivers/gpu/drm/amd/amdkfd/kfd_debug.c| 19 ++-
.../drm/amd
[Public]
Might be worth changing the commit headline to what the patch does, something
like
Don't ignore return codes
Or
Various return code cleanup
Otherwise it sounds like your patch is intentionally ignoring return codes,
which is the opposite of what you're doing. Also 2 comments below.
>
[Public]
> -Original Message-
> From: Russell, Kent
> Sent: Monday, December 30, 2024 12:44 PM
> To: Martin, Andrew ; amd-
> g...@lists.freedesktop.org
> Cc: Kuehling, Felix ; Martin, Andrew
>
> Subject: RE: [PATCH v2] drm/amdkfd: Ignored various return code
>
> [Public]
>
> Might be wor
This patch checks and handles the return code of various functions.
Signed-off-by: Andrew Martin
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 2 ++
drivers/gpu/drm/amd/amdkfd/kfd_debug.c| 19 ++-
.../drm/amd/a
This patch adds the cec_notifier feature to amdgpu driver.
The changes will allow amdgpu driver code to notify EDID
and HPD changes to an eventual CEC adapter.
Signed-off-by: Kun Liu
---
drivers/gpu/drm/amd/display/Kconfig | 2 +
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 82
在 2024/12/30 04:11, Christian König 写道:
Am 28.12.24 um 07:32 schrieb Shuai Xue:
It's observed that most GPU jobs utilize less than one server, typically
with each GPU being used by an independent job. If a job consumed poisoned
data, a SIGBUS signal will be sent to terminate it. Meanwhile, th
On 2024-12-18 16:35:21, Darrick J. Wong wrote:
> On Tue, Dec 17, 2024 at 11:58:12PM +0100, Mirsad Todorovac wrote:
> > The source static analysis tool gave the following advice:
> >
> > ./fs/xfs/libxfs/xfs_dir2.c:382:15-22: WARNING opportunity for kmemdup
> >
> > → 382 args->value = kmal
This patch checks and handles the return code of the called function.
Signed-off-by: Andrew Martin
---
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 2 ++
drivers/gpu/drm/amd/amdkfd/kfd_debug.c| 19 ++-
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 11 ++-
3
[Public]
> -Original Message-
> From: Martin, Andrew
> Sent: Monday, December 30, 2024 1:15 PM
> To: Russell, Kent ; amd-gfx@lists.freedesktop.org
> Cc: Kuehling, Felix
> Subject: RE: [PATCH v2] drm/amdkfd: Ignored various return code
>
> [Public]
>
> > -Original Message-
> > Fro
[Public]
@Russell, Kent
Thanks, I will send out the next version soon!
> -Original Message-
> From: Russell, Kent
> Sent: Monday, December 30, 2024 1:37 PM
> To: Martin, Andrew ; amd-
> g...@lists.freedesktop.org
> Cc: Kuehling, Felix
> Subject: RE: [PATCH v2] drm/amdkfd: Ignored vario
12 matches
Mail list logo