Jack (Jian); amd-gfx@lists.freedesktop.org; Grodzovsky,
Andrey; Liu, Monk; Deng, Emily
*主题:* Re: [PATCH v4] drm/amd/amdgpu implement tdr advanced mode
Andrey needs to review the reste, but essentially I don't see the
reason why you need this drm_sched_resubmit_jobs2().
Christian.
Am 10
(Jian); amd-gfx@lists.freedesktop.org; Grodzovsky, Andrey;
Liu, Monk; Deng, Emily
主题: Re: [PATCH v4] drm/amd/amdgpu implement tdr advanced mode
Andrey needs to review the reste, but essentially I don't see the reason why
you need this drm_sched_resubmit_jobs2().
Christian.
Am 10.03.21 um
PATCH v4] drm/amd/amdgpu implement tdr advanced mode
Am 10.03.21 um 12:19 schrieb Jack Zhang:
> [Why]
> Previous tdr design treats the first job in job_timeout as the bad job.
> But sometimes a later bad compute job can block a good gfx job and
> cause an unexpected gfx job timeout becaus
; Grodzovsky, Andrey
; Liu, Monk ; Deng, Emily
Subject: Re: [PATCH v4] drm/amd/amdgpu implement tdr advanced mode
Am 10.03.21 um 12:19 schrieb Jack Zhang:
> [Why]
> Previous tdr design treats the first job in job_timeout as the bad job.
> But sometimes a later bad compute job can block a goo
Am 10.03.21 um 12:19 schrieb Jack Zhang:
[Why]
Previous tdr design treats the first job in job_timeout as the bad job.
But sometimes a later bad compute job can block a good gfx job and
cause an unexpected gfx job timeout because gfx and compute ring share
internal GC HW mutually.
[How]
This pat
[Why]
Previous tdr design treats the first job in job_timeout as the bad job.
But sometimes a later bad compute job can block a good gfx job and
cause an unexpected gfx job timeout because gfx and compute ring share
internal GC HW mutually.
[How]
This patch implements an advanced tdr mode.It invol
