Re: [PATCH] radeon: Use only a single work queue thread for crt

On Sun, Sep 6, 2020 at 4:54 AM Christian König < ckoenig.leichtzumer...@gmail.com> wrote: > Am 03.08.19 um 02:09 schrieb Andi Kleen: > > From: Andi Kleen > > > > I got tired of seeing a lot of radeon-crt kernel threads in ps on my > > workstation, one for each CPU and one for each display, which

Re: Slow memory access when using OpenCL without X11

On Sat, Mar 9, 2019 at 1:54 AM Lauri Ehrenpreis wrote: > > Even if it's using CPU for OCL (I know it's not doing this), why does memcpy > on CPU slow down permanently, if I'm not doing anything with OpenCL after > clCreateContext? > > As you see from test program it just does clCreateContext and

Re: [PATCH] drm/amdgpu: Partially revert commit 2dc80b006

an to send this patch internally for discussion. > So just thought that "Revert x" can cause the attention. > > Best Regards > Rex > > > > > -- > *From:* jv...@scarletmail.rutgers.edu on > behalf of Jan Vesely > *Sent:* Wed

Re: [PATCH] drm/amdgpu: Partially revert commit 2dc80b006

Hi, can you please improve the commit message? seeing "Revert $HASH" conveys zero information about the code change. I'm sorry for bringing this up again, but following AMDGPU/Radeon driver development is an exercise in frustration for anyone who is not on AMD's payroll. git commit logs like: "rev

Re: [PATCH libdrm 3/3] amdgpu: Destroy fd_hash table when the last device is removed.

On Fri, 2018-05-18 at 13:00 -0400, Jan Vesely wrote: > Fixes memory leak on module unload. > Analogous to mesa commit of the same name. > Signed-off-by: Jan Vesely > --- > amdgpu/amdgpu_device.c | 4 > 1 file changed, 4 insertions(+) > > diff --git a/amdgpu/

[PATCH libdrm 3/3] amdgpu: Destroy fd_hash table when the last device is removed.

Fixes memory leak on module unload. Analogous to mesa commit of the same name. Signed-off-by: Jan Vesely --- amdgpu/amdgpu_device.c | 4 1 file changed, 4 insertions(+) diff --git a/amdgpu/amdgpu_device.c b/amdgpu/amdgpu_device.c index e23dd3b3..34ac95b8 100644 --- a/amdgpu/amdgpu_device.c

[PATCH libdrm v2 1/3] amdgpu: Take lock before removing devices from fd_tab hash table.

Close the file descriptors under lock as well. v2: close fds after removing from hash table Signed-off-by: Jan Vesely --- amdgpu/amdgpu_device.c | 11 +++ 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/amdgpu/amdgpu_device.c b/amdgpu/amdgpu_device.c index 983b19ab

[PATCH libdrm 2/3] amdgpu/util_hash_table: Add helper function to count the number of entries in hash table

Analogous to the mesa commit of the same name. Signed-off-by: Jan Vesely --- amdgpu/util_hash_table.c | 12 amdgpu/util_hash_table.h | 2 ++ 2 files changed, 14 insertions(+) diff --git a/amdgpu/util_hash_table.c b/amdgpu/util_hash_table.c index 89a8bf9b..e06d4415 100644 --- a

Re: [PATCH libdrm 1/1] amdgpu: Take lock before removing devices from fd_tab hash table.

On Thu, 2018-05-10 at 19:33 -0400, Jan Vesely wrote: > Close the file descriptors under lock as well. > > Signed-off-by: Jan Vesely > --- > amdgpu/amdgpu_device.c | 11 +++ > 1 file changed, 7 insertions(+), 4 deletions(-) > > diff --git a/amdgpu/

[PATCH libdrm 1/1] amdgpu: Take lock before removing devices from fd_tab hash table.

Close the file descriptors under lock as well. Signed-off-by: Jan Vesely --- amdgpu/amdgpu_device.c | 11 +++ 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/amdgpu/amdgpu_device.c b/amdgpu/amdgpu_device.c index 983b19ab..f71fc050 100644 --- a/amdgpu/amdgpu_device.c +++ b

Re: [PATCH 1/1] drm/amdkfd: Do not ignore requested queue size during allocation

20 resume commads fit (otherwise I get spurious ENOMEM when the queue is full but still advancing). thanks, Jan > > Regards, > Felix > > > On 2017-11-29 04:43 PM, Jan Vesely wrote: > > On Mon, 2017-11-20 at 14:22 -0500, Felix Kuehling wrote: > > > I think this

Re: [PATCH 1/1] drm/amdkfd: Do not ignore requested queue size during allocation

at reason? (I'm running ROCK-1.6.x based kernel) thanks, Jan > > Regards, > Felix > > > On 2017-11-19 03:19 AM, Oded Gabbay wrote: > > On Thu, Nov 16, 2017 at 11:36 PM, Jan Vesely wrote: > > > Signed-off-by: Jan Vesely > > > --- > > > d

Re: [PATCH 1/2] drm/amdgpu:fix virtual dce bug

Message- > From: Jan Vesely [mailto:jv...@scarletmail.rutgers.edu] On Behalf Of Jan > Vesely > Sent: 2017年11月17日 0:40 > To: Liu, Monk ; amd-gfx@lists.freedesktop.org > Subject: Re: [PATCH 1/2] drm/amdgpu:fix virtual dce bug > > On Thu, 2017-11-16 at 11:14 +0800, Monk

[PATCH 1/1] drm/amdkfd: Do not ignore requested queue size during allocation

Signed-off-by: Jan Vesely --- drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c index f1d48281e322..b3bee39661ab 100644

Re: [PATCH 1/2] drm/amdgpu:fix virtual dce bug

On Thu, 2017-11-16 at 11:14 +0800, Monk Liu wrote: > this fix the issue that access memory after freed > after driver unloaded. can you please change the patch subject and commit message to something more descriptive? Jan > > Change-Id: I64e2488c18f5dc044b57c74567785da21fc028da > Signed-off-by:

Re: [PATCH 03/11] drm/amdkfd: Rectify the jiffies calculation error with milliseconds

On Fri, 2017-09-15 at 19:42 -0400, Felix Kuehling wrote: > From: Yong Zhao > > The timeout in milliseconds should not be regarded as jiffies. This > commit fixed that. > > Signed-off-by: Yong Zhao > Signed-off-by: Felix Kuehling > --- > drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c |

[PATCH libdrm 1/1] amdgpu: Add FX-9800P Bristol Ridge iGPU id

Signed-off-by: Jan Vesely --- data/amdgpu.ids | 1 + 1 file changed, 1 insertion(+) diff --git a/data/amdgpu.ids b/data/amdgpu.ids index 0b98c3c3..f6c65dd9 100644 --- a/data/amdgpu.ids +++ b/data/amdgpu.ids @@ -153,6 +153,7 @@ 9874, C5, AMD Radeon R6 Graphics 9874, C6, AMD Radeon R6

Re: [PATCH] iommu/amd: flush IOTLB for specific domains only (v2)

es.h > @@ -454,6 +454,8 @@ struct protection_domain { > bool updated; /* complete domain flush required */ > unsigned dev_cnt; /* devices assigned to this domain */ > unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ > + bool already_flushed;