This patch LGTM.
The p returned by cl_program_link should be checked NULL immediately, anyway
this function is called several times in other place, I will send another patch
to fix it.
Luo Xionghu
Best Regards
-Original Message-
From: Beignet
suboffset() will not set .subnr correctly, as vec1() will get a horizontal
stride 0 register.
Signed-off-by: Ruiling Song
---
backend/src/backend/gen_register.hpp | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git
let's just keep things simple.
Signed-off-by: Ruiling Song
---
backend/src/backend/gen_register.hpp | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/backend/src/backend/gen_register.hpp
b/backend/src/backend/gen_register.hpp
index
All programs or none programs specified by input_programs contain a compiled
binary or library
for the device. Otherwise return CL_INVALID_OPERATION.
Correct this condition check.
Signed-off-by: Yang Rong
---
src/cl_api.c | 2 +-
src/cl_program.c | 43
From: Luo Xionghu
catch the error: out of host memery.
Signed-off-by: Luo Xionghu
---
src/cl_program.c | 18 ++
1 file changed, 18 insertions(+)
diff --git a/src/cl_program.c b/src/cl_program.c
index 0564b6f..82dd3e3 100644
---
I just think of another optimization opportunity that may be missed in your
algorithm.
As you use a map to record the possible to-be-coaleased
pair.
The phiCopySrc may be used in another phiNode in the same way.
Which the algorithm would not record. We may do it later.
Could
I have found this message was from drm and may be related to this patch
http://cgit.freedesktop.org/mesa/drm/commit/?id=30921483c70c6939f017476eac13da6aa26b3b3c.
And it was in drm just after 2.4.60, which I have tried that won't show this
message(I am using mesa/drm master now). As the patch
Nice catch! But may not be a correct fix.
We don't need to do the blocking event updating all the time.
We only need to do that when there is potential possibility
to leak a event. If a event has a user call back function
registered is such a case, and my best guessing here is:
one event in the
I have looked into the clWaitForEvents function and read about ocl spec, maybe
the uncompleted evnet in the last_event should not be there at all. It should
be finished in the waitforevent function and be deleted and freed in the
clReleaseEvent. My patch may cause unexpectable user function
LGTM, pushed, thanks.
> -Original Message-
> From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of
> xionghu@intel.com
> Sent: Monday, September 21, 2015 15:51
> To: beignet@lists.freedesktop.org
> Cc: Luo, Xionghu
> Subject: [Beignet] [PATCH] should check the
Patchset LGTM, pushed, thanks.
> -Original Message-
> From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of
> Ruiling Song
> Sent: Monday, September 21, 2015 15:40
> To: beignet@lists.freedesktop.org
> Cc: Song, Ruiling
> Subject: [Beignet] [PATCH 2/2] GBE: Minor
Before this patch, Beignet can only create cl buffer from external bo by
its handle using clCreateBufferFromLibvaIntel. Render node is the first
choice of accessing gpu in currect Beignet implementation. DRM_IOCTL_GEM_OPEN
is used by clCreateBufferFromLibvaIntel but forbidden in Render node mode.
Before this patch, Beignet can only create cl image from external bo by
its handle using clCreateImageFromLibvaIntel. Render node is the first
choice of accessing gpu in currect Beignet implementation. DRM_IOCTL_GEM_OPEN
is used by clCreateBufferFromLibvaIntel but forbidden in Render node mode.
So
This bug is cased by event flush, we should not only run usr event but also
event made by enqueue functions.
If the event haven't been completed before it is been overwite in the
last_event, the related gpgpu buffer will not be unreference. And will cause
all related drm buffers unreference and
14 matches
Mail list logo