> -Original Message-
> From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of
> xionghu@intel.com
> Sent: Thursday, August 13, 2015 14:28
> To: beignet@lists.freedesktop.org
> Cc: Luo, Xionghu
> Subject: [Beignet] [PATCH 1/3] fix bswap bug.
>
> From: Luo Xionghu
>
> -Original Message-
> From: Luo, Xionghu
> Sent: Tuesday, September 8, 2015 2:09 PM
> To: Gong, Zhigang; beignet@lists.freedesktop.org
> Cc: Gong, Zhigang
> Subject: RE: [Beignet] [PATCH] GBE: Use addRemappedFile to avoid creating
> temporary cl source file.
>
> This patch LGTM except som
This patch LGTM except some questions.
How didn't decide the name "stringInput.cl"?
And since this method works, we could also remap all the input headers in API
clCompileProgram to avoid create temp files under /tmp, anyway, this could be
processed in another patch.
Luo Xionghu
Best Regards
-
> -Original Message-
> From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of
> Guo, Yejun
> Sent: Monday, September 7, 2015 8:27 PM
> To: Zhigang Gong; beignet@lists.freedesktop.org
> Subject: Re: [Beignet] [PATCH 3/3] add optimization for local copy propagation
>
> Yes
Yes, there will be penalty for the case in your example. I read several
documents for local copy propagation, and none mentioned this case. :(
For the method to iterate new instructions/registers, it requires to add the
'new' flag during GenIR to SelectionIR period, since the current implementat
From: Guo Yejun
if the CL device does not support this builtin kernel,
the test returns PASS.
Signed-off-by: Guo Yejun
---
utests/CMakeLists.txt | 1 +
.../builtin_kernel_block_motion_estimate_intel.cpp | 109 +
utests/utest_helper.hpp
Signed-off-by: Chuanbo Weng
---
docs/Beignet.mdwn | 1 +
docs/howto/video-motion-estimation-howto.mdwn | 79 +++
2 files changed, 80 insertions(+)
create mode 100644 docs/howto/video-motion-estimation-howto.mdwn
diff --git a/docs/Beignet.mdwn
v2:
1. Just upload the first vme_state.
2. Remove duplicated code in check_opt1_extension.
3. Check image format before cl_gpgpu_bind_image_for_vme.
4. Fix error of getting mv. Because we suppose this kernel run in SIMD16
mode, so dword 0 of grf 1 should be
__gen_ocl_region(8,vme_result.s0),
__gen_ocl_vme is used for hardware accelerated video motion estimation.
It gets payload values as parameters and uses MOV to pass these payload
values to VME SEND Message's payload grfs. The int8 return value is used
to store SEND Message writeback.
v2:
Remove unnecessary 5 parameters(src_grf*) of
Please ignore this patchset, I will send out a new version soon.
-Original Message-
From: Weng, Chuanbo
Sent: Monday, September 07, 2015 13:01
To: beignet@lists.freedesktop.org
Cc: Weng, Chuanbo
Subject: [PATCH v2 1/4] Add built-in function __gen_ocl_vme.
__gen_ocl_vme is used for hardwa
10 matches
Mail list logo
