diff options
| author | Chuanbo Weng <chuanbo.weng@intel.com> | 2015-02-13 11:33:44 +0800 |
|---|---|---|
| committer | Zhigang Gong <zhigang.gong@intel.com> | 2015-02-13 11:56:29 +0800 |
| commit | 84aa07be3ec418c617b06f8e65e198795ffe7011 (patch) | |
| tree | 8bfa5779d807b299d7323c5e01c363b3ac9f8244 /src/CMakeLists.txt | |
| parent | 4f711f957791a2724272b2c88ee496d8e5412b17 (diff) | |
| download | beignet-84aa07be3ec418c617b06f8e65e198795ffe7011.tar.gz | |
Optimization of clEnqueueCopyImageToBuffer for 16 aligned case.
We can change the image_channel_order to CL_RGBA and
image_channel_data_type to CL_UNSIGNED_INT32 for some special
case, thus 16 bytes can be read by one work item. Bandwidth is
fully used.
v2:
Now we just optimize for IMAGE2D, so add judgement to not affect
other image type's code path.
Signed-off-by: Chuanbo Weng <chuanbo.weng@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Diffstat (limited to 'src/CMakeLists.txt')
| -rw-r--r-- | src/CMakeLists.txt | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index 939f58da..d4181d8d 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -49,7 +49,7 @@ cl_internal_copy_image_3d_to_2d cl_internal_copy_image_2d_to_3d cl_internal_copy cl_internal_copy_image_2d_to_2d_array cl_internal_copy_image_1d_array_to_1d_array cl_internal_copy_image_2d_array_to_2d_array cl_internal_copy_image_2d_array_to_2d cl_internal_copy_image_2d_array_to_3d cl_internal_copy_image_3d_to_2d_array -cl_internal_copy_image_2d_to_buffer cl_internal_copy_image_3d_to_buffer +cl_internal_copy_image_2d_to_buffer cl_internal_copy_image_2d_to_buffer_align16 cl_internal_copy_image_3d_to_buffer cl_internal_copy_buffer_to_image_2d cl_internal_copy_buffer_to_image_3d cl_internal_fill_buf_align8 cl_internal_fill_buf_align4 cl_internal_fill_buf_align2 cl_internal_fill_buf_unalign |