diff options
author | Adnan AlSinan <adnan.alsinan@arm.com> | 2021-11-08 17:46:39 +0000 |
---|---|---|
committer | Adnan AlSinan <adnan.alsinan@arm.com> | 2021-11-09 14:42:08 +0000 |
commit | 17975a61c5d7cbdc37c11d38e23eab8afa43f27c (patch) | |
tree | 2b9a82377dc90399dfb1a2e9e70e2dabb9735987 /src/core/CL/cl_kernels/tile_helpers.h | |
parent | a3b13b500e61a02d1e73148ccd97d054ef7c22ec (diff) | |
download | ComputeLibrary-17975a61c5d7cbdc37c11d38e23eab8afa43f27c.tar.gz |
Improve start-up time for ClScale
- Add macro guard for different kernels in scale.cl
- Rework TENSOR4D to the new format
- Pass scale_x and scale_y at runtime
Resolves COMPMID-4886
Signed-off-by: Adnan AlSinan <adnan.alsinan@arm.com>
Change-Id: Ib904a703d511fb8260618057ac92e5ea9efeee2b
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6619
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/CL/cl_kernels/tile_helpers.h')
-rw-r--r-- | src/core/CL/cl_kernels/tile_helpers.h | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/src/core/CL/cl_kernels/tile_helpers.h b/src/core/CL/cl_kernels/tile_helpers.h index f36f273e1d..cc20616867 100644 --- a/src/core/CL/cl_kernels/tile_helpers.h +++ b/src/core/CL/cl_kernels/tile_helpers.h @@ -104,6 +104,32 @@ #define TENSOR4D_STR(name, type) TENSOR4D_##type(name) #define TENSOR4D(name, type) TENSOR4D_STR(name, type) +#define TENSOR4D_T_IMAGE(name) \ + __read_only image2d_t name##_img, \ + __global uchar *name##_ptr, \ + uint name##_stride_y, \ + uint name##_stride_z, \ + uint name##_stride_w, \ + uint name##_c, \ + uint name##_w, \ + uint name##_h, \ + uint name##_n, \ + uint name##_offset_first_element_in_bytes + +#define TENSOR4D_T_BUFFER(name) \ + __global uchar *name##_ptr, \ + uint name##_stride_y, \ + uint name##_stride_z, \ + uint name##_stride_w, \ + uint name##_c, \ + uint name##_w, \ + uint name##_h, \ + uint name##_n, \ + uint name##_offset_first_element_in_bytes + +#define TENSOR4D_T_STR(name, type) TENSOR4D_T_##type(name) +#define TENSOR4D_T(name, type) TENSOR4D_T_STR(name, type) + #if !defined(UNROLL_WITH_PRAGMA) #define UNROLL_INCR(idx, step, macro) idx += (step); (macro) |