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>
diff --git a/src/core/CL/cl_kernels/tile_helpers.h b/src/core/CL/cl_kernels/tile_helpers.h
index f36f273..cc20616 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)