diff options
author | Giorgio Arena <giorgio.arena@arm.com> | 2021-04-28 16:11:51 +0100 |
---|---|---|
committer | Giorgio Arena <giorgio.arena@arm.com> | 2021-04-29 17:06:28 +0000 |
commit | 3ecf9fefa6f6299a0736599f150d4791cc8345d9 (patch) | |
tree | 749d73c8496d152600f528e442b4e4f11a81621e /src/core/CL/cl_kernels/helpers.h | |
parent | 8ed3ac11352d1ebb2c69787432fa5893997f1c50 (diff) | |
download | ComputeLibrary-3ecf9fefa6f6299a0736599f150d4791cc8345d9.tar.gz |
Remove OpenCL padding: CLReductionOperationKernel
Change the parallel implementation across the X, now every thread computes one row
Add missing test for MEAN_SUM
Make reduction on any axis != 0 work with num_channels > 1
Resolve COMPMID-3917
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: Ib0f99540104e3c253bcd1ea637833db533f5e76e
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5522
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/CL/cl_kernels/helpers.h')
-rw-r--r-- | src/core/CL/cl_kernels/helpers.h | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/src/core/CL/cl_kernels/helpers.h b/src/core/CL/cl_kernels/helpers.h index 2eae5ee1c9..6cd76373d2 100644 --- a/src/core/CL/cl_kernels/helpers.h +++ b/src/core/CL/cl_kernels/helpers.h @@ -567,6 +567,16 @@ #define SUM_REDUCE_STR(x, size) sum_reduce_##size(x) #define SUM_REDUCE(x, size) SUM_REDUCE_STR(x, size) +#define prod_reduce_1(x) (x) +#define prod_reduce_2(x) ((x).s0) * ((x).s1) +#define prod_reduce_3(x) prod_reduce_2((x).s01) * ((x).s2) +#define prod_reduce_4(x) prod_reduce_2((x).s01) * prod_reduce_2((x).s23) +#define prod_reduce_8(x) prod_reduce_4((x).s0123) * prod_reduce_4((x).s4567) +#define prod_reduce_16(x) prod_reduce_8((x).s01234567) * prod_reduce_8((x).s89ABCDEF) + +#define PROD_REDUCE_STR(x, size) prod_reduce_##size(x) +#define PROD_REDUCE(x, size) PROD_REDUCE_STR(x, size) + #define max_reduce_1(x) (x) #define max_reduce_2(x) max(((x).s0), ((x).s1)) #define max_reduce_3(x) max(max_reduce_2((x).s01), ((x).s2)) |