diff options
author | Felix Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com> | 2023-09-27 17:46:17 +0100 |
---|---|---|
committer | felixjohnny.thomasmathibalan <felixjohnny.thomasmathibalan@arm.com> | 2023-09-28 12:08:05 +0000 |
commit | afd38f0c617d6f89b2b4532c6c44f116617e2b6f (patch) | |
tree | 03bc7d5a762099989b16a656fa8d397b490ed70e /src/dynamic_fusion/sketch/gpu/ckw_driver/components/utils/WriterHelper.h | |
parent | bdcb4c148ee2fdeaaddf4cf1e57bbb0de02bb894 (diff) | |
download | ComputeLibrary-afd38f0c617d6f89b2b4532c6c44f116617e2b6f.tar.gz |
Apply clang-format on repository
Code is formatted as per a revised clang format configuration
file(not part of this delivery). Version 14.0.6 is used.
Exclusion List:
- files with .cl extension
- files that are not strictly C/C++ (e.g. Android.bp, Sconscript ...)
And the following directories
- compute_kernel_writer/validation/
- tests/
- include/
- src/core/NEON/kernels/convolution/
- src/core/NEON/kernels/arm_gemm/
- src/core/NEON/kernels/arm_conv/
- data/
There will be a follow up for formatting of .cl files and the
files under tests/ and compute_kernel_writer/validation/.
Signed-off-by: Felix Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>
Change-Id: Ib7eb1fcf4e7537b9feaefcfc15098a804a3fde0a
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10391
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Diffstat (limited to 'src/dynamic_fusion/sketch/gpu/ckw_driver/components/utils/WriterHelper.h')
-rw-r--r-- | src/dynamic_fusion/sketch/gpu/ckw_driver/components/utils/WriterHelper.h | 31 |
1 files changed, 25 insertions, 6 deletions
diff --git a/src/dynamic_fusion/sketch/gpu/ckw_driver/components/utils/WriterHelper.h b/src/dynamic_fusion/sketch/gpu/ckw_driver/components/utils/WriterHelper.h index e2b8584b99..6ba2b2f651 100644 --- a/src/dynamic_fusion/sketch/gpu/ckw_driver/components/utils/WriterHelper.h +++ b/src/dynamic_fusion/sketch/gpu/ckw_driver/components/utils/WriterHelper.h @@ -26,6 +26,7 @@ #include "arm_compute/core/utils/misc/Utility.h" #include "ckw/TensorTileSampler.h" + #include "src/dynamic_fusion/sketch/gpu/ckw_driver/GpuCkwComponentArgument.h" #include "src/dynamic_fusion/sketch/gpu/ckw_driver/GpuCkwKernelWriter.h" #include "src/dynamic_fusion/sketch/gpu/ckw_driver/GpuCkwScopedKernelWriter.h" @@ -44,9 +45,14 @@ using SamplerCreator = std::function<TensorTileSampler(GpuCkwScopedKernelWriter /** Load src and dst tiles of dimension [m0, n0] only when not loaded and prepare the sampler */ -inline void load_src_dst_tiles_and_prepare_sampler(GpuCkwScopedKernelWriter &writer, GpuCkwComponentArgument *src, GpuCkwComponentArgument *dst, int32_t m0, int32_t n0, SamplerCreator create_sampler) +inline void load_src_dst_tiles_and_prepare_sampler(GpuCkwScopedKernelWriter &writer, + GpuCkwComponentArgument *src, + GpuCkwComponentArgument *dst, + int32_t m0, + int32_t n0, + SamplerCreator create_sampler) { - if(!src->has_tile()) + if (!src->has_tile()) { const auto sampler = create_sampler(writer, m0, n0); writer->op_load_once(src, sampler); @@ -61,7 +67,7 @@ inline void load_src_dst_tiles_and_prepare_sampler(GpuCkwScopedKernelWriter &wri const auto &sampler = src->tile_sampler(); // Prepare the output tile. - if(!dst->has_tile()) + if (!dst->has_tile()) { auto &tile = writer->declare_tile("dst_tile", src_tile.tile_info()); dst->init_virtual_tensor(tile, sampler); @@ -78,7 +84,13 @@ inline void load_src_dst_tiles_and_prepare_sampler(GpuCkwScopedKernelWriter &wri * @param[in] prefix Prefix to all the tiles declared within this function * @param[in] const_0 Constant tile of value 0 */ -inline void get_coord(GpuCkwScopedKernelWriter writer, TileOperand &coord, const TileOperand &gid, int32_t step_v, int32_t leftover_step_v, const std::string &prefix, const TileOperand &const_0) +inline void get_coord(GpuCkwScopedKernelWriter writer, + TileOperand &coord, + const TileOperand &gid, + int32_t step_v, + int32_t leftover_step_v, + const std::string &prefix, + const TileOperand &const_0) { auto &step = writer->declare_tile(prefix + "step", step_v); auto &leftover_step = writer->declare_tile(prefix + "leftover_step", leftover_step_v); @@ -122,8 +134,15 @@ inline void get_coord(GpuCkwScopedKernelWriter writer, TileOperand &coord, const * * @return TensorTileSampler */ -inline TensorTileSampler create_boundary_aware_2d_sampler(GpuCkwScopedKernelWriter writer, TileOperand &gid_0, TileOperand &gid_1, int32_t dim0_v, int32_t dim1_v, int32_t n0_v, int32_t m0_v, - const std::string prefix, TileOperand &const_0) +inline TensorTileSampler create_boundary_aware_2d_sampler(GpuCkwScopedKernelWriter writer, + TileOperand &gid_0, + TileOperand &gid_1, + int32_t dim0_v, + int32_t dim1_v, + int32_t n0_v, + int32_t m0_v, + const std::string prefix, + TileOperand &const_0) { // Clamp tile size [n0, m0] against dimension [dim0, dim1] // This is needed to: |