diff --git a/dnn/src/arm_common/pooling/algo.cpp b/dnn/src/arm_common/pooling/algo.cpp index 061c8083..efb700e2 100644 --- a/dnn/src/arm_common/pooling/algo.cpp +++ b/dnn/src/arm_common/pooling/algo.cpp @@ -13,6 +13,7 @@ #include "megdnn/opr_param_defs.h" #include "src/arm_common/pooling/do_max_pooling_3x3_s2x2_int8.h" #include "src/arm_common/pooling/do_max_pooling_3x3_s2x2_nchw44.h" +#include "src/arm_common/pooling/do_max_pooling_3x3_s1x1_nchw44.h" #include "src/arm_common/pooling/do_max_pooling_w2x2_s2x2.h" #include "src/arm_common/pooling/do_max_pooling_w4x4_s2x2.h" @@ -612,6 +613,59 @@ void PoolingImpl::AlgoFilter3MaxStride2NCHW44::exec( #undef DISPATCH_FUNC } +bool PoolingImpl::AlgoFilter3MaxStride1NCHW44::usable( + const PoolingKernSizeParam& param) const { + auto SH = param.stride[0]; + auto SW = param.stride[1]; + auto FH = param.filter[0]; + auto FW = param.filter[1]; + auto PH = param.padding[0]; + auto PW = param.padding[1]; + + bool avaible = param.src_type.enumv() == DTypeEnum::QuantizedS8 && + param.format == Param::Format::NCHW44 && + param.mode == Mode::MAX && FH == 3 && FW == 3 && SH == 1 && + SW == 1 && PH == 0 && PW == 0; + return avaible; +} + +void PoolingImpl::AlgoFilter3MaxStride1NCHW44::exec( + const PoolingKernParam& param) const { + auto IH = param.isz[0], IW = param.isz[1]; + auto OH = param.osz[0], OW = param.osz[1]; + auto N = param.n, C = param.ic; + auto PH = param.padding[0]; + auto PW = param.padding[1]; + + void* src_ptr = param.src_ptr; + void* dst_ptr = param.dst_ptr; + +#define DISPATCH_FUNC(type, func, midout_type_id) \ + MIDOUT_BEGIN(megdnn_arm_common_pooling, midout_iv(2), \ + midout_iv(midout_type_id)) { \ + auto run = [C, IH, IW, OH, OW, PH, PW, src_ptr, dst_ptr]( \ + size_t index, size_t thread_id) { \ + MEGDNN_MARK_USED_VAR(thread_id); \ + size_t n = index / C; \ + size_t c = index % C; \ + do_max_pooling_3x3_s1x1_##func##_nchw44_NEON( \ + static_cast(src_ptr) + n * C * IH * IW * 4 + \ + c * IH * IW * 4, \ + static_cast(dst_ptr) + n * C * OH * OW * 4 + \ + c * OH * OW * 4, \ + IH, IW, OH, OW, PH, PW); \ + }; \ + MEGDNN_DISPATCH_MULTI_THREAD_CPU_KERN( \ + static_cast<::megdnn::naive::HandleImpl*>(param.handle), N* C, \ + run); \ + } \ + MIDOUT_END(); + + DISPATCH_FUNC(int8_t, int8, 10); + +#undef DISPATCH_FUNC +} + } // namespace arm_common } // namespace megdnn // vim: syntax=cpp.doxygen diff --git a/dnn/src/arm_common/pooling/algo.h b/dnn/src/arm_common/pooling/algo.h index b4c3291f..0465615c 100644 --- a/dnn/src/arm_common/pooling/algo.h +++ b/dnn/src/arm_common/pooling/algo.h @@ -91,6 +91,14 @@ public: void exec(const PoolingKernParam& param) const override; }; +class PoolingImpl::AlgoFilter3MaxStride1NCHW44 final : public AlgoBase { +public: + bool is_reproducible() const override { return true; } + const char* name() const override { return "ARM_POOLING_FILTER3_MAX_STRIDE1_NCHW44"; } + bool usable(const PoolingKernSizeParam& param) const override; + void exec(const PoolingKernParam& param) const override; +}; + WorkspaceBundle get_bundle(const PoolingImpl::PoolingKernSizeParam& param); } // namespace arm_common diff --git a/dnn/src/arm_common/pooling/do_max_pooling_3x3_s1x1_nchw44.cpp b/dnn/src/arm_common/pooling/do_max_pooling_3x3_s1x1_nchw44.cpp new file mode 100644 index 00000000..d3b0a48c --- /dev/null +++ b/dnn/src/arm_common/pooling/do_max_pooling_3x3_s1x1_nchw44.cpp @@ -0,0 +1,91 @@ +/** + * \file dnn/src/arm_common/pooling/do_max_pooling_3x3_s2x2_nchw44.cpp + * MegEngine is Licensed under the Apache License, Version 2.0 (the "License") + * + * Copyright (c) 2014-2020 Megvii Inc. All rights reserved. + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT ARRANTIES OR CONDITIONS OF ANY KIND, either express or + * implied. + */ +#include "src/arm_common/pooling/do_max_pooling_3x3_s1x1_nchw44.h" +#include "src/arm_common/simd_macro/marm_neon.h" +#include "src/common/unroll_macro.h" + +namespace megdnn { +namespace arm_common { + +void do_max_pooling_3x3_s1x1_int8_nchw44_NEON(const int8_t* src, int8_t* dst, + size_t IH, size_t IW, size_t OH, + size_t OW, size_t PH, size_t PW) { + size_t oh = 0; + for (; oh < OH; ++oh) { + size_t ih = oh; + const int8_t* __restrict sptr0 = src + (ih + 0) * IW * 4; + const int8_t* __restrict sptr1 = src + (ih + 1) * IW * 4; + const int8_t* __restrict sptr2 = src + (ih + 2) * IW * 4; + int8_t* __restrict dptr = dst + oh * OW * 4; + size_t ow = 0; + for (; ow + 3 < OW; ow += 4) { + int8x16_t src0123 = vld1q_s8(sptr0); + int8x16_t src1234 = vld1q_s8(sptr0 + 4); + int8x16_t src2345 = vld1q_s8(sptr0 + 8); + int8x16_t max0 = vmaxq_s8(src0123, src1234); + max0 = vmaxq_s8(max0, src2345); + + src0123 = vld1q_s8(sptr1); + src1234 = vld1q_s8(sptr1 + 4); + src2345 = vld1q_s8(sptr1 + 8); + int8x16_t max1 = vmaxq_s8(src0123, src1234); + max1 = vmaxq_s8(max1, src2345); + + src0123 = vld1q_s8(sptr2); + src1234 = vld1q_s8(sptr2 + 4); + src2345 = vld1q_s8(sptr2 + 8); + int8x16_t max2 = vmaxq_s8(src0123, src1234); + max2 = vmaxq_s8(max2, src2345); + + int8x16_t max_out = vmaxq_s8(max0, max1); + max_out = vmaxq_s8(max_out, max2); + + vst1q_s8(dptr, max_out); + + sptr0 += 16; + sptr1 += 16; + sptr2 += 16; + dptr += 16; + } + for (; ow < OW; ++ow) { + int8x8_t src001 = vld1_s8(sptr0); + int8x8_t src012 = vld1_s8(sptr0 + 4); + + int8x8_t src101 = vld1_s8(sptr1); + int8x8_t src112 = vld1_s8(sptr1 + 4); + + int8x8_t src201 = vld1_s8(sptr2); + int8x8_t src212 = vld1_s8(sptr2 + 4); + int8x8_t max01_tmp = vmax_s8(src001, src101); + max01_tmp = vmax_s8(max01_tmp, src201); + + int8x8_t max12_tmp = vmax_s8(src012, src112); + max12_tmp = vmax_s8(max12_tmp, src212); +#define cb(i) \ + int8_t dst##i = std::max(std::max(max01_tmp[i], max01_tmp[i + 4]), \ + max12_tmp[i + 4]); +#define store(i) *(dptr + i) = dst##i; + UNROLL_CALL_NOWRAPPER(4, cb) + UNROLL_CALL_NOWRAPPER(4, store) +#undef store +#undef cb + sptr0 += 4; + sptr1 += 4; + sptr2 += 4; + dptr += 4; + } + } +} + +} // namespace arm_common +} // namespace megdnn + // vim: syntax=cpp.doxygen diff --git a/dnn/src/arm_common/pooling/do_max_pooling_3x3_s1x1_nchw44.h b/dnn/src/arm_common/pooling/do_max_pooling_3x3_s1x1_nchw44.h new file mode 100644 index 00000000..6630d1c1 --- /dev/null +++ b/dnn/src/arm_common/pooling/do_max_pooling_3x3_s1x1_nchw44.h @@ -0,0 +1,25 @@ +/** + * \file dnn/src/arm_common/pooling/do_max_pooling_3x3_s2x2_nchw44.h + * MegEngine is Licensed under the Apache License, Version 2.0 (the "License") + * + * Copyright (c) 2014-2020 Megvii Inc. All rights reserved. + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT ARRANTIES OR CONDITIONS OF ANY KIND, either express or + * implied. + */ +#pragma once +#include "src/common/utils.h" + +namespace megdnn { +namespace arm_common { + +void do_max_pooling_3x3_s1x1_int8_nchw44_NEON(const int8_t* src, int8_t* dst, + size_t IH, size_t IW, size_t OH, + size_t OW, size_t PH, size_t PW); + +} // namespace arm_common +} // namespace megdnn + +// vim: syntax=cpp.doxygen diff --git a/dnn/src/arm_common/pooling/opr_impl.cpp b/dnn/src/arm_common/pooling/opr_impl.cpp index 1e27ea15..7304d7d6 100644 --- a/dnn/src/arm_common/pooling/opr_impl.cpp +++ b/dnn/src/arm_common/pooling/opr_impl.cpp @@ -26,6 +26,7 @@ class PoolingImpl::AlgoPack : NonCopyableObj { AlgoInt8Filter2MaxStride2 algo_int8_filter2_max_stride2; AlgoInt8Filter3MaxStride2 algo_int8_filter3_max_stride2; AlgoFilter3MaxStride2NCHW44 algo_filter3_max_stride2_nchw4; + AlgoFilter3MaxStride1NCHW44 algo_filter3_max_stride1_nchw4; public: AlgoPack() { @@ -38,6 +39,7 @@ public: all_algos.emplace_back(&algo_int8_filter2_max_stride2); all_algos.emplace_back(&algo_int8_filter3_max_stride2); all_algos.emplace_back(&algo_filter3_max_stride2_nchw4); + all_algos.emplace_back(&algo_filter3_max_stride1_nchw4); } SmallVector all_algos; }; diff --git a/dnn/src/arm_common/pooling/opr_impl.h b/dnn/src/arm_common/pooling/opr_impl.h index b7bde287..c45f13f6 100644 --- a/dnn/src/arm_common/pooling/opr_impl.h +++ b/dnn/src/arm_common/pooling/opr_impl.h @@ -84,6 +84,7 @@ private: class AlgoInt8Filter2MaxStride2; class AlgoInt8Filter3MaxStride2; class AlgoFilter3MaxStride2NCHW44; + class AlgoFilter3MaxStride1NCHW44; class AlgoPack; }; } // namespace arm_common diff --git a/dnn/test/arm_common/pooling.cpp b/dnn/test/arm_common/pooling.cpp index 8822824c..d002858e 100644 --- a/dnn/test/arm_common/pooling.cpp +++ b/dnn/test/arm_common/pooling.cpp @@ -128,6 +128,32 @@ TEST_F(ARM_COMMON, POOLING_MAX_W3x3_S2x2_NCHW44) // clang-format on } +TEST_F(ARM_COMMON, POOLING_MAX_W3x3_S1x1_NCHW44) +{ + // clang-format off + for (size_t ih: {3, 5, 10}) + for (size_t iw: {3, 5, 7, 9, 15, 20}) + for (size_t ph: {0}) + for (size_t pw: {0}) + if (ih+2*ph >= 3 && iw+2*pw >= 3) + { + UniformIntRNG rng{INT8_MIN >> 1, INT8_MAX >> 1}; + Checker checker(handle()); + checker.set_dtype(0, dtype::QuantizedS8(1.1f)); + checker.set_rng(0,&rng); + + param::Pooling param; + param.mode = param::Pooling::Mode::MAX; + param.format = param::Pooling::Format::NCHW44; + param.pad_h = ph; + param.pad_w = pw; + param.stride_h = param.stride_w = 1; + param.window_h = param.window_w = 3; + checker.set_param(param).exec(TensorShapeArray{{2, 2, ih, iw, 4}, {}}); + } + // clang-format on +} + #if __ARM_FEATURE_FP16_VECTOR_ARITHMETIC TEST_F(ARM_COMMON, POOLING_FP16) { Checker checker(handle()); diff --git a/dnn/test/arm_common/pooling_multi_thread.cpp b/dnn/test/arm_common/pooling_multi_thread.cpp index e9dd7d9c..90796e16 100644 --- a/dnn/test/arm_common/pooling_multi_thread.cpp +++ b/dnn/test/arm_common/pooling_multi_thread.cpp @@ -78,6 +78,32 @@ TEST_F(ARM_COMMON_MULTI_THREADS, POOLING_MAX_W3x3_S2x2_NCHW44) } // clang-format on } +TEST_F(ARM_COMMON_MULTI_THREADS, POOLING_MAX_W3x3_S1x1_NCHW44) +{ + // clang-format off + for (size_t ih: {3, 5, 10}) + for (size_t iw: {3, 5, 7, 9, 15, 20}) + for (size_t ph: {0}) + for (size_t pw: {0}) + if (ih+2*ph >= 3 && iw+2*pw >= 3) + { + UniformIntRNG rng{INT8_MIN >> 1, INT8_MAX >> 1}; + Checker checker(handle()); + checker.set_dtype(0, dtype::QuantizedS8(1.1f)); + checker.set_rng(0,&rng); + + param::Pooling param; + param.mode = param::Pooling::Mode::MAX; + param.format = param::Pooling::Format::NCHW44; + param.pad_h = ph; + param.pad_w = pw; + param.stride_h = param.stride_w = 1; + param.window_h = param.window_w = 3; + checker.set_param(param).exec(TensorShapeArray{{2, 2, ih, iw, 4}, {}}); + } + // clang-format on +} + TEST_F(ARM_COMMON_MULTI_THREADS, POOLING_INT8_W3x3_S2x2) { for (size_t ih: {2, 3, 7, 13, 52, 53, 54, 55})