提交 8eb1f262 编写于 作者: X xiaolil1 提交者: Tao Luo

Enable INT8 pool OP (#15046)

* Enable INT8 pool OP
test=develop

* fix unittest
test=develop

* Clean unittest code.
test=develop
上级 227e0c45
develop 2.0.1-rocm-post Ligoml-patch-1 OliverLPH-patch-1 OliverLPH-patch-2 PaddlePM-patch-1 PaddlePM-patch-2 ZHUI-patch-1 add_default_att add_model_benchmark_ci add_some_yaml_config addfile all_new_design_exec ascendrc ascendrelease cherry_undefined_var compile_windows delete_2.0.1-rocm-post delete_add_default_att delete_all_new_design_exec delete_ascendrc delete_compile_windows delete_delete_addfile delete_disable_iterable_dataset_unittest delete_fix_dataloader_memory_leak delete_fix_imperative_dygraph_error delete_fix_retry_ci delete_fix_undefined_var delete_improve_sccache delete_incubate/lite delete_paddle_tiny_install delete_paralleltest delete_prv-disable-more-cache delete_revert-31068-fix_conv3d_windows delete_revert-31562-mean delete_revert-33630-bug-fix delete_revert-34159-add_npu_bce_logical_dev delete_revert-34910-spinlocks_for_allocator delete_revert-35069-revert-34910-spinlocks_for_allocator delete_revert-36057-dev/read_flags_in_ut dingjiaweiww-patch-1 disable_iterable_dataset_unittest dy2static enable_eager_model_test final_state_gen_python_c final_state_intermediate fix-numpy-issue fix_concat_slice fix_dataloader_memory_leak fix_imperative_dygraph_error fix_npu_ci fix_op_flops fix_retry_ci fix_rnn_docs fix_tensor_type fix_undefined_var fixiscan fixiscan1 fixiscan2 fixiscan3 github/fork/123malin/netifaces github/fork/123malin/tdm_abacus github/fork/AshburnLee/dev_unique github/fork/ForFishes/fix_memory_matmul github/fork/ForFishes/rm_fluid github/fork/LielinJiang/move-2.0-api github/fork/LielinJiang/visual-dl-cb github/fork/LiuChiachi/add-transformer-generate-square-subsequent-mask-api github/fork/LiuChiachi/fix-example-code-for-hapi-Model github/fork/LiuChiachi/remove-input-requirment-in-dygraph-Model github/fork/MrChengmo/fix_ps_profiler github/fork/MrChengmo/update_ps_heter github/fork/PWhiddy/patch-1 github/fork/Shixiaowei02/dev/save_load_upgrade github/fork/TCChenlong/fix_hapi github/fork/TCChenlong/fix_inden github/fork/Thunderbrook/xpu_slice github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_2 github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_3 github/fork/XieYunshen/timeout_20S_ut github/fork/ZeyuChen/remove-nltk github/fork/arlesniak/arlesniak/selective__mkldnn_flags github/fork/baiyfbupt/code_doc_mig github/fork/chalsliu/set_timeout github/fork/chen-zhiyu/develop github/fork/chenwhql/ci/try_to_find_test_buffer_shared_memory_reuse_pass_error github/fork/chenwhql/dygraph/remove_scale_loss_and_apply_collective_grads github/fork/chenwhql/saveload/add_get_inference_program github/fork/chenwhql/saveload/remove_save_load_config github/fork/cryoco/pass-compatibility-trt github/fork/danleifeng/isempty_api2.0 github/fork/frankwhzhang/api_transfer github/fork/hbwx24/error_msg/cuda_kernel_error_msg github/fork/heavengate/cherry_yolo_box github/fork/heavengate/update_yolo_box github/fork/iclementine/rnn_fix github/fork/iducn/testestse github/fork/jczaja/prv-25537-fix github/fork/jeff41404/release/1.8 github/fork/jiweibo/api_2.0 github/fork/jiweibo/fix_lite_resnet50_test github/fork/juncaipeng/fix_doc_1 github/fork/lfchener/sample_code github/fork/littletomatodonkey/fix_reg_doc github/fork/liym27/dy2stat_update_assign_to_rc20 github/fork/luotao1/profiler_ut github/fork/mapingshuo/add_wait github/fork/mapingshuo/doc_2.0 github/fork/mapingshuo/zero-0.5 github/fork/miraiwk/dev github/fork/pangyoki/add-Categorical-class-branch github/fork/pangyoki/add-multinomial-op-branch github/fork/pangyoki/fix-test_distritbution-CI github/fork/qjing666/doublegrad github/fork/qjing666/fix_hdfs_download github/fork/sandyhouse/add_gather_etc github/fork/sandyhouse/add_send_recv_alltoall_etc github/fork/sandyhouse/pipeline_exe_run github/fork/seiriosPlus/feature/large_scale_kv_save_delta github/fork/seiriosPlus/fix/paddle_errors_fix github/fork/seiriosPlus/fix/paddle_op_errors github/fork/shangzhizhou/fix_test_activation_op_random_bug github/fork/smallv0221/yxp0924 github/fork/smallv0221/yxp0925 github/fork/swtkiwi/del-matplotlib github/fork/tianshuo78520a/kunlun_test github/fork/tianshuo78520a/update_dockerfile github/fork/wanghaoshuang/bert_fuse github/fork/wanghaoshuang/label_smooth github/fork/wanghuancoder/develop_CUDASynchronize github/fork/wanghuancoder/develop_Layer_doc github/fork/wanghuancoder/develop_ParameterList_doc github/fork/wanghuancoder/develop_Sequential_doc github/fork/wanghuancoder/develop_bilinear_tensor_product github/fork/wanghuancoder/develop_coverage_build_sh github/fork/wanghuancoder/develop_in_dynamic_mode_doc github/fork/wanghuancoder/develop_unique_name_doc github/fork/wangxicoding/fleet_meta_combine github/fork/wawltor/error_message_fix_5 github/fork/willthefrog/remove_l2_norm github/fork/windstamp/momentum_op github/fork/windstamp/mv_op_5 github/fork/windstamp/normal_api github/fork/wojtuss/wojtuss/fusion_gru_quantization github/fork/wojtuss/wojtuss/quantization-with-shift github/fork/wzzju/fix_err_info github/fork/wzzju/pure_fp16 github/fork/xiemoyuan/op_error_message github/fork/xiemoyuan/optimize_error_message github/fork/yaoxuefeng6/fix_doc github/fork/yaoxuefeng6/mod_dataset_v2 github/fork/yongqiangma/lod github/fork/ysh329/fix-clip-by-norm-error github/fork/ysh329/fix-error-clip-by-value github/fork/yukavio/error_info github/fork/zhangting2020/conv_filter_grad github/fork/zhangting2020/is_compile_with_cuda github/fork/zhangting2020/place_doc github/fork/zhangting2020/program github/fork/zhhsplendid/fix_any github/fork/zhhsplendid/refine_api2 github/fork/zhhsplendid/refine_api2_test github/fork/zhhsplendid/refine_api_test_ptb_lm github/fork/zhhsplendid/refine_api_test_resnet github/fork/zhhsplendid/refine_api_test_simnet github/fork/zhiqiu/dev/refine_initializer github/fork/zhiqiu/dev/remove_inplace_argument github/fork/zlsh80826/nvinfer_plugin_var_len_cuda11 improve_sccache incubate/infrt incubate/lite inplace_addto make_flag_adding_easier move_embedding_to_phi move_histogram_to_pten move_sgd_to_phi move_slice_to_pten move_temporal_shift_to_phi move_yolo_box_to_phi npu_fix_alloc numel paddle_tiny_install paralleltest preln_ernie prv-disable-more-cache prv-md-even-more prv-onednn-2.5 pten_tensor_refactor release/1.3 release/1.4 release/1.5 release/1.6 release/1.7 release/1.8 release/2.0 release/2.0-alpha release/2.0-beta release/2.0-rc release/2.0-rc1 release/2.1 release/2.2 release/2.3 release/2.3-fc-ernie-fix release/2.4 release/lite-0.1 revert-24981-add_device_attr_for_regulization revert-26856-strategy_example2 revert-27520-disable_pr revert-31068-fix_conv3d_windows revert-31562-mean revert-32290-develop-hardlabel revert-33037-forci revert-33475-fix_cifar_label_dimension revert-33630-bug-fix revert-34159-add_npu_bce_logical_dev revert-34406-add_copy_from_tensor revert-34910-spinlocks_for_allocator revert-35069-revert-34910-spinlocks_for_allocator revert-36057-dev/read_flags_in_ut revert-36201-refine_fast_threaded_ssa_graph_executor revert-36985-add_license revert-37318-refactor_dygraph_to_eager revert-37926-eager_coreops_500 revert-37956-revert-37727-pylayer_support_tuple revert-38100-mingdong revert-38301-allocation_rearrange_pr revert-38703-numpy_bf16_package_reupload revert-38732-remove_useless_header_in_elementwise_mul_grad revert-38959-Reduce_Grad revert-39143-adjust_empty revert-39227-move_trace_op_to_pten revert-39268-dev/remove_concat_fluid_kernel revert-40170-support_partial_grad revert-41056-revert-40727-move_some_activaion_to_phi revert-41065-revert-40993-mv_ele_floordiv_pow revert-41068-revert-40790-phi_new revert-41944-smaller_inference_api_test revert-42149-do-not-reset-default-stream-for-stream-safe-cuda-allocator revert-43155-fix_ut_tempfile revert-43882-revert-41944-smaller_inference_api_test revert-45808-phi/simplify_size_op revert-46827-deform_comment rocm_dev_0217 support_weight_transpose test_benchmark_ci test_feature_precision_test_c test_model_benchmark test_model_benchmark_ci zhiqiu-patch-1 v2.4.0-rc0 v2.3.2 v2.3.1 v2.3.0 v2.3.0-rc0 v2.2.2 v2.2.1 v2.2.0 v2.2.0-rc0 v2.2.0-bak0 v2.1.3 v2.1.2 v2.1.1 v2.1.0 v2.1.0-rc0 v2.0.2 v2.0.1 v2.0.0 v2.0.0-rc1 v2.0.0-rc0 v2.0.0-beta0 v2.0.0-alpha0 v1.8.5 v1.8.4 v1.8.3 v1.8.2 v1.8.1 v1.8.0 v1.7.2 v1.7.1 v1.7.0 v1.6.3 v1.6.2 v1.6.1 v1.6.0 v1.6.0-rc0 v1.5.2 v1.5.1 v1.5.0 v1.4.1 v1.4.0 v1.3.2 v1.3.1 v1.3.0 lite-v0.1
无相关合并请求
......@@ -12,6 +12,7 @@ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. */
#include "paddle/fluid/framework/data_layout_transform.h"
#include "paddle/fluid/operators/pool_op.h"
#include "paddle/fluid/platform/mkldnn_helper.h"
......@@ -71,7 +72,6 @@ class PoolMKLDNNOpKernel : public paddle::framework::OpKernel<T> {
void Compute(const paddle::framework::ExecutionContext& ctx) const override {
PADDLE_ENFORCE(paddle::platform::is_cpu_place(ctx.GetPlace()),
"It must use CPUPlace.");
auto& dev_ctx =
ctx.template device_context<platform::MKLDNNDeviceContext>();
const auto& mkldnn_engine = dev_ctx.GetEngine();
......@@ -130,20 +130,25 @@ class PoolMKLDNNOpKernel : public paddle::framework::OpKernel<T> {
CorrectOutputSize(src_tz, dst_tz, ksize, paddings, strides,
padding_right_bottom);
}
auto src_md = platform::MKLDNNMemDesc(
src_tz, platform::MKLDNNGetDataType<T>(), input_format);
mkldnn::memory::data_type dt =
paddle::framework::ToMKLDNNDataType(input->type());
auto src_md = platform::MKLDNNMemDesc(src_tz, dt, input_format);
/* create memory descriptor for pooling without specified format
* ('any') which lets a primitive (pooling in this case) choose
* the memory format preferred for best performance
*/
auto dst_md = platform::MKLDNNMemDesc(dst_tz, mkldnn::memory::f32,
mkldnn::memory::format::any);
auto dst_md =
platform::MKLDNNMemDesc(dst_tz, dt, mkldnn::memory::format::any);
auto propagation = src_md.data.data_type == mkldnn_f32
? mkldnn::prop_kind::forward_training
: mkldnn::prop_kind::forward_scoring;
std::shared_ptr<mkldnn::pooling_forward::primitive_desc> pool_pd =
CreatePrimitiveDesc(src_md, dst_md, strides, padding_left_top,
padding_right_bottom, ksize, pooling_type,
mkldnn_engine, ceil_mode, is_test);
CreatePrimitiveDesc(src_md, dst_md, propagation, strides,
padding_left_top, padding_right_bottom, ksize,
pooling_type, mkldnn_engine, ceil_mode, is_test);
// save pool_pd into global device context to be referred in backward path
if (!is_test) dev_ctx.SetBlob(key_pool_pd, pool_pd);
......@@ -203,7 +208,8 @@ class PoolMKLDNNOpKernel : public paddle::framework::OpKernel<T> {
private:
std::unique_ptr<mkldnn::pooling_forward::primitive_desc> CreatePrimitiveDesc(
const mkldnn::memory::desc& src, const mkldnn::memory::desc& dst,
const std::vector<int>& stride, const std::vector<int>& padding_left_top,
const mkldnn::prop_kind& propagation, const std::vector<int>& stride,
const std::vector<int>& padding_left_top,
const std::vector<int>& padding_right_bot, const std::vector<int>& kernel,
const std::string& pooling_type, const mkldnn::engine& engine,
bool ceil_mode, bool is_test) const {
......@@ -411,6 +417,9 @@ class PoolMKLDNNGradOpKernel : public paddle::framework::OpKernel<T> {
namespace ops = paddle::operators;
REGISTER_OP_KERNEL(pool2d, MKLDNN, ::paddle::platform::CPUPlace,
ops::PoolMKLDNNOpKernel<float>);
ops::PoolMKLDNNOpKernel<float>,
ops::PoolMKLDNNOpKernel<int8_t>,
ops::PoolMKLDNNOpKernel<uint8_t>);
REGISTER_OP_KERNEL(pool2d_grad, MKLDNN, ::paddle::platform::CPUPlace,
ops::PoolMKLDNNGradOpKernel<float>);
# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import print_function
from __future__ import division
import unittest
import numpy as np
import paddle.fluid.core as core
from op_test import OpTest
from test_pool2d_op import TestPool2D_Op, avg_pool2D_forward_naive, max_pool2D_forward_naive
class TestPool2dMKLDNNInt8_Op(TestPool2D_Op):
def init_kernel_type(self):
self.use_mkldnn = True
def init_data_type(self):
self.dtype = np.int8
def setUp(self):
TestPool2D_Op.setUp(self)
assert self.dtype in [np.int8, np.uint8
], 'Dtype should be int8 or uint8'
def test_check_output(self):
self.check_output_with_place(core.CPUPlace(), atol=1e-5)
def test_check_grad(self):
pass
class TestCase1Avg(TestPool2dMKLDNNInt8_Op):
def init_test_case(self):
self.shape = [2, 3, 7, 7]
self.ksize = [3, 3]
self.strides = [1, 1]
self.paddings = [0, 0]
def init_global_pool(self):
self.global_pool = False
class TestCase2Avg(TestPool2dMKLDNNInt8_Op):
def init_test_case(self):
self.shape = [2, 3, 7, 7]
self.ksize = [3, 3]
self.strides = [1, 1]
self.paddings = [1, 1]
def init_global_pool(self):
self.global_pool = False
class TestCase0Max(TestPool2dMKLDNNInt8_Op):
def init_pool_type(self):
self.pool_type = "max"
self.pool2D_forward_naive = max_pool2D_forward_naive
class TestCase1Max(TestCase1Avg):
def init_pool_type(self):
self.pool_type = "max"
self.pool2D_forward_naive = max_pool2D_forward_naive
class TestCase2Max(TestCase2Avg):
def init_pool_type(self):
self.pool_type = "max"
self.pool2D_forward_naive = max_pool2D_forward_naive
def create_test_s8_u8_class(parent):
class TestS8Case(parent):
def init_data_type(self):
self.dtype = np.int8
class TestU8Case(parent):
def init_data_type(self):
self.dtype = np.uint8
cls_name_s8 = "{0}_{1}".format(parent.__name__, "mkldnn_s8")
cls_name_u8 = "{0}_{1}".format(parent.__name__, "mkldnn_u8")
TestS8Case.__name__ = cls_name_s8
TestU8Case.__name__ = cls_name_u8
globals()[cls_name_s8] = TestS8Case
globals()[cls_name_u8] = TestU8Case
create_test_s8_u8_class(TestPool2dMKLDNNInt8_Op)
create_test_s8_u8_class(TestCase1Avg)
create_test_s8_u8_class(TestCase2Avg)
create_test_s8_u8_class(TestCase0Max)
create_test_s8_u8_class(TestCase1Max)
create_test_s8_u8_class(TestCase2Max)
if __name__ == '__main__':
unittest.main()
......@@ -18,35 +18,22 @@ import unittest
from test_pool2d_op import TestPool2D_Op, TestCase1, TestCase2, TestCase3, TestCase4, TestCase5
class TestMKLDNNCase1(TestPool2D_Op):
def init_kernel_type(self):
self.use_mkldnn = True
class TestMKLDNNCase2(TestCase1):
def init_kernel_type(self):
self.use_mkldnn = True
class TestMKLDNNCase3(TestCase2):
def init_kernel_type(self):
self.use_mkldnn = True
class TestMKLDNNCase4(TestCase3):
def init_kernel_type(self):
self.use_mkldnn = True
class TestMKLDNNCase5(TestCase4):
def init_kernel_type(self):
self.use_mkldnn = True
class TestMKLDNNCase6(TestCase5):
def init_kernel_type(self):
self.use_mkldnn = True
def create_test_mkldnn_class(parent):
class TestMKLDNNCase(parent):
def init_kernel_type(self):
self.use_mkldnn = True
cls_name = "{0}_{1}".format(parent.__name__, "MKLDNNOp")
TestMKLDNNCase.__name__ = cls_name
globals()[cls_name] = TestMKLDNNCase
create_test_mkldnn_class(TestPool2D_Op)
create_test_mkldnn_class(TestCase1)
create_test_mkldnn_class(TestCase2)
create_test_mkldnn_class(TestCase3)
create_test_mkldnn_class(TestCase4)
create_test_mkldnn_class(TestCase5)
if __name__ == '__main__':
unittest.main()
......@@ -115,7 +115,7 @@ class TestPool2D_Op(OpTest):
self.op_type = "pool2d"
self.use_cudnn = False
self.use_mkldnn = False
self.dtype = np.float32
self.init_data_type()
self.init_test_case()
self.init_global_pool()
self.init_kernel_type()
......@@ -177,6 +177,9 @@ class TestPool2D_Op(OpTest):
def init_kernel_type(self):
pass
def init_data_type(self):
self.dtype = np.float32
def init_pool_type(self):
self.pool_type = "avg"
self.pool2D_forward_naive = avg_pool2D_forward_naive
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部