提交 b67584a6 编写于 作者: T tensor-tang

jit benchmark use tensor

test=develop
上级 3008fa12
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 cp_2.4_fix_numpy 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_dlpack_for fix_imperative_dygraph_error fix_npu_ci fix_op_flops fix_retry_ci fix_rnn_docs fix_tensor_type fix_undefined_var fix_var_stop_gradient_error 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/frl_train_eval incubate/infrt incubate/lite inplace_addto layer_norm make_flag_adding_easier matmul_double_grad 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 prv-reshape-mkldnn-ut2 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 revert-47325-remove_cudnn_hardcode revert-47645-add_npu_storage_dims revert-48815-set_free_when_no_cache_hit_default_value_true revert-49654-prim_api_gen revert-49763-fix_static_composite_gen rocm_dev_0217 support-0D-sort support_weight_transpose test_benchmark_ci test_feature_precision_test_c test_for_Filtetfiles test_model_benchmark test_model_benchmark_ci zhiqiu-patch-1 v2.4.1 v2.4.0 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
......@@ -21,5 +21,5 @@ endif()
cc_library(jit_kernel_helper SRCS ${jit_kernel_cc_srcs} DEPS ${JIT_KERNEL_DEPS})
cc_test(jit_kernel_test SRCS test.cc DEPS jit_kernel_helper)
if(NOT WIN32)
cc_binary(jit_kernel_benchmark SRCS benchmark.cc DEPS jit_kernel_helper device_tracer)
cc_binary(jit_kernel_benchmark SRCS benchmark.cc DEPS jit_kernel_helper device_tracer tensor)
endif()
......@@ -18,6 +18,7 @@
#include <vector>
#include "gflags/gflags.h"
#include "glog/logging.h"
#include "paddle/fluid/framework/tensor.h"
#include "paddle/fluid/operators/jit/kernels.h"
#include "paddle/fluid/platform/device_tracer.h"
#include "paddle/fluid/platform/place.h"
......@@ -155,14 +156,22 @@ void BenchAllImpls(const typename KernelTuples::attr_type& attr, Args... args) {
LOG(INFO) << loginfos.str();
}
using Tensor = paddle::framework::Tensor;
template <paddle::operators::jit::KernelType KT, typename T, typename PlaceType>
void BenchXYZNKernel() {
for (int d : TestSizes()) {
std::vector<T> x(d), y(d), z(d);
RandomVec<T>(d, x.data());
RandomVec<T>(d, y.data());
BenchAllImpls<KT, jit::XYZNTuples<T>, PlaceType>(d, x.data(), y.data(),
z.data(), d);
Tensor x, y, z;
x.Resize({d});
y.Resize({d});
z.Resize({d});
T* x_data = x.mutable_data<T>(PlaceType());
T* y_data = y.mutable_data<T>(PlaceType());
T* z_data = z.mutable_data<T>(PlaceType());
RandomVec<T>(d, x_data);
RandomVec<T>(d, y_data);
BenchAllImpls<KT, jit::XYZNTuples<T>, PlaceType>(d, x.data<T>(),
y.data<T>(), z_data, d);
}
}
......@@ -170,9 +179,13 @@ template <paddle::operators::jit::KernelType KT, typename T, typename PlaceType>
void BenchAXYNKernel() {
for (int d : TestSizes()) {
const T a = static_cast<T>(3);
std::vector<T> x(d), y(d);
RandomVec<T>(d, x.data());
BenchAllImpls<KT, jit::AXYNTuples<T>, PlaceType>(d, &a, x.data(), y.data(),
Tensor x, y;
x.Resize({d});
y.Resize({d});
T* x_data = x.mutable_data<T>(PlaceType());
T* y_data = y.mutable_data<T>(PlaceType());
RandomVec<T>(d, x_data);
BenchAllImpls<KT, jit::AXYNTuples<T>, PlaceType>(d, &a, x.data<T>(), y_data,
d);
}
}
......@@ -180,9 +193,13 @@ void BenchAXYNKernel() {
template <paddle::operators::jit::KernelType KT, typename T, typename PlaceType>
void BenchXYNKernel() {
for (int d : TestSizes()) {
std::vector<T> x(d), y(d);
RandomVec<T>(d, x.data());
BenchAllImpls<KT, jit::XYNTuples<T>, PlaceType>(d, x.data(), y.data(), d);
Tensor x, y;
x.Resize({d});
y.Resize({d});
T* x_data = x.mutable_data<T>(PlaceType());
T* y_data = y.mutable_data<T>(PlaceType());
RandomVec<T>(d, x_data);
BenchAllImpls<KT, jit::XYNTuples<T>, PlaceType>(d, x.data<T>(), y_data, d);
}
}
......@@ -192,16 +209,23 @@ void BenchLSTMKernel() {
for (int d : TestSizes()) {
const jit::lstm_attr_t attr(d, jit::kVSigmoid, jit::kVTanh, jit::kVTanh,
use_peephole);
std::vector<T> x(4 * d), ct_1(d), ct(d), ht(d), wp(3 * d), checked(2 * d);
RandomVec<T>(4 * d, x.data(), -2.f, 2.f);
RandomVec<T>(3 * d, wp.data(), -2.f, 2.f);
RandomVec<T>(d, ct_1.data(), -2.f, 2.f);
const T* ct_1_data = ct_1.data();
const T* wp_data = wp.data();
T* x_data = x.data();
T* checked_data = checked.data();
T* ct_data = ct.data();
T* ht_data = ht.data();
Tensor x, ct_1, ct, ht, wp, checked;
x.Resize({4 * d});
ct_1.Resize({d});
ct.Resize({d});
ht.Resize({d});
wp.Resize({3 * d});
checked.Resize({2 * d});
auto place = PlaceType();
RandomVec<T>(x.numel(), x.mutable_data<T>(place), -2.f, 2.f);
RandomVec<T>(wp.numel(), wp.mutable_data<T>(place), -2.f, 2.f);
RandomVec<T>(ct_1.numel(), ct_1.mutable_data<T>(place), -2.f, 2.f);
const T* ct_1_data = ct_1.data<T>();
const T* wp_data = wp.data<T>();
T* x_data = x.mutable_data<T>(place);
T* checked_data = checked.mutable_data<T>(place);
T* ct_data = ct.mutable_data<T>(place);
T* ht_data = ht.mutable_data<T>(place);
jit::lstm_t step;
step.gates = x_data;
step.ct_1 = ct_1_data;
......@@ -220,12 +244,16 @@ template <paddle::operators::jit::KernelType KT, typename T, typename PlaceType>
void BenchGRUKernel() {
for (int d : TestSizes()) {
const jit::gru_attr_t attr(d, jit::kVSigmoid, jit::kVTanh);
std::vector<T> x(3 * d), ht_1(d), ht(d);
RandomVec<T>(3 * d, x.data(), -2.f, 2.f);
RandomVec<T>(d, ht_1.data(), -2.f, 2.f);
const T* ht_1_data = ht_1.data();
T* x_data = x.data();
T* ht_data = ht.data();
auto place = PlaceType();
Tensor x, ht_1, ht;
x.Resize({3 * d});
ht_1.Resize({d});
ht.Resize({d});
RandomVec<T>(3 * d, x.mutable_data<T>(place), -2.f, 2.f);
RandomVec<T>(d, ht_1.mutable_data<T>(place), -2.f, 2.f);
const T* ht_1_data = ht_1.data<T>();
T* x_data = x.mutable_data<T>(place);
T* ht_data = ht.mutable_data<T>(place);
jit::gru_t step;
step.gates = x_data;
step.ht_1 = ht_1_data;
......@@ -243,10 +271,12 @@ void BenchSeqPoolKernel() {
jit::seq_pool_attr_t attr(w, type);
for (int h : TestSizes()) {
attr.h = h;
std::vector<T> x(h * w), y(w);
RandomVec<T>(h * w, x.data(), -2.f, 2.f);
const T* x_data = x.data();
T* y_data = y.data();
Tensor x, y;
x.Resize({h * w});
y.Resize({w});
RandomVec<T>(h * w, x.mutable_data<T>(PlaceType()), -2.f, 2.f);
const T* x_data = x.data<T>();
T* y_data = y.mutable_data<T>(PlaceType());
BenchAllImpls<KT, jit::SeqPoolTuples<T>, PlaceType>(attr, x_data,
y_data, &attr);
}
......@@ -259,12 +289,15 @@ void BenchMatMulKernel() {
for (int m : {1, 2, 3, 4}) {
for (int n : TestSizes()) {
for (int k : TestSizes()) {
std::vector<T> a(m * k), b(k * n), c(m * n);
RandomVec<T>(m * k, a.data(), -2.f, 2.f);
RandomVec<T>(k * n, b.data(), -2.f, 2.f);
const T* a_data = a.data();
const T* b_data = b.data();
T* c_data = c.data();
Tensor a, b, c;
a.Resize({m * k});
b.Resize({k * n});
c.Resize({m * n});
RandomVec<T>(m * k, a.mutable_data<T>(PlaceType()), -2.f, 2.f);
RandomVec<T>(k * n, b.mutable_data<T>(PlaceType()), -2.f, 2.f);
const T* a_data = a.data<T>();
const T* b_data = b.data<T>();
T* c_data = c.mutable_data<T>(PlaceType());
BenchAllImpls<KT, jit::MatMulTuples<T>, PlaceType>(k, a_data, b_data,
c_data, m, n, k);
}
......
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
新手
引导
客服 返回
顶部