From d05c182e93194787000659ad0d53e408795c4171 Mon Sep 17 00:00:00 2001
From: fengjiayi <fengjiayi@baidu.com>
Date: Sun, 5 Nov 2017 14:59:54 -0800
Subject: [PATCH] Add LoD's slice and append function (#5368)

* Add GetFineGrainedLoDLength and AppendLoD

* Follow comments and fix bugs

* fix a compile error

* fix a compile bug
---
 paddle/framework/lod_tensor.cc      | 38 ++++++++++++++++++++++++++
 paddle/framework/lod_tensor.h       |  6 +++++
 paddle/framework/lod_tensor_test.cc | 42 +++++++++++++++++++++++++++++
 3 files changed, 86 insertions(+)

diff --git a/paddle/framework/lod_tensor.cc b/paddle/framework/lod_tensor.cc
index 584308a53..2bcfffb13 100644
--- a/paddle/framework/lod_tensor.cc
+++ b/paddle/framework/lod_tensor.cc
@@ -135,5 +135,43 @@ void LoDTensor::ShrinkInLevel(size_t level, size_t elem_begin,
   PADDLE_ENFORCE_LT(begin, end, "Cannot shrink, the result tensor is empty.");
   ShareDataWith(Slice(begin, end));
 }
+
+void GetFineGrainedLoDLength(const LoD& lod, size_t start_idx, size_t end_idx,
+                             std::vector<std::vector<size_t>>* lod_length,
+                             size_t* start_offset) {
+  lod_length->clear();
+  PADDLE_ENFORCE(start_idx < lod.size() - 1,
+                 "start_idx should be >= 0 and < lod.size() - 1.");
+  PADDLE_ENFORCE(end_idx < lod.size(),
+                 "end_idx should be >= 0 and < lod.size().");
+  PADDLE_ENFORCE_LE(start_idx, end_idx,
+                    "start_idx should be less than end_idx.");
+  for (size_t level_idx = 0; level_idx < lod.size(); ++level_idx) {
+    std::vector<size_t> level_lens;
+    for (size_t i = start_idx; i < end_idx; ++i) {
+      level_lens.push_back(lod[level_idx][i + 1] - lod[level_idx][i]);
+    }
+    lod_length->emplace_back(level_lens);
+    start_idx = lod[level_idx][start_idx];
+    end_idx = lod[level_idx][end_idx];
+  }
+  *start_offset = start_idx;
+}
+
+void AppendLoD(LoD* lod, const std::vector<std::vector<size_t>>& lod_length) {
+  PADDLE_ENFORCE_EQ(
+      lod->size(), lod_length.size(),
+      "The lod_length should has the same size with the appended lod.");
+  for (size_t i = 0; i < lod->size(); ++i) {
+    auto& level = (*lod)[i];
+    if (level.empty()) {
+      level.push_back(0);
+    }
+    for (size_t len : lod_length[i]) {
+      level.push_back(level.back() + len);
+    }
+  }
+}
+
 }  // namespace framework
 }  // namespace paddle
diff --git a/paddle/framework/lod_tensor.h b/paddle/framework/lod_tensor.h
index f4fe4cdac..1437da399 100644
--- a/paddle/framework/lod_tensor.h
+++ b/paddle/framework/lod_tensor.h
@@ -181,5 +181,11 @@ LoDTensor LodExpand(const LoDTensor& source, const LoD& lod, size_t level,
   return tensor;
 }
 
+void GetFineGrainedLoDLength(const LoD& lod, size_t start_idx, size_t end_idx,
+                             std::vector<std::vector<size_t>>* lod_length,
+                             size_t* start_offset);
+
+void AppendLoD(LoD* lod, const std::vector<std::vector<size_t>>& lod_length);
+
 }  // namespace framework
 }  // namespace paddle
diff --git a/paddle/framework/lod_tensor_test.cc b/paddle/framework/lod_tensor_test.cc
index aa2f6c993..bf61c9ee7 100644
--- a/paddle/framework/lod_tensor_test.cc
+++ b/paddle/framework/lod_tensor_test.cc
@@ -144,5 +144,47 @@ TEST(LodExpand, test) {
   }
 }
 
+TEST(LoD, GetFineGrainedLoDLength) {
+  LoD lod;
+  lod.push_back(std::vector<size_t>{0, 2, 4, 5});
+  lod.push_back(std::vector<size_t>{0, 1, 6, 8, 10, 11});
+  lod.push_back(
+      std::vector<size_t>{0, 2, 5, 7, 10, 12, 15, 17, 20, 24, 26, 29});
+
+  std::vector<std::vector<size_t>> lod_length;
+  size_t start_offset;
+  paddle::framework::GetFineGrainedLoDLength(lod, 1, 2, &lod_length,
+                                             &start_offset);
+
+  std::vector<std::vector<size_t>> expected;
+  expected.push_back(std::vector<size_t>{2});
+  expected.push_back(std::vector<size_t>{2, 2});
+  expected.push_back(std::vector<size_t>{2, 3, 4, 2});
+  EXPECT_EQ(lod_length, expected);
+  EXPECT_EQ(start_offset, 15UL);
+}
+
+TEST(LoD, AppendLoD) {
+  std::vector<std::vector<size_t>> lod_lens;
+  lod_lens.push_back(std::vector<size_t>{2});
+  lod_lens.push_back(std::vector<size_t>{2, 2});
+  lod_lens.push_back(std::vector<size_t>{2, 3, 4, 2});
+
+  LoD origin;
+  origin.push_back(std::vector<size_t>{0, 2});
+  origin.push_back(std::vector<size_t>{0, 1, 6});
+  origin.push_back(std::vector<size_t>{0, 2, 5, 7, 10, 12, 15});
+
+  paddle::framework::AppendLoD(&origin, lod_lens);
+
+  LoD expected;
+  expected.push_back(std::vector<size_t>{0, 2, 4});
+  expected.push_back(std::vector<size_t>{0, 1, 6, 8, 10});
+  expected.push_back(
+      std::vector<size_t>{0, 2, 5, 7, 10, 12, 15, 17, 20, 24, 26});
+
+  EXPECT_EQ(origin, expected);
+}
+
 }  // namespace framework
 }  // namespace paddle
-- 
GitLab