llvm/unittests/Analysis/TFUtilsTest.cpp

   1 //===- TFUtilsTest.cpp - test for TFUtils ---------------------------------===//
   2 //
   3 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
   4 // See https://llvm.org/LICENSE.txt for license information.
   5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
   6 //
   7 //===----------------------------------------------------------------------===//
   8
   9 #include "llvm/Analysis/Utils/TFUtils.h"
  10 #include "llvm/Analysis/ModelUnderTrainingRunner.h"
  11 #include "llvm/Analysis/TensorSpec.h"
  12 #include "llvm/AsmParser/Parser.h"
  13 #include "llvm/IR/Dominators.h"
  14 #include "llvm/IR/Instructions.h"
  15 #include "llvm/IR/LLVMContext.h"
  16 #include "llvm/IR/Module.h"
  17 #include "llvm/Support/Path.h"
  18 #include "llvm/Support/SourceMgr.h"
  19 #include "llvm/Testing/Support/SupportHelpers.h"
  20 #include "gtest/gtest.h"
  21
  22 using namespace llvm;
  23
  24 extern const char *TestMainArgv0;
  25
  26 // NOTE! This test model is currently also used by test/Transforms/Inline/ML tests
  27 //- relevant if updating this model.
  28 static std::string getModelPath() {
  29   SmallString<128> InputsDir = unittest::getInputFileDirectory(TestMainArgv0);
  30   llvm::sys::path::append(InputsDir, "ir2native_x86_64_model");
  31   return std::string(InputsDir);
  32 }
  33
  34 // Test observable behavior when no model is provided.
  35 TEST(TFUtilsTest, NoModel) {
  36   TFModelEvaluator Evaluator("", {}, {});
  37   EXPECT_FALSE(Evaluator.isValid());
  38 }
  39
  40 // Test we can correctly load a savedmodel and evaluate it.
  41 TEST(TFUtilsTest, LoadAndExecuteTest) {
  42   // We use the ir2native model for test. We know it has one feature of
  43   // dimension (1, 214)
  44   const static int64_t KnownSize = 214;
  45   std::vector<TensorSpec> InputSpecs{TensorSpec::createSpec<int32_t>(
  46       "serving_default_input_1", {1, KnownSize})};
  47   std::vector<TensorSpec> OutputSpecs{
  48       TensorSpec::createSpec<float>("StatefulPartitionedCall", {1})};
  49
  50   TFModelEvaluator Evaluator(getModelPath(), InputSpecs, OutputSpecs);
  51   EXPECT_TRUE(Evaluator.isValid());
  52
  53   int32_t *V = Evaluator.getInput<int32_t>(0);
  54   // Fill it up with 1's, we know the output.
  55   for (auto I = 0; I < KnownSize; ++I) {
  56     V[I] = 1;
  57   }
  58   {
  59     auto ER = Evaluator.evaluate();
  60     EXPECT_TRUE(ER.has_value());
  61     float Ret = *ER->getTensorValue<float>(0);
  62     EXPECT_EQ(static_cast<int64_t>(Ret), 80);
  63     EXPECT_EQ(ER->getUntypedTensorValue(0),
  64               reinterpret_cast<const void *>(ER->getTensorValue<float>(0)));
  65   }
  66   // The input vector should be unchanged
  67   for (auto I = 0; I < KnownSize; ++I) {
  68     EXPECT_EQ(V[I], 1);
  69   }
  70   // Zero-out the unused position '0' of the instruction histogram, which is
  71   // after the first 9 calculated values. Should the the same result.
  72   V[9] = 0;
  73   {
  74     auto ER = Evaluator.evaluate();
  75     EXPECT_TRUE(ER.has_value());
  76     float Ret = *ER->getTensorValue<float>(0);
  77     EXPECT_EQ(static_cast<int64_t>(Ret), 80);
  78   }
  79 }
  80
  81 // Test incorrect input setup
  82 TEST(TFUtilsTest, EvalError) {
  83   // We use the ir2native model for test. We know it has one feature of
  84   // dimension (1, 214)
  85   const static int64_t KnownSize = 213;
  86   std::vector<TensorSpec> InputSpecs{TensorSpec::createSpec<int32_t>(
  87       "serving_default_input_1", {1, KnownSize})};
  88   std::vector<TensorSpec> OutputSpecs{
  89       TensorSpec::createSpec<float>("StatefulPartitionedCall", {1})};
  90
  91   TFModelEvaluator Evaluator(getModelPath(), InputSpecs, OutputSpecs);
  92   EXPECT_FALSE(Evaluator.isValid());
  93 }
  94
  95 TEST(TFUtilsTest, UnsupportedFeature) {
  96   const static int64_t KnownSize = 214;
  97   std::vector<TensorSpec> InputSpecs{
  98       TensorSpec::createSpec<int32_t>("serving_default_input_1",
  99                                       {1, KnownSize}),
 100       TensorSpec::createSpec<float>("this_feature_does_not_exist", {2, 5})};
 101
 102   LLVMContext Ctx;
 103   auto Evaluator = ModelUnderTrainingRunner::createAndEnsureValid(
 104       Ctx, getModelPath(), "StatefulPartitionedCall", InputSpecs,
 105       {LoggedFeatureSpec{
 106           TensorSpec::createSpec<float>("StatefulPartitionedCall", {1}),
 107           None}});
 108   int32_t *V = Evaluator->getTensor<int32_t>(0);
 109   // Fill it up with 1s, we know the output.
 110   for (auto I = 0; I < KnownSize; ++I)
 111     V[I] = 1;
 112
 113   float *F = Evaluator->getTensor<float>(1);
 114   for (auto I = 0; I < 2 * 5; ++I)
 115     F[I] = 3.14 + I;
 116   float Ret = Evaluator->evaluate<float>();
 117   EXPECT_EQ(static_cast<int64_t>(Ret), 80);
 118   // The input vector should be unchanged
 119   for (auto I = 0; I < KnownSize; ++I)
 120     EXPECT_EQ(V[I], 1);
 121   for (auto I = 0; I < 2 * 5; ++I)
 122     EXPECT_FLOAT_EQ(F[I], 3.14 + I);
 123 }
 124
 125 TEST(TFUtilsTest, MissingFeature) {
 126   std::vector<TensorSpec> InputSpecs{};
 127   std::vector<TensorSpec> OutputSpecs{
 128       TensorSpec::createSpec<float>("StatefulPartitionedCall", {1})};
 129
 130   TFModelEvaluator Evaluator(getModelPath(), InputSpecs, OutputSpecs);
 131   EXPECT_FALSE(Evaluator.isValid());
 132 }