summaryrefslogtreecommitdiff
path: root/examples/ParallelJIT/ParallelJIT.cpp
blob: 64a388695ff2d136ed2cb24daa3c3eb07498e3be (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
//===-- examples/ParallelJIT/ParallelJIT.cpp - Exercise threaded-safe JIT -===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Parallel JIT
//
// This test program creates two LLVM functions then calls them from three
// separate threads.  It requires the pthreads library.
// The three threads are created and then block waiting on a condition variable.
// Once all threads are blocked on the conditional variable, the main thread
// wakes them up. This complicated work is performed so that all three threads
// call into the JIT at the same time (or the best possible approximation of the
// same time). This test had assertion errors until I got the locking right.

#include "llvm/ExecutionEngine/GenericValue.h"
#include "llvm/ExecutionEngine/Interpreter.h"
#include "llvm/ExecutionEngine/JIT.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/Support/TargetSelect.h"
#include <iostream>
#include <pthread.h>
using namespace llvm;

static Function* createAdd1(Module *M) {
  // Create the add1 function entry and insert this entry into module M.  The
  // function will have a return type of "int" and take an argument of "int".
  // The '0' terminates the list of argument types.
  Function *Add1F =
    cast<Function>(M->getOrInsertFunction("add1",
                                          Type::getInt32Ty(M->getContext()),
                                          Type::getInt32Ty(M->getContext()),
                                          (Type *)0));

  // Add a basic block to the function. As before, it automatically inserts
  // because of the last argument.
  BasicBlock *BB = BasicBlock::Create(M->getContext(), "EntryBlock", Add1F);

  // Get pointers to the constant `1'.
  Value *One = ConstantInt::get(Type::getInt32Ty(M->getContext()), 1);

  // Get pointers to the integer argument of the add1 function...
  assert(Add1F->arg_begin() != Add1F->arg_end()); // Make sure there's an arg
  Argument *ArgX = Add1F->arg_begin();  // Get the arg
  ArgX->setName("AnArg");            // Give it a nice symbolic name for fun.

  // Create the add instruction, inserting it into the end of BB.
  Instruction *Add = BinaryOperator::CreateAdd(One, ArgX, "addresult", BB);

  // Create the return instruction and add it to the basic block
  ReturnInst::Create(M->getContext(), Add, BB);

  // Now, function add1 is ready.
  return Add1F;
}

static Function *CreateFibFunction(Module *M) {
  // Create the fib function and insert it into module M.  This function is said
  // to return an int and take an int parameter.
  Function *FibF = 
    cast<Function>(M->getOrInsertFunction("fib",
                                          Type::getInt32Ty(M->getContext()),
                                          Type::getInt32Ty(M->getContext()),
                                          (Type *)0));

  // Add a basic block to the function.
  BasicBlock *BB = BasicBlock::Create(M->getContext(), "EntryBlock", FibF);

  // Get pointers to the constants.
  Value *One = ConstantInt::get(Type::getInt32Ty(M->getContext()), 1);
  Value *Two = ConstantInt::get(Type::getInt32Ty(M->getContext()), 2);

  // Get pointer to the integer argument of the add1 function...
  Argument *ArgX = FibF->arg_begin();   // Get the arg.
  ArgX->setName("AnArg");            // Give it a nice symbolic name for fun.

  // Create the true_block.
  BasicBlock *RetBB = BasicBlock::Create(M->getContext(), "return", FibF);
  // Create an exit block.
  BasicBlock* RecurseBB = BasicBlock::Create(M->getContext(), "recurse", FibF);

  // Create the "if (arg < 2) goto exitbb"
  Value *CondInst = new ICmpInst(*BB, ICmpInst::ICMP_SLE, ArgX, Two, "cond");
  BranchInst::Create(RetBB, RecurseBB, CondInst, BB);

  // Create: ret int 1
  ReturnInst::Create(M->getContext(), One, RetBB);

  // create fib(x-1)
  Value *Sub = BinaryOperator::CreateSub(ArgX, One, "arg", RecurseBB);
  Value *CallFibX1 = CallInst::Create(FibF, Sub, "fibx1", RecurseBB);

  // create fib(x-2)
  Sub = BinaryOperator::CreateSub(ArgX, Two, "arg", RecurseBB);
  Value *CallFibX2 = CallInst::Create(FibF, Sub, "fibx2", RecurseBB);

  // fib(x-1)+fib(x-2)
  Value *Sum =
    BinaryOperator::CreateAdd(CallFibX1, CallFibX2, "addresult", RecurseBB);

  // Create the return instruction and add it to the basic block
  ReturnInst::Create(M->getContext(), Sum, RecurseBB);

  return FibF;
}

struct threadParams {
  ExecutionEngine* EE;
  Function* F;
  int value;
};

// We block the subthreads just before they begin to execute:
// we want all of them to call into the JIT at the same time,
// to verify that the locking is working correctly.
class WaitForThreads
{
public:
  WaitForThreads()
  {
    n = 0;
    waitFor = 0;

    int result = pthread_cond_init( &condition, NULL );
    assert( result == 0 );

    result = pthread_mutex_init( &mutex, NULL );
    assert( result == 0 );
  }

  ~WaitForThreads()
  {
    int result = pthread_cond_destroy( &condition );
    assert( result == 0 );

    result = pthread_mutex_destroy( &mutex );
    assert( result == 0 );
  }

  // All threads will stop here until another thread calls releaseThreads
  void block()
  {
    int result = pthread_mutex_lock( &mutex );
    assert( result == 0 );
    n ++;
    //~ std::cout << "block() n " << n << " waitFor " << waitFor << std::endl;

    assert( waitFor == 0 || n <= waitFor );
    if ( waitFor > 0 && n == waitFor )
    {
      // There are enough threads blocked that we can release all of them
      std::cout << "Unblocking threads from block()" << std::endl;
      unblockThreads();
    }
    else
    {
      // We just need to wait until someone unblocks us
      result = pthread_cond_wait( &condition, &mutex );
      assert( result == 0 );
    }

    // unlock the mutex before returning
    result = pthread_mutex_unlock( &mutex );
    assert( result == 0 );
  }

  // If there are num or more threads blocked, it will signal them all
  // Otherwise, this thread blocks until there are enough OTHER threads
  // blocked
  void releaseThreads( size_t num )
  {
    int result = pthread_mutex_lock( &mutex );
    assert( result == 0 );

    if ( n >= num ) {
      std::cout << "Unblocking threads from releaseThreads()" << std::endl;
      unblockThreads();
    }
    else
    {
      waitFor = num;
      pthread_cond_wait( &condition, &mutex );
    }

    // unlock the mutex before returning
    result = pthread_mutex_unlock( &mutex );
    assert( result == 0 );
  }

private:
  void unblockThreads()
  {
    // Reset the counters to zero: this way, if any new threads
    // enter while threads are exiting, they will block instead
    // of triggering a new release of threads
    n = 0;

    // Reset waitFor to zero: this way, if waitFor threads enter
    // while threads are exiting, they will block instead of
    // triggering a new release of threads
    waitFor = 0;

    int result = pthread_cond_broadcast( &condition );
    (void)result;
    assert(result == 0);
  }

  size_t n;
  size_t waitFor;
  pthread_cond_t condition;
  pthread_mutex_t mutex;
};

static WaitForThreads synchronize;

void* callFunc( void* param )
{
  struct threadParams* p = (struct threadParams*) param;

  // Call the `foo' function with no arguments:
  std::vector<GenericValue> Args(1);
  Args[0].IntVal = APInt(32, p->value);

  synchronize.block(); // wait until other threads are at this point
  GenericValue gv = p->EE->runFunction(p->F, Args);

  return (void*)(intptr_t)gv.IntVal.getZExtValue();
}

int main() {
  InitializeNativeTarget();
  LLVMContext Context;

  // Create some module to put our function into it.
  Module *M = new Module("test", Context);

  Function* add1F = createAdd1( M );
  Function* fibF = CreateFibFunction( M );

  // Now we create the JIT.
  ExecutionEngine* EE = EngineBuilder(M).create();

  //~ std::cout << "We just constructed this LLVM module:\n\n" << *M;
  //~ std::cout << "\n\nRunning foo: " << std::flush;

  // Create one thread for add1 and two threads for fib
  struct threadParams add1 = { EE, add1F, 1000 };
  struct threadParams fib1 = { EE, fibF, 39 };
  struct threadParams fib2 = { EE, fibF, 42 };

  pthread_t add1Thread;
  int result = pthread_create( &add1Thread, NULL, callFunc, &add1 );
  if ( result != 0 ) {
          std::cerr << "Could not create thread" << std::endl;
          return 1;
  }

  pthread_t fibThread1;
  result = pthread_create( &fibThread1, NULL, callFunc, &fib1 );
  if ( result != 0 ) {
          std::cerr << "Could not create thread" << std::endl;
          return 1;
  }

  pthread_t fibThread2;
  result = pthread_create( &fibThread2, NULL, callFunc, &fib2 );
  if ( result != 0 ) {
          std::cerr << "Could not create thread" << std::endl;
          return 1;
  }

  synchronize.releaseThreads(3); // wait until other threads are at this point

  void* returnValue;
  result = pthread_join( add1Thread, &returnValue );
  if ( result != 0 ) {
          std::cerr << "Could not join thread" << std::endl;
          return 1;
  }
  std::cout << "Add1 returned " << intptr_t(returnValue) << std::endl;

  result = pthread_join( fibThread1, &returnValue );
  if ( result != 0 ) {
          std::cerr << "Could not join thread" << std::endl;
          return 1;
  }
  std::cout << "Fib1 returned " << intptr_t(returnValue) << std::endl;

  result = pthread_join( fibThread2, &returnValue );
  if ( result != 0 ) {
          std::cerr << "Could not join thread" << std::endl;
          return 1;
  }
  std::cout << "Fib2 returned " << intptr_t(returnValue) << std::endl;

  return 0;
}