4

我正在尝试编写一个使用 OpenCL 执行蒙特卡洛模拟的程序。我遇到了一个涉及指数的问题。当变量step的值变大，大约 20000 时，指数计算意外失败，程序以“Abort Trap: 6”退出。鉴于步骤不应影响内存分配，这似乎是一个奇怪的错误。我尝试设置normal、alpha和beta到 0 但这并不能解决问题，但是注释掉指数并用常数 1 替换它似乎可以解决问题。我已经在 AWS GPU 实例上运行了我的代码，它没有遇到任何问题。有没有人知道为什么这可能是集成显卡的问题？

解决方案

在较小的范围内多次执行内核以将内核执行时间保持在 5 秒以下

代码片段

#ifndef M_PI
#define M_PI 3.14159265358979323846
#endif

static uint MWC64X(uint2 *state) {
  enum { A = 4294883355U };
  uint x = (*state).x, c = (*state).y; 
  uint res = x ^ c;                    
  uint hi = mul_hi(x, A);              
  x = x * A + c;
  c = hi + (x < c);
  *state = (uint2)(x, c); 
  return res;          
}

__kernel void discreteMonteCarloKernel(...) {

  float cumulativeWalk = stockPrice;
  float currentValue = stockPrice;

  ...

  uint n = get_global_id(0);
  uint2 seed2 = (uint2)(n, seed);
  uint random1 = MWC64X(&seed2);
  uint2 seed3 = (uint2)(random1, seed);
  uint random2 = MWC64X(&seed3);

  float alpha = (interestRate - 0.5 * sigma * sigma) * dt;
  float beta = sigma * sqrt(dt);

  float u1;
  float u2;
  float a;
  float b;
  float normal;

  for (int j = 0; j < steps; j++) {

    random1 = MWC64X(&seed2);

    if (random1 == 0) {
      random1 = MWC64X(&seed2);
    }

    random2 = MWC64X(&seed3);

    u1 = (float)random1 / (float)0xffffffff;
    u2 = (float)random2 / (float)0xffffffff;

    a = sqrt(-2 * log(u1));
    b = 2 * M_PI * u2;

    normal = a * sin(b);

    exponent = exp(alpha + beta * normal);
    currentValue = currentValue * exponent;
    cumulativeWalk += currentValue;

    ...
}

问题报告

Exception Type:        EXC_CRASH (SIGABRT)
Exception Codes:       0x0000000000000000, 0x0000000000000000
Exception Note:        EXC_CORPSE_NOTIFY

Application Specific Information:
abort() called

Application Specific Signatures:
Graphics hardware encountered an error and was reset: 0x00000813


Thread 0 Crashed:: Dispatch queue: opencl_runtime
0   libsystem_kernel.dylib          0x00007fffb14bad42 __pthread_kill + 10
1   libsystem_pthread.dylib         0x00007fffb15a85bf pthread_kill + 90
2   libsystem_c.dylib               0x00007fffb1420420 abort + 129
3   libGPUSupportMercury.dylib      0x00007fffa98e6fbf gpusGenerateCrashLog + 158
4   com.apple.driver.AppleIntelHD5000GraphicsGLDriver   0x000000010915f13b gpusKillClientExt + 9
5   libGPUSupportMercury.dylib      0x00007fffa98e7983 gpusQueueSubmitDataBuffers + 168
6   com.apple.driver.AppleIntelHD5000GraphicsGLDriver   0x00000001091aa031 IntelCLCommandBuffer::getNew(GLDQueueRec*) + 31
7   com.apple.driver.AppleIntelHD5000GraphicsGLDriver   0x00000001091a9f99 intelSubmitCLCommands(GLDQueueRec*, unsigned int) + 65
8   com.apple.driver.AppleIntelHD5000GraphicsGLDriver   0x00000001091b00a1 CHAL_INTEL::ChalContext::ChalFlush() + 83
9   com.apple.driver.AppleIntelHD5000GraphicsGLDriver   0x00000001091aa2c3 gldFinishQueue + 43
10  com.apple.opencl                0x00007fff9ffeeb37 0x7fff9ffed000 + 6967
11  com.apple.opencl                0x00007fff9ffef000 0x7fff9ffed000 + 8192
12  com.apple.opencl                0x00007fffa000ccca 0x7fff9ffed000 + 130250
13  com.apple.opencl                0x00007fffa001029d 0x7fff9ffed000 + 144029
14  libdispatch.dylib               0x00007fffb13568fc _dispatch_client_callout + 8
15  libdispatch.dylib               0x00007fffb1357536 _dispatch_barrier_sync_f_invoke + 83
16  com.apple.opencl                0x00007fffa001011d 0x7fff9ffed000 + 143645
17  com.apple.opencl                0x00007fffa000bda6 0x7fff9ffed000 + 126374
18  com.apple.opencl                0x00007fffa00011df clEnqueueReadBuffer + 813
19  simplisticComparison            0x0000000107b953cf BinomialMultiplication::execute(int) + 1791
20  simplisticComparison            0x0000000107b9ec7f main + 767
21  libdyld.dylib                   0x00007fffb138c235 start + 1

Thread 1:
0   libsystem_pthread.dylib         0x00007fffb15a50e4 start_wqthread + 0
1   ???                             0x000070000eed6b30 0 + 123145552751408

Thread 2:
0   libsystem_pthread.dylib         0x00007fffb15a50e4 start_wqthread + 0

Thread 3:
0   libsystem_pthread.dylib         0x00007fffb15a50e4 start_wqthread + 0
1   ???                             0x007865646e496d65 0 + 33888479226719589

Thread 0 crashed with X86 Thread State (64-bit):
  rax: 0x0000000000000000  rbx: 0x0000000000000006  rcx: 0x00007fff58074078  rdx: 0x0000000000000000
  rdi: 0x0000000000000307  rsi: 0x0000000000000006  rbp: 0x00007fff580740a0  rsp: 0x00007fff58074078
   r8: 0x0000000000000000   r9: 0x00007fffb140ba50  r10: 0x0000000008000000  r11: 0x0000000000000206
  r12: 0x00007f92de80a7e0  r13: 0x00007f92e0008c00  r14: 0x00007fffba29e3c0  r15: 0x00007f92de801a00
  rip: 0x00007fffb14bad42  rfl: 0x0000000000000206  cr2: 0x00007fffba280128

Logical CPU:     0
Error Code:      0x02000148
Trap Number:     133
4

1 回答 1

1

我有一个猜测。驱动程序可能会以两种方式崩溃：

  1. 我们引用了一个错误的缓冲区地址。这可能不是你的情况。
  2. 我们超时（超过 TDR）。内核需要几秒钟才能完成。

我的钱在#2。如果较大的值（步数）使 GPU 运行时间过长，系统就会杀死东西。

我不熟悉 Apple 英特尔驱动程序的内容，但通常有一种方法可以在极端情况下禁用 TDR。例如，请参阅 TDR 上的Windows 文档以了解要点。（Linux 驱动程序也有办法禁用它。）

通常我们希望避免运行耗时超长的事情，并且以某种方式分解工作负载可能是个好主意，这样您自然就不会按下这个终止开关。例如，也许将“步骤”分成更小的块（传入并保存您无法重新计算的部分的状态）。

于 2017-05-16T02:17:10.187 回答