Halide入門教程04
// Halide tutorial lesson 4: Debugging with tracing, print, and print_when
// Halide入門第四課：用tracing，print，print_when調試
// This lesson demonstrates how to follow what Halide is doing at runtime.
// 本課展示瞭如何跟蹤Halide在運行時的行爲
// On linux, you can compile and run it like so:
// g++ lesson_04*.cpp -g -I ../include -L ../bin -lHalide -lpthread -ldl -o lesson_04 -std=c++11
// LD_LIBRARY_PATH=../bin ./lesson_04
// On os x:
// g++ lesson_04*.cpp -g -I ../include -L ../bin -lHalide -o lesson_04 -std=c++11
// DYLD_LIBRARY_PATH=../bin ./lesson_04
// If you have the entire Halide source tree, you can also build it by
// running:
// make tutorial_lesson_04_debugging_2
// in a shell with the current directory at the top of the halide
// source tree.
#include "Halide.h"
#include <stdio.h>
using namespace Halide;
int main(int argc, char **argv) {
Var x("x"), y("y");
// Printing out the value of Funcs as they are computed.
// 打印函數（Func）在計算時刻的值
{
// We'll define our gradient function as before.
Func gradient("gradient");
gradient(x, y) = x + y;
// And tell Halide that we'd like to be notified of all
// evaluations.
// 告訴Halide我們想要跟蹤所有的函數計算值
gradient.trace_stores();
// Realize the function over an 8x8 region.
printf("Evaluating gradient\n");
Buffer<int> output = gradient.realize(8, 8);
// This will print out all the times gradient(x, y) gets
// evaluated.
// Now that we can snoop on what Halide is doing, let's try our
// first scheduling primitive. We'll make a new version of
// gradient that processes each scanline in parallel.
Func parallel_gradient("parallel_gradient");
parallel_gradient(x, y) = x + y;
// We'll also trace this function.
parallel_gradient.trace_stores();
// Things are the same so far. We've defined the algorithm, but
// haven't said anything about how to schedule it. In general,
// exploring different scheduling decisions doesn't change the code
// that describes the algorithm.
// 在Halide中，由於算法和調度解耦合，算法的調度並不影響算法的描述
// Now we tell Halide to use a parallel for loop over the y
// coordinate. On Linux we run this using a thread pool and a task
// queue. On OS X we call into grand central dispatch, which does
// the same thing for us.
// 在y方形並行執行for循環
parallel_gradient.parallel(y);
// This time the printfs should come out of order, because each
// scanline is potentially being processed in a different
// thread. The number of threads should adapt to your system, but
// on linux you can control it manually using the environment
// variable HL_NUM_THREADS.
// 由於採用了並行計算飯，每行的計算可能位於不同的線程，因此輸出結果可能會是亂序的。
// 可以通過環境變量HL_NUM_THREADS來指定parallel的線程數
printf("\nEvaluating parallel_gradient\n");
parallel_gradient.realize(8, 8);
}
// Printing individual Exprs.
{
// trace_stores() can only print the value of a
// Func. Sometimes you want to inspect the value of
// sub-expressions rather than the entire Func. The built-in
// function 'print' can be wrapped around any Expr to print
// the value of that Expr every time it is evaluated.
// trace_stores()函數打印函數值，內置的print函數可以答應表達式（Expr）對象的值
// For example, say we have some Func that is the sum of two terms:
Func f;
f(x, y) = sin(x) + cos(y);
// If we want to inspect just one of the terms, we can wrap
// 'print' around it like so:
// 如果我們僅僅需要關注表達式中的一個條目，我們可以在這個條目上加上print函數
Func g;
g(x, y) = sin(x) + print(cos(y));
printf("\nEvaluating sin(x) + cos(y), and just printing cos(y)\n");
g.realize(4, 4);
}
// Printing additional context.
{
// print can take multiple arguments. It prints all of them
// and evaluates to the first one. The arguments can be Exprs
// or constant strings. This can be used to print additional
// context alongside the value:
// 如果需要，可以在打印單個條目上加上額外的文本
Func f;
f(x, y) = sin(x) + print(cos(y), "<- this is cos(", y, ") when x =", x);
printf("\nEvaluating sin(x) + cos(y), and printing cos(y) with more context\n");
f.realize(4, 4);
// It can be useful to split expressions like the one above
// across multiple lines to make it easier to turn on and off
// printing certain values while debugging.
Expr e = cos(y);
// Uncomment the following line to print the value of cos(y)
// e = print(e, "<- this is cos(", y, ") when x =", x);
Func g;
g(x, y) = sin(x) + e;
g.realize(4, 4);
}
// Conditional printing
{
// Both print and trace_stores can produce a lot of output. If
// you're looking for a rare event, or just want to see what
// happens at a single pixel, this amount of output can be
// difficult to dig through. Instead, the function print_when
// can be used to conditionally print an Expr. The first
// argument to print_when is a boolean Expr. If the Expr
// evaluates to true, it returns the second argument and
// prints all of the arguments. If the Expr evaluates to false
// it just returns the second argument and does not print.
// 如果需要查看中間某個特定的結果，可以調用條件打印函數，打印出在特定條件下，表達式的結果。
// print_when(bool_expr, expr, context)
// 如果 bool_expr == ture: 返回expr，打印context內容
// 否則只返回expr
Func f;
Expr e = cos(y);
e = print_when(x == 37 && y == 42, e, "<- this is cos(y) at x, y == (37, 42)");
f(x, y) = sin(x) + e;
printf("\nEvaluating sin(x) + cos(y), and printing cos(y) at a single pixel\n");
f.realize(640, 480);
// print_when can also be used to check for values you're not expecting:
Func g;
e = cos(y);
e = print_when(e < 0, e, "cos(y) < 0 at y ==", y);
g(x, y) = sin(x) + e;
printf("\nEvaluating sin(x) + cos(y), and printing whenever cos(y) < 0\n");
g.realize(4, 4);
}
// Printing expressions at compile-time.
{
// The code above builds up a Halide Expr across several lines
// of code. If you're programmatically constructing a complex
// expression, and you want to check the Expr you've created
// is what you think it is, you can also print out the
// expression itself using C++ streams:
// 在編寫一些複雜的表達式時，如果你想要查看錶達式是否和你想象中一樣，可以用c++
// 的輸出流將表達式結果打印到標準輸出上，檢查是否如預期一致。
Var fizz("fizz"), buzz("buzz");
Expr e = 1;
for (int i = 2; i < 100; i++) {
if (i % 3 == 0 && i % 5 == 0) e += fizz*buzz;
else if (i % 3 == 0) e += fizz;
else if (i % 5 == 0) e += buzz;
else e += i;
}
std::cout << "Printing a complex Expr: " << e << "\n";
}
printf("Success!\n");
return 0;
}
編譯執行：
$ g++ lesson_04*.cpp -g -I ../include -L ../bin -lHalide -lpthread -ldl -o lesson_04 -std=c++11
$ ./lesson_04結果：
Begin pipeline gradient.0()
Store gradient.0(0, 0) = 0
Store gradient.0(1, 0) = 1
Store gradient.0(2, 0) = 2
Store gradient.0(3, 0) = 3
Store gradient.0(4, 0) = 4
Store gradient.0(5, 0) = 5
Store gradient.0(6, 0) = 6
Store gradient.0(7, 0) = 7
Store gradient.0(0, 1) = 1
Store gradient.0(1, 1) = 2
Store gradient.0(2, 1) = 3
Store gradient.0(3, 1) = 4
Store gradient.0(4, 1) = 5
Store gradient.0(5, 1) = 6
Store gradient.0(6, 1) = 7
Store gradient.0(7, 1) = 8
Store gradient.0(0, 2) = 2
Store gradient.0(1, 2) = 3
Store gradient.0(2, 2) = 4
Store gradient.0(3, 2) = 5
Store gradient.0(4, 2) = 6
Store gradient.0(5, 2) = 7
Store gradient.0(6, 2) = 8
Store gradient.0(7, 2) = 9
Store gradient.0(0, 3) = 3
Store gradient.0(1, 3) = 4
Store gradient.0(2, 3) = 5
Store gradient.0(3, 3) = 6
Store gradient.0(4, 3) = 7
Store gradient.0(5, 3) = 8
Store gradient.0(6, 3) = 9
Store gradient.0(7, 3) = 10
Store gradient.0(0, 4) = 4
Store gradient.0(1, 4) = 5
Store gradient.0(2, 4) = 6
Store gradient.0(3, 4) = 7
Store gradient.0(4, 4) = 8
Store gradient.0(5, 4) = 9
Store gradient.0(6, 4) = 10
Store gradient.0(7, 4) = 11
Store gradient.0(0, 5) = 5
Store gradient.0(1, 5) = 6
Store gradient.0(2, 5) = 7
Store gradient.0(3, 5) = 8
Store gradient.0(4, 5) = 9
Store gradient.0(5, 5) = 10
Store gradient.0(6, 5) = 11
Store gradient.0(7, 5) = 12
Store gradient.0(0, 6) = 6
Store gradient.0(1, 6) = 7
Store gradient.0(2, 6) = 8
Store gradient.0(3, 6) = 9
Store gradient.0(4, 6) = 10
Store gradient.0(5, 6) = 11
Store gradient.0(6, 6) = 12
Store gradient.0(7, 6) = 13
Store gradient.0(0, 7) = 7
Store gradient.0(1, 7) = 8
Store gradient.0(2, 7) = 9
Store gradient.0(3, 7) = 10
Store gradient.0(4, 7) = 11
Store gradient.0(5, 7) = 12
Store gradient.0(6, 7) = 13
Store gradient.0(7, 7) = 14
End pipeline gradient.0()
Begin pipeline parallel_gradient.0()
Store parallel_gradient.0(0, 0) = 0
Store parallel_gradient.0(1, 0) = 1
Store parallel_gradient.0(2, 0) = 2
Store parallel_gradient.0(3, 0) = 3
Store parallel_gradient.0(4, 0) = 4
Store parallel_gradient.0(5, 0) = 5
Store parallel_gradient.0(6, 0) = 6
Store parallel_gradient.0(7, 0) = 7
Store parallel_gradient.0(0, 1) = 1
Store parallel_gradient.0(1, 1) = 2
Store parallel_gradient.0(2, 1) = 3
Store parallel_gradient.0(3, 1) = 4
Store parallel_gradient.0(4, 1) = 5
Store parallel_gradient.0(5, 1) = 6
Store parallel_gradient.0(6, 1) = 7
Store parallel_gradient.0(7, 1) = 8
Store parallel_gradient.0(0, 2) = 2
Store parallel_gradient.0(0, 3) = 3
Store parallel_gradient.0(1, 2) = 3
Store parallel_gradient.0(1, 3) = 4
Store parallel_gradient.0(0, 4) = 4
Store parallel_gradient.0(2, 3) = 5
Store parallel_gradient.0(2, 2) = 4
Store parallel_gradient.0(1, 4) = 5
Store parallel_gradient.0(3, 2) = 5
Store parallel_gradient.0(2, 4) = 6
Store parallel_gradient.0(3, 3) = 6
Store parallel_gradient.0(4, 2) = 6
Store parallel_gradient.0(4, 3) = 7
Store parallel_gradient.0(3, 4) = 7
Store parallel_gradient.0(5, 2) = 7
Store parallel_gradient.0(5, 3) = 8
Store parallel_gradient.0(4, 4) = 8
Store parallel_gradient.0(6, 2) = 8
Store parallel_gradient.0(6, 3) = 9
Store parallel_gradient.0(7, 2) = 9
Store parallel_gradient.0(5, 4) = 9
Store parallel_gradient.0(7, 3) = 10
Store parallel_gradient.0(0, 6) = 6
Store parallel_gradient.0(6, 4) = 10
Store parallel_gradient.0(0, 7) = 7
Store parallel_gradient.0(1, 6) = 7
Store parallel_gradient.0(1, 7) = 8
Store parallel_gradient.0(7, 4) = 11
Store parallel_gradient.0(2, 6) = 8
Store parallel_gradient.0(2, 7) = 9
Store parallel_gradient.0(3, 6) = 9
Store parallel_gradient.0(3, 7) = 10
Store parallel_gradient.0(4, 6) = 10
Store parallel_gradient.0(4, 7) = 11
Store parallel_gradient.0(5, 7) = 12
Store parallel_gradient.0(5, 6) = 11
Store parallel_gradient.0(0, 5) = 5
Store parallel_gradient.0(6, 7) = 13
Store parallel_gradient.0(6, 6) = 12
Store parallel_gradient.0(1, 5) = 6
Store parallel_gradient.0(7, 7) = 14
Store parallel_gradient.0(2, 5) = 7
Store parallel_gradient.0(7, 6) = 13
Store parallel_gradient.0(3, 5) = 8
Store parallel_gradient.0(4, 5) = 9
Store parallel_gradient.0(5, 5) = 10
Store parallel_gradient.0(6, 5) = 11
Store parallel_gradient.0(7, 5) = 12
End pipeline parallel_gradient.0()
1.000000
1.000000
1.000000
1.000000
0.540302
0.540302
0.540302
0.540302
-0.416147
-0.416147
-0.416147
-0.416147
-0.989992
-0.989992
-0.989992
-0.989992
1.000000 <- this is cos( 0 ) when x = 0
1.000000 <- this is cos( 0 ) when x = 1
1.000000 <- this is cos( 0 ) when x = 2
1.000000 <- this is cos( 0 ) when x = 3
0.540302 <- this is cos( 1 ) when x = 0
0.540302 <- this is cos( 1 ) when x = 1
0.540302 <- this is cos( 1 ) when x = 2
0.540302 <- this is cos( 1 ) when x = 3
-0.416147 <- this is cos( 2 ) when x = 0
-0.416147 <- this is cos( 2 ) when x = 1
-0.416147 <- this is cos( 2 ) when x = 2
-0.416147 <- this is cos( 2 ) when x = 3
-0.989992 <- this is cos( 3 ) when x = 0
-0.989992 <- this is cos( 3 ) when x = 1
-0.989992 <- this is cos( 3 ) when x = 2
-0.989992 <- this is cos( 3 ) when x = 3
-0.399985 <- this is cos(y) at x, y == (37, 42)
-0.416147 cos(y) < 0 at y == 2
-0.416147 cos(y) < 0 at y == 2
-0.416147 cos(y) < 0 at y == 2
-0.416147 cos(y) < 0 at y == 2
-0.989992 cos(y) < 0 at y == 3
-0.989992 cos(y) < 0 at y == 3
-0.989992 cos(y) < 0 at y == 3
-0.989992 cos(y) < 0 at y == 3
Evaluating gradient
Evaluating parallel_gradient
Evaluating sin(x) + cos(y), and just printing cos(y)
Evaluating sin(x) + cos(y), and printing cos(y) with more context
Evaluating sin(x) + cos(y), and printing cos(y) at a single pixel
Evaluating sin(x) + cos(y), and printing whenever cos(y) < 0
Printing a complex Expr: ((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((1 + 2) + fizz) + 4) + buzz) + fizz) + 7) + 8) + fizz) + buzz) + 11) + fizz) + 13) + 14) + (fizz*buzz)) + 16) + 17) + fizz) + 19) + buzz) + fizz) + 22) + 23) + fizz) + buzz) + 26) + fizz) + 28) + 29) + (fizz*buzz)) + 31) + 32) + fizz) + 34) + buzz) + fizz) + 37) + 38) + fizz) + buzz) + 41) + fizz) + 43) + 44) + (fizz*buzz)) + 46) + 47) + fizz) + 49) + buzz) + fizz) + 52) + 53) + fizz) + buzz) + 56) + fizz) + 58) + 59) + (fizz*buzz)) + 61) + 62) + fizz) + 64) + buzz) + fizz) + 67) + 68) + fizz) + buzz) + 71) + fizz) + 73) + 74) + (fizz*buzz)) + 76) + 77) + fizz) + 79) + buzz) + fizz) + 82) + 83) + fizz) + buzz) + 86) + fizz) + 88) + 89) + (fizz*buzz)) + 91) + 92) + fizz) + 94) + buzz) + fizz) + 97) + 98) + fizz)
Success!
Halide提供的debug方法要點提煉：
1. Func.trace_stores() 跟蹤函數運行時計算結果
2. Func.parallel(y) 在某個domain方向多線程並行計算
3. print() 打印所關注表達式的值
4. print_when() 打印在指定條件爲真情況下的值，也可用於屏蔽條件爲假時的輸出
5. 用c++的輸出流輸出複雜表達式，檢查表達式構造是否和預期一致