Benchmarking sigmoid function between C and D

[Arun Chandrasekaran]

What am I doing wrong here that makes the D equivalent 2.5 times 
slower than it's C equivalent?

Compilers used:

LDC2: LDC - the LLVM D compiler (1.8.0)
GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609

11:36:39 ~/code/c/test2$ ldc2 sigmoid.d -O5 && ./sigmoid
Max deviation is 0.001664
10^7 iterations using sigmoid1: 308 ms
10^7 iterations using sigmoid2: 30 ms
11:36:55 ~/code/c/test2
$ gcc sigmoid.c -o sigmoid-c -O3 -lm 2>/dev/null && ./sigmoid-c
Max deviation is 0.001664
10^7 iterations using sigmoid1: 134 ms
10^7 iterations using sigmoid2: 29 ms
11:37:10 ~/code/c/test2
$

C code, taken from 
https://stackoverflow.com/questions/412019/math-optimization-in-c-sharp#412176:

```
#include <math.h>
#include <stdio.h>
#include <time.h>

#define SCALE 320.0f
#define RESOLUTION 2047
#define MIN -RESOLUTION / SCALE
#define MAX RESOLUTION / SCALE

static float sigmoid_lut[RESOLUTION + 1];

void init_sigmoid_lut(void) {
     int i;
     for (i = 0; i < RESOLUTION + 1; i++) {
         sigmoid_lut[i] =  (1.0 / (1.0 + exp(-i / SCALE)));
     }
}

static float sigmoid1(const float value) {
     return (1.0f / (1.0f + expf(-value)));
}

static float sigmoid2(const float value) {
     if (value <= MIN) return 0.0f;
     if (value >= MAX) return 1.0f;
     if (value >= 0) return sigmoid_lut[(int)(value * SCALE + 
0.5f)];
     return 1.0f-sigmoid_lut[(int)(-value * SCALE + 0.5f)];
}

float test_error() {
     float x;
     float emax = 0.0;

     for (x = -10.0f; x < 10.0f; x+=0.00001f) {
         float v0 = sigmoid1(x);
         float v1 = sigmoid2(x);
         float error = fabsf(v1 - v0);
         if (error > emax) { emax = error; }
     }
     return emax;
}

int sigmoid1_perf() {
     clock_t t0, t1;
     int i;
     float x, y = 0.0f;

     t0 = clock();
     for (i = 0; i < 10; i++) {
         for (x = -5.0f; x <= 5.0f; x+=0.00001f) {
             y = sigmoid1(x);
         }
     }
     t1 = clock();
     printf("", y); /* To avoid sigmoidX() calls being optimized 
away */
     return (t1 - t0) / (CLOCKS_PER_SEC / 1000);
}

int sigmoid2_perf() {
     clock_t t0, t1;
     int i;
     float x, y = 0.0f;
     t0 = clock();
     for (i = 0; i < 10; i++) {
         for (x = -5.0f; x <= 5.0f; x+=0.00001f) {
             y = sigmoid2(x);
         }
     }
     t1 = clock();
     printf("", y); /* To avoid sigmoidX() calls being optimized 
away */
     return (t1 - t0) / (CLOCKS_PER_SEC / 1000);
}

int main(void) {
     init_sigmoid_lut();
     printf("Max deviation is %0.6f\n", test_error());
     printf("10^7 iterations using sigmoid1: %d ms\n", 
sigmoid1_perf());
     printf("10^7 iterations using sigmoid2: %d ms\n", 
sigmoid2_perf());

     return 0;
}
```

D equivalent:

```
module sigmoid;

import std.stdio;
import std.math;
import std.datetime.stopwatch;

enum SCALE = 320.0f;
enum RESOLUTION = 2047;
enum MIN = -RESOLUTION / SCALE;
enum MAX = RESOLUTION / SCALE;

float[RESOLUTION + 1] sigmoid_lut;

void init_sigmoid_lut() {
     int i;
     for (i = 0; i < RESOLUTION + 1; i++) {
         sigmoid_lut[i] =  (1.0 / (1.0 + exp(-i / SCALE)));
     }
}

private float sigmoid1(const float value) {
     return (1.0f / (1.0f + exp(-value)));
}

private float sigmoid2(const float value) {
     if (value <= MIN) return 0.0f;
     if (value >= MAX) return 1.0f;
     if (value >= 0) return sigmoid_lut[cast(int)(value * SCALE + 
0.5f)];
     return 1.0f-sigmoid_lut[cast(int)(-value * SCALE + 0.5f)];
}

private float test_error() {
     float x;
     float emax = 0.0;

     for (x = -10.0f; x < 10.0f; x+=0.00001f) {
         float v0 = sigmoid1(x);
         float v1 = sigmoid2(x);
         float error = fabs(v1 - v0);
         if (error > emax) { emax = error; }
     }
     return emax;
}

private auto sigmoid1_perf() {
     auto sw = StopWatch(AutoStart.yes);
     int i;
     float x, y = 0.0f;

     for (i = 0; i < 10; i++) {
         for (x = -5.0f; x <= 5.0f; x+=0.00001f) {
             y = sigmoid1(x);
         }
     }
     return sw.peek.total!"msecs";
}

private auto sigmoid2_perf() {
     auto sw = StopWatch(AutoStart.yes);
     int i;
     float x, y = 0.0f;
     for (i = 0; i < 10; i++) {
         for (x = -5.0f; x <= 5.0f; x+=0.00001f) {
             y = sigmoid2(x);
         }
     }
     return sw.peek.total!"msecs";
}

int main() {
     init_sigmoid_lut();
     writefln("Max deviation is %0.6f", test_error());
     writefln("10^7 iterations using sigmoid1: %s ms", 
sigmoid1_perf());
     writefln("10^7 iterations using sigmoid2: %s ms", 
sigmoid2_perf());

     return 0;
}
```