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;
}
```

can you try it with c math functions?

instead of std.math, try to use core.stdc.math

On Sat, Apr 7, 2018 at 8:53 PM, Arun Chandrasekaran via Digitalmars-d-learn <digitalmars-d-learn@puremagic.com> wrote:

> 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/ques tions/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;
> }
> ```
>

On Saturday, 7 April 2018 at 18:53:57 UTC, Arun Chandrasekaran wrote:
> 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

When benchmarking against C you need to add more switches to ldc2, like:
-release -boundscheck=off

or for ldc http://docs.algorithm.dlang.io/latest/mir_math_common.html

On Sat, Apr 7, 2018 at 9:10 PM, Daniel Kozak <kozzi11@gmail.com> wrote:

> can you try it with c math functions?
>
> instead of std.math, try to use core.stdc.math
>
> On Sat, Apr 7, 2018 at 8:53 PM, Arun Chandrasekaran via Digitalmars-d-learn <digitalmars-d-learn@puremagic.com> wrote:
>
>> 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/ques tions/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;
>> }
>> ```
>>
>
>

On Saturday, 7 April 2018 at 19:14:27 UTC, Daniel Kozak wrote:
> or for ldc http://docs.algorithm.dlang.io/latest/mir_math_common.html
>
> On Sat, Apr 7, 2018 at 9:10 PM, Daniel Kozak <kozzi11@gmail.com> wrote:
>
>> can you try it with c math functions?
>>
>> instead of std.math, try to use core.stdc.math
>>
>> On Sat, Apr 7, 2018 at 8:53 PM, Arun Chandrasekaran via Digitalmars-d-learn <digitalmars-d-learn@puremagic.com> wrote:
>>
>>> [...]

Much better with mir.math.common, still a bit slower than C (even with larger loops):

10^7 iterations using sigmoid1: 168 ms
10^7 iterations using sigmoid2: 39 ms

Also LDC optimized away the computation. So I had to modify the code a bit.

```
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);
        }
    }
    auto t = sw.peek.total!"msecs";
    return tuple(y, t);
}

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);
        }
    }
    auto t = sw.peek.total!"msecs";
    return tuple(y, t);
}
```

On Saturday, 7 April 2018 at 20:33:13 UTC, Arun Chandrasekaran wrote:
> On Saturday, 7 April 2018 at 19:14:27 UTC, Daniel Kozak wrote:
>> or for ldc http://docs.algorithm.dlang.io/latest/mir_math_common.html
>>
>> On Sat, Apr 7, 2018 at 9:10 PM, Daniel Kozak <kozzi11@gmail.com> wrote:
>>
>>> can you try it with c math functions?
>>>
>>> instead of std.math, try to use core.stdc.math
>>>
>>> On Sat, Apr 7, 2018 at 8:53 PM, Arun Chandrasekaran via Digitalmars-d-learn <digitalmars-d-learn@puremagic.com> wrote:
>>>
>>>> [...]
>
> Much better with mir.math.common, still a bit slower than C (even with larger loops):
>
> 10^7 iterations using sigmoid1: 168 ms
> 10^7 iterations using sigmoid2: 39 ms
>
> Also LDC optimized away the computation. So I had to modify the code a bit.
>


Have you tried LLVM intrinsics? say llvm_exp

On Saturday, 7 April 2018 at 20:33:13 UTC, Arun Chandrasekaran wrote:
> Much better with mir.math.common, still a bit slower than C (even with larger loops):

As this appears to be benchmarking mostly the std.math.exp(float) performance - some/many basic algos in std.math, incl. exp(), are currently using the x87 FPU for all 3 floating-point types, although there are treacherous float/double overloads, sacrificing performance in many cases.
See https://github.com/dlang/phobos/pull/6272#issuecomment-373967109 (and the later numbers for current Intel and GCC compilers) for a performance comparison of some std.math algos incl. exp(). For LDC, the double/float versions of the few worked-on algos in that PR were sped-up by an overall factor of 3 [but only by 1.46 for exp(float)].

On Saturday, 7 April 2018 at 23:48:36 UTC, kinke wrote:
> On Saturday, 7 April 2018 at 20:33:13 UTC, Arun Chandrasekaran wrote:
>> [...]
>
> As this appears to be benchmarking mostly the std.math.exp(float) performance - some/many basic algos in std.math, incl. exp(), are currently using the x87 FPU for all 3 floating-point types, although there are treacherous float/double overloads, sacrificing performance in many cases.
> See https://github.com/dlang/phobos/pull/6272#issuecomment-373967109 (and the later numbers for current Intel and GCC compilers) for a performance comparison of some std.math algos incl. exp(). For LDC, the double/float versions of the few worked-on algos in that PR were sped-up by an overall factor of 3 [but only by 1.46 for exp(float)].

Interesting to see this, thanks! Did you also generate the bar graph plot using D?

On Sunday, 8 April 2018 at 05:35:10 UTC, Arun Chandrasekaran wrote:
> Did you also generate the bar graph plot using D?

Heh nope, I used LibreOffice Calc for that.

I would say he has, becaue AFAIK mir.math.common using LLVM intrinsics

On Sat, Apr 7, 2018 at 11:53 PM, Guillaume Piolat via Digitalmars-d-learn < digitalmars-d-learn@puremagic.com> wrote:

> On Saturday, 7 April 2018 at 20:33:13 UTC, Arun Chandrasekaran wrote:
>
>> On Saturday, 7 April 2018 at 19:14:27 UTC, Daniel Kozak wrote:
>>
>>> or for ldc http://docs.algorithm.dlang.io/latest/mir_math_common.html
>>>
>>> On Sat, Apr 7, 2018 at 9:10 PM, Daniel Kozak <kozzi11@gmail.com> wrote:
>>>
>>> can you try it with c math functions?
>>>>
>>>> instead of std.math, try to use core.stdc.math
>>>>
>>>> On Sat, Apr 7, 2018 at 8:53 PM, Arun Chandrasekaran via Digitalmars-d-learn <digitalmars-d-learn@puremagic.com> wrote:
>>>>
>>>> [...]
>>>>>
>>>>
>> Much better with mir.math.common, still a bit slower than C (even with
>> larger loops):
>>
>> 10^7 iterations using sigmoid1: 168 ms
>> 10^7 iterations using sigmoid2: 39 ms
>>
>> Also LDC optimized away the computation. So I had to modify the code a bit.
>>
>>
>
> Have you tried LLVM intrinsics? say llvm_exp
>