Server : Apache/2.4.41 (Ubuntu) System : Linux absol.cf 5.4.0-198-generic #218-Ubuntu SMP Fri Sep 27 20:18:53 UTC 2024 x86_64 User : www-data ( 33) PHP Version : 7.4.33 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_get_handler,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,pcntl_async_signals,pcntl_unshare, Directory :  /usr/share/emscripten/tests/core/

Upload File : current_dir [ Writeable ] document_root [ Writeable ]

#include <stdio.h>
#include <xmmintrin.h>

static __inline__ __m128 __attribute__((__always_inline__))
_mm_load_ps(const float *__p)
{
  return *(__m128*)__p;
}

float simdAverage(float *src, int len) {
  __m128 sumx4 = _mm_setzero_ps();
  for (int i = 0; i < len; i += 4) {
    __m128 v = _mm_load_ps(src);
    sumx4 = _mm_add_ps(sumx4, v);
    src += 4;
  }
  float sumx4_mem[4];
  float *sumx4_ptr = sumx4_mem;
  _mm_store_ps(sumx4_ptr, sumx4);
  return (sumx4_mem[0] + sumx4_mem[1] +
          sumx4_mem[2] + sumx4_mem[3])/len;
}

void initArray(float *src, int len) {
	for (int i = 0; i < len; ++i) {
    src[i] = 0.1 * i;
  }
}

int main() {
  const int len = 100000;
  float src[len];
  float result = 0.0;

  initArray(src, len);

  result = simdAverage(src, len);
  printf("averagex4 result: %.1f\n", result);
}