different compares clock cycle test ???

[sinsi]

What's happened to this forum ?,nobody wants to test run code anymore ? :(
I have a comparison that might not been tested yet :
A loop with many scalar compares with conditional jumps vs packed compares ???

The skeleton code I wrote earlier is all you need, just add the code you want to test.

[zedd151]

What's happened to this forum ?,nobody wants to test run code anymore ? :(

It's usually the OP that supplies the testing method. This will ensure that all testers will use the same testbed (I.e., testing methods), for better comparison between processors where the test is being conducted, and even to test for any differences between OS's etc. that are testing the same function or algorithm.

[NoCforMe]

We look forward to your test results, hopefully soon.

[daydreamer]

Scalar vs packed SSE compare

Code Select Expand

// primesx.cpp

#include "pch.h"
#include <iostream>
using namespace std;
float zero = 0.0;
int pflag = 0;
alignas(16) float flut[]{ 2.0,3.0,5.0,7.0,11.0,13.0,17.0,19.0,0.0,0.0,0.0 };
alignas(16) float arr[]{ 0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0 };
char lut[]{ 0, 0, 2, 3, 0, 5, 0, 7, 0, 0,0,11,0,13,0,0,0,0,0,0 };
int main()
{
int i, j=3;
float f = 3.0;
float fresult = 0;
    cout << "Primesx\n";
for (i = 0; i < 14; i++) {
cout << i << " ";
if (lut[i] != 0) cout << "prime " << (int)lut[i] << " ";
cout << f << " ";
//f = f + 1.0;
}
cout << f << " ";
cout << "\n\n\n\n";
for (j = 1; j < 14; j=j+1) {
f = (float)j; //test all floats
_asm {
push ebx

mov ecx, 14
mov ebx, 1
; lea ebx, [ebx * 4]
lea ebx, [flut + ebx * 4]
; lea ebx, flut
L2 :
movss xmm0, f
movss xmm1, [ebx]
; subss xmm0, xmm1
ucomiss xmm0, xmm1
jne L1; found prime
ja L4s;ja jump if above,jb jump if below
mov eax, 1
mov pflag, eax
movss xmm0, [ebx]
movss fresult, xmm0
jmp l3;have found prime, jump out of loop
L4s:
mov eax,0ffffffffh
jmp L3
L1 :
xorps xmm0, xmm0
mov eax,0
mov pflag,eax
; movss fresult, xmm0
add ebx, 4
dec ecx
jne L2
L3:
pop ebx


}
fresult = fresult * pflag;
cout << fresult << " ";
}//j
cout << "\n";
for (j = 2; j < 20; j++) {
f = (float)j;

_asm {
push ebx
lea ebx, flut
movss xmm0, f
shufps xmm0, xmm0, 0
movups xmm1, [ebx]
movaps xmm3, xmm1
CMPEQPS xmm1, xmm0
pand xmm1, xmm3
movaps xmm7, xmm1
add ebx, 16
movups xmm1, [ebx]
movaps xmm3, xmm1
CMPEQPS xmm1, xmm0
pand xmm1, xmm3
por xmm1, xmm7
movups arr, xmm1
haddps xmm1, xmm1
haddps xmm1, xmm1
movss fresult, xmm1


pop ebx
}
cout << "xmm reg float 0,float 1,float 2,float 3 : "<< arr[0] << " " << arr[1] << " " << arr[2] << " " << arr[3] << "\n";
cout << fresult << " zero = non prime\n";

}//second time j


}




[jack]

where is "pch.h" ?
never mind

[NoCforMe]

I don't see any results, only C code.

[TimoVJL]

I don't see any results, only C code.

C++ code with part of assembler block.
C and C++ aren't same thing.

I don't use C++, as i don't need it, and as it isn't universal at all, as it can't share object files nor libraries.