Today I have found sample code which slowed down by 50%, after adding some unrelated code. After debugging I have figured out the problem was in the loop alignment. Depending of the loop code placement there is different execution time e.g.:
| Address | Time[us] |
|---|---|
| 00007FF780A01270 | 980us |
| 00007FF7750B1280 | 1500us |
| 00007FF7750B1290 | 986us |
| 00007FF7750B12A0 | 1500us |
I didn't expect previously that code alignment may have such a big impact. And I thought my compiler is smart enough to align the code correctly.
What exactly cause such a big difference in execution time ? (I suppose some processor architecture details).
The test program I have compiled in Release mode with Visual Studio 2019 and run it on Windows 10. I have checked the program on 2 processors: i7-8700k (the results above), and on intel i5-3570k but the problem does not exist there and the execution time is always about 1250us. I have also tried to compile the program with clang, but with clang the result is always ~1500us (on i7-8700k).
My test program:
#include <chrono>
#include <iostream>
#include <intrin.h>
using namespace std;
template<int N>
__forceinline void noops()
{
__nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop(); __nop();
noops<N - 1>();
}
template<>
__forceinline void noops<0>(){}
template<int OFFSET>
__declspec(noinline) void SumHorizontalLine(const unsigned char* __restrict src, int width, int a, unsigned short* __restrict dst)
{
unsigned short sum = 0;
const unsigned char* srcP1 = src - a - 1;
const unsigned char* srcP2 = src + a;
//some dummy loop,just a few iterations
for (int i = 0; i < a; ++i)
dst[i] = src[i] / (double)dst[i];
noops<OFFSET>();
//the important loop
for (int x = a + 1; x < width - a; x++)
{
unsigned char v1 = srcP1[x];
unsigned char v2 = srcP2[x];
sum -= v1;
sum += v2;
dst[x] = sum;
}
}
template<int OFFSET>
void RunTest(unsigned char* __restrict src, int width, int a, unsigned short* __restrict dst)
{
double minTime = 99999999;
for(int i = 0; i < 20; ++i)
{
auto start = chrono::steady_clock::now();
for (int i = 0; i < 1024; ++i)
{
SumHorizontalLine<OFFSET>(src, width, a, dst);
}
auto end = chrono::steady_clock::now();
auto us = chrono::duration_cast<chrono::microseconds>(end - start).count();
if (us < minTime)
{
minTime = us;
}
}
cout << OFFSET << " : " << minTime << " us" << endl;
}
int main()
{
const int width = 2048;
const int x = 3;
unsigned char* src = new unsigned char[width * 5];
unsigned short* dst = new unsigned short[width];
memset(src, 0, sizeof(unsigned char) * width);
memset(dst, 0, sizeof(unsigned short) * width);
while(true)
RunTest<1>(src, width, x, dst);
}
To verify different alignment, just recompile the program and change RunTest<0> to RunTest<1> etc. Compiler always align the code to 16bytes. In my test code I just insert additional nops to move the code a bit more.
Assembly code generated for the loop with OFFSET=1 (for other offset only the amount of npads is different):
0007c 90 npad 1
0007d 90 npad 1
0007e 49 83 c1 08 add r9, 8
00082 90 npad 1
00083 90 npad 1
00084 90 npad 1
00085 90 npad 1
00086 90 npad 1
00087 90 npad 1
00088 90 npad 1
00089 90 npad 1
0008a 90 npad 1
0008b 90 npad 1
0008c 90 npad 1
0008d 90 npad 1
0008e 90 npad 1
0008f 90 npad 1
$LL15@SumHorizon:
; 25 :
; 26 : noops<OFFSET>();
; 27 :
; 28 : for (int x = a + 1; x < width - a; x++)
; 29 : {
; 30 : unsigned char v1 = srcP1[x];
; 31 : unsigned char v2 = srcP2[x];
; 32 : sum -= v1;
00090 0f b6 42 f9 movzx eax, BYTE PTR [rdx-7]
00094 4d 8d 49 02 lea r9, QWORD PTR [r9+2]
; 33 : sum += v2;
00098 0f b6 0a movzx ecx, BYTE PTR [rdx]
0009b 48 8d 52 01 lea rdx, QWORD PTR [rdx+1]
0009f 66 2b c8 sub cx, ax
000a2 66 44 03 c1 add r8w, cx
; 34 : dst[x] = sum;
000a6 66 45 89 41 fe mov WORD PTR [r9-2], r8w
000ab 49 83 ea 01 sub r10, 1
000af 75 df jne SHORT $LL15@SumHorizon
; 35 : }
; 36 :
; 37 : }
000b1 c3 ret 0
??$SumHorizontalLine@$00@@YAXPEIBEHHPEIAG@Z ENDP ; SumHorizont
