Ternary operator is twice as slow as an if

I read everywhere that ternary operator is supposed to be faster than, or at least the same as, its equivalent if - else block.

However, I did the following test and found out it's not the case:

Random r = new Random();
int[] array = new int[20000000];
for(int i = 0; i < array.Length; i++)
{
    array[i] = r.Next(int.MinValue, int.MaxValue);
}
Array.Sort(array);

long value = 0;
DateTime begin = DateTime.UtcNow;

foreach (int i in array)
{
    if (i > 0)
    {
        value += 2;
    }
    else
    {
        value += 3;
    }
    // if-else block above takes on average 85 ms

    // OR I can use a ternary operator:
    // value += i > 0 ? 2 : 3; // takes 157 ms
}
DateTime end = DateTime.UtcNow;
MessageBox.Show("Measured time: " + (end-begin).TotalMilliseconds + " ms.rnResult = " + value.ToString());

My computer took 85 ms to run the code above. But if I comment out the if - else chunk, and uncomment the ternary operator line, it will take about 157 ms.

Why is this happening?


To answer this question, we'll examine the assembly code produced by the X86 and X64 JITs for each of these cases.

X86, if/then

    32:                 foreach (int i in array)
0000007c 33 D2                xor         edx,edx 
0000007e 83 7E 04 00          cmp         dword ptr [esi+4],0 
00000082 7E 1C                jle         000000A0 
00000084 8B 44 96 08          mov         eax,dword ptr [esi+edx*4+8] 
    33:                 {
    34:                     if (i > 0)
00000088 85 C0                test        eax,eax 
0000008a 7E 08                jle         00000094 
    35:                     {
    36:                         value += 2;
0000008c 83 C3 02             add         ebx,2 
0000008f 83 D7 00             adc         edi,0 
00000092 EB 06                jmp         0000009A 
    37:                     }
    38:                     else
    39:                     {
    40:                         value += 3;
00000094 83 C3 03             add         ebx,3 
00000097 83 D7 00             adc         edi,0 
0000009a 42                   inc         edx 
    32:                 foreach (int i in array)
0000009b 39 56 04             cmp         dword ptr [esi+4],edx 
0000009e 7F E4                jg          00000084 
    30:             for (int x = 0; x < iterations; x++)
000000a0 41                   inc         ecx 
000000a1 3B 4D F0             cmp         ecx,dword ptr [ebp-10h] 
000000a4 7C D6                jl          0000007C 

X86, ternary

    59:                 foreach (int i in array)
00000075 33 F6                xor         esi,esi 
00000077 83 7F 04 00          cmp         dword ptr [edi+4],0 
0000007b 7E 2D                jle         000000AA 
0000007d 8B 44 B7 08          mov         eax,dword ptr [edi+esi*4+8] 
    60:                 {
    61:                     value += i > 0 ? 2 : 3;
00000081 85 C0                test        eax,eax 
00000083 7F 07                jg          0000008C 
00000085 BA 03 00 00 00       mov         edx,3 
0000008a EB 05                jmp         00000091 
0000008c BA 02 00 00 00       mov         edx,2 
00000091 8B C3                mov         eax,ebx 
00000093 8B 4D EC             mov         ecx,dword ptr [ebp-14h] 
00000096 8B DA                mov         ebx,edx 
00000098 C1 FB 1F             sar         ebx,1Fh 
0000009b 03 C2                add         eax,edx 
0000009d 13 CB                adc         ecx,ebx 
0000009f 89 4D EC             mov         dword ptr [ebp-14h],ecx 
000000a2 8B D8                mov         ebx,eax 
000000a4 46                   inc         esi 
    59:                 foreach (int i in array)
000000a5 39 77 04             cmp         dword ptr [edi+4],esi 
000000a8 7F D3                jg          0000007D 
    57:             for (int x = 0; x < iterations; x++)
000000aa FF 45 E4             inc         dword ptr [ebp-1Ch] 
000000ad 8B 45 E4             mov         eax,dword ptr [ebp-1Ch] 
000000b0 3B 45 F0             cmp         eax,dword ptr [ebp-10h] 
000000b3 7C C0                jl          00000075 

X64, if/then

    32:                 foreach (int i in array)
00000059 4C 8B 4F 08          mov         r9,qword ptr [rdi+8] 
0000005d 0F 1F 00             nop         dword ptr [rax] 
00000060 45 85 C9             test        r9d,r9d 
00000063 7E 2B                jle         0000000000000090 
00000065 33 D2                xor         edx,edx 
00000067 45 33 C0             xor         r8d,r8d 
0000006a 4C 8B 57 08          mov         r10,qword ptr [rdi+8] 
0000006e 66 90                xchg        ax,ax 
00000070 42 8B 44 07 10       mov         eax,dword ptr [rdi+r8+10h] 
    33:                 {
    34:                     if (i > 0)
00000075 85 C0                test        eax,eax 
00000077 7E 07                jle         0000000000000080 
    35:                     {
    36:                         value += 2;
00000079 48 83 C5 02          add         rbp,2 
0000007d EB 05                jmp         0000000000000084 
0000007f 90                   nop 
    37:                     }
    38:                     else
    39:                     {
    40:                         value += 3;
00000080 48 83 C5 03          add         rbp,3 
00000084 FF C2                inc         edx 
00000086 49 83 C0 04          add         r8,4 
    32:                 foreach (int i in array)
0000008a 41 3B D2             cmp         edx,r10d 
0000008d 7C E1                jl          0000000000000070 
0000008f 90                   nop 
    30:             for (int x = 0; x < iterations; x++)
00000090 FF C1                inc         ecx 
00000092 41 3B CC             cmp         ecx,r12d 
00000095 7C C9                jl          0000000000000060 

X64, ternary

    59:                 foreach (int i in array)
00000044 4C 8B 4F 08          mov         r9,qword ptr [rdi+8] 
00000048 45 85 C9             test        r9d,r9d 
0000004b 7E 2F                jle         000000000000007C 
0000004d 45 33 C0             xor         r8d,r8d 
00000050 33 D2                xor         edx,edx 
00000052 4C 8B 57 08          mov         r10,qword ptr [rdi+8] 
00000056 8B 44 17 10          mov         eax,dword ptr [rdi+rdx+10h] 
    60:                 {
    61:                     value += i > 0 ? 2 : 3;
0000005a 85 C0                test        eax,eax 
0000005c 7F 07                jg          0000000000000065 
0000005e B8 03 00 00 00       mov         eax,3 
00000063 EB 05                jmp         000000000000006A 
00000065 B8 02 00 00 00       mov         eax,2 
0000006a 48 63 C0             movsxd      rax,eax 
0000006d 4C 03 E0             add         r12,rax 
00000070 41 FF C0             inc         r8d 
00000073 48 83 C2 04          add         rdx,4 
    59:                 foreach (int i in array)
00000077 45 3B C2             cmp         r8d,r10d 
0000007a 7C DA                jl          0000000000000056 
    57:             for (int x = 0; x < iterations; x++)
0000007c FF C1                inc         ecx 
0000007e 3B CD                cmp         ecx,ebp 
00000080 7C C6                jl          0000000000000048 

First: why is the X86 code so much slower than X64?

This is due to the following characteristics of the code:

  • X64 has several additional registers available, and each register is 64-bits. This allows the X64 JIT to perform the inner loop entirely using registers aside from loading i from the array, while the X86 JIT places several stack operations (memory access) in the loop.
  • value is a 64-bit integer, which requires 2 machine instructions on X86 ( add followed by adc ) but only 1 on X64 ( add ).
  • Second: why is the ternary operator slower on both X86 and X64?

    This is due to a subtle difference in the order of operations impacting the JIT's optimizer. To JIT the ternary operator, rather than directly coding 2 and 3 in the add machine instructions themselves, the JIT creating an intermediate variable (in a register) to hold the result. This register is then sign-extended from 32-bits to 64-bits before adding it to value . Since all of this is performed in registers for X64, despite the significant increase in complexity for the ternary operator the net impact is somewhat minimized.

    The X86 JIT on the other hand is impacted to a greater extent because the addition of a new intermediate value in the inner loop causes it to "spill" another value, resulting in at least 2 additional memory accesses in the inner loop (see the accesses to [ebp-14h] in the X86 ternary code).


    EDIT: All change... see below.

    I can't reproduce your results on the x64 CLR, but I can on x86. On x64 I can see a small difference (less than 10%) between the conditional operator and the if/else, but it's much smaller than you're seeing.

    I've made the following potential changes:

  • Run in a console app
  • Build with /o+ /debug- , and run outside the debugger
  • Run both pieces of code once to JIT them, then lots of times for more accuracy
  • Use Stopwatch
  • Results with /platform:x64 (without the "ignore" lines):

    if/else with 1 iterations: 17ms
    conditional with 1 iterations: 19ms
    if/else with 1000 iterations: 17875ms
    conditional with 1000 iterations: 19089ms
    

    Results with /platform:x86 (without the "ignore" lines):

    if/else with 1 iterations: 18ms
    conditional with 1 iterations: 49ms
    if/else with 1000 iterations: 17901ms
    conditional with 1000 iterations: 47710ms
    

    My system details:

  • x64 i7-2720QM CPU @2.20GHz
  • 64-bit Windows 8
  • .NET 4.5
  • So unlike before, I think you are seeing a real difference - and it's all to do with the x86 JIT. I wouldn't like to say exactly what is causing the difference - I may update the post later on with more details if I can bother to go into cordbg :)

    Interestingly, without sorting the array first, I end up with tests which take about 4.5x as long, at least on x64. My guess is that this is to do with branch prediction.

    Code:

    using System;
    using System.Diagnostics;
    
    class Test
    {
        static void Main()
        {
            Random r = new Random(0);
            int[] array = new int[20000000];
            for(int i = 0; i < array.Length; i++)
            {
                array[i] = r.Next(int.MinValue, int.MaxValue);
            }
            Array.Sort(array);
            // JIT everything...
            RunIfElse(array, 1);
            RunConditional(array, 1);
            // Now really time it
            RunIfElse(array, 1000);
            RunConditional(array, 1000);
        }
    
        static void RunIfElse(int[] array, int iterations)
        {        
            long value = 0;
            Stopwatch sw = Stopwatch.StartNew();
    
            for (int x = 0; x < iterations; x++)
            {
                foreach (int i in array)
                {
                    if (i > 0)
                    {
                        value += 2;
                    }
                    else
                    {
                        value += 3;
                    }
                }
            }
            sw.Stop();
            Console.WriteLine("if/else with {0} iterations: {1}ms",
                              iterations,
                              sw.ElapsedMilliseconds);
            // Just to avoid optimizing everything away
            Console.WriteLine("Value (ignore): {0}", value);
        }
    
        static void RunConditional(int[] array, int iterations)
        {        
            long value = 0;
            Stopwatch sw = Stopwatch.StartNew();
    
            for (int x = 0; x < iterations; x++)
            {
                foreach (int i in array)
                {
                    value += i > 0 ? 2 : 3;
                }
            }
            sw.Stop();
            Console.WriteLine("conditional with {0} iterations: {1}ms",
                              iterations,
                              sw.ElapsedMilliseconds);
            // Just to avoid optimizing everything away
            Console.WriteLine("Value (ignore): {0}", value);
        }
    }
    

    The difference really doesn't have much to do with if/else vs ternary.

    Looking at the jitted disassemblies (I won't repaste here, pls see @280Z28's answer), it turns out you're comparing apples and oranges . In one case, you create two different += operations with constant values and which one you pick depends on a condition, and in the other case, you create a += where the value to add depends on a condition.

    If you want to truly compare if/else vs ternary, this would be a more fair comparison (now both will be equally "slow", or we could even say ternary is a bit faster):

    int diff;
    if (i > 0) 
        diff = 2;
    else 
        diff = 3;
    value += diff;
    

    vs.

    value += i > 0 ? 2 : 3;
    

    Now the disassembly for the if/else becomes as shown below. Note that this is bit worse than the ternary case, since it quit using the registers for the loop variable( i ) as well.

                    if (i > 0)
    0000009d  cmp         dword ptr [ebp-20h],0 
    000000a1  jle         000000AD 
                    {
                        diff = 2;
    000000a3  mov         dword ptr [ebp-24h],2 
    000000aa  nop 
    000000ab  jmp         000000B4 
                    }
                    else
                    {
                        diff = 3;
    000000ad  mov         dword ptr [ebp-24h],3 
                    }
                    value += diff;
    000000b4  mov         eax,dword ptr [ebp-18h] 
    000000b7  mov         edx,dword ptr [ebp-14h] 
    000000ba  mov         ecx,dword ptr [ebp-24h] 
    000000bd  mov         ebx,ecx 
    000000bf  sar         ebx,1Fh 
    000000c2  add         eax,ecx 
    000000c4  adc         edx,ebx 
    000000c6  mov         dword ptr [ebp-18h],eax 
    000000c9  mov         dword ptr [ebp-14h],edx 
    000000cc  inc         dword ptr [ebp-28h] 
    
    链接地址: http://www.djcxy.com/p/5376.html

    上一篇: 好的或不好的做法? 在getter中初始化对象

    下一篇: 三元运算符的速度是if的两倍