Coder Perfect

Is it true that a ternary operator is twice as fast as an if-else block?

Problem

According to what I’ve read, the ternary operator is faster than, or at least equivalent to, the if-else block.

However, I conducted the following investigation and discovered that this is 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.\r\nResult = " + value.ToString());

The code above took 85 milliseconds to run on my PC. It will take roughly 157 milliseconds if I comment out the if-else block and uncomment the ternary operator line.

What’s up with this?

Asked by WSBT

Solution #1

To get an explanation, we’ll look at the assembly code generated by the X86 and X64 JITs in each of these scenarios.

    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 
    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 
    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 
    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 and foremost, why is the X86 code so much slower than the X64 code?

This is because of the code’s features:

Second, on both X86 and X64, why is the ternary operator slower?

This is because the JIT’s optimizer is affected by a minor variation in the order of operations. Rather than explicitly coding 2 and 3 in the add machine instructions, the JIT creates an intermediary variable (in a register) to hold the result to JIT the ternary operator. Before being added to value, this register is sign-extended from 32 to 64 bits. Despite the large increase in complexity for the ternary operator, the net impact is slightly lessened because everything is done in registers for X64.

The X86 JIT, on the other hand, is more impacted because adding a new intermediate value in the inner loop leads it to “spill” another value, resulting in at least two extra memory accesses in the inner loop (see the accesses to [ebp-14h] in the X86 ternary code).

Answered by Sam Harwell

Solution #2

EDIT: Everything has changed… check the section below for further information.

On the x64 CLR, I can’t duplicate your results, but on the x86 CLR, I can. I can observe a minor difference between the conditional operator and the if/else on x64 (less than 10%), but it’s far smaller than you’re seeing.

The following possible modifications have been made:

The following are the results of using /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

The following are the results of using /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:

So, unlike before, I believe you are noticing a significant difference, and it is entirely due to the x86 JIT. I’m not going to explain what’s causing the difference; if I can get into cordbg, I’ll update the post with further information later.

Surprisingly, if I run the tests without first sorting the array, they take around 4.5 times as long, at least on x64. This, I believe, has something 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);
    }
}

Answered by Jon Skeet

Solution #3

The difference between if/else and ternary has little to do with it.

Looking at the jittered disassemblies (which I won’t repeat here; instead, see @280Z28’s response), it appears that you’re comparing apples to oranges. In one case, you create two alternative += operations with constant values, and which one you choose is determined by a condition; in the other case, you create a += where the value to add is determined by a condition.

If you really want to compare if/else and ternary, this is a better comparison (now both are “slow,” or we could even argue ternary is a little faster):

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

vs.

value += i > 0 ? 2 : 3;

The disassembly for the if/else now looks like this. This is a little worse than the ternary case, because it also stops using the registers for the loop variable(i).

                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] 

Answered by Eren Ersönmez

Solution #4

Edit:

A new example was added that uses the if-else statement rather than the conditional operator.

Please read [Which is faster?] on Mr. Lippert’s blog before answering. And I believe Mr. Ersönmez’s response is the most accurate.

I’m trying to emphasize something important to remember when using a high-level programming language.

To begin with, I’ve never heard that the conditional operator or the if-else statement in C are supposed to be faster or perform as well.

The explanation for this is simple: what if the if-else statement doesn’t have any operations:

if (i > 0)
{
    value += 2;
}
else
{
}

The conditional operator necessitates the presence of a value on either side, and in C, both sides of: must be of the same type. This just distinguishes it from the if-else sentence. As a result, your query becomes a question about how the machine code instruction is created, resulting in the performance disparity.

In terms of semantics, the conditional operator is:

There is a value for any expression that is evaluated.

However, using an if-else statement:

If the expression is true, do something; if it isn’t, do something else.

With an if-else expression, a value isn’t always required. Only optimization allows you to make your assumption.

Another example to explain the distinction between them is as follows:

var array1=new[] { 1, 2, 3 };
var array2=new[] { 5, 6, 7 };

if(i>0)
    array1[1]=4;
else
    array2[2]=4;

However, if you replace the if-else line with the conditional operator, the code will not compile:

var array1=new[] { 1, 2, 3 };
var array2=new[] { 5, 6, 7 };
(i>0?array1[1]:array2[2])=4; // incorrect usage 

When doing the same thing, the conditional operator and the if-else statements are conceptually the same; however, the conditional operator in C may be faster because C is closer to the platform assembly.

The conditional operator is used in a foreach-loop in the original code you gave, which makes it difficult to see the difference between them. As a result, I propose the following code:

public static class TestClass {
    public static void TestConditionalOperator(int i) {
        long value=0;
        value+=i>0?2:3;
    }

    public static void TestIfElse(int i) {
        long value=0;

        if(i>0) {
            value+=2;
        }
        else {
            value+=3;
        }
    }

    public static void TestMethod() {
        TestConditionalOperator(0);
        TestIfElse(0);
    }
}

The optimized and non-optimized versions of the IL are shown below. I’m using an image to demonstrate them because they’re long: The right hand side is the optimized one:

The IL of the conditional operator appears to be shorter in both versions of the code than the if-else statement, and there is still some question about the machine code generated. The directions for both methods are as follows, with the former image being non-optimized and the latter being optimized:

The code in the latter is only performed if i=0, whereas the code in the former is only executed when i>0. The if-else statement is shorter in both versions of the instructions.

It’s worth noting that the [CPI] isn’t always the same for different instructions. More instructions, therefore, cost a longer cycle for the same instruction. However, when instruction fetching time and pipe/cache time are included in, the real total execution time is dependent on the processor. The processor is also capable of foreseeing the branching.

Because modern CPUs have many cores, things can become more complicated. If you use Intel processors, [Intel® 64 and IA-32 Architectures Optimization Reference Manual] may be of interest to you.

I’m not sure if there was a hardware-implemented CLR, but if there was, the conditional operator is definitely faster because the IL is plainly lower.

Note that all of the machine code is written in x86.

Answered by Ken Kin

Solution #5

I did what Jon Skeet did and ran through 1 iteration and 1,000 iterations and received a different result from both OP and Jon. The ternary is slightly faster in my case. Below is the exact code:

static void runIfElse(int[] array, int iterations)
    {
        long value = 0;
        Stopwatch ifElse = new Stopwatch();
        ifElse.Start();
        for (int c = 0; c < iterations; c++)
        {
            foreach (int i in array)
            {
                if (i > 0)
                {
                    value += 2;
                }
                else
                {
                    value += 3;
                }
            }
        }
        ifElse.Stop();
        Console.WriteLine(String.Format("Elapsed time for If-Else: {0}", ifElse.Elapsed));
    }

    static void runTernary(int[] array, int iterations)
    {
        long value = 0;
        Stopwatch ternary = new Stopwatch();
        ternary.Start();
        for (int c = 0; c < iterations; c++)
        {
            foreach (int i in array)
            {
                value += i > 0 ? 2 : 3;
            }
        }
        ternary.Stop();


        Console.WriteLine(String.Format("Elapsed time for Ternary: {0}", ternary.Elapsed));
    }

    static void Main(string[] args)
    {
        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;

        runIfElse(array, 1);
        runTernary(array, 1);
        runIfElse(array, 1000);
        runTernary(array, 1000);

        Console.ReadLine();
    }

My program’s result is as follows:

In milliseconds, another run:

I ran this without debugging in 64-bit XP.

Edit – x86 compatibility:

Using x86 makes a significant difference. This was done without debugging on the identical xp 64-bit computer as was used previously, but constructed for x86 CPUs. This appears to be the same as the OP’s.

Answered by Shaz

Post is based on https://stackoverflow.com/questions/17328641/ternary-operator-is-twice-as-slow-as-an-if-else-block