Caveat: It is not necessary to put the implementation in the header file, see the alternative solution at the end of this answer.

Anyway, the reason your code is failing is that, when instantiating a template, the compiler creates a new class with the given template argument. For example:

template<typename T>
struct Foo
{
    T bar;
    void doSomething(T param) {/* do stuff using T */}
};

// somewhere in a .cpp
Foo<int> f; 

When reading this line, the compiler will create a new class (let's call it FooInt), which is equivalent to the following:

struct FooInt
{
    int bar;
    void doSomething(int param) {/* do stuff using int */}
}

Consequently, the compiler needs to have access to the implementation of the methods, to instantiate them with the template argument (in this case int). If these implementations were not in the header, they wouldn't be accessible, and therefore the compiler wouldn't be able to instantiate the template.

A common solution to this is to write the template declaration in a header file, then implement the class in an implementation file (for example .tpp), and include this implementation file at the end of the header.

Foo.h

template <typename T>
struct Foo
{
    void doSomething(T param);
};

#include "Foo.tpp"

Foo.tpp

template <typename T>
void Foo<T>::doSomething(T param)
{
    //implementation
}

This way, implementation is still separated from declaration, but is accessible to the compiler.

Alternative solution

Another solution is to keep the implementation separated, and explicitly instantiate all the template instances you'll need:

Foo.h

// no implementation
template <typename T> struct Foo { ... };

Foo.cpp

// implementation of Foo's methods

// explicit instantiations
template class Foo<int>;
template class Foo<float>;
// You will only be able to use Foo with int or float

If my explanation isn't clear enough, you can have a look at the C++ Super-FAQ on this subject.

Culprit: False Data Dependency (and the compiler isn't even aware of it)

On Sandy/Ivy Bridge and Haswell processors, the instruction:

popcnt  src, dest

appears to have a false dependency on the destination register dest. Even though the instruction only writes to it, the instruction will wait until dest is ready before executing. This false dependency is (now) documented by Intel as erratum HSD146 (Haswell) and SKL029 (Skylake)

Skylake fixed this for lzcnt and tzcnt.
Cannon Lake (and Ice Lake) fixed this for popcnt.
bsf/bsr have a true output dependency: output unmodified for input=0. (But no way to take advantage of that with intrinsics - only AMD documents it and compilers don't expose it.)

(Yes, these instructions all run on the same execution unit).

This dependency doesn't just hold up the 4 popcnts from a single loop iteration. It can carry across loop iterations making it impossible for the processor to parallelize different loop iterations.

The unsigned vs. uint64_t and other tweaks don't directly affect the problem. But they influence the register allocator which assigns the registers to the variables.

In your case, the speeds are a direct result of what is stuck to the (false) dependency chain depending on what the register allocator decided to do.

• 13 GB/s has a chain: popcnt-add-popcnt-popcnt → next iteration
• 15 GB/s has a chain: popcnt-add-popcnt-add → next iteration
• 20 GB/s has a chain: popcnt-popcnt → next iteration
• 26 GB/s has a chain: popcnt-popcnt → next iteration

The difference between 20 GB/s and 26 GB/s seems to be a minor artifact of the indirect addressing. Either way, the processor starts to hit other bottlenecks once you reach this speed.

To test this, I used inline assembly to bypass the compiler and get exactly the assembly I want. I also split up the count variable to break all other dependencies that might mess with the benchmarks.

Here are the results:

Sandy Bridge Xeon @ 3.5 GHz: (full test code can be found at the bottom)

• GCC 4.6.3: g++ popcnt.cpp -std=c++0x -O3 -save-temps -march=native
• Ubuntu 12

Different Registers: 18.6195 GB/s

.L4:
    movq    (%rbx,%rax,8), %r8
    movq    8(%rbx,%rax,8), %r9
    movq    16(%rbx,%rax,8), %r10
    movq    24(%rbx,%rax,8), %r11
    addq    $4, %rax

    popcnt %r8, %r8
    add    %r8, %rdx
    popcnt %r9, %r9
    add    %r9, %rcx
    popcnt %r10, %r10
    add    %r10, %rdi
    popcnt %r11, %r11
    add    %r11, %rsi

    cmpq    $131072, %rax
    jne .L4

Same Register: 8.49272 GB/s

.L9:
    movq    (%rbx,%rdx,8), %r9
    movq    8(%rbx,%rdx,8), %r10
    movq    16(%rbx,%rdx,8), %r11
    movq    24(%rbx,%rdx,8), %rbp
    addq    $4, %rdx

    # This time reuse "rax" for all the popcnts.
    popcnt %r9, %rax
    add    %rax, %rcx
    popcnt %r10, %rax
    add    %rax, %rsi
    popcnt %r11, %rax
    add    %rax, %r8
    popcnt %rbp, %rax
    add    %rax, %rdi

    cmpq    $131072, %rdx
    jne .L9

Same Register with broken chain: 17.8869 GB/s

.L14:
    movq    (%rbx,%rdx,8), %r9
    movq    8(%rbx,%rdx,8), %r10
    movq    16(%rbx,%rdx,8), %r11
    movq    24(%rbx,%rdx,8), %rbp
    addq    $4, %rdx

    # Reuse "rax" for all the popcnts.
    xor    %rax, %rax    # Break the cross-iteration dependency by zeroing "rax".
    popcnt %r9, %rax
    add    %rax, %rcx
    popcnt %r10, %rax
    add    %rax, %rsi
    popcnt %r11, %rax
    add    %rax, %r8
    popcnt %rbp, %rax
    add    %rax, %rdi

    cmpq    $131072, %rdx
    jne .L14

So what went wrong with the compiler?

It seems that neither GCC nor Visual Studio are aware that popcnt has such a false dependency. Nevertheless, these false dependencies aren't uncommon. It's just a matter of whether the compiler is aware of it.

popcnt isn't exactly the most used instruction. So it's not really a surprise that a major compiler could miss something like this. There also appears to be no documentation anywhere that mentions this problem. If Intel doesn't disclose it, then nobody outside will know until someone runs into it by chance.

(Update: As of version 4.9.2, GCC is aware of this false-dependency and generates code to compensate it when optimizations are enabled. Major compilers from other vendors, including Clang, MSVC, and even Intel's own ICC are not yet aware of this microarchitectural erratum and will not emit code that compensates for it.)

Why does the CPU have such a false dependency?

We can speculate: it runs on the same execution unit as bsf / bsr which do have an output dependency. (How is POPCNT implemented in hardware?). For those instructions, Intel documents the integer result for input=0 as "undefined" (with ZF=1), but Intel hardware actually gives a stronger guarantee to avoid breaking old software: output unmodified. AMD documents this behaviour.

Presumably it was somehow inconvenient to make some uops for this execution unit dependent on the output but others not.

AMD processors do not appear to have this false dependency.

The full test code is below for reference:

#include <iostream>
#include <chrono>
#include <x86intrin.h>

int main(int argc, char* argv[]) {

   using namespace std;
   uint64_t size=1<<20;

   uint64_t* buffer = new uint64_t[size/8];
   char* charbuffer=reinterpret_cast<char*>(buffer);
   for (unsigned i=0;i<size;++i) charbuffer[i]=rand()%256;

   uint64_t count,duration;
   chrono::time_point<chrono::system_clock> startP,endP;
   {
      uint64_t c0 = 0;
      uint64_t c1 = 0;
      uint64_t c2 = 0;
      uint64_t c3 = 0;
      startP = chrono::system_clock::now();
      for( unsigned k = 0; k < 10000; k++){
         for (uint64_t i=0;i<size/8;i+=4) {
            uint64_t r0 = buffer[i + 0];
            uint64_t r1 = buffer[i + 1];
            uint64_t r2 = buffer[i + 2];
            uint64_t r3 = buffer[i + 3];
            __asm__(
                "popcnt %4, %4  \n\t"
                "add %4, %0     \n\t"
                "popcnt %5, %5  \n\t"
                "add %5, %1     \n\t"
                "popcnt %6, %6  \n\t"
                "add %6, %2     \n\t"
                "popcnt %7, %7  \n\t"
                "add %7, %3     \n\t"
                : "+r" (c0), "+r" (c1), "+r" (c2), "+r" (c3)
                : "r"  (r0), "r"  (r1), "r"  (r2), "r"  (r3)
            );
         }
      }
      count = c0 + c1 + c2 + c3;
      endP = chrono::system_clock::now();
      duration=chrono::duration_cast<std::chrono::nanoseconds>(endP-startP).count();
      cout << "No Chain\t" << count << '\t' << (duration/1.0E9) << " sec \t"
            << (10000.0*size)/(duration) << " GB/s" << endl;
   }
   {
      uint64_t c0 = 0;
      uint64_t c1 = 0;
      uint64_t c2 = 0;
      uint64_t c3 = 0;
      startP = chrono::system_clock::now();
      for( unsigned k = 0; k < 10000; k++){
         for (uint64_t i=0;i<size/8;i+=4) {
            uint64_t r0 = buffer[i + 0];
            uint64_t r1 = buffer[i + 1];
            uint64_t r2 = buffer[i + 2];
            uint64_t r3 = buffer[i + 3];
            __asm__(
                "popcnt %4, %%rax   \n\t"
                "add %%rax, %0      \n\t"
                "popcnt %5, %%rax   \n\t"
                "add %%rax, %1      \n\t"
                "popcnt %6, %%rax   \n\t"
                "add %%rax, %2      \n\t"
                "popcnt %7, %%rax   \n\t"
                "add %%rax, %3      \n\t"
                : "+r" (c0), "+r" (c1), "+r" (c2), "+r" (c3)
                : "r"  (r0), "r"  (r1), "r"  (r2), "r"  (r3)
                : "rax"
            );
         }
      }
      count = c0 + c1 + c2 + c3;
      endP = chrono::system_clock::now();
      duration=chrono::duration_cast<std::chrono::nanoseconds>(endP-startP).count();
      cout << "Chain 4   \t"  << count << '\t' << (duration/1.0E9) << " sec \t"
            << (10000.0*size)/(duration) << " GB/s" << endl;
   }
   {
      uint64_t c0 = 0;
      uint64_t c1 = 0;
      uint64_t c2 = 0;
      uint64_t c3 = 0;
      startP = chrono::system_clock::now();
      for( unsigned k = 0; k < 10000; k++){
         for (uint64_t i=0;i<size/8;i+=4) {
            uint64_t r0 = buffer[i + 0];
            uint64_t r1 = buffer[i + 1];
            uint64_t r2 = buffer[i + 2];
            uint64_t r3 = buffer[i + 3];
            __asm__(
                "xor %%rax, %%rax   \n\t"   // <--- Break the chain.
                "popcnt %4, %%rax   \n\t"
                "add %%rax, %0      \n\t"
                "popcnt %5, %%rax   \n\t"
                "add %%rax, %1      \n\t"
                "popcnt %6, %%rax   \n\t"
                "add %%rax, %2      \n\t"
                "popcnt %7, %%rax   \n\t"
                "add %%rax, %3      \n\t"
                : "+r" (c0), "+r" (c1), "+r" (c2), "+r" (c3)
                : "r"  (r0), "r"  (r1), "r"  (r2), "r"  (r3)
                : "rax"
            );
         }
      }
      count = c0 + c1 + c2 + c3;
      endP = chrono::system_clock::now();
      duration=chrono::duration_cast<std::chrono::nanoseconds>(endP-startP).count();
      cout << "Broken Chain\t"  << count << '\t' << (duration/1.0E9) << " sec \t"
            << (10000.0*size)/(duration) << " GB/s" << endl;
   }

   free(charbuffer);
}

An equally interesting benchmark can be found here: http://pastebin.com/kbzgL8si
This benchmark varies the number of popcnts that are in the (false) dependency chain.

False Chain 0:  41959360000 0.57748 sec     18.1578 GB/s
False Chain 1:  41959360000 0.585398 sec    17.9122 GB/s
False Chain 2:  41959360000 0.645483 sec    16.2448 GB/s
False Chain 3:  41959360000 0.929718 sec    11.2784 GB/s
False Chain 4:  41959360000 1.23572 sec     8.48557 GB/s