Dispatching SIMD instructions + SIMDPP + qmake

Question

I'm developing a QT widget that makes use of SIMD instruction sets. I've compiled 3 versions: SSE3, AVX, and AVX2(simdpp allows to switch between them by a single #define).

Now, what I want is for my widget to switch automatically between these implementations, according to best supported instruction set. Guide that is provided with simdpp makes use of some makefile magic:

CXXFLAGS=""

test: main.o test_sse2.o test_sse3.o test_sse4_1.o test_null.o
    g++ $^ -o test

main.o: main.cc
    g++ main.cc $(CXXFLAGS) -c -o main.o

test_null.o: test.cc
    g++ test.cc -c $(CXXFLAGS) -DSIMDPP_EMIT_DISPATCHER \
        -DSIMDPP_DISPATCH_ARCH1=SIMDPP_ARCH_X86_SSE2 \
        -DSIMDPP_DISPATCH_ARCH2=SIMDPP_ARCH_X86_SSE3 \
        -DSIMDPP_DISPATCH_ARCH3=SIMDPP_ARCH_X86_SSE4_1 -o test_null.o

test_sse2.o: test.cc
    g++ test.cc -c $(CXXFLAGS) -DSIMDPP_ARCH_X86_SSE2 -msse2 -o test_sse2.o

test_sse3.o: test.cc
    g++ test.cc -c $(CXXFLAGS) -DSIMDPP_ARCH_X86_SSE3 -msse3 -o test_sse3.o

test_sse4_1.o: test.cc
    g++ test.cc -c $(CXXFLAGS) -DSIMDPP_ARCH_X86_SSE4_1 -msse4.1 -o test_sse4_1.o

Here is a link to the guide: http://p12tic.github.io/libsimdpp/v2.0~rc2/libsimdpp/arch/dispatch.html

I have no idea how to implement such behavior with qmake. Any ideas?

First that comes to mind is to create a shared library with dispatched code, and link it to the project. Here I'm stuck again. App is cross-platform, which means it has to compile with both GCC and MSVC(vc120, to be exact), which forces using nmake in Windows, and I tried, really, but it was like the worst experience in my whole programmer life.

Thanks in advance, programmers of the world!

Answer 1

sorry if this is a bit late. Hope I can still help.

You need to consider 2 areas: Compile time and run time.

Compile time - need to create code to support different features. Run time - need to create code to decide which features you can run.

What you are wanting to do is create a dispatcher...

FuncImpl.h:

#pragma once
void execAvx2();
void execAvx();
void execSse();
void execDefault();

FuncImpl.cpp:

// Compile this file once for each variant with different compiler settings.
#if defined(__AVX2__)
void execAvx2()
{
 // AVX2 impl
...
}

#elif defined (__AVX__)

void execAvx()
{
// AVX impl
...
}

#elif defined (__SSE4_2__)

void execSse()
{
 // Sse impl
...
}

#else

void execDefault()
{
 // Vanilla impl
...
}

#endif

DispatchFunc.cpp

#include "FuncImpl.h"

// Decide at runtime which code to run
void dispatchFunc()
{
     if(CheckCpuAvx2Flag())
     {
         execAvx2();
     } 
     else if(CheckCpuAvxFlag())
     {
         execAvx();
     }
     else if(CheckCpuSseFlags())
     {
         execSse();
     }
     else
     {
         execDefault();
     }
}

What you can do is create a set of QMAKE_EXTRA_COMPILERS.

SampleCompiler.pri (Do this for each variant):

MyCompiler.name = MyCompiler         # Name
MyCompiler.input = MY_SOURCES        # Symbol of the source list to compile
MyCompiler.dependency_type = TYPE_C
MyCompiler.variable_out = OBJECTS
# EXTRA_CXXFLAGS = -mavx / -mavx2 / -msse4.2
# _var = creates FileName_var.o => replace with own variant (_sse, etc)  
MyCompiler.output = ${QMAKE_VAR_OBJECTS_DIR}${QMAKE_FILE_IN_BASE}_var$${first(QMAKE_EXT_OBJ)}
MyCompiler.commands = $${QMAKE_CXX} $(CXXFLAGS) $${EXTRA_CXXFLAGS} $(INCPATH) -c ${QMAKE_FILE_IN} -o${QMAKE_FILE_OUT}
QMAKE_EXTRA_COMPILERS += MyCompiler   # Add my compiler

MyProject.pro

...
include(SseCompiler.pri)
include(AvxCompiler.pri)
include(Avx2Compiler.pri)
..

# Normal sources
# Will create FuncImpl.o and DispatchFunc.o
SOURCES += FuncImpl.cpp \
           DispatchFunc.cpp

# Give the other compilers their sources
# Will create FuncImpl_avx2.o FuncImpl_avx.o FuncImpl_sse.o
AVX2_SOURCES += FuncImpl.cpp
AVX_SOURCES += FuncImpl.cpp
SSE_SOURCES += FuncImpl.cpp

# Link all objects
...

All you need now is to call dispatchFunc()!

Checking cpu flags is another exercise for you: cpuid