#define _N_GP
//#define _N_YMM

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h> // uint64_t needed
#include <string.h>

#ifdef _N_YMM
#include <emmintrin.h> // SSE2 intrinsics
#include <smmintrin.h> // SSE4.1 intrinsics
#include <immintrin.h> // AVX intrinsics
#endif

#ifdef _N_YMM
void SlowCopy256bit (const char *SOURCE, char *TARGET) { _mm256_storeu_si256((__m256i *)(TARGET), _mm256_loadu_si256((const __m256i *)(SOURCE))); }
#endif

#ifndef NULL
#ifdef __cplusplus
#define NULL 0
#else
#define NULL ((void*)0)
#endif
#endif

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

	unsigned char* retLOCAL;
	unsigned char* srcLOCAL;
	unsigned int DWORDtrio;
	unsigned int Flag; // This line made my hair white! For some reason it should be 64bit, otherwise it makes 'FlagMASKnegated' 32bit during 'FlagMASKnegated= Flag - 1; // -1|0'
	//uint64_t Flag;
	uint64_t FlagMASK; //=       0xFFFFFFFFFFFFFFFF;
	uint64_t FlagMASKnegated; //=0x0000000000000000;

	srcLOCAL = (unsigned char*)malloc(512);
	retLOCAL = (unsigned char*)malloc((1LL<<32)+512);

if( srcLOCAL == NULL )
{ printf("Needed memory allocation denied!\n"); return(1); }
if( retLOCAL == NULL )
{ printf("Needed memory allocation denied!\n"); return(1); }

		DWORDtrio = *(unsigned int*)srcLOCAL;

		DWORDtrio = DWORDtrio&( 0xFFFFFFFF >> ((3-(DWORDtrio & 0x03))<<3) );
		Flag=!((DWORDtrio & 0x0F)-0x0C);
		// In here Flag=0|1
		FlagMASKnegated= Flag - 1; // -1|0
		FlagMASK= ~FlagMASKnegated;

				#ifdef _N_YMM
		SlowCopy256bit( (const char *)( 1+ ((uint64_t)(srcLOCAL)&FlagMASK) + ((uint64_t)(retLOCAL-(DWORDtrio>>4)-1)&FlagMASKnegated) ), retLOCAL);
				#endif
				#ifdef _N_GP
		memcpy(retLOCAL, (const char *)( 1+ ((uint64_t)(srcLOCAL)&FlagMASK) + ((uint64_t)(retLOCAL-(DWORDtrio>>4)-1)&FlagMASKnegated) ), 16*2);
				#endif

printf("retLOCAL = %p\n", retLOCAL);
printf("((uint64_t)(retLOCAL-(DWORDtrio>>4)-1)&FlagMASKnegated) = %p\n", ((uint64_t)(retLOCAL-(DWORDtrio>>4)-1)&FlagMASKnegated)); //00000001 3F 9C 00 3B
exit(0);
}

// Output when non-workaround is in effect (i.e. 'unsigned int Flag;' is active):
/*
D:\_KAZE\Instructions_per_tick_during_branchless_decompression_32-threaded>icl /O3 losingHigh4bytes.c
Intel(R) C++ Intel(R) 64 Compiler XE for applications running on Intel(R) 64, Version 15.0.0.108 Build 20140726
Copyright (C) 1985-2014 Intel Corporation.  All rights reserved.

losingHigh4bytes.c
Microsoft (R) Incremental Linker Version 10.00.30319.01
Copyright (C) Microsoft Corporation.  All rights reserved.

-out:losingHigh4bytes.exe
losingHigh4bytes.obj

D:\_KAZE\Instructions_per_tick_during_branchless_decompression_32-threaded>losingHigh4bytes.exe
!!! CRASH !!!
D:\_KAZE\Instructions_per_tick_during_branchless_decompression_32-threaded>
*/

// Output when workaround is in effect (i.e. 'uint64_t Flag;' is active):
/*
D:\_KAZE\Instructions_per_tick_during_branchless_decompression_32-threaded>icl /O3 losingHigh4bytes.c
Intel(R) C++ Intel(R) 64 Compiler XE for applications running on Intel(R) 64, Version 15.0.0.108 Build 20140726
Copyright (C) 1985-2014 Intel Corporation.  All rights reserved.

losingHigh4bytes.c
Microsoft (R) Incremental Linker Version 10.00.30319.01
Copyright (C) Microsoft Corporation.  All rights reserved.

-out:losingHigh4bytes.exe
losingHigh4bytes.obj

D:\_KAZE\Instructions_per_tick_during_branchless_decompression_32-threaded>losingHigh4bytes.exe
retLOCAL = 000000013F920040
((uint64_t)(retLOCAL-(DWORDtrio>>4)-1)&FlagMASKnegated) = 000000013F92003B

D:\_KAZE\Instructions_per_tick_during_branchless_decompression_32-threaded>
*/