Confronta il testo

Trova la differenza tra due file di testo

Editor live

Comprimi invariate

Senza a capo

Layout

Livello di dettaglio

Evidenziazione sintassi

Diffchecker Desktop Il modo più sicuro per usare Diffchecker. Ottieni l'app Diffchecker Desktop: i tuoi diff non lasciano mai il tuo computer!Ottieni Desktop

Untitled diff

Creato 10 anni faIl diff non scade mai

23 rimozioni

Linee
Totale
Rimosso

Caratteri
Totale
Rimosso

Per continuare a utilizzare questa funzione, aggiorna a Diffchecker Pro Visualizza prezzi

110 linee

71 aggiunte

Linee
Totale
Aggiunto

Caratteri
Totale
Aggiunto

Per continuare a utilizzare questa funzione, aggiorna a Diffchecker Pro Visualizza prezzi

135 linee

// WARRANTY DISCLAIMER

// THESE MATERIALS ARE PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS

// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT

// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR

// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL OR ITS

// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,

// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,

// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR

// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY

// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY OR TORT (INCLUDING

// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THESE

// MATERIALS, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

// Intel Corporation is the author of the Materials, and requests that all

// problem reports or change requests be submitted to it directly

// https://software.intel.com/en-us/articles/bitonic-sorting

// Modified to sort int2 key-value array

__kernel void /*__attribute__((vec_type_hint(int4)))*/ BitonicSort(__global int4 * theArray,

__kernel void BitonicSort(__global int8* theArray,

const uint stage,

const uint passOfStage,

const uint dir)

{

size_t i = get_global_id(0);

int4 srcLeft, srcRight, mask;

int8 srcLeft, srcRight, mask;

int4 pseudomask;

int4 imask10 = (int4)(0, 0, -1, -1);

int4 imask11 = (int4)(0, -1, 0, -1);

if(stage > 0)

{

if(passOfStage > 0) // upper level pass, exchange between two fours, operating on half size

if(passOfStage > 0) // upper level pass, exchange between two fours,

{

size_t r = 1 << (passOfStage - 1);

size_t lmask = r - 1;

size_t left = ((i>>(passOfStage-1)) << passOfStage) + (i & lmask);

size_t right = left + r;

srcLeft = theArray[left];

srcRight = theArray[right];

mask = srcLeft < srcRight;

pseudomask = srcLeft.even < srcRight.even;

mask = pseudomask.xxyyzzww;

int4 imin = (srcLeft & mask) | (srcRight & ~mask);

int8 imin = (srcLeft & mask) | (srcRight & ~mask);

int4 imax = (srcLeft & ~mask) | (srcRight & mask);

int8 imax = (srcLeft & ~mask) | (srcRight & mask);

if( ((i>>(stage-1)) & 1) ^ dir )

{

theArray[left] = imin;

theArray[right] = imax;

}

else

{

theArray[right] = imin;

theArray[left] = imax;

}

else // last pass, sort inside one four, operating on full size

else // last pass, sort inside one four

{

srcLeft = theArray[i];

srcRight = srcLeft.zwxy;

srcRight = srcLeft.s45670123;

mask = (srcLeft < srcRight) ^ imask10;

pseudomask = (srcLeft.even < srcRight.even) ^ imask10;

mask = pseudomask.xxyyzzww;

if(((i >> stage) & 1) ^ dir)

{

srcLeft = (srcLeft & mask) | (srcRight & ~mask);

srcRight = srcLeft.yxwz;

mask = (srcLeft < srcRight) ^ imask11;

srcRight = srcLeft.s23016745;

pseudomask = (srcLeft.even < srcRight.even) ^ imask11;

mask = pseudomask.xxyyzzww;

theArray[i] = (srcLeft & mask) | (srcRight & ~mask);

}

else

{

srcLeft = (srcLeft & ~mask) | (srcRight & mask);

srcRight = srcLeft.yxwz;

mask = (srcLeft < srcRight) ^ imask11;

srcRight = srcLeft.s23016745;

pseudomask = (srcLeft.even < srcRight.even) ^ imask11;

mask = pseudomask.xxyyzzww;

theArray[i] = (srcLeft & ~mask) | (srcRight & mask);

}

else // first stage, sort inside one four

{

int4 imask0 = (int4)(0, -1, -1, 0);

srcLeft = theArray[i];

srcRight = srcLeft.yxwz;

srcRight = srcLeft.s23016745;

mask = (srcLeft < srcRight) ^ imask0;

pseudomask = (srcLeft.even < srcRight.even) ^ imask0;

mask = pseudomask.xxyyzzww;

if( dir )

srcLeft = (srcLeft & mask) | (srcRight & ~mask);

else

srcLeft = (srcLeft & ~mask) | (srcRight & mask);

srcRight = srcLeft.zwxy;

mask = (srcLeft < srcRight) ^ imask10;

srcRight = srcLeft.s45670123;

pseudomask = (srcLeft.even < srcRight.even) ^ imask10;

mask = pseudomask.xxyyzzww;

if((i & 1) ^ dir)

{

srcLeft = (srcLeft & mask) | (srcRight & ~mask);

srcRight = srcLeft.yxwz;

mask = (srcLeft < srcRight) ^ imask11;

srcRight = srcLeft.s23016745;

pseudomask = (srcLeft.even < srcRight.even) ^ imask11;

mask = pseudomask.xxyyzzww;

theArray[i] = (srcLeft & mask) | (srcRight & ~mask);

}

else

{

srcLeft = (srcLeft & ~mask) | (srcRight & mask);

srcRight = srcLeft.yxwz;

mask = (srcLeft < srcRight) ^ imask11;

srcRight = srcLeft.s23016745;

pseudomask = (srcLeft.even < srcRight.even) ^ imask11;

mask = pseudomask.xxyyzzww;

theArray[i] = (srcLeft & ~mask) | (srcRight & mask);

}

Diff salvati

Testo originale

Apri file

// Copyright (c) 2009-2011 Intel Corporation
// All rights reserved.
//
// WARRANTY DISCLAIMER
//
// THESE MATERIALS ARE PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL OR ITS
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY OR TORT (INCLUDING
// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THESE
// MATERIALS, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Intel Corporation is the author of the Materials, and requests that all
// problem reports or change requests be submitted to it directly

__kernel void /*__attribute__((vec_type_hint(int4)))*/ BitonicSort(__global int4 * theArray,
                         const uint stage,
                         const uint passOfStage,
                         const uint dir)
{
    size_t i = get_global_id(0);
    int4 srcLeft, srcRight, mask;
    int4 imask10 = (int4)(0,  0, -1, -1);
    int4 imask11 = (int4)(0, -1,  0, -1);

if(stage > 0)
    {
        if(passOfStage > 0)    // upper level pass, exchange between two fours,    operating on half size
        {
            size_t r = 1 << (passOfStage - 1);
            size_t lmask = r - 1;
            size_t left = ((i>>(passOfStage-1)) << passOfStage) + (i & lmask);
            size_t right = left + r;

srcLeft = theArray[left];
            srcRight = theArray[right];
            mask = srcLeft < srcRight;

int4 imin = (srcLeft & mask) | (srcRight & ~mask);
            int4 imax = (srcLeft & ~mask) | (srcRight & mask);

if( ((i>>(stage-1)) & 1) ^ dir )
            {
                theArray[left]  = imin;
                theArray[right] = imax;
            }
            else
            {
                theArray[right] = imin;
                theArray[left]  = imax;
            }
        }
        else    // last pass, sort inside one four,   operating on full size
        {
            srcLeft = theArray[i];
            srcRight = srcLeft.zwxy;
            mask = (srcLeft < srcRight) ^ imask10;

if(((i >> stage) & 1) ^ dir)
            {
                srcLeft = (srcLeft & mask) | (srcRight & ~mask);
                srcRight = srcLeft.yxwz;
                mask = (srcLeft < srcRight) ^ imask11;
                theArray[i] = (srcLeft & mask) | (srcRight & ~mask);
            }
            else
            {
                srcLeft = (srcLeft & ~mask) | (srcRight & mask);
                srcRight = srcLeft.yxwz;
                mask = (srcLeft < srcRight) ^ imask11;
                theArray[i] = (srcLeft & ~mask) | (srcRight & mask);
            }
        }
    }
    else    // first stage, sort inside one four
    {
        int4 imask0 = (int4)(0, -1, -1,  0);
        srcLeft = theArray[i];
        srcRight = srcLeft.yxwz;
        mask = (srcLeft < srcRight) ^ imask0;
        if( dir )
            srcLeft = (srcLeft & mask) | (srcRight & ~mask);
        else
            srcLeft = (srcLeft & ~mask) | (srcRight & mask);

srcRight = srcLeft.zwxy;
        mask = (srcLeft < srcRight) ^ imask10;

if((i & 1) ^ dir)
        {
            srcLeft = (srcLeft & mask) | (srcRight & ~mask);
            srcRight = srcLeft.yxwz;
            mask = (srcLeft < srcRight) ^ imask11;
            theArray[i] = (srcLeft & mask) | (srcRight & ~mask);
        }
        else
        {
            srcLeft = (srcLeft & ~mask) | (srcRight & mask);
            srcRight = srcLeft.yxwz;
            mask = (srcLeft < srcRight) ^ imask11;
            theArray[i] = (srcLeft & ~mask) | (srcRight & mask);
        }
    }
}

Testo modificato

Apri file

// https://software.intel.com/en-us/articles/bitonic-sorting
// Modified to sort int2 key-value array

__kernel void BitonicSort(__global int8* theArray,
                         const uint stage,
                         const uint passOfStage,
                         const uint dir)
{
    size_t i = get_global_id(0);
    int8 srcLeft, srcRight, mask;
    int4 pseudomask;
    int4 imask10 = (int4)(0,  0, -1, -1);
    int4 imask11 = (int4)(0, -1,  0, -1);

if(stage > 0)
    {
        if(passOfStage > 0)    // upper level pass, exchange between two fours,
        {
            size_t r = 1 << (passOfStage - 1);
            size_t lmask = r - 1;
            size_t left = ((i>>(passOfStage-1)) << passOfStage) + (i & lmask);
            size_t right = left + r;

srcLeft = theArray[left];
            srcRight = theArray[right];
            pseudomask = srcLeft.even < srcRight.even;
            mask = pseudomask.xxyyzzww;

int8 imin = (srcLeft & mask) | (srcRight & ~mask);
            int8 imax = (srcLeft & ~mask) | (srcRight & mask);

if( ((i>>(stage-1)) & 1) ^ dir )
            {
                theArray[left]  = imin;
                theArray[right] = imax;
            }
            else
            {
                theArray[right] = imin;
                theArray[left]  = imax;
            }
        }
        else    // last pass, sort inside one four
        {
            srcLeft = theArray[i];
            srcRight = srcLeft.s45670123;
            pseudomask = (srcLeft.even < srcRight.even) ^ imask10;
            mask = pseudomask.xxyyzzww;

if(((i >> stage) & 1) ^ dir)
            {
                srcLeft = (srcLeft & mask) | (srcRight & ~mask);

srcRight = srcLeft.s23016745;
                pseudomask = (srcLeft.even < srcRight.even) ^ imask11;
                mask = pseudomask.xxyyzzww;

theArray[i] = (srcLeft & mask) | (srcRight & ~mask);
            }
            else
            {
                srcLeft = (srcLeft & ~mask) | (srcRight & mask);

srcRight = srcLeft.s23016745;
                pseudomask = (srcLeft.even < srcRight.even) ^ imask11;
                mask = pseudomask.xxyyzzww;

theArray[i] = (srcLeft & ~mask) | (srcRight & mask);
            }
        }
    }
    else    // first stage, sort inside one four
    {
        int4 imask0 = (int4)(0, -1, -1,  0);
        srcLeft = theArray[i];
        srcRight = srcLeft.s23016745;

pseudomask = (srcLeft.even < srcRight.even) ^ imask0;
        mask = pseudomask.xxyyzzww;

if( dir )
            srcLeft = (srcLeft & mask) | (srcRight & ~mask);
        else
            srcLeft = (srcLeft & ~mask) | (srcRight & mask);

srcRight = srcLeft.s45670123;

pseudomask = (srcLeft.even < srcRight.even) ^ imask10;
        mask = pseudomask.xxyyzzww;

if((i & 1) ^ dir)
        {

srcLeft = (srcLeft & mask) | (srcRight & ~mask);

srcRight = srcLeft.s23016745;
            pseudomask = (srcLeft.even < srcRight.even) ^ imask11;
            mask = pseudomask.xxyyzzww;

theArray[i] = (srcLeft & mask) | (srcRight & ~mask);
        }
        else
        {
            srcLeft = (srcLeft & ~mask) | (srcRight & mask);

srcRight = srcLeft.s23016745;
            pseudomask = (srcLeft.even < srcRight.even) ^ imask11;
            mask = pseudomask.xxyyzzww;

theArray[i] = (srcLeft & ~mask) | (srcRight & mask);
        }
    }
}