How to make parallelizing loops and vectorization work at the same time?

How to make parallelizing loops and vectorization work at the same time?

[Hanke Zhang]

Hi I'm trying to accelerate my program with -ftree-vectorize and
-ftree-parallelize-loops.

Here are my test results using the different options (based on
gcc10.3.0 on i9-12900KF):
gcc-10 test.c -O3 -flto
> time: 29000 ms
gcc-10 test.c -O3 -flto -mavx2 -ftree-vectorize
> time: 17000 ms
gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24
> time: 5000 ms
gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24 -mavx2 -ftree-vectorize
> time: 5000 ms

I found that these two options do not work at the same time, that is,
if I use the `-ftree-vectorize` option alone, it can bring a big
efficiency gain compared to doing nothing; At the same time, if I use
the option of `-ftree-parallelize-loops` alone, it will also bring a
big efficiency gain. But if I use both options, vectorization fails,
that is, I can't get the benefits of vectorization, I can only get the
benefits of parallelizing loops.

I know that the reason may be that after parallelizing the loop,
vectorization cannot be performed, but is there any way I can reap the
benefits of both optimizations?

Here is my example program, adapted from the 462.libquantum in speccpu2006:

```
#include <stdio.h>
#include <stdlib.h>
#include <time.h>

#define MAX_UNSIGNED unsigned long long

struct quantum_reg_node_struct {
    float _Complex *amplitude; /* alpha_j */
    MAX_UNSIGNED *state;       /* j */
};

typedef struct quantum_reg_node_struct quantum_reg_node;

struct quantum_reg_struct {
    int width; /* number of qubits in the qureg */
    int size;  /* number of non-zero vectors */
    int hashw; /* width of the hash array */
    quantum_reg_node *node;
    int *hash;
};

typedef struct quantum_reg_struct quantum_reg;

void quantum_toffoli(int control1, int control2, int target, quantum_reg *reg) {
    for (int i = 0; i < reg->size; i++) {
        if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control1)) {
            if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control2))  {
                reg->node->state[i] ^= ((MAX_UNSIGNED)1 << target);
            }
        }
    }
}

int get_random() {
    return rand() % 64;
}

void init(quantum_reg *reg) {
    reg->size = 2097152;
    for (int i = 0; i < reg->size; i++)  {
        reg->node = (quantum_reg_node *)malloc(sizeof(quantum_reg_node));
        reg->node->state = (MAX_UNSIGNED *)malloc(sizeof(MAX_UNSIGNED)
* reg->size);
        reg->node->amplitude = (float _Complex *)malloc(sizeof(float
_Complex) * reg->size);
        if (i >= 1) break;
    }
    for (int i = 0; i < reg->size; i++)  {
        reg->node->amplitude[i] = 0;
        reg->node->state[i] = 0;
    }
}

int main() {
    quantum_reg reg;
    init(&reg);
    for (int i = 0; i < 65000; i++) {
        quantum_toffoli(get_random(), get_random(), get_random(), &reg);
    }
}
```

Thanks so much.

Re: How to make parallelizing loops and vectorization work at the same time?

[Richard Biener]

On Fri, Sep 15, 2023 at 1:21 PM Hanke Zhang via Gcc <gcc@gcc.gnu.org> wrote:
>
> Hi I'm trying to accelerate my program with -ftree-vectorize and
> -ftree-parallelize-loops.
>
> Here are my test results using the different options (based on
> gcc10.3.0 on i9-12900KF):
> gcc-10 test.c -O3 -flto
> > time: 29000 ms
> gcc-10 test.c -O3 -flto -mavx2 -ftree-vectorize
> > time: 17000 ms
> gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24
> > time: 5000 ms
> gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24 -mavx2 -ftree-vectorize
> > time: 5000 ms
>

First of all -O3 already enables -ftree-vectorize, adding -mavx2 is what brings
the first gain.  So adding -ftree-vectorize to the last command-line is not
expected to change anything.  Instead you can use -fno-tree-vectorize on
the second last one.  Doing that I get 111s vs 41s thus doing both helps.

Note parallelization hasn't seen any development in the last years.

Richard.

> I found that these two options do not work at the same time, that is,
> if I use the `-ftree-vectorize` option alone, it can bring a big
> efficiency gain compared to doing nothing; At the same time, if I use
> the option of `-ftree-parallelize-loops` alone, it will also bring a
> big efficiency gain. But if I use both options, vectorization fails,
> that is, I can't get the benefits of vectorization, I can only get the
> benefits of parallelizing loops.
>
> I know that the reason may be that after parallelizing the loop,
> vectorization cannot be performed, but is there any way I can reap the
> benefits of both optimizations?
>
> Here is my example program, adapted from the 462.libquantum in speccpu2006:
>
> ```
> #include <stdio.h>
> #include <stdlib.h>
> #include <time.h>
>
> #define MAX_UNSIGNED unsigned long long
>
> struct quantum_reg_node_struct {
>     float _Complex *amplitude; /* alpha_j */
>     MAX_UNSIGNED *state;       /* j */
> };
>
> typedef struct quantum_reg_node_struct quantum_reg_node;
>
> struct quantum_reg_struct {
>     int width; /* number of qubits in the qureg */
>     int size;  /* number of non-zero vectors */
>     int hashw; /* width of the hash array */
>     quantum_reg_node *node;
>     int *hash;
> };
>
> typedef struct quantum_reg_struct quantum_reg;
>
> void quantum_toffoli(int control1, int control2, int target, quantum_reg *reg) {
>     for (int i = 0; i < reg->size; i++) {
>         if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control1)) {
>             if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control2))  {
>                 reg->node->state[i] ^= ((MAX_UNSIGNED)1 << target);
>             }
>         }
>     }
> }
>
> int get_random() {
>     return rand() % 64;
> }
>
> void init(quantum_reg *reg) {
>     reg->size = 2097152;
>     for (int i = 0; i < reg->size; i++)  {
>         reg->node = (quantum_reg_node *)malloc(sizeof(quantum_reg_node));
>         reg->node->state = (MAX_UNSIGNED *)malloc(sizeof(MAX_UNSIGNED)
> * reg->size);
>         reg->node->amplitude = (float _Complex *)malloc(sizeof(float
> _Complex) * reg->size);
>         if (i >= 1) break;
>     }
>     for (int i = 0; i < reg->size; i++)  {
>         reg->node->amplitude[i] = 0;
>         reg->node->state[i] = 0;
>     }
> }
>
> int main() {
>     quantum_reg reg;
>     init(&reg);
>     for (int i = 0; i < 65000; i++) {
>         quantum_toffoli(get_random(), get_random(), get_random(), &reg);
>     }
> }
> ```
>
> Thanks so much.

Re: How to make parallelizing loops and vectorization work at the same time?

[Hanke Zhang]

Richard Biener <richard.guenther@gmail.com> 于2023年9月15日周五 19:59写道：

>
> On Fri, Sep 15, 2023 at 1:21 PM Hanke Zhang via Gcc <gcc@gcc.gnu.org> wrote:
> >
> > Hi I'm trying to accelerate my program with -ftree-vectorize and
> > -ftree-parallelize-loops.
> >
> > Here are my test results using the different options (based on
> > gcc10.3.0 on i9-12900KF):
> > gcc-10 test.c -O3 -flto
> > > time: 29000 ms
> > gcc-10 test.c -O3 -flto -mavx2 -ftree-vectorize
> > > time: 17000 ms
> > gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24
> > > time: 5000 ms
> > gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24 -mavx2 -ftree-vectorize
> > > time: 5000 ms
> >
>
> First of all -O3 already enables -ftree-vectorize, adding -mavx2 is what brings
> the first gain.  So adding -ftree-vectorize to the last command-line is not
> expected to change anything.  Instead you can use -fno-tree-vectorize on
> the second last one.  Doing that I get 111s vs 41s thus doing both helps.
>
> Note parallelization hasn't seen any development in the last years.
>
> Richard.

Hi Richard:

Thank you for your sincere reply.

I get what you mean above. But I still see the following after I add
`-fipo-info-vec`:

gcc-10 test.c -O3 -flto -mavx2 -fopt-info-vec
> test.c:29:5: optimized: loop vectorized using 32 byte vectors
gcc-10 test.c -O3 -flto -mavx2 -fopt-info-vec -ftree-parallelize-loops=24
> nothing happened

That means the vectorization does nothing help actually.

At the same time, I added `-fno-tree-vectorize` to the second last one
command. It did not bring about a performance change on my computer.

So I still think only parallel loops work.

Hanke Zhang

>
> > I found that these two options do not work at the same time, that is,
> > if I use the `-ftree-vectorize` option alone, it can bring a big
> > efficiency gain compared to doing nothing; At the same time, if I use
> > the option of `-ftree-parallelize-loops` alone, it will also bring a
> > big efficiency gain. But if I use both options, vectorization fails,
> > that is, I can't get the benefits of vectorization, I can only get the
> > benefits of parallelizing loops.
> >
> > I know that the reason may be that after parallelizing the loop,
> > vectorization cannot be performed, but is there any way I can reap the
> > benefits of both optimizations?
> >
> > Here is my example program, adapted from the 462.libquantum in speccpu2006:
> >
> > ```
> > #include <stdio.h>
> > #include <stdlib.h>
> > #include <time.h>
> >
> > #define MAX_UNSIGNED unsigned long long
> >
> > struct quantum_reg_node_struct {
> >     float _Complex *amplitude; /* alpha_j */
> >     MAX_UNSIGNED *state;       /* j */
> > };
> >
> > typedef struct quantum_reg_node_struct quantum_reg_node;
> >
> > struct quantum_reg_struct {
> >     int width; /* number of qubits in the qureg */
> >     int size;  /* number of non-zero vectors */
> >     int hashw; /* width of the hash array */
> >     quantum_reg_node *node;
> >     int *hash;
> > };
> >
> > typedef struct quantum_reg_struct quantum_reg;
> >
> > void quantum_toffoli(int control1, int control2, int target, quantum_reg *reg) {
> >     for (int i = 0; i < reg->size; i++) {
> >         if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control1)) {
> >             if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control2))  {
> >                 reg->node->state[i] ^= ((MAX_UNSIGNED)1 << target);
> >             }
> >         }
> >     }
> > }
> >
> > int get_random() {
> >     return rand() % 64;
> > }
> >
> > void init(quantum_reg *reg) {
> >     reg->size = 2097152;
> >     for (int i = 0; i < reg->size; i++)  {
> >         reg->node = (quantum_reg_node *)malloc(sizeof(quantum_reg_node));
> >         reg->node->state = (MAX_UNSIGNED *)malloc(sizeof(MAX_UNSIGNED)
> > * reg->size);
> >         reg->node->amplitude = (float _Complex *)malloc(sizeof(float
> > _Complex) * reg->size);
> >         if (i >= 1) break;
> >     }
> >     for (int i = 0; i < reg->size; i++)  {
> >         reg->node->amplitude[i] = 0;
> >         reg->node->state[i] = 0;
> >     }
> > }
> >
> > int main() {
> >     quantum_reg reg;
> >     init(&reg);
> >     for (int i = 0; i < 65000; i++) {
> >         quantum_toffoli(get_random(), get_random(), get_random(), &reg);
> >     }
> > }
> > ```
> >
> > Thanks so much.

Re: How to make parallelizing loops and vectorization work at the same time?

[Richard Biener]

On Fri, Sep 15, 2023 at 3:09 PM Hanke Zhang <hkzhang455@gmail.com> wrote:
>
> Richard Biener <richard.guenther@gmail.com> 于2023年9月15日周五 19:59写道：
>
> >
> > On Fri, Sep 15, 2023 at 1:21 PM Hanke Zhang via Gcc <gcc@gcc.gnu.org> wrote:
> > >
> > > Hi I'm trying to accelerate my program with -ftree-vectorize and
> > > -ftree-parallelize-loops.
> > >
> > > Here are my test results using the different options (based on
> > > gcc10.3.0 on i9-12900KF):
> > > gcc-10 test.c -O3 -flto
> > > > time: 29000 ms
> > > gcc-10 test.c -O3 -flto -mavx2 -ftree-vectorize
> > > > time: 17000 ms
> > > gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24
> > > > time: 5000 ms
> > > gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24 -mavx2 -ftree-vectorize
> > > > time: 5000 ms
> > >
> >
> > First of all -O3 already enables -ftree-vectorize, adding -mavx2 is what brings
> > the first gain.  So adding -ftree-vectorize to the last command-line is not
> > expected to change anything.  Instead you can use -fno-tree-vectorize on
> > the second last one.  Doing that I get 111s vs 41s thus doing both helps.
> >
> > Note parallelization hasn't seen any development in the last years.
> >
> > Richard.
>
> Hi Richard:
>
> Thank you for your sincere reply.
>
> I get what you mean above. But I still see the following after I add
> `-fipo-info-vec`:
>
> gcc-10 test.c -O3 -flto -mavx2 -fopt-info-vec
> > test.c:29:5: optimized: loop vectorized using 32 byte vectors
> gcc-10 test.c -O3 -flto -mavx2 -fopt-info-vec -ftree-parallelize-loops=24
> > nothing happened
>
> That means the vectorization does nothing help actually.
>
> At the same time, I added `-fno-tree-vectorize` to the second last one
> command. It did not bring about a performance change on my computer.
>
> So I still think only parallel loops work.

I checked GCC 13 and do see vectorized loops when parallelizing.

Richard.

> Hanke Zhang
>
> >
> > > I found that these two options do not work at the same time, that is,
> > > if I use the `-ftree-vectorize` option alone, it can bring a big
> > > efficiency gain compared to doing nothing; At the same time, if I use
> > > the option of `-ftree-parallelize-loops` alone, it will also bring a
> > > big efficiency gain. But if I use both options, vectorization fails,
> > > that is, I can't get the benefits of vectorization, I can only get the
> > > benefits of parallelizing loops.
> > >
> > > I know that the reason may be that after parallelizing the loop,
> > > vectorization cannot be performed, but is there any way I can reap the
> > > benefits of both optimizations?
> > >
> > > Here is my example program, adapted from the 462.libquantum in speccpu2006:
> > >
> > > ```
> > > #include <stdio.h>
> > > #include <stdlib.h>
> > > #include <time.h>
> > >
> > > #define MAX_UNSIGNED unsigned long long
> > >
> > > struct quantum_reg_node_struct {
> > >     float _Complex *amplitude; /* alpha_j */
> > >     MAX_UNSIGNED *state;       /* j */
> > > };
> > >
> > > typedef struct quantum_reg_node_struct quantum_reg_node;
> > >
> > > struct quantum_reg_struct {
> > >     int width; /* number of qubits in the qureg */
> > >     int size;  /* number of non-zero vectors */
> > >     int hashw; /* width of the hash array */
> > >     quantum_reg_node *node;
> > >     int *hash;
> > > };
> > >
> > > typedef struct quantum_reg_struct quantum_reg;
> > >
> > > void quantum_toffoli(int control1, int control2, int target, quantum_reg *reg) {
> > >     for (int i = 0; i < reg->size; i++) {
> > >         if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control1)) {
> > >             if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control2))  {
> > >                 reg->node->state[i] ^= ((MAX_UNSIGNED)1 << target);
> > >             }
> > >         }
> > >     }
> > > }
> > >
> > > int get_random() {
> > >     return rand() % 64;
> > > }
> > >
> > > void init(quantum_reg *reg) {
> > >     reg->size = 2097152;
> > >     for (int i = 0; i < reg->size; i++)  {
> > >         reg->node = (quantum_reg_node *)malloc(sizeof(quantum_reg_node));
> > >         reg->node->state = (MAX_UNSIGNED *)malloc(sizeof(MAX_UNSIGNED)
> > > * reg->size);
> > >         reg->node->amplitude = (float _Complex *)malloc(sizeof(float
> > > _Complex) * reg->size);
> > >         if (i >= 1) break;
> > >     }
> > >     for (int i = 0; i < reg->size; i++)  {
> > >         reg->node->amplitude[i] = 0;
> > >         reg->node->state[i] = 0;
> > >     }
> > > }
> > >
> > > int main() {
> > >     quantum_reg reg;
> > >     init(&reg);
> > >     for (int i = 0; i < 65000; i++) {
> > >         quantum_toffoli(get_random(), get_random(), get_random(), &reg);
> > >     }
> > > }
> > > ```
> > >
> > > Thanks so much.

Re: How to make parallelizing loops and vectorization work at the same time?

[Hanke Zhang]

I get it. It's a `lto` problem. If I remove `-flto`, both work.

Thanks for your help again!

Richard Biener <richard.guenther@gmail.com> 于2023年9月15日周五 21:13写道：
>
> On Fri, Sep 15, 2023 at 3:09 PM Hanke Zhang <hkzhang455@gmail.com> wrote:
> >
> > Richard Biener <richard.guenther@gmail.com> 于2023年9月15日周五 19:59写道：
> >
> > >
> > > On Fri, Sep 15, 2023 at 1:21 PM Hanke Zhang via Gcc <gcc@gcc.gnu.org> wrote:
> > > >
> > > > Hi I'm trying to accelerate my program with -ftree-vectorize and
> > > > -ftree-parallelize-loops.
> > > >
> > > > Here are my test results using the different options (based on
> > > > gcc10.3.0 on i9-12900KF):
> > > > gcc-10 test.c -O3 -flto
> > > > > time: 29000 ms
> > > > gcc-10 test.c -O3 -flto -mavx2 -ftree-vectorize
> > > > > time: 17000 ms
> > > > gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24
> > > > > time: 5000 ms
> > > > gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24 -mavx2 -ftree-vectorize
> > > > > time: 5000 ms
> > > >
> > >
> > > First of all -O3 already enables -ftree-vectorize, adding -mavx2 is what brings
> > > the first gain.  So adding -ftree-vectorize to the last command-line is not
> > > expected to change anything.  Instead you can use -fno-tree-vectorize on
> > > the second last one.  Doing that I get 111s vs 41s thus doing both helps.
> > >
> > > Note parallelization hasn't seen any development in the last years.
> > >
> > > Richard.
> >
> > Hi Richard:
> >
> > Thank you for your sincere reply.
> >
> > I get what you mean above. But I still see the following after I add
> > `-fipo-info-vec`:
> >
> > gcc-10 test.c -O3 -flto -mavx2 -fopt-info-vec
> > > test.c:29:5: optimized: loop vectorized using 32 byte vectors
> > gcc-10 test.c -O3 -flto -mavx2 -fopt-info-vec -ftree-parallelize-loops=24
> > > nothing happened
> >
> > That means the vectorization does nothing help actually.
> >
> > At the same time, I added `-fno-tree-vectorize` to the second last one
> > command. It did not bring about a performance change on my computer.
> >
> > So I still think only parallel loops work.
>
> I checked GCC 13 and do see vectorized loops when parallelizing.
>
> Richard.
>
> > Hanke Zhang
> >
> > >
> > > > I found that these two options do not work at the same time, that is,
> > > > if I use the `-ftree-vectorize` option alone, it can bring a big
> > > > efficiency gain compared to doing nothing; At the same time, if I use
> > > > the option of `-ftree-parallelize-loops` alone, it will also bring a
> > > > big efficiency gain. But if I use both options, vectorization fails,
> > > > that is, I can't get the benefits of vectorization, I can only get the
> > > > benefits of parallelizing loops.
> > > >
> > > > I know that the reason may be that after parallelizing the loop,
> > > > vectorization cannot be performed, but is there any way I can reap the
> > > > benefits of both optimizations?
> > > >
> > > > Here is my example program, adapted from the 462.libquantum in speccpu2006:
> > > >
> > > > ```
> > > > #include <stdio.h>
> > > > #include <stdlib.h>
> > > > #include <time.h>
> > > >
> > > > #define MAX_UNSIGNED unsigned long long
> > > >
> > > > struct quantum_reg_node_struct {
> > > >     float _Complex *amplitude; /* alpha_j */
> > > >     MAX_UNSIGNED *state;       /* j */
> > > > };
> > > >
> > > > typedef struct quantum_reg_node_struct quantum_reg_node;
> > > >
> > > > struct quantum_reg_struct {
> > > >     int width; /* number of qubits in the qureg */
> > > >     int size;  /* number of non-zero vectors */
> > > >     int hashw; /* width of the hash array */
> > > >     quantum_reg_node *node;
> > > >     int *hash;
> > > > };
> > > >
> > > > typedef struct quantum_reg_struct quantum_reg;
> > > >
> > > > void quantum_toffoli(int control1, int control2, int target, quantum_reg *reg) {
> > > >     for (int i = 0; i < reg->size; i++) {
> > > >         if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control1)) {
> > > >             if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control2))  {
> > > >                 reg->node->state[i] ^= ((MAX_UNSIGNED)1 << target);
> > > >             }
> > > >         }
> > > >     }
> > > > }
> > > >
> > > > int get_random() {
> > > >     return rand() % 64;
> > > > }
> > > >
> > > > void init(quantum_reg *reg) {
> > > >     reg->size = 2097152;
> > > >     for (int i = 0; i < reg->size; i++)  {
> > > >         reg->node = (quantum_reg_node *)malloc(sizeof(quantum_reg_node));
> > > >         reg->node->state = (MAX_UNSIGNED *)malloc(sizeof(MAX_UNSIGNED)
> > > > * reg->size);
> > > >         reg->node->amplitude = (float _Complex *)malloc(sizeof(float
> > > > _Complex) * reg->size);
> > > >         if (i >= 1) break;
> > > >     }
> > > >     for (int i = 0; i < reg->size; i++)  {
> > > >         reg->node->amplitude[i] = 0;
> > > >         reg->node->state[i] = 0;
> > > >     }
> > > > }
> > > >
> > > > int main() {
> > > >     quantum_reg reg;
> > > >     init(&reg);
> > > >     for (int i = 0; i < 65000; i++) {
> > > >         quantum_toffoli(get_random(), get_random(), get_random(), &reg);
> > > >     }
> > > > }
> > > > ```
> > > >
> > > > Thanks so much.

Re: How to make parallelizing loops and vectorization work at the same time?

[Richard Biener]

On Fri, Sep 15, 2023 at 4:07 PM Hanke Zhang <hkzhang455@gmail.com> wrote:
>
> I get it. It's a `lto` problem. If I remove `-flto`, both work.

That's odd - it might be that GCC thinks part of the program is cold and doesn't
optimize it.  Does using -fwhole-program instead of -flto also not work?

Richard.

> Thanks for your help again!
>
> Richard Biener <richard.guenther@gmail.com> 于2023年9月15日周五 21:13写道：
> >
> > On Fri, Sep 15, 2023 at 3:09 PM Hanke Zhang <hkzhang455@gmail.com> wrote:
> > >
> > > Richard Biener <richard.guenther@gmail.com> 于2023年9月15日周五 19:59写道：
> > >
> > > >
> > > > On Fri, Sep 15, 2023 at 1:21 PM Hanke Zhang via Gcc <gcc@gcc.gnu.org> wrote:
> > > > >
> > > > > Hi I'm trying to accelerate my program with -ftree-vectorize and
> > > > > -ftree-parallelize-loops.
> > > > >
> > > > > Here are my test results using the different options (based on
> > > > > gcc10.3.0 on i9-12900KF):
> > > > > gcc-10 test.c -O3 -flto
> > > > > > time: 29000 ms
> > > > > gcc-10 test.c -O3 -flto -mavx2 -ftree-vectorize
> > > > > > time: 17000 ms
> > > > > gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24
> > > > > > time: 5000 ms
> > > > > gcc-10 test.c -O3 -flto -ftree-parallelize-loops=24 -mavx2 -ftree-vectorize
> > > > > > time: 5000 ms
> > > > >
> > > >
> > > > First of all -O3 already enables -ftree-vectorize, adding -mavx2 is what brings
> > > > the first gain.  So adding -ftree-vectorize to the last command-line is not
> > > > expected to change anything.  Instead you can use -fno-tree-vectorize on
> > > > the second last one.  Doing that I get 111s vs 41s thus doing both helps.
> > > >
> > > > Note parallelization hasn't seen any development in the last years.
> > > >
> > > > Richard.
> > >
> > > Hi Richard:
> > >
> > > Thank you for your sincere reply.
> > >
> > > I get what you mean above. But I still see the following after I add
> > > `-fipo-info-vec`:
> > >
> > > gcc-10 test.c -O3 -flto -mavx2 -fopt-info-vec
> > > > test.c:29:5: optimized: loop vectorized using 32 byte vectors
> > > gcc-10 test.c -O3 -flto -mavx2 -fopt-info-vec -ftree-parallelize-loops=24
> > > > nothing happened
> > >
> > > That means the vectorization does nothing help actually.
> > >
> > > At the same time, I added `-fno-tree-vectorize` to the second last one
> > > command. It did not bring about a performance change on my computer.
> > >
> > > So I still think only parallel loops work.
> >
> > I checked GCC 13 and do see vectorized loops when parallelizing.
> >
> > Richard.
> >
> > > Hanke Zhang
> > >
> > > >
> > > > > I found that these two options do not work at the same time, that is,
> > > > > if I use the `-ftree-vectorize` option alone, it can bring a big
> > > > > efficiency gain compared to doing nothing; At the same time, if I use
> > > > > the option of `-ftree-parallelize-loops` alone, it will also bring a
> > > > > big efficiency gain. But if I use both options, vectorization fails,
> > > > > that is, I can't get the benefits of vectorization, I can only get the
> > > > > benefits of parallelizing loops.
> > > > >
> > > > > I know that the reason may be that after parallelizing the loop,
> > > > > vectorization cannot be performed, but is there any way I can reap the
> > > > > benefits of both optimizations?
> > > > >
> > > > > Here is my example program, adapted from the 462.libquantum in speccpu2006:
> > > > >
> > > > > ```
> > > > > #include <stdio.h>
> > > > > #include <stdlib.h>
> > > > > #include <time.h>
> > > > >
> > > > > #define MAX_UNSIGNED unsigned long long
> > > > >
> > > > > struct quantum_reg_node_struct {
> > > > >     float _Complex *amplitude; /* alpha_j */
> > > > >     MAX_UNSIGNED *state;       /* j */
> > > > > };
> > > > >
> > > > > typedef struct quantum_reg_node_struct quantum_reg_node;
> > > > >
> > > > > struct quantum_reg_struct {
> > > > >     int width; /* number of qubits in the qureg */
> > > > >     int size;  /* number of non-zero vectors */
> > > > >     int hashw; /* width of the hash array */
> > > > >     quantum_reg_node *node;
> > > > >     int *hash;
> > > > > };
> > > > >
> > > > > typedef struct quantum_reg_struct quantum_reg;
> > > > >
> > > > > void quantum_toffoli(int control1, int control2, int target, quantum_reg *reg) {
> > > > >     for (int i = 0; i < reg->size; i++) {
> > > > >         if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control1)) {
> > > > >             if (reg->node->state[i] & ((MAX_UNSIGNED)1 << control2))  {
> > > > >                 reg->node->state[i] ^= ((MAX_UNSIGNED)1 << target);
> > > > >             }
> > > > >         }
> > > > >     }
> > > > > }
> > > > >
> > > > > int get_random() {
> > > > >     return rand() % 64;
> > > > > }
> > > > >
> > > > > void init(quantum_reg *reg) {
> > > > >     reg->size = 2097152;
> > > > >     for (int i = 0; i < reg->size; i++)  {
> > > > >         reg->node = (quantum_reg_node *)malloc(sizeof(quantum_reg_node));
> > > > >         reg->node->state = (MAX_UNSIGNED *)malloc(sizeof(MAX_UNSIGNED)
> > > > > * reg->size);
> > > > >         reg->node->amplitude = (float _Complex *)malloc(sizeof(float
> > > > > _Complex) * reg->size);
> > > > >         if (i >= 1) break;
> > > > >     }
> > > > >     for (int i = 0; i < reg->size; i++)  {
> > > > >         reg->node->amplitude[i] = 0;
> > > > >         reg->node->state[i] = 0;
> > > > >     }
> > > > > }
> > > > >
> > > > > int main() {
> > > > >     quantum_reg reg;
> > > > >     init(&reg);
> > > > >     for (int i = 0; i < 65000; i++) {
> > > > >         quantum_toffoli(get_random(), get_random(), get_random(), &reg);
> > > > >     }
> > > > > }
> > > > > ```
> > > > >
> > > > > Thanks so much.