NumPy 1.26 中文文档（四十九）

#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION 

#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION 

type PyDataMem_Handler

typedef  struct  {
  char  name[127];  /* multiple of 64 to keep the struct aligned */
  uint8_t  version;  /* currently 1 */
  PyDataMemAllocator  allocator;
}  PyDataMem_Handler; 

/* The declaration of free differs from PyMemAllocatorEx */
typedef  struct  {
  void  *ctx;
  void*  (*malloc)  (void  *ctx,  size_t  size);
  void*  (*calloc)  (void  *ctx,  size_t  nelem,  size_t  elsize);
  void*  (*realloc)  (void  *ctx,  void  *ptr,  size_t  new_size);
  void  (*free)  (void  *ctx,  void  *ptr,  size_t  size);
}  PyDataMemAllocator; 

*PyDataMem_SetHandler( *handler)

*PyDataMem_GetHandler()

void PyDataMem_EventHookFunc(void *inp, void *outp, size_t size, void *user_data);

*PyDataMem_SetEventHook( *newhook, void *user_data, void **old_data)

result  =  PyDataMem_NEW(size)  ->  (*hook)(NULL,  result,  size,  user_data)
PyDataMem_FREE(ptr)  ->  (*hook)(ptr,  NULL,  0,  user_data)
result  =  PyDataMem_RENEW(ptr,  size)  ->  (*hook)(ptr,  result,  size,  user_data) 

/* define a PyCapsule_Destructor, using the correct deallocator for buff */
void  free_wrap(void  *capsule){
  void  *  obj  =  PyCapsule_GetPointer(capsule,  PyCapsule_GetName(capsule));
  free(obj);
};

/* then inside the function that creates arr from buff */
...
arr  =  PyArray_NewFromDescr(...  buf,  ...);
if  (arr  ==  NULL)  {
  return  NULL;
}
capsule  =  PyCapsule_New(buf,  "my_wrapped_buffer",
  (PyCapsule_Destructor)&free_wrap);
if  (PyArray_SetBaseObject(arr,  capsule)  ==  -1)  {
  Py_DECREF(arr);
  return  NULL;
}
... 

"""
 The goal of this example is to show how to trace memory
 from an application that has NumPy and non-NumPy sections.
 We only select the sections using NumPy related calls.
"""

import tracemalloc
import numpy as np

# Flag to determine if we select NumPy domain
use_np_domain = True

nx = 300
ny = 500

# Start to trace memory
tracemalloc.start()

# Section 1
# ---------

# NumPy related call
a = np.zeros((nx,ny))

# non-NumPy related call
b = [i**2 for i in range(nx*ny)]

snapshot1 = tracemalloc.take_snapshot()
# We filter the snapshot to only select NumPy related calls
np_domain = np.lib.tracemalloc_domain
dom_filter = tracemalloc.DomainFilter(inclusive=use_np_domain,
                                      domain=np_domain)
snapshot1 = snapshot1.filter_traces([dom_filter])
top_stats1 = snapshot1.statistics('traceback')

print("================ SNAPSHOT 1 =================")
for stat in top_stats1:
    print(f"{stat.count} memory blocks: {stat.size  /  1024:.1f} KiB")
    print(stat.traceback.format()[-1])

# Clear traces of memory blocks allocated by Python
# before moving to the next section.
tracemalloc.clear_traces()

# Section 2
#----------

# We are only using NumPy
c = np.sum(a*a)

snapshot2 = tracemalloc.take_snapshot()
top_stats2 = snapshot2.statistics('traceback')

print()
print("================ SNAPSHOT 2 =================")
for stat in top_stats2:
    print(f"{stat.count} memory blocks: {stat.size  /  1024:.1f} KiB")
    print(stat.traceback.format()[-1])

tracemalloc.stop()

print()
print("============================================")
print("\nTracing Status : ", tracemalloc.is_tracing())

try:
    print("\nTrying to Take Snapshot After Tracing is Stopped.")
    snap = tracemalloc.take_snapshot()
except Exception as e:
    print("Exception : ", e) 

type PyDataMem_Handler

typedef  struct  {
  char  name[127];  /* multiple of 64 to keep the struct aligned */
  uint8_t  version;  /* currently 1 */
  PyDataMemAllocator  allocator;
}  PyDataMem_Handler; 

/* The declaration of free differs from PyMemAllocatorEx */
typedef  struct  {
  void  *ctx;
  void*  (*malloc)  (void  *ctx,  size_t  size);
  void*  (*calloc)  (void  *ctx,  size_t  nelem,  size_t  elsize);
  void*  (*realloc)  (void  *ctx,  void  *ptr,  size_t  new_size);
  void  (*free)  (void  *ctx,  void  *ptr,  size_t  size);
}  PyDataMemAllocator; 

*PyDataMem_SetHandler( *handler)

*PyDataMem_GetHandler()

void PyDataMem_EventHookFunc(void *inp, void *outp, size_t size, void *user_data);

*PyDataMem_SetEventHook( *newhook, void *user_data, void **old_data)

result  =  PyDataMem_NEW(size)  ->  (*hook)(NULL,  result,  size,  user_data)
PyDataMem_FREE(ptr)  ->  (*hook)(ptr,  NULL,  0,  user_data)
result  =  PyDataMem_RENEW(ptr,  size)  ->  (*hook)(ptr,  result,  size,  user_data) 

/* define a PyCapsule_Destructor, using the correct deallocator for buff */
void  free_wrap(void  *capsule){
  void  *  obj  =  PyCapsule_GetPointer(capsule,  PyCapsule_GetName(capsule));
  free(obj);
};

/* then inside the function that creates arr from buff */
...
arr  =  PyArray_NewFromDescr(...  buf,  ...);
if  (arr  ==  NULL)  {
  return  NULL;
}
capsule  =  PyCapsule_New(buf,  "my_wrapped_buffer",
  (PyCapsule_Destructor)&free_wrap);
if  (PyArray_SetBaseObject(arr,  capsule)  ==  -1)  {
  Py_DECREF(arr);
  return  NULL;
}
... 

"""
 The goal of this example is to show how to trace memory
 from an application that has NumPy and non-NumPy sections.
 We only select the sections using NumPy related calls.
"""

import tracemalloc
import numpy as np

# Flag to determine if we select NumPy domain
use_np_domain = True

nx = 300
ny = 500

# Start to trace memory
tracemalloc.start()

# Section 1
# ---------

# NumPy related call
a = np.zeros((nx,ny))

# non-NumPy related call
b = [i**2 for i in range(nx*ny)]

snapshot1 = tracemalloc.take_snapshot()
# We filter the snapshot to only select NumPy related calls
np_domain = np.lib.tracemalloc_domain
dom_filter = tracemalloc.DomainFilter(inclusive=use_np_domain,
                                      domain=np_domain)
snapshot1 = snapshot1.filter_traces([dom_filter])
top_stats1 = snapshot1.statistics('traceback')

print("================ SNAPSHOT 1 =================")
for stat in top_stats1:
    print(f"{stat.count} memory blocks: {stat.size  /  1024:.1f} KiB")
    print(stat.traceback.format()[-1])

# Clear traces of memory blocks allocated by Python
# before moving to the next section.
tracemalloc.clear_traces()

# Section 2
#----------

# We are only using NumPy
c = np.sum(a*a)

snapshot2 = tracemalloc.take_snapshot()
top_stats2 = snapshot2.statistics('traceback')

print()
print("================ SNAPSHOT 2 =================")
for stat in top_stats2:
    print(f"{stat.count} memory blocks: {stat.size  /  1024:.1f} KiB")
    print(stat.traceback.format()[-1])

tracemalloc.stop()

print()
print("============================================")
print("\nTracing Status : ", tracemalloc.is_tracing())

try:
    print("\nTrying to Take Snapshot After Tracing is Stopped.")
    snap = tracemalloc.take_snapshot()
except Exception as e:
    print("Exception : ", e) 

cd /path/to/numpy
python setup.py build --cpu-baseline="avx2 fma3" install --user 

cd /path/to/numpy
python setup.py build_ext --cpu-baseline="avx2 fma3" install --user 

cd /path/to/numpy
python setup.py build_clib --cpu-baseline="avx2 fma3" install --user 

pip install --no-use-pep517 --global-option=build \
--global-option="--cpu-baseline=avx2 fma3" \
--global-option="--cpu-dispatch=max" ./ 

python setup.py build --cpu-baseline="native" bdist 

python setup.py build --cpu-baseline=native --cpu-dispatch=none bdist 

python setup.py build --cpu-baseline="avx f16c" bdist 

python setup.py build --cpu-baseline="vsx2" bdist 

python setup.py build --cpu-dispatch="max -avx512f -avx512cd \
-avx512_knl -avx512_knm -avx512_skx -avx512_clx -avx512_cnl -avx512_icl" \
bdist 

python setup.py build --cpu-dispatch="SSE41 avx2 FMA3" 

python setup.py build --cpu-dispatch="SSE41 AVX2 FMA3"
# equivalent to
python setup.py build --cpu-dispatch="FMA3 AVX2 SSE41" 

python setup.py build --cpu-dispatch="avx2 avx512f"
# or
python setup.py build --cpu-dispatch=avx2,avx512f
# or
python setup.py build --cpu-dispatch="avx2+avx512f" 

python setup.py build --cpu-baseline=sse42
# equivalent to
python setup.py build --cpu-baseline="sse sse2 sse3 ssse3 sse41 popcnt sse42" 

export CFLAGS="-march=native"
python setup.py install --user
# is equivalent to
python setup.py build --cpu-baseline=native install --user 

# Requesting `AVX2,FMA3` but the compiler only support **SSE** features
python setup.py build --cpu-baseline="avx2 fma3"
# is equivalent to
python setup.py build --cpu-baseline="sse sse2 sse3 ssse3 sse41 popcnt sse42" 

# Only dispatches AVX2 and FMA3
python setup.py build --cpu-dispatch=avx2,fma3
# Dispatches AVX and SSE features
python setup.py build --cpu-baseline=ssse3,sse41,sse42,avx,avx2,fma3 

# On ARMv8/A64, specify NEON is going to enable Advanced SIMD
# and all predecessor extensions
python setup.py build --cpu-baseline=neon
# which equivalent to
python setup.py build --cpu-baseline="neon neon_fp16 neon_vfpv4 asimd" 

# Specify AVX2 will force enables FMA3 on Intel compilers
python setup.py build --cpu-baseline=avx2
# which equivalent to
python setup.py build --cpu-baseline="avx2 fma3" 

########### EXT COMPILER OPTIMIZATION ###########
Platform  :
  Architecture:  x64
  Compiler  :  gcc

CPU  baseline  :
  Requested  :  'min'
  Enabled  :  SSE  SSE2  SSE3
  Flags  :  -msse  -msse2  -msse3
  Extra  checks:  none

CPU  dispatch  :
  Requested  :  'max -xop -fma4'
  Enabled  :  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C  FMA3  AVX2  AVX512F  AVX512CD  AVX512_KNL  AVX512_KNM  AVX512_SKX  AVX512_CLX  AVX512_CNL  AVX512_ICL
  Generated  :
  :
  SSE41  :  SSE  SSE2  SSE3  SSSE3
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1
  Extra  checks:  none
  Detect  :  SSE  SSE2  SSE3  SSSE3  SSE41
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithmetic.dispatch.c
  :  numpy/core/src/umath/_umath_tests.dispatch.c
  :
  SSE42  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2
  Extra  checks:  none
  Detect  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42
  :  build/src.linux-x86_64-3.9/numpy/core/src/_simd/_simd.dispatch.c
  :
  AVX2  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2  -mavx  -mf16c  -mavx2
  Extra  checks:  none
  Detect  :  AVX  F16C  AVX2
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithm_fp.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithmetic.dispatch.c
  :  numpy/core/src/umath/_umath_tests.dispatch.c
  :
  (FMA3  AVX2)  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2  -mavx  -mf16c  -mfma  -mavx2
  Extra  checks:  none
  Detect  :  AVX  F16C  FMA3  AVX2
  :  build/src.linux-x86_64-3.9/numpy/core/src/_simd/_simd.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_exponent_log.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_trigonometric.dispatch.c
  :
  AVX512F  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C  FMA3  AVX2
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2  -mavx  -mf16c  -mfma  -mavx2  -mavx512f
  Extra  checks:  AVX512F_REDUCE
  Detect  :  AVX512F
  :  build/src.linux-x86_64-3.9/numpy/core/src/_simd/_simd.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithm_fp.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithmetic.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_exponent_log.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_trigonometric.dispatch.c
  :
  AVX512_SKX  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C  FMA3  AVX2  AVX512F  AVX512CD
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2  -mavx  -mf16c  -mfma  -mavx2  -mavx512f  -mavx512cd  -mavx512vl  -mavx512bw  -mavx512dq
  Extra  checks:  AVX512BW_MASK  AVX512DQ_MASK
  Detect  :  AVX512_SKX
  :  build/src.linux-x86_64-3.9/numpy/core/src/_simd/_simd.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithmetic.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_exponent_log.dispatch.c
CCompilerOpt.cache_flush[804]  :  write  cache  to  path  ->  /home/seiko/work/repos/numpy/build/temp.linux-x86_64-3.9/ccompiler_opt_cache_ext.py

########### CLIB COMPILER OPTIMIZATION ###########
Platform  :
  Architecture:  x64
  Compiler  :  gcc

CPU  baseline  :
  Requested  :  'min'
  Enabled  :  SSE  SSE2  SSE3
  Flags  :  -msse  -msse2  -msse3
  Extra  checks:  none

CPU  dispatch  :
  Requested  :  'max -xop -fma4'
  Enabled  :  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C  FMA3  AVX2  AVX512F  AVX512CD  AVX512_KNL  AVX512_KNM  AVX512_SKX  AVX512_CLX  AVX512_CNL  AVX512_ICL
  Generated  :  none 

NPY_DISABLE_CPU_FEATURES="AVX2,FMA3" 

cd /path/to/numpy
python setup.py build --cpu-baseline="avx2 fma3" install --user 

cd /path/to/numpy
python setup.py build_ext --cpu-baseline="avx2 fma3" install --user 

cd /path/to/numpy
python setup.py build_clib --cpu-baseline="avx2 fma3" install --user 

pip install --no-use-pep517 --global-option=build \
--global-option="--cpu-baseline=avx2 fma3" \
--global-option="--cpu-dispatch=max" ./ 

python setup.py build --cpu-baseline="native" bdist 

python setup.py build --cpu-baseline=native --cpu-dispatch=none bdist 

python setup.py build --cpu-baseline="avx f16c" bdist 

python setup.py build --cpu-baseline="vsx2" bdist 

python setup.py build --cpu-dispatch="max -avx512f -avx512cd \
-avx512_knl -avx512_knm -avx512_skx -avx512_clx -avx512_cnl -avx512_icl" \
bdist 

python setup.py build --cpu-baseline="native" bdist 

python setup.py build --cpu-baseline=native --cpu-dispatch=none bdist 

python setup.py build --cpu-baseline="avx f16c" bdist 

python setup.py build --cpu-baseline="vsx2" bdist 

python setup.py build --cpu-dispatch="max -avx512f -avx512cd \
-avx512_knl -avx512_knm -avx512_skx -avx512_clx -avx512_cnl -avx512_icl" \
bdist 

python setup.py build --cpu-dispatch="SSE41 avx2 FMA3" 

python setup.py build --cpu-dispatch="SSE41 AVX2 FMA3"
# equivalent to
python setup.py build --cpu-dispatch="FMA3 AVX2 SSE41" 

python setup.py build --cpu-dispatch="avx2 avx512f"
# or
python setup.py build --cpu-dispatch=avx2,avx512f
# or
python setup.py build --cpu-dispatch="avx2+avx512f" 

python setup.py build --cpu-baseline=sse42
# equivalent to
python setup.py build --cpu-baseline="sse sse2 sse3 ssse3 sse41 popcnt sse42" 

export CFLAGS="-march=native"
python setup.py install --user
# is equivalent to
python setup.py build --cpu-baseline=native install --user 

# Requesting `AVX2,FMA3` but the compiler only support **SSE** features
python setup.py build --cpu-baseline="avx2 fma3"
# is equivalent to
python setup.py build --cpu-baseline="sse sse2 sse3 ssse3 sse41 popcnt sse42" 

# Only dispatches AVX2 and FMA3
python setup.py build --cpu-dispatch=avx2,fma3
# Dispatches AVX and SSE features
python setup.py build --cpu-baseline=ssse3,sse41,sse42,avx,avx2,fma3 

# On ARMv8/A64, specify NEON is going to enable Advanced SIMD
# and all predecessor extensions
python setup.py build --cpu-baseline=neon
# which equivalent to
python setup.py build --cpu-baseline="neon neon_fp16 neon_vfpv4 asimd" 

# Specify AVX2 will force enables FMA3 on Intel compilers
python setup.py build --cpu-baseline=avx2
# which equivalent to
python setup.py build --cpu-baseline="avx2 fma3" 

########### EXT COMPILER OPTIMIZATION ###########
Platform  :
  Architecture:  x64
  Compiler  :  gcc

CPU  baseline  :
  Requested  :  'min'
  Enabled  :  SSE  SSE2  SSE3
  Flags  :  -msse  -msse2  -msse3
  Extra  checks:  none

CPU  dispatch  :
  Requested  :  'max -xop -fma4'
  Enabled  :  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C  FMA3  AVX2  AVX512F  AVX512CD  AVX512_KNL  AVX512_KNM  AVX512_SKX  AVX512_CLX  AVX512_CNL  AVX512_ICL
  Generated  :
  :
  SSE41  :  SSE  SSE2  SSE3  SSSE3
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1
  Extra  checks:  none
  Detect  :  SSE  SSE2  SSE3  SSSE3  SSE41
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithmetic.dispatch.c
  :  numpy/core/src/umath/_umath_tests.dispatch.c
  :
  SSE42  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2
  Extra  checks:  none
  Detect  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42
  :  build/src.linux-x86_64-3.9/numpy/core/src/_simd/_simd.dispatch.c
  :
  AVX2  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2  -mavx  -mf16c  -mavx2
  Extra  checks:  none
  Detect  :  AVX  F16C  AVX2
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithm_fp.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithmetic.dispatch.c
  :  numpy/core/src/umath/_umath_tests.dispatch.c
  :
  (FMA3  AVX2)  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2  -mavx  -mf16c  -mfma  -mavx2
  Extra  checks:  none
  Detect  :  AVX  F16C  FMA3  AVX2
  :  build/src.linux-x86_64-3.9/numpy/core/src/_simd/_simd.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_exponent_log.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_trigonometric.dispatch.c
  :
  AVX512F  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C  FMA3  AVX2
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2  -mavx  -mf16c  -mfma  -mavx2  -mavx512f
  Extra  checks:  AVX512F_REDUCE
  Detect  :  AVX512F
  :  build/src.linux-x86_64-3.9/numpy/core/src/_simd/_simd.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithm_fp.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithmetic.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_exponent_log.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_trigonometric.dispatch.c
  :
  AVX512_SKX  :  SSE  SSE2  SSE3  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C  FMA3  AVX2  AVX512F  AVX512CD
  Flags  :  -msse  -msse2  -msse3  -mssse3  -msse4.1  -mpopcnt  -msse4.2  -mavx  -mf16c  -mfma  -mavx2  -mavx512f  -mavx512cd  -mavx512vl  -mavx512bw  -mavx512dq
  Extra  checks:  AVX512BW_MASK  AVX512DQ_MASK
  Detect  :  AVX512_SKX
  :  build/src.linux-x86_64-3.9/numpy/core/src/_simd/_simd.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_arithmetic.dispatch.c
  :  build/src.linux-x86_64-3.9/numpy/core/src/umath/loops_exponent_log.dispatch.c
CCompilerOpt.cache_flush[804]  :  write  cache  to  path  ->  /home/seiko/work/repos/numpy/build/temp.linux-x86_64-3.9/ccompiler_opt_cache_ext.py

########### CLIB COMPILER OPTIMIZATION ###########
Platform  :
  Architecture:  x64
  Compiler  :  gcc

CPU  baseline  :
  Requested  :  'min'
  Enabled  :  SSE  SSE2  SSE3
  Flags  :  -msse  -msse2  -msse3
  Extra  checks:  none

CPU  dispatch  :
  Requested  :  'max -xop -fma4'
  Enabled  :  SSSE3  SSE41  POPCNT  SSE42  AVX  F16C  FMA3  AVX2  AVX512F  AVX512CD  AVX512_KNL  AVX512_KNM  AVX512_SKX  AVX512_CLX  AVX512_CNL  AVX512_ICL
  Generated  :  none 

NPY_DISABLE_CPU_FEATURES="AVX2,FMA3" 

// The header should be located at numpy/numpy/core/src/common/_cpu_dispatch.h
/**NOTE
 ** C definitions prefixed with "NPY_HAVE_" represent
 ** the required optimizations.
 **
 ** C definitions prefixed with 'NPY__CPU_TARGET_' are protected and
 ** shouldn't be used by any NumPy C sources.
 */
/******* baseline features *******/
/** SSE **/
#define NPY_HAVE_SSE 1
#include  <xmmintrin.h>
/** SSE2 **/
#define NPY_HAVE_SSE2 1
#include  <emmintrin.h>
/** SSE3 **/
#define NPY_HAVE_SSE3 1
#include  <pmmintrin.h>

/******* dispatch-able features *******/
#ifdef NPY__CPU_TARGET_SSSE3
  /** SSSE3 **/
  #define NPY_HAVE_SSSE3 1
  #include  <tmmintrin.h>
#endif
#ifdef NPY__CPU_TARGET_SSE41
  /** SSE41 **/
  #define NPY_HAVE_SSE41 1
  #include  <smmintrin.h>
#endif 

/*@targets avx2 avx512f vsx2 vsx3 asimd asimdhp */
// C code 

/*
 * this definition is used by NumPy utilities as suffixes for the
 * exported symbols
 */
#define NPY__CPU_TARGET_CURRENT AVX512F
/*
 * The following definitions enable
 * definitions of the dispatch-able features that are defined within the main
 * configuration header. These are definitions for the implied features.
 */
#define NPY__CPU_TARGET_SSE
#define NPY__CPU_TARGET_SSE2
#define NPY__CPU_TARGET_SSE3
#define NPY__CPU_TARGET_SSSE3
#define NPY__CPU_TARGET_SSE41
#define NPY__CPU_TARGET_POPCNT
#define NPY__CPU_TARGET_SSE42
#define NPY__CPU_TARGET_AVX
#define NPY__CPU_TARGET_F16C
#define NPY__CPU_TARGET_FMA3
#define NPY__CPU_TARGET_AVX2
#define NPY__CPU_TARGET_AVX512F
// our dispatch-able source
#include  "/the/absuolate/path/of/hello.dispatch.c" 

// hello.dispatch.c
/*@targets baseline sse42 avx512f */
#include  <stdio.h>
#include  "numpy/utils.h" // NPY_CAT, NPY_TOSTR

#ifndef NPY__CPU_TARGET_CURRENT
  // wrapping the dispatch-able source only happens to the additional optimizations
  // but if the keyword 'baseline' provided within the configuration statements,
  // the infrastructure will add extra compiling for the dispatch-able source by
  // passing it as-is to the compiler without any changes.
  #define CURRENT_TARGET(X) X
  #define NPY__CPU_TARGET_CURRENT baseline // for printing only
#else
  // since we reach to this point, that's mean we're dealing with
  // the additional optimizations, so it could be SSE42 or AVX512F
  #define CURRENT_TARGET(X) NPY_CAT(NPY_CAT(X, _), NPY__CPU_TARGET_CURRENT)
#endif
// Macro 'CURRENT_TARGET' adding the current target as suffux to the exported symbols,
// to avoid linking duplications, NumPy already has a macro called
// 'NPY_CPU_DISPATCH_CURFX' similar to it, located at
// numpy/numpy/core/src/common/npy_cpu_dispatch.h
// NOTE: we tend to not adding suffixes to the baseline exported symbols
void  CURRENT_TARGET(simd_whoami)(const  char  *extra_info)
{
  printf("I'm "  NPY_TOSTR(NPY__CPU_TARGET_CURRENT)  ", %s\n",  extra_info);
} 

#ifndef NPY__CPU_DISPATCH_EXPAND_
  // To expand the macro calls in this header
  #define NPY__CPU_DISPATCH_EXPAND_(X) X
#endif
// Undefining the following macros, due to the possibility of including config headers
// multiple times within the same source and since each config header represents
// different required optimizations according to the specified configuration
// statements in the dispatch-able source that derived from it.
#undef NPY__CPU_DISPATCH_BASELINE_CALL
#undef NPY__CPU_DISPATCH_CALL
// nothing strange here, just a normal preprocessor callback
// enabled only if 'baseline' specified within the configuration statements
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
 NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
// 'NPY__CPU_DISPATCH_CALL' is an abstract macro is used for dispatching
// the required optimizations that specified within the configuration statements.
//
// @param CHK, Expected a macro that can be used to detect CPU features
// in runtime, which takes a CPU feature name without string quotes and
// returns the testing result in a shape of boolean value.
// NumPy already has macro called "NPY_CPU_HAVE", which fits this requirement.
//
// @param CB, a callback macro that expected to be called multiple times depending
// on the required optimizations, the callback should receive the following arguments:
//  1- The pending calls of @param CHK filled up with the required CPU features,
//     that need to be tested first in runtime before executing call belong to
//     the compiled object.
//  2- The required optimization name, same as in 'NPY__CPU_TARGET_CURRENT'
//  3- Extra arguments in the macro itself
//
// By default the callback calls are sorted depending on the highest interest
// unless the policy "$keep_sort" was in place within the configuration statements
// see "Dive into the CPU dispatcher" for more clarification.
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
 NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512F)), AVX512F, __VA_ARGS__)) \
 NPY__CPU_DISPATCH_EXPAND_(CB((CHK(SSE)&&CHK(SSE2)&&CHK(SSE3)&&CHK(SSSE3)&&CHK(SSE41)), SSE41, __VA_ARGS__)) 

// NOTE: The following macros are only defined for demonstration purposes only.
// NumPy already has a collections of macros located at
// numpy/numpy/core/src/common/npy_cpu_dispatch.h, that covers all dispatching
// and declarations scenarios.

#include  "numpy/npy_cpu_features.h" // NPY_CPU_HAVE
#include  "numpy/utils.h" // NPY_CAT, NPY_EXPAND

// An example for setting a macro that calls all the exported symbols at once
// after checking if they're supported by the running machine.
#define DISPATCH_CALL_ALL(FN, ARGS) \
 NPY__CPU_DISPATCH_CALL(NPY_CPU_HAVE, DISPATCH_CALL_ALL_CB, FN, ARGS) \
 NPY__CPU_DISPATCH_BASELINE_CALL(DISPATCH_CALL_BASELINE_ALL_CB, FN, ARGS)
// The preprocessor callbacks.
// The same suffixes as we define it in the dispatch-able source.
#define DISPATCH_CALL_ALL_CB(CHECK, TARGET_NAME, FN, ARGS) \
 if (CHECK) { NPY_CAT(NPY_CAT(FN, _), TARGET_NAME) ARGS; }
#define DISPATCH_CALL_BASELINE_ALL_CB(FN, ARGS) \
 FN NPY_EXPAND(ARGS);

// An example for setting a macro that calls the exported symbols of highest
// interest optimization, after checking if they're supported by the running machine.
#define DISPATCH_CALL_HIGH(FN, ARGS) \
 if (0) {} \
 NPY__CPU_DISPATCH_CALL(NPY_CPU_HAVE, DISPATCH_CALL_HIGH_CB, FN, ARGS) \
 NPY__CPU_DISPATCH_BASELINE_CALL(DISPATCH_CALL_BASELINE_HIGH_CB, FN, ARGS)
// The preprocessor callbacks
// The same suffixes as we define it in the dispatch-able source.
#define DISPATCH_CALL_HIGH_CB(CHECK, TARGET_NAME, FN, ARGS) \
 else if (CHECK) { NPY_CAT(NPY_CAT(FN, _), TARGET_NAME) ARGS; }
#define DISPATCH_CALL_BASELINE_HIGH_CB(FN, ARGS) \
 else { FN NPY_EXPAND(ARGS); }

// NumPy has a macro called 'NPY_CPU_DISPATCH_DECLARE' can be used
// for forward declarations any kind of prototypes based on
// 'NPY__CPU_DISPATCH_CALL' and 'NPY__CPU_DISPATCH_BASELINE_CALL'.
// However in this example, we just handle it manually.
void  simd_whoami(const  char  *extra_info);
void  simd_whoami_AVX512F(const  char  *extra_info);
void  simd_whoami_SSE41(const  char  *extra_info);

void  trigger_me(void)
{
  // bring the auto-generated config header
  // which contains config macros 'NPY__CPU_DISPATCH_CALL' and
  // 'NPY__CPU_DISPATCH_BASELINE_CALL'.
  // it is highly recommended to include the config header before executing
  // the dispatching macros in case if there's another header in the scope.
  #include  "hello.dispatch.h"
  DISPATCH_CALL_ALL(simd_whoami,  ("all"))
  DISPATCH_CALL_HIGH(simd_whoami,  ("the highest interest"))
  // An example of including multiple config headers in the same source
  // #include "hello2.dispatch.h"
  // DISPATCH_CALL_HIGH(another_function, ("the highest interest"))
} 

// The header should be located at numpy/numpy/core/src/common/_cpu_dispatch.h
/**NOTE
 ** C definitions prefixed with "NPY_HAVE_" represent
 ** the required optimizations.
 **
 ** C definitions prefixed with 'NPY__CPU_TARGET_' are protected and
 ** shouldn't be used by any NumPy C sources.
 */
/******* baseline features *******/
/** SSE **/
#define NPY_HAVE_SSE 1
#include  <xmmintrin.h>
/** SSE2 **/
#define NPY_HAVE_SSE2 1
#include  <emmintrin.h>
/** SSE3 **/
#define NPY_HAVE_SSE3 1
#include  <pmmintrin.h>

/******* dispatch-able features *******/
#ifdef NPY__CPU_TARGET_SSSE3
  /** SSSE3 **/
  #define NPY_HAVE_SSSE3 1
  #include  <tmmintrin.h>
#endif
#ifdef NPY__CPU_TARGET_SSE41
  /** SSE41 **/
  #define NPY_HAVE_SSE41 1
  #include  <smmintrin.h>
#endif 

/*@targets avx2 avx512f vsx2 vsx3 asimd asimdhp */
// C code 

/*
 * this definition is used by NumPy utilities as suffixes for the
 * exported symbols
 */
#define NPY__CPU_TARGET_CURRENT AVX512F
/*
 * The following definitions enable
 * definitions of the dispatch-able features that are defined within the main
 * configuration header. These are definitions for the implied features.
 */
#define NPY__CPU_TARGET_SSE
#define NPY__CPU_TARGET_SSE2
#define NPY__CPU_TARGET_SSE3
#define NPY__CPU_TARGET_SSSE3
#define NPY__CPU_TARGET_SSE41
#define NPY__CPU_TARGET_POPCNT
#define NPY__CPU_TARGET_SSE42
#define NPY__CPU_TARGET_AVX
#define NPY__CPU_TARGET_F16C
#define NPY__CPU_TARGET_FMA3
#define NPY__CPU_TARGET_AVX2
#define NPY__CPU_TARGET_AVX512F
// our dispatch-able source
#include  "/the/absuolate/path/of/hello.dispatch.c" 

// hello.dispatch.c
/*@targets baseline sse42 avx512f */
#include  <stdio.h>
#include  "numpy/utils.h" // NPY_CAT, NPY_TOSTR

#ifndef NPY__CPU_TARGET_CURRENT
  // wrapping the dispatch-able source only happens to the additional optimizations
  // but if the keyword 'baseline' provided within the configuration statements,
  // the infrastructure will add extra compiling for the dispatch-able source by
  // passing it as-is to the compiler without any changes.
  #define CURRENT_TARGET(X) X
  #define NPY__CPU_TARGET_CURRENT baseline // for printing only
#else
  // since we reach to this point, that's mean we're dealing with
  // the additional optimizations, so it could be SSE42 or AVX512F
  #define CURRENT_TARGET(X) NPY_CAT(NPY_CAT(X, _), NPY__CPU_TARGET_CURRENT)
#endif
// Macro 'CURRENT_TARGET' adding the current target as suffux to the exported symbols,
// to avoid linking duplications, NumPy already has a macro called
// 'NPY_CPU_DISPATCH_CURFX' similar to it, located at
// numpy/numpy/core/src/common/npy_cpu_dispatch.h
// NOTE: we tend to not adding suffixes to the baseline exported symbols
void  CURRENT_TARGET(simd_whoami)(const  char  *extra_info)
{
  printf("I'm "  NPY_TOSTR(NPY__CPU_TARGET_CURRENT)  ", %s\n",  extra_info);
} 

#ifndef NPY__CPU_DISPATCH_EXPAND_
  // To expand the macro calls in this header
  #define NPY__CPU_DISPATCH_EXPAND_(X) X
#endif
// Undefining the following macros, due to the possibility of including config headers
// multiple times within the same source and since each config header represents
// different required optimizations according to the specified configuration
// statements in the dispatch-able source that derived from it.
#undef NPY__CPU_DISPATCH_BASELINE_CALL
#undef NPY__CPU_DISPATCH_CALL
// nothing strange here, just a normal preprocessor callback
// enabled only if 'baseline' specified within the configuration statements
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
 NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
// 'NPY__CPU_DISPATCH_CALL' is an abstract macro is used for dispatching
// the required optimizations that specified within the configuration statements.
//
// @param CHK, Expected a macro that can be used to detect CPU features
// in runtime, which takes a CPU feature name without string quotes and
// returns the testing result in a shape of boolean value.
// NumPy already has macro called "NPY_CPU_HAVE", which fits this requirement.
//
// @param CB, a callback macro that expected to be called multiple times depending
// on the required optimizations, the callback should receive the following arguments:
//  1- The pending calls of @param CHK filled up with the required CPU features,
//     that need to be tested first in runtime before executing call belong to
//     the compiled object.
//  2- The required optimization name, same as in 'NPY__CPU_TARGET_CURRENT'
//  3- Extra arguments in the macro itself
//
// By default the callback calls are sorted depending on the highest interest
// unless the policy "$keep_sort" was in place within the configuration statements
// see "Dive into the CPU dispatcher" for more clarification.
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
 NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512F)), AVX512F, __VA_ARGS__)) \
 NPY__CPU_DISPATCH_EXPAND_(CB((CHK(SSE)&&CHK(SSE2)&&CHK(SSE3)&&CHK(SSSE3)&&CHK(SSE41)), SSE41, __VA_ARGS__)) 

// NOTE: The following macros are only defined for demonstration purposes only.
// NumPy already has a collections of macros located at
// numpy/numpy/core/src/common/npy_cpu_dispatch.h, that covers all dispatching
// and declarations scenarios.

#include  "numpy/npy_cpu_features.h" // NPY_CPU_HAVE
#include  "numpy/utils.h" // NPY_CAT, NPY_EXPAND

// An example for setting a macro that calls all the exported symbols at once
// after checking if they're supported by the running machine.
#define DISPATCH_CALL_ALL(FN, ARGS) \
 NPY__CPU_DISPATCH_CALL(NPY_CPU_HAVE, DISPATCH_CALL_ALL_CB, FN, ARGS) \
 NPY__CPU_DISPATCH_BASELINE_CALL(DISPATCH_CALL_BASELINE_ALL_CB, FN, ARGS)
// The preprocessor callbacks.
// The same suffixes as we define it in the dispatch-able source.
#define DISPATCH_CALL_ALL_CB(CHECK, TARGET_NAME, FN, ARGS) \
 if (CHECK) { NPY_CAT(NPY_CAT(FN, _), TARGET_NAME) ARGS; }
#define DISPATCH_CALL_BASELINE_ALL_CB(FN, ARGS) \
 FN NPY_EXPAND(ARGS);

// An example for setting a macro that calls the exported symbols of highest
// interest optimization, after checking if they're supported by the running machine.
#define DISPATCH_CALL_HIGH(FN, ARGS) \
 if (0) {} \
 NPY__CPU_DISPATCH_CALL(NPY_CPU_HAVE, DISPATCH_CALL_HIGH_CB, FN, ARGS) \
 NPY__CPU_DISPATCH_BASELINE_CALL(DISPATCH_CALL_BASELINE_HIGH_CB, FN, ARGS)
// The preprocessor callbacks
// The same suffixes as we define it in the dispatch-able source.
#define DISPATCH_CALL_HIGH_CB(CHECK, TARGET_NAME, FN, ARGS) \
 else if (CHECK) { NPY_CAT(NPY_CAT(FN, _), TARGET_NAME) ARGS; }
#define DISPATCH_CALL_BASELINE_HIGH_CB(FN, ARGS) \
 else { FN NPY_EXPAND(ARGS); }

// NumPy has a macro called 'NPY_CPU_DISPATCH_DECLARE' can be used
// for forward declarations any kind of prototypes based on
// 'NPY__CPU_DISPATCH_CALL' and 'NPY__CPU_DISPATCH_BASELINE_CALL'.
// However in this example, we just handle it manually.
void  simd_whoami(const  char  *extra_info);
void  simd_whoami_AVX512F(const  char  *extra_info);
void  simd_whoami_SSE41(const  char  *extra_info);

void  trigger_me(void)
{
  // bring the auto-generated config header
  // which contains config macros 'NPY__CPU_DISPATCH_CALL' and
  // 'NPY__CPU_DISPATCH_BASELINE_CALL'.
  // it is highly recommended to include the config header before executing
  // the dispatching macros in case if there's another header in the scope.
  #include  "hello.dispatch.h"
  DISPATCH_CALL_ALL(simd_whoami,  ("all"))
  DISPATCH_CALL_HIGH(simd_whoami,  ("the highest interest"))
  // An example of including multiple config headers in the same source
  // #include "hello2.dispatch.h"
  // DISPATCH_CALL_HIGH(another_function, ("the highest interest"))
} 

// An example for setting a macro that calls the exported symbols of highest
// interest optimization, after checking if they're supported by the running machine.
#define DISPATCH_CALL_HIGH(FN, ARGS) \
 if (0) {} \
 NPY__CPU_DISPATCH_CALL(NPY_CPU_HAVE, DISPATCH_CALL_HIGH_CB, FN, ARGS) \
 NPY__CPU_DISPATCH_BASELINE_CALL(DISPATCH_CALL_BASELINE_HIGH_CB, FN, ARGS)
// The preprocessor callbacks
// The same suffixes as we define it in the dispatch-able source.
#define DISPATCH_CALL_HIGH_CB(CHECK, TARGET_NAME, FN, ARGS) \
 else if (CHECK) { NPY_CAT(NPY_CAT(FN, _), TARGET_NAME) ARGS; }
#define DISPATCH_CALL_BASELINE_HIGH_CB(FN, ARGS) \
 else { FN NPY_EXPAND(ARGS); }

// NumPy has a macro called 'NPY_CPU_DISPATCH_DECLARE' can be used
// for forward declarations any kind of prototypes based on
// 'NPY__CPU_DISPATCH_CALL' and 'NPY__CPU_DISPATCH_BASELINE_CALL'.
// However in this example, we just handle it manually.
void  simd_whoami(const  char  *extra_info);
void  simd_whoami_AVX512F(const  char  *extra_info);
void  simd_whoami_SSE41(const  char  *extra_info);

void  trigger_me(void)
{
  // bring the auto-generated config header
  // which contains config macros 'NPY__CPU_DISPATCH_CALL' and
  // 'NPY__CPU_DISPATCH_BASELINE_CALL'.
  // it is highly recommended to include the config header before executing
  // the dispatching macros in case if there's another header in the scope.
  #include  "hello.dispatch.h"
  DISPATCH_CALL_ALL(simd_whoami,  ("all"))
  DISPATCH_CALL_HIGH(simd_whoami,  ("the highest interest"))
  // An example of including multiple config headers in the same source
  // #include "hello2.dispatch.h"
  // DISPATCH_CALL_HIGH(another_function, ("the highest interest"))
} 
```