Ray*_*out 8 python assembly linker numba
在一个奇怪的事件中，我最终陷入了以下困境，我使用以下 Python 代码将 Numba 生成的程序集写入文件：
@jit(nopython=True, nogil=True)
def six():
return 6
with open("six.asm", "w") as f:
for k, v in six.inspect_asm().items():
f.write(v)
汇编代码已成功写入文件，但我不知道如何执行它。我尝试了以下方法：
$ as -o six.o six.asm
$ ld six.o -o six.bin
$ chmod +x six.bin
$ ./six.bin
但是，链接步骤失败并显示以下内容：
ld: warning: cannot find entry symbol _start; defaulting to 00000000004000f0
six.o: In function `cpython::__main__::six$241':
<string>:(.text+0x20): undefined reference to `PyArg_UnpackTuple'
<string>:(.text+0x47): undefined reference to `PyEval_SaveThread'
<string>:(.text+0x53): undefined reference to `PyEval_RestoreThread'
<string>:(.text+0x62): undefined reference to `PyLong_FromLongLong'
<string>:(.text+0x74): undefined reference to `PyExc_RuntimeError'
<string>:(.text+0x88): undefined reference to `PyErr_SetString'
我怀疑 Numba 和/或 Python 标准库需要与生成的目标文件动态链接才能成功运行，但我不确定如何完成（如果它甚至可以在第一个地方）。
我还尝试了以下将中间 LLVM 代码写入文件而不是程序集的方法：
ld: warning: cannot find entry symbol _start; defaulting to 00000000004000f0
six.o: In function `cpython::__main__::six$241':
<string>:(.text+0x20): undefined reference to `PyArg_UnpackTuple'
<string>:(.text+0x47): undefined reference to `PyEval_SaveThread'
<string>:(.text+0x53): undefined reference to `PyEval_RestoreThread'
<string>:(.text+0x62): undefined reference to `PyLong_FromLongLong'
<string>:(.text+0x74): undefined reference to `PyExc_RuntimeError'
<string>:(.text+0x88): undefined reference to `PyErr_SetString'
进而
with open("six.ll", "w") as f:
for k, v in six.inspect_llvm().items():
f.write(v)
但这也失败了，并出现以下错误：
'main' function not found in module.
更新：
事实证明，存在一个实用程序来查找相关标志以传递给ld命令以动态链接 Python 标准库。
$ lli six.ll
退货
-L/Users/rayan/anaconda3/lib/python3.7/config-3.7m-darwin -lpython3.7m -ldl -framework CoreFoundation
再次运行以下命令，这次使用正确的标志：
'main' function not found in module.
我现在得到
ld: warning: No version-min specified on command line
ld: entry point (_main) undefined. for inferred architecture x86_64
我曾尝试_main在程序集文件中添加标签，但这似乎没有任何作用。关于如何定义入口点的任何想法？
更新 2：
这是有用的汇编代码，似乎目标函数是带有标签的函数_ZN8__main__7six$241E：
.text
.file "<string>"
.globl _ZN8__main__7six$241E
.p2align 4, 0x90
.type _ZN8__main__7six$241E,@function
_ZN8__main__7six$241E:
movq $6, (%rdi)
xorl %eax, %eax
retq
.Lfunc_end0:
.size _ZN8__main__7six$241E, .Lfunc_end0-_ZN8__main__7six$241E
.globl _ZN7cpython8__main__7six$241E
.p2align 4, 0x90
.type _ZN7cpython8__main__7six$241E,@function
_ZN7cpython8__main__7six$241E:
.cfi_startproc
pushq %rax
.cfi_def_cfa_offset 16
movq %rsi, %rdi
movabsq $.const.six, %rsi
movabsq $PyArg_UnpackTuple, %r8
xorl %edx, %edx
xorl %ecx, %ecx
xorl %eax, %eax
callq *%r8
testl %eax, %eax
je .LBB1_3
movabsq $_ZN08NumbaEnv8__main__7six$241E, %rax
cmpq $0, (%rax)
je .LBB1_2
movabsq $PyEval_SaveThread, %rax
callq *%rax
movabsq $PyEval_RestoreThread, %rcx
movq %rax, %rdi
callq *%rcx
movabsq $PyLong_FromLongLong, %rax
movl $6, %edi
popq %rcx
.cfi_def_cfa_offset 8
jmpq *%rax
.LBB1_2:
.cfi_def_cfa_offset 16
movabsq $PyExc_RuntimeError, %rdi
movabsq $".const.missing Environment", %rsi
movabsq $PyErr_SetString, %rax
callq *%rax
.LBB1_3:
xorl %eax, %eax
popq %rcx
.cfi_def_cfa_offset 8
retq
.Lfunc_end1:
.size _ZN7cpython8__main__7six$241E, .Lfunc_end1-_ZN7cpython8__main__7six$241E
.cfi_endproc
.globl cfunc._ZN8__main__7six$241E
.p2align 4, 0x90
.type cfunc._ZN8__main__7six$241E,@function
cfunc._ZN8__main__7six$241E:
movl $6, %eax
retq
.Lfunc_end2:
.size cfunc._ZN8__main__7six$241E, .Lfunc_end2-cfunc._ZN8__main__7six$241E
.type _ZN08NumbaEnv8__main__7six$241E,@object
.comm _ZN08NumbaEnv8__main__7six$241E,8,8
.type .const.six,@object
.section .rodata,"a",@progbits
.const.six:
.asciz "six"
.size .const.six, 4
.type ".const.missing Environment",@object
.p2align 4
.const.missing Environment:
.asciz "missing Environment"
.size ".const.missing Environment", 20
.section ".note.GNU-stack","",@progbits
在浏览[PyData.Numba]: Numba doc s，以及一些调试、试验和错误后，我得出一个结论：你似乎偏离了你的追求之路（正如评论中所指出的那样）。
Numba将Python代码（函数）转换为机器代码（原因很明显：速度）。它可以即时完成所有操作（在运行过程中进行转换、构建、插入），程序员只需要将函数修饰为例如 @numba.jit（[PyData.Numba]：即时编译）。
您遇到的行为是正确的。所述分派器对象（通过装饰用6个函数）仅生成用于函数本身（它是没有（组装）代码主要存在，作为代码在当前过程（执行的Python解释器的主要功能））。因此，链接器抱怨没有主符号是正常的。这就像编写一个只包含以下内容的C文件：
int six() {
return 6;
}
为了使事情正常工作，您必须：
将.asm文件构建为.o（对象）文件（完成）
包含#1 中的.o文件。进入一个图书馆，可以
该库将在（最终）可执行文件中链接。此步骤是可选的，因为您可以直接使用.o文件
构建另一个定义main 的文件（并调用6 - 我认为这是整个目的）到.o文件中。由于我对汇编不是很满意，所以我用C编写了它
将 2 个实体（来自#2. ( #1. ) 和#3.）连接在一起
作为替代方案，您可以查看[PyData.Numba]：提前编译代码，但请记住，它会生成一个Python（扩展）模块。
回到当前的问题。在Ubuntu 18.04 64bit上进行了测试。
代码00.py：
#!/usr/bin/env python
import sys
import math
import numba
@numba.jit(nopython=True, nogil=True)
def six():
return 6
def main(*argv):
six() # Call the function(s), otherwise `inspect_asm()` would return empty dict
speed_funcs = [
(six, numba.int32()),
]
for func, _ in speed_funcs:
file_name_asm = "numba_{0:s}_{1:s}_{2:03d}_{3:02d}{4:02d}{5:02d}.asm".format(func.__name__, sys.platform, int(round(math.log2(sys.maxsize))) + 1, *sys.version_info[:3])
asm = func.inspect_asm()
print("Writing to {0:s}:".format(file_name_asm))
with open(file_name_asm, "wb") as fout:
for k, v in asm.items():
print(" {0:}".format(k))
fout.write(v.encode())
if __name__ == "__main__":
print("Python {0:s} {1:d}bit on {2:s}\n".format(" ".join(item.strip() for item in sys.version.split("\n")), 64 if sys.maxsize > 0x100000000 else 32, sys.platform))
main(*sys.argv[1:])
print("\nDone.")
主00.c：
#include <stdio.h>
#include <dlfcn.h>
//#define SYMBOL_SIX "_ZN8__main__7six$241E"
#define SYMBOL_SIX "cfunc._ZN8__main__7six$241E"
typedef int (*SixFuncPtr)();
int main() {
void *pMod = dlopen("./libnumba_six_linux.so", RTLD_LAZY);
if (!pMod) {
printf("Error (%s) loading module\n", dlerror());
return -1;
}
SixFuncPtr pSixFunc = dlsym(pMod, SYMBOL_SIX);
if (!pSixFunc)
{
printf("Error (%s) loading function\n", dlerror());
dlclose(pMod);
return -2;
}
printf("six() returned: %d\n", (*pSixFunc)());
dlclose(pMod);
return 0;
}
构建.sh：
CC=gcc
LIB_BASE_NAME=numba_six_linux
FLAG_LD_LIB_NUMBALINUX="-Wl,-L. -Wl,-l${LIB_BASE_NAME}"
FLAG_LD_LIB_PYTHON="-Wl,-L/usr/lib/python3.7/config-3.7m-x86_64-linux-gnu -Wl,-lpython3.7m"
rm -f *.asm *.o *.a *.so *.exe
echo Generate .asm
python3 code00.py
echo Assemble
as -o ${LIB_BASE_NAME}.o ${LIB_BASE_NAME}_064_030705.asm
echo Link library
LIB_NUMBA="./lib${LIB_BASE_NAME}.so"
#ar -scr ${LIB_NUMBA} ${LIB_BASE_NAME}.o
${CC} -o ${LIB_NUMBA} -shared ${LIB_BASE_NAME}.o ${FLAG_LD_LIB_PYTHON}
echo Dump library contents
nm -S ${LIB_NUMBA}
#objdump -t ${LIB_NUMBA}
echo Compile and link executable
${CC} -o main00.exe main00.c -ldl
echo Exit script
输出：
Run Code Online (Sandbox Code Playgroud)(py_venv_pc064_03.07.05_test0) [cfati@cfati-ubtu-18-064-00:~/Work/Dev/StackOverflow/q061678226]> ~/sopr.sh *** Set shorter prompt to better fit when pasted in StackOverflow (or other) pages *** [064bit prompt]> [064bit prompt]> ls build.sh code00.py main00.c [064bit prompt]> [064bit prompt]> ./build.sh Generate .asm Python 3.7.5 (default, Nov 7 2019, 10:50:52) [GCC 8.3.0] 64bit on linux Writing to numba_six_linux_064_030705.asm: () Done. Assemble Link library Dump library contents 0000000000201020 B __bss_start 00000000000008b0 0000000000000006 T cfunc._ZN8__main__7six$241E 0000000000201020 0000000000000001 b completed.7698 00000000000008e0 0000000000000014 r .const.missing Environment 00000000000008d0 0000000000000004 r .const.six w __cxa_finalize 0000000000000730 t deregister_tm_clones 00000000000007c0 t __do_global_dtors_aux 0000000000200e58 t __do_global_dtors_aux_fini_array_entry 0000000000201018 d __dso_handle 0000000000200e60 d _DYNAMIC 0000000000201020 D _edata 0000000000201030 B _end 00000000000008b8 T _fini 0000000000000800 t frame_dummy 0000000000200e50 t __frame_dummy_init_array_entry 0000000000000990 r __FRAME_END__ 0000000000201000 d _GLOBAL_OFFSET_TABLE_ w __gmon_start__ 00000000000008f4 r __GNU_EH_FRAME_HDR 00000000000006f0 T _init w _ITM_deregisterTMCloneTable w _ITM_registerTMCloneTable U PyArg_UnpackTuple U PyErr_SetString U PyEval_RestoreThread U PyEval_SaveThread U PyExc_RuntimeError U PyLong_FromLongLong 0000000000000770 t register_tm_clones 0000000000201020 d __TMC_END__ 0000000000201028 0000000000000008 B _ZN08NumbaEnv8__main__7six$241E 0000000000000820 0000000000000086 T _ZN7cpython8__main__7six$241E 0000000000000810 000000000000000a T _ZN8__main__7six$241E Compile and link executable Exit script [064bit prompt]> [064bit prompt]> ls build.sh code00.py libnumba_six_linux.so main00.c main00.exe numba_six_linux_064_030705.asm numba_six_linux.o [064bit prompt]> [064bit prompt]> # Run the executable [064bit prompt]> [064bit prompt]> ./main00.exe six() returned: 6 [064bit prompt]>
同时发布（因为它很重要）numba_six_linux_064_030705.asm：
.text
.file "<string>"
.globl _ZN8__main__7six$241E
.p2align 4, 0x90
.type _ZN8__main__7six$241E,@function
_ZN8__main__7six$241E:
movq $6, (%rdi)
xorl %eax, %eax
retq
.Lfunc_end0:
.size _ZN8__main__7six$241E, .Lfunc_end0-_ZN8__main__7six$241E
.globl _ZN7cpython8__main__7six$241E
.p2align 4, 0x90
.type _ZN7cpython8__main__7six$241E,@function
_ZN7cpython8__main__7six$241E:
.cfi_startproc
pushq %rax
.cfi_def_cfa_offset 16
movq %rsi, %rdi
movabsq $.const.six, %rsi
movabsq $PyArg_UnpackTuple, %r8
xorl %edx, %edx
xorl %ecx, %ecx
xorl %eax, %eax
callq *%r8
testl %eax, %eax
je .LBB1_3
movabsq $_ZN08NumbaEnv8__main__7six$241E, %rax
cmpq $0, (%rax)
je .LBB1_2
movabsq $PyEval_SaveThread, %rax
callq *%rax
movabsq $PyEval_RestoreThread, %rcx
movq %rax, %rdi
callq *%rcx
movabsq $PyLong_FromLongLong, %rax
movl $6, %edi
popq %rcx
.cfi_def_cfa_offset 8
jmpq *%rax
.LBB1_2:
.cfi_def_cfa_offset 16
movabsq $PyExc_RuntimeError, %rdi
movabsq $".const.missing Environment", %rsi
movabsq $PyErr_SetString, %rax
callq *%rax
.LBB1_3:
xorl %eax, %eax
popq %rcx
.cfi_def_cfa_offset 8
retq
.Lfunc_end1:
.size _ZN7cpython8__main__7six$241E, .Lfunc_end1-_ZN7cpython8__main__7six$241E
.cfi_endproc
.globl cfunc._ZN8__main__7six$241E
.p2align 4, 0x90
.type cfunc._ZN8__main__7six$241E,@function
cfunc._ZN8__main__7six$241E:
movl $6, %eax
retq
.Lfunc_end2:
.size cfunc._ZN8__main__7six$241E, .Lfunc_end2-cfunc._ZN8__main__7six$241E
.type _ZN08NumbaEnv8__main__7six$241E,@object
.comm _ZN08NumbaEnv8__main__7six$241E,8,8
.type .const.six,@object
.section .rodata,"a",@progbits
.const.six:
.asciz "six"
.size .const.six, 4
.type ".const.missing Environment",@object
.p2align 4
".const.missing Environment":
.asciz "missing Environment"
.size ".const.missing Environment", 20
.section ".note.GNU-stack","",@progbits
注意事项：
numba_six_linux_064_030705.asm（以及从它派生的所有内容）包含六函数的代码。实际上，有一堆符号（在OSX 上，您也可以使用 native otool -T），例如：
cfunc._ZN8__main__7six$241E - ( C ) 函数本身
_ZN7cpython8__main__7six$241E - Python包装器：
nopython=True在这种情况下无效此外，这些符号的主要部分不是指可执行入口点（main函数），而是指Python模块的顶级命名空间（__main__）。毕竟，这段代码应该是从Python运行的
由于C普通函数的名称中包含一个点( . )，我无法直接从C调用它（因为它是一个无效的标识符名称），所以我不得不加载（.so和）函数手动（dlopen / dlsym），导致比简单地调用函数更多的代码。
我没有尝试过，但我认为对生成的.asm文件进行以下（手动）更改将简化工作是有意义的：
感谢@PeterCordes，他分享了我遗漏的确切信息（[GNU.GCC]: Controlling Names Used in Assembler Code），这是一个更简单的版本。
主01.c：
(py_venv_pc064_03.07.05_test0) [cfati@cfati-ubtu-18-064-00:~/Work/Dev/StackOverflow/q061678226]> ~/sopr.sh
*** Set shorter prompt to better fit when pasted in StackOverflow (or other) pages ***
[064bit prompt]>
[064bit prompt]> ls
build.sh code00.py main00.c
[064bit prompt]>
[064bit prompt]> ./build.sh
Generate .asm
Python 3.7.5 (default, Nov 7 2019, 10:50:52) [GCC 8.3.0] 64bit on linux
Writing to numba_six_linux_064_030705.asm:
()
Done.
Assemble
Link library
Dump library contents
0000000000201020 B __bss_start
00000000000008b0 0000000000000006 T cfunc._ZN8__main__7six$241E
0000000000201020 0000000000000001 b completed.7698
00000000000008e0 0000000000000014 r .const.missing Environment
00000000000008d0 0000000000000004 r .const.six
w __cxa_finalize
0000000000000730 t deregister_tm_clones
00000000000007c0 t __do_global_dtors_aux
0000000000200e58 t __do_global_dtors_aux_fini_array_entry
0000000000201018 d __dso_handle
0000000000200e60 d _DYNAMIC
0000000000201020 D _edata
0000000000201030 B _end
00000000000008b8 T _fini
0000000000000800 t frame_dummy
0000000000200e50 t __frame_dummy_init_array_entry
0000000000000990 r __FRAME_END__
0000000000201000 d _GLOBAL_OFFSET_TABLE_
w __gmon_start__
00000000000008f4 r __GNU_EH_FRAME_HDR
00000000000006f0 T _init
w _ITM_deregisterTMCloneTable
w _ITM_registerTMCloneTable
U PyArg_UnpackTuple
U PyErr_SetString
U PyEval_RestoreThread
U PyEval_SaveThread
U PyExc_RuntimeError
U PyLong_FromLongLong
0000000000000770 t register_tm_clones
0000000000201020 d __TMC_END__
0000000000201028 0000000000000008 B _ZN08NumbaEnv8__main__7six$241E
0000000000000820 0000000000000086 T _ZN7cpython8__main__7six$241E
0000000000000810 000000000000000a T _ZN8__main__7six$241E
Compile and link executable
Exit script
[064bit prompt]>
[064bit prompt]> ls
build.sh code00.py libnumba_six_linux.so main00.c main00.exe numba_six_linux_064_030705.asm numba_six_linux.o
[064bit prompt]>
[064bit prompt]> # Run the executable
[064bit prompt]>
[064bit prompt]> ./main00.exe
six() returned: 6
[064bit prompt]>
输出：
Run Code Online (Sandbox Code Playgroud)[064bit prompt]> # Resume from previous point + main01.c [064bit prompt]> [064bit prompt]> ls build.sh code00.py libnumba_six_linux.so main00.c main00.exe main01.c numba_six_linux_064_030705.asm numba_six_linux.o [064bit prompt]> [064bit prompt]> ar -scr libnumba_six_linux.a numba_six_linux.o [064bit prompt]> [064bit prompt]> gcc -o main01.exe main01.c ./libnumba_six_linux.a -Wl,-L/usr/lib/python3.7/config-3.7m-x86_64-linux-gnu -Wl,-lpython3.7m [064bit prompt]> [064bit prompt]> ls build.sh code00.py libnumba_six_linux.a libnumba_six_linux.so main00.c main00.exe main01.c main01.exe numba_six_linux_064_030705.asm numba_six_linux.o [064bit prompt]> [064bit prompt]> ./main01.exe six() returned: 6 [064bit prompt]>