Question

    the following code works fine on linux-x86, darwin-x86, but not for ios-armv7.

    the right output should be: 
        m[0]: 0.500000, v: 0.500000
        m[1]: 0.500000, v: 0.500000
        m[2]: 0.500000, v: 0.500000
        m[3]: 0.500000, v: 0.500000
        m[4]: 0.500000, v: 0.500000

    but I found the wrong output:
        m[0]: 0.500000, v: 0.500000
        m[1]: 0.500000, v: 0.000000
        m[2]: 0.500000, v: 0.000000
        m[3]: 0.500000, v: 0.000000
        m[4]: 0.500000, v: 0.000000

    I also found the stange when it's built for ios-armv7:

    [a] remove function 'func', move the function body to 'main' function, it works fine
    [b] declare the array 'm[5]' as 'double m[5]', it works fine
    [c] set the variable 'v' as 'v = 0.5 or v = sqrt(2.0f/8)', it works fine
    [d] if the gcc optimize option is '-O0', it works fine, but when it's '-O1 or -O2', wrong output occurs


    My iPad1 was cracked, so I can cross-compile a executable on my MacBook Air, and 'scp' the executable to iPad1 and run it. The following is details:

    1. cross-compile a executable on Mac:
    /Applications/Xcode.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/usr/bin/llvm-gcc -O1 -Wall -arch armv7 -mcpu=cortex-a8 -isysroot /Applications/Xcode.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS6.1.sdk -I/Applications/Xcode.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS6.1.sdk/usr/include -D__IPHONE_OS__ -miphoneos-version-min=4.0 foo.c

    2. 'scp' the executable to iPad
    scp a.out mobile@192.168.1.106:~

    3. 'ssh' to iPad
    ssh mobile@192.168.1.106 #the default password is 'alpine'

    4. run a.out on iPad
    ./a.out

#include <stdio.h>
#include <math.h>

int
func(int n) /* [a] */
{
    int i;
    float m[5]; /* [b] */
    double v;

    v = sqrt(2.0f/n); /* [c] */

    for(i=0;i<5;++i) {
        m[i]=v;
        printf("m[%d]: %f, v: %f\n", i, m[i], v);
    }

    return 0;
}


int
main(int argc, char **argv)
{
    return func(8);
}

您还可以在https://gist.github.com/ashun/5992120

上找到整个代码

以下是装配。你可以在命令'vim -d'

的帮助下找到差异

汇编前面的代码，将数组'm [5]'声明为'double m [5]'

        .section    __TEXT,__text,regular,pure_instructions
        .section    __TEXT,__textcoal_nt,coalesced,pure_instructions
        .section    __TEXT,__const_coal,coalesced
        .section    __TEXT,__picsymbolstub4,symbol_stubs,none,16
        .section    __TEXT,__StaticInit,regular,pure_instructions
        .syntax unified
        .section    __TEXT,__text,regular,pure_instructions
        .globl  _func
        .align  2
        .code   16
        .thumb_func _func
    _func:
        push    {r4, r5, r6, r7, lr}
        add r7, sp, #12
        str r8, [sp, #-4]!
        sub sp, #8
        vmov.f32    s0, #2.000000e+00
        movw    r8, :lower16:(L_.str-(LPC0_0+4))
        vmov    s2, r0
        movt    r8, :upper16:(L_.str-(LPC0_0+4))
        vcvt.f32.s32    d1, d1
    LPC0_0:
        add r8, pc
        movs    r4, #0
        vdiv.f32    s0, s0, s2
        vsqrt.f32   s0, s0
        vcvt.f64.f32    d16, s0
        vmov    r5, r6, d16
    LBB0_1:
        mov r1, r4
        mov r0, r8
        mov r2, r5
        mov r3, r6
        vstr.64 d16, [sp]
        adds    r4, #1
        blx _printf
        cmp r4, #5
        bne LBB0_1
        movs    r0, #0
        add sp, #8
        ldr r8, [sp], #4
        pop {r4, r5, r6, r7, pc}

        .globl  _main
        .align  2
        .code   16
        .thumb_func _main
    _main:
        push    {r7, lr}
        mov r7, sp
        movs    r0, #8
        bl  _func
        movs    r0, #0
        pop {r7, pc}

        .section    __TEXT,__cstring,cstring_literals
    L_.str:
        .asciz   "m[%d]: %f, v: %f\n"


    .subsections_via_symbols

汇编前面的代码，将数组'm [5]'声明为'double m [5]'

        .section    __TEXT,__text,regular,pure_instructions
        .section    __TEXT,__textcoal_nt,coalesced,pure_instructions
        .section    __TEXT,__const_coal,coalesced
        .section    __TEXT,__picsymbolstub4,symbol_stubs,none,16
        .section    __TEXT,__StaticInit,regular,pure_instructions
        .syntax unified
        .section    __TEXT,__text,regular,pure_instructions
        .globl  _func
        .align  2
        .code   16
        .thumb_func _func
    _func:
        push    {r4, r5, r6, r7, lr}
        add r7, sp, #12
        str r8, [sp, #-4]!
        **vpush {d8}**
        sub sp, #8
        vmov.f32    s0, #2.000000e+00
        movw    r8, :lower16:(L_.str-(LPC0_0+4))
        vmov    s2, r0
        movt    r8, :upper16:(L_.str-(LPC0_0+4))
        vcvt.f32.s32    d1, d1
    LPC0_0:
        add r8, pc
        movs    r4, #0
        vdiv.f32    s0, s0, s2
        vcvt.f64.f32    d16, s0
        vsqrt.f64   d8, d16
        vmov    r5, r6, d8
    LBB0_1:
        mov r1, r4
        mov r0, r8
        mov r2, r5
        mov r3, r6
        vstr.64 d8, [sp]
        adds    r4, #1
        blx _printf
        cmp r4, #5
        bne LBB0_1
        movs    r0, #0
        add sp, #8
        vpop    {d8}
        ldr r8, [sp], #4
        pop {r4, r5, r6, r7, pc}

        .globl  _main
        .align  2
        .code   16
        .thumb_func _main
    _main:
        push    {r7, lr}
        mov r7, sp
        movs    r0, #8
        bl  _func
        movs    r0, #0
        pop {r7, pc}

        .section    __TEXT,__cstring,cstring_literals
    L_.str:
        .asciz   "m[%d]: %f, v: %f\n"


    .subsections_via_symbols

Answer 1

目前尚不清楚哪个程序集出错，因为它们都标记为'将数组m[5]声明为double m[5]'，遗憾的是我没有硬件或交叉编译器来重现您的问题

值得注意的是，两个汇编代码中的循环非常相似。唯一的区别是v位于第一个d16和第二个d8。传递给v的{{1}}位于printf的两个循环中，并在调用(r5,r6)之前正确复制到(r2,r3)。对于可变函数，与非可变函数相反，浮点寄存器不应用于传递参数。因此两个循环看起来都是正确的。

我能想到的唯一解释是用于编译代码的ABI与包含printf的库的ABI不匹配。特别是考虑到编译后的代码来自交叉编译器，我假设printf来自系统上的动态库。由于printf被称为符合ARM的EABI，我认为该错误位于库的printf。

如果您的交叉编译器允许静态链接，您可以尝试这样做，因为您将使用与编译器对应的库。当然应用程序变得更大，但它至少可以证实对printf的实现的怀疑。您可能想要检查库是否使用符合EABI的编译器进行编译。如果您可以在iPad上的调试器上单步执行printf，那么您应该能够确定printf从哪里获取其浮点参数。它应该从printf开始。

不幸的是，我不能给出一个确凿的答案，但我希望我的进一步调查指示是有帮助的。

这可能是ios-armv7的llvm-gcc的错误，我无法解释

1 个答案: