[MIPS] __builtin_bswap16 miscompilation

[markus-oberhumer]

(EDIT: I've added a new Godbolt link and updated the example to make it clear that the bug needs -march=mips32 to trigger)

Godbolt link: https://gcc.godbolt.org/z/vMGc86deh

clang 18.1.8 MIPS miscompilation in Debug mode

// clang -target mips-linux-musl -march=mips32 bug.c -o bug.out
// qemu-mips ./bug.out

unsigned bswap16_fails(unsigned v) {
    // FAILS - cast seems ignored ??
    return __builtin_bswap16((unsigned short) v);
}

unsigned bswap16_ok(unsigned v) {
    return __builtin_bswap16((unsigned short) (v & 0xffff)); // OK
}

int main(void) {
    if (bswap16_ok(0x04030201) != 0x0102)
        return 1;
    if (bswap16_fails(0x04030201) != 0x0102)
        return 2; // ERROR HERE
    return 0;
}

[llvmbot]

@llvm/issue-subscribers-backend-mips

Author: Markus F.X.J. Oberhumer (markus-oberhumer)

clang 18.1.8 MIPS miscompilation in Debug mode

// clang -target mips-linux-musl bug.c -o bug.out
// qemu-mips ./bug.out

unsigned bswap16_fails(unsigned v) {
    // FAILS - cast seems ignored ??
    return __builtin_bswap16((unsigned short) v);
}

unsigned bswap16_ok(unsigned v) {
    return __builtin_bswap16((unsigned short) (v & 0xffff)); // OK
}

int main() {
    if (bswap16_ok(0x04030201) != 0x0102)
        return 1;
    if (bswap16_fails(0x04030201) != 0x0102)
        return 2; // ERROR HERE
}

[dtcxzyw]

https://godbolt.org/z/MGWGPz1aE

bswap16_fails:                          # @bswap16_fails
        addiu   $sp, $sp, -8
        sw      $4, 4($sp)
        sll     $1, $4, 8
        andi    $2, $4, 65280
        srl     $2, $2, 8
        or      $1, $1, $2
        andi    $2, $1, 65535
        jr      $ra
        addiu   $sp, $sp, 8
bswap16_ok:                             # @bswap16_ok
        addiu   $sp, $sp, -8
        sw      $4, 4($sp)
        sll     $1, $4, 8
        andi    $2, $4, 65280
        srl     $2, $2, 8
        or      $1, $1, $2
        andi    $2, $1, 65535
        jr      $ra
        addiu   $sp, $sp, 8
main:                                   # @main
        addiu   $sp, $sp, -32
        sw      $ra, 28($sp)                    # 4-byte Folded Spill
        sw      $17, 24($sp)                    # 4-byte Folded Spill
        sw      $16, 20($sp)                    # 4-byte Folded Spill
        sw      $zero, 16($sp)
        lui     $1, 1027
        ori     $16, $1, 513
        jal     bswap16_ok
        move    $4, $16
        addiu   $17, $zero, 258
        beq     $2, $17, $BB2_2
        nop
        addiu   $1, $zero, 1
        j       $BB2_4
        sw      $1, 16($sp)
$BB2_2:                                 # %if.end
        jal     bswap16_fails
        move    $4, $16
        beq     $2, $17, $BB2_4
        nop
        addiu   $1, $zero, 2
        sw      $1, 16($sp)
$BB2_4:                                 # %if.end4
        lw      $2, 16($sp)
        lw      $16, 20($sp)                    # 4-byte Folded Reload
        lw      $17, 24($sp)                    # 4-byte Folded Reload
        lw      $ra, 28($sp)                    # 4-byte Folded Reload
        jr      $ra
        addiu   $sp, $sp, 32

I cannot reproduce this issue.

[markus-oberhumer]

@dtcxzyw Please try this link https://gcc.godbolt.org/z/cseeoKe35

This bug might be a clang/frontend issue.

(Edit: note that the bug only happens when using NO optimizations)

[dtcxzyw]

bswap16_fails(unsigned int):
        addiu   $sp, $sp, -16
        sw      $ra, 12($sp)
        sw      $fp, 8($sp)
        move    $fp, $sp
        sw      $4, 4($fp)
        lw      $1, 4($fp)
        wsbh    $1, $1
        andi    $2, $1, 65535
        move    $sp, $fp
        lw      $fp, 8($sp)
        lw      $ra, 12($sp)
        addiu   $sp, $sp, 16
        jr      $ra
        nop

bswap16_ok(unsigned int):
        addiu   $sp, $sp, -16
        sw      $ra, 12($sp)
        sw      $fp, 8($sp)
        move    $fp, $sp
        sw      $4, 4($fp)
        lw      $1, 4($fp)
        ori     $2, $zero, 65535
        and     $1, $1, $2
        wsbh    $1, $1
        andi    $2, $1, 65535
        move    $sp, $fp
        lw      $fp, 8($sp)
        lw      $ra, 12($sp)
        addiu   $sp, $sp, 16
        jr      $ra
        nop

These two pieces of assembly code look equivalent.
Can you print out the result of bswap16_fails(0x04030201)?

cc @topperc

[markus-oberhumer]

I get

bswap16_fails(0x04030201) == 0x00000302 WRONG

bswap16_ok(0x04030201) == 0x00000102 OK

(Edit: using qemu-mips)

[topperc]

Best guess is it's a problem with fast-isel. Can you try with -mllvm -fast-isel=false

[markus-oberhumer]

@topperc Indeed, -mllvm -fast-isel=false fixes the problem!

[topperc]

Can you check what you get for bswap16_fails(0x14233241)?