霓虹灯代码没有优化

Posted 2021-04-21

我为android NDK编写了一些简单的Neon内在函数。 这是代码：

float32x4_t vec1;
float32x4_t vec2;
float32x4_t mulneon;
vec1 = vld1q_f32(&a1[0]);
vec2 = vld1q_f32(&a2[0]);
mulneon = vmulq_f32(vec1, vec2);

我期待看到一些像

vld1.32 {v0} ...
vld1.32 {v1} ...
vmul.f32 v0, v1, v0

但我看到的是很多ldr和str指令后跟vmul。见下文。我的问题是android版本不支持vld1吗？或者我是否需要启用其他一些优化

0x7f6ae33a20 <+792>:  ldr    x8, [sp, #0x198]
0x7f6ae33a24 <+796>:  ldr    q0, [x8]
0x7f6ae33a28 <+800>:  str    q0, [sp, #0x120]
0x7f6ae33a2c <+804>:  ldr    q0, [sp, #0x120]
0x7f6ae33a30 <+808>:  str    q0, [sp, #0x110]
0x7f6ae33a34 <+812>:  ldr    q0, [sp, #0x110]
0x7f6ae33a38 <+816>:  str    q0, [sp, #0x180]
0x7f6ae33a3c <+820>:  ldr    x8, [sp, #0x1a0]
0x7f6ae33a40 <+824>:  ldr    q0, [x8]
0x7f6ae33a44 <+828>:  str    q0, [sp, #0x100]
0x7f6ae33a48 <+832>:  ldr    q0, [sp, #0x100]
0x7f6ae33a4c <+836>:  str    q0, [sp, #0xf0]
0x7f6ae33a50 <+840>:  ldr    q0, [sp, #0xf0]
0x7f6ae33a54 <+844>:  str    q0, [sp, #0x170]
0x7f6ae33a58 <+848>:  ldr    x8, [sp, #0x228]
0x7f6ae33a5c <+852>:  ldr    x10, [sp, #0x198]
0x7f6ae33a60 <+856>:  add    x8, x10, x8, lsl #2
0x7f6ae33a64 <+860>:  str    x8, [sp, #0x198]
0x7f6ae33a68 <+864>:  ldr    x8, [sp, #0x250]
0x7f6ae33a6c <+868>:  ldr    x10, [sp, #0x1a0]
0x7f6ae33a70 <+872>:  add    x8, x10, x8, lsl #2
0x7f6ae33a74 <+876>:  str    x8, [sp, #0x1a0]
0x7f6ae33a78 <+880>:  ldr    q0, [sp, #0x170]
0x7f6ae33a7c <+884>:  str    q0, [sp, #0xe0]
0x7f6ae33a80 <+888>:  ldr    x8, [sp, #0x1a0]
0x7f6ae33a84 <+892>:  ldr    q0, [sp, #0xe0]
0x7f6ae33a88 <+896>:  ldr    s1, [x8]
0x7f6ae33a8c <+900>:  mov    v2.16b, v1.16b
0x7f6ae33a90 <+904>:  ins    v0.s[3], v2.s[0]
0x7f6ae33a94 <+908>:  str    q0, [sp, #0xd0]
0x7f6ae33a98 <+912>:  ldr    q0, [sp, #0xd0]
0x7f6ae33a9c <+916>:  str    q0, [sp, #0xc0]
0x7f6ae33aa0 <+920>:  ldr    q0, [sp, #0xc0]
0x7f6ae33aa4 <+924>:  str    q0, [sp, #0x170]
0x7f6ae33aa8 <+928>:  ldr    q0, [sp, #0x180]
0x7f6ae33aac <+932>:  ldr    q2, [sp, #0x170]
0x7f6ae33ab0 <+936>:  stur   q0, [x29, #-0xa0]
0x7f6ae33ab4 <+940>:  stur   q2, [x29, #-0xb0]
0x7f6ae33ab8 <+944>:  ldur   q0, [x29, #-0xa0]
0x7f6ae33abc <+948>:  ldur   q2, [x29, #-0xb0]
0x7f6ae33ac0 <+952>:  fmul   v0.4s, v0.4s, v2.4s

答案

问题：

• 看来你是在调试模式下编译的。
• 似乎数组是全局变量或非静态局部常量。
• Android Studio内置的Clang（v4.9）首先从内在函数生成高效的机器代码非常糟糕。

解：

• 将构建类型更改为Release
• 仅使用局部变量，尤其是内部循环，如果常量数组是本地变量，则将它们声明为静态变量。
• 不要将Clang用于内在函数，或者更好，不要使用内在函数。