Load/Store Unit and 16-bit arithmetic from mali oc are not as expected

#version 450
#define LENGTH  512 // 1024

layout(set = 0, binding = 0, std140) mediump uniform ubo0 {
mediump vec4 data[LENGTH];
} _ubo0;

layout(set = 0, binding = 1, std140) mediump uniform ubo1 {
mediump vec4 data[LENGTH];
} _ubo1;

layout(location = 0) out mediump vec4 outColor;

void main() 
{
    outColor = vec4(0);
    for(int i = 0; i < LENGTH; i++)
    {
        outColor+= _ubo0.data[i];
    }
    
    //for(int i = 0; i < LENGTH; i++)
    //{
    //    outColor+= _ubo1.data[i];
    //}
}

void confusedMain() 
{
    outColor = vec4(0);
    for(int i = 0; i < LENGTH; i++)
    {
        outColor+= _ubo0.data[i];
        outColor+= _ubo1.data[i];
    }
}