what is the difference between tex_cache_hit_rate and global_hit_rate?

I want to verify the L1/tex cache and L2 cache on my Maxwell GPU. For two simple kernels;
global void init(int n, float x, float y)
{
int index= threadIdx.x+blockDim.x
blockIdx.x;
int stride= blockDim.x
gridDim.x;
for(int i=index;i<n;i+=stride)
{
x[i]=1.0f;
y[i]=2.0f;
}
}
global
void add(int n, float *x, float y)
{
int index=threadIdx.x;
int stride=blockDim.x
gridDim.x;
for(int i= index;i<n;i+=stride)
y[i] = x[i] + y[i];
}

The nvprof gives results shown below:
Invocations Metric Name Metric Description Min Max Avg
Device “GeForce GTX TITAN X (0)”
Kernel: init(int, float*, float*)
1 global_hit_rate Global Hit Rate in unified l1/tex 0.00% 0.00% 0.00%
1 tex_cache_hit_rate Unified Cache Hit Rate 50.00% 50.00% 50.00%
Kernel: add(int, float*, float*)
1 global_hit_rate Global Hit Rate in unified l1/tex 0.00% 0.00% 0.00%
1 tex_cache_hit_rate Unified Cache Hit Rate 50.00% 50.00% 50.00%

The global_hit_rate is zero. I searched some explanations that said it is because the L1 cache is not used by default in Maxwell. Then why the tex_cache_hit_rate is not zero? Could someone help me clarify the puzzling metrics? Any idea is appreciated. Thank you very much

Hi,zzhuae

Thanks for using nvprof.
I have posted your question in our internal system. Let’s wait dev’s update.

Best Regards
VeraJ

Thank you very much. looking forward to your reply.

Hi, veraj,

Is there any new update in your internal system?

[quote]

Hi,zzhuae

I’m sorry I haven’t got the response.
I’ll push today.