# Profile TX2 cache misses

**URL:** <https://forums.developer.nvidia.com/t/profile-tx2-cache-misses/70926>\
**Category:** Jetson TX2\
**Created:** [February 27, 2019, 11:57am UTC](https://forums.developer.nvidia.com/t/profile-tx2-cache-misses/70926 "2019-02-27T11:57:23Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![HeroGian](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@HeroGian](https://forums.developer.nvidia.com/u/HeroGian)\
**Post date:** [February 27, 2019, 11:57am UTC](https://forums.developer.nvidia.com/t/profile-tx2-cache-misses/70926/1 "2019-02-27T11:57:23Z")

</div>

Hello,

I’m trying to profile the LLC cache misses of the GPU, generated by a CUDA kernel that runs on my Tegra X2.

There are some documentation and tool for performing this test?

thanks

---

<div class="post-metadata">

**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\
**Post date:** [March 4, 2019, 2:23am UTC](https://forums.developer.nvidia.com/t/profile-tx2-cache-misses/70926/2 "2019-03-04T02:23:56Z")

</div>

Hi,

You can find the nvprof document here: [url][Profiler :: CUDA Toolkit Documentation](https://docs.nvidia.com/cuda/profiler-users-guide/index.html#nvprof-command-line-options%5B/url%5D)  
But please noticed that not all profiling supports Jetson platform since some hardware design issue.

Thanks.

---

<div class="post-metadata">

**Author:** ![HeroGian](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@HeroGian](https://forums.developer.nvidia.com/u/HeroGian)\
**Post date:** [March 11, 2019, 4:36pm UTC](https://forums.developer.nvidia.com/t/profile-tx2-cache-misses/70926/3 "2019-03-11T16:36:16Z")

</div>

> [@AastaLLL](#):
>
> Hi,
> 
> You can find the _nvprof_ document here: [https://docs.nvidia.com/cuda/profiler-users-guide/index.html#nvprof-command-line-options](https://docs.nvidia.com/cuda/profiler-users-guide/index.html#nvprof-command-line-options)  
> But please noticed that not all profiling supports Jetson platform since some hardware design issue.
> 
> Thanks.

Thanks for the answer,

I read the documentation of nvprof and I think that the right metric for my experiment is the _l2\_l1\_read\_hit\_rate_, but if I run the query metric ( _nvprof --query-metrics_ ), it does not return the _l2\_l1\_read\_hit\_rate_ metric.  
Then I suppose that it is not possibile to profile L2 cache misses on Jetson TX2, right?

---

<div class="post-metadata">

**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\
**Post date:** [March 15, 2019, 7:28am UTC](https://forums.developer.nvidia.com/t/profile-tx2-cache-misses/70926/4 "2019-03-15T07:28:00Z")

</div>

Hi,

Could you also check if NVidia System profiler can meet your requirement?  
[https://docs.nvidia.com/nvidia-system-profiler/index.html](https://docs.nvidia.com/nvidia-system-profiler/index.html)  
\>\> Sampling counters from ARM PMU (Performance Monitoring Unit). Information such as cache misses gets statistically correlated with function execution.  
   
Thanks.

---

<div class="post-metadata">

**Author:** ![nadeemm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nadeemm/32/367020_2.png) [@nadeemm](https://forums.developer.nvidia.com/u/nadeemm)\
**Post date:** [October 18, 2021, 6:31pm UTC](https://forums.developer.nvidia.com/t/profile-tx2-cache-misses/70926/5 "2021-10-18T18:31:47Z")

</div>

Closed on October 18, 2021, 6:31pm UTC