What's the meaning of performance counter: lts__t_sectors_srcunit_ltcfabric

Development Tools Nsight Compute
1

Hi all,

Now I’m trying to analysis the performance counter collected by ncu of a GeMM task. And I encounter a counter: lts__t_sectors_srcunit_ltcfabric_evict_normal_lookup_miss, I look up “ltcfabric” and “srcunit” in the document (Kernel Profiling Guide :: Nsight Compute Documentation), and there’s even no apperance of these two words. I wonder what’s the meaning of this counter.

2

The ltcfabric is the communication fabric for the L2 partitions that were introduced in Ampere A100. For more information see the “A100 L2 Cache” section in the white paper https://images.nvidia.com/aem-dam/en-zz/Solutions/data-center/nvidia-ampere-architecture-whitepaper.pdf That metric would be related to L2 accesses that access the other partition.

3

lts → L2 cache slice
t → T stage on L2 cache
sectors → sectors count(what you will collect)
srcunit → source hardware unit which send data to current hardware
ltcfabric → L2 cache communication

So, srcunit_ltcfabric means another L2 partition send data to current L2 partition, and this metric will collect related the number of sectors sent.

4

That’s correct

5

Thanks, that helps me alot.