What is slice (as shown by nvprof --query-events)?

When I execute command ‘$ nvprof --query-events’, among the events, I see the following:

l2_subp0_read_tex_sector_queries: Number of read requests from Texture cache to slice 0 of L2 cache. This increments by 1 for each 32-byte access.

l2_subp1_read_tex_sector_queries: Number of read requests from Texture cache to slice 1 of L2 cache. This increments by 1 for each 32-byte access.

So what are the slice 0/1 of L2 cache? How do they improve/effect performance?

Also, can someone clarify that ‘system memory’ refers to GPU DRAMs, correct?

Hi,sakjain92

Each l2 unit has different number of sub partition and we call each sub-partition as slice.

-------------Also, can someone clarify that ‘system memory’ refers to GPU DRAMs, correct?
No, system memory doesn’t represent GPU DRAM. It represent CPU memory, fb(frame buffer) represent GPU DRAM