nvprof --query-events

tex0_cache_sector_queries: Number of texture cache 0 requests. This increments by 1 for each 32-byte access.
tex1_cache_sector_queries: Number of texture cache 1 requests. This increments by 1 for each 32-byte access.
tex0_cache_sector_misses: Number of texture cache 0 misses. This increments by 1 for each 32-byte access.
tex1_cache_sector_misses: Number of texture cache 1 misses. This increments by 1 for each 32-byte access.
elapsed_cycles_sm: Elapsed clocks

fb_subp0_read_sectors: Number of DRAM read requests to sub partition 0, increments by 1 for 32 byte access.
fb_subp1_read_sectors: Number of DRAM read requests to sub partition 1, increments by 1 for 32 byte access.
fb_subp0_write_sectors: Number of DRAM write requests to sub partition 0, increments by 1 for 32 byte access.
fb_subp1_write_sectors: Number of DRAM write requests to sub partition 1, increments by 1 for 32 byte access.

gld_inst_8bit: Total number of 8-bit global load instructions that are executed by all the threads across all thread blocks.
gld_inst_16bit: Total number of 16-bit global load instructions that are executed by all the threads across all thread blocks.
gld_inst_32bit: Total number of 32-bit global load instructions that are executed by all the threads across all thread blocks.
gld_inst_64bit: Total number of 64-bit global load instructions that are executed by all the threads across all thread blocks.
gld_inst_128bit: Total number of 128-bit global load instructions that are executed by all the threads across all thread blocks.
gst_inst_8bit: Total number of 8-bit global store instructions that are executed by all the threads across all thread blocks.
gst_inst_16bit: Total number of 16-bit global store instructions that are executed by all the threads across all thread blocks.
gst_inst_32bit: Total number of 32-bit global store instructions that are executed by all the threads across all thread blocks.
gst_inst_64bit: Total number of 64-bit global store instructions that are executed by all the threads across all thread blocks.
gst_inst_128bit: Total number of 128-bit global store instructions that are executed by all the threads across all thread blocks.

prof_trigger_00: User profiled generic trigger that can be inserted in any place of the code to collect the related information. Increments per warp.
prof_trigger_01: User profiled generic trigger that can be inserted in any place of the code to collect the related information. Increments per warp.
prof_trigger_02: User profiled generic trigger that can be inserted in any place of the code to collect the related information. Increments per warp.
prof_trigger_03: User profiled generic trigger that can be inserted in any place of the code to collect the related information. Increments per warp.
prof_trigger_04: User profiled generic trigger that can be inserted in any place of the code to collect the related information. Increments per warp.
prof_trigger_05: User profiled generic trigger that can be inserted in any place of the code to collect the related information. Increments per warp.
prof_trigger_06: User profiled generic trigger that can be inserted in any place of the code to collect the related information. Increments per warp.
prof_trigger_07: User profiled generic trigger that can be inserted in any place of the code to collect the related information. Increments per warp.
warps_launched: Number of warps launched.
inst_issued0: Number of cycles that did not issue any instruction, increments per warp.
inst_issued1: Number of cycles that issued single instruction, increments per warp.
inst_issued2: Number of cycles that issued dual instructions, increments per warp.
inst_executed: Number of instructions executed per warp.
thread_inst_executed: Number of instructions executed by the active threads. For each instruction it increments by number of threads, including predicated-off threads, that execute the instruction. It does not include replays.
not_predicated_off_thread_inst_executed: Number of instructions executed by active and not predicated off threads, does not include replays. For each instruction it increments by the number of not predicated off threads that execute this instruction.
local_store: Number of executed store instructions where state space is specified as local, increments per warp on a multiprocessor.
local_load: Number of executed load instructions where state space is specified as local, increments per warp on a multiprocessor.
shared_load: Number of executed load instructions where state space is specified as shared, increments per warp on a multiprocessor.
shared_store: Number of executed store instructions where state space is specified as shared, increments per warp on a multiprocessor.
shared_atom_cas: Number of ATOMS.CAS instructions executed per warp.
shared_atom: Number of ATOMS instructions executed per warp.
global_atom_cas: Number of ATOM.CAS instructions executed per warp.
atom_count: Number of ATOM instructions executed per warp.
global_load: Number of executed load instructions where state space is specified as global, increments per warp on a multiprocessor.
global_store: Number of executed store instructions where state space is specified as global, increments per warp on a multiprocessor.
gred_count: Number of reduction operations performed per warp.
divergent_branch: Number of divergent branches within a warp. This counter will be incremented by one if at least one thread in a warp diverges (that is, follows a different execution path) via a conditional branch.
branch: Number of branch instructions executed per warp on a multiprocessor.
active_cycles: Number of cycles a multiprocessor has at least one active warp.
active_warps: Accumulated number of active warps per cycle. For every cycle it increments by the number of active warps in the cycle which can be in the range 0 to 64.
active_ctas: Accumulated number of active blocks per cycle. For every cycle it increments by the number of active blocks in the cycle which can be in the range 0 to 32.
sm_cta_launched: Number of blocks launched
shared_ld_bank_conflict: Number of shared load bank conflict generated when the addresses for two or more shared memory load requests fall in the same memory bank.
shared_st_bank_conflict: Number of shared store bank conflict generated when the addresses for two or more shared memory store requests fall in the same memory bank.
shared_ld_transactions: Number of transactions for shared load accesses. Maximum transaction size in maxwell is 128 bytes, any warp accessing more that 128 bytes will cause multiple transactions for a shared load instruction. This also includes extra transactions caused by shared bank conflicts.
shared_st_transactions: Number of transactions for shared store accesses. Maximum transaction size in maxwell is 128 bytes, any warp accessing more that 128 bytes will cause multiple transactions for a shared store instruction. This also includes extra transactions caused by shared bank conflicts.

l2_subp0_write_sector_misses: Number of write requests sent to DRAM from slice 0 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp0_read_sector_misses: Number of read requests sent to DRAM from slice 0 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp1_write_sector_misses: Number of write requests sent to DRAM from slice 1 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp1_read_sector_misses: Number of read requests sent to DRAM from slice 1 of L2 cache. This increments by 1 for each 32-byte access.
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_subp0_write_tex_sector_queries: Number of write requests from Texture cache to slice 0 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp0_read_tex_hit_sectors: Number of read requests from Texture cache that hit in slice 0 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp0_write_tex_hit_sectors: Number of write requests from Texture cache that hit in slice 0 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp0_read_sysmem_sector_queries: Number of system memory read requests to slice 0 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp0_write_sysmem_sector_queries: Number of system memory write requests to slice 0 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp0_total_read_sector_queries: Total read requests to slice 0 of L2 cache. This includes requests from L1, Texture cache, system memory. This increments by 1 for each 32-byte access.
l2_subp0_total_write_sector_queries: Total write requests to slice 0 of L2 cache. This includes requests from L1, Texture cache, system memory. 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.
l2_subp1_write_tex_sector_queries: Number of write requests from Texture cache to slice 1 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp1_read_tex_hit_sectors: Number of read requests from Texture cache that hit in slice 1 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp1_write_tex_hit_sectors: Number of write requests from Texture cache that hit in slice 1 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp1_read_sysmem_sector_queries: Number of system memory read requests to slice 1 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp1_write_sysmem_sector_queries: Number of system memory write requests to slice 1 of L2 cache. This increments by 1 for each 32-byte access.
l2_subp1_total_read_sector_queries: Total read requests to slice 1 of L2 cache. This includes requests from L1, Texture cache, system memory. This increments by 1 for each 32-byte access.
l2_subp1_total_write_sector_queries: Total write requests to slice 1 of L2 cache. This includes requests from L1, Texture cache, system memory. This increments by 1 for each 32-byte access.