Skip to content

Instantly share code, notes, and snippets.

@neoblizz
Created March 26, 2020 15:49
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save neoblizz/df68e634e0ac09baa982e72a8631d8ad to your computer and use it in GitHub Desktop.
Save neoblizz/df68e634e0ac09baa982e72a8631d8ad to your computer and use it in GitHub Desktop.
CUPTI Events for NVIDIA Volta V100 (32 GB)

CUPTI Events for Volta V100 (32 GB)

Following is the list of CUPTI events that you can profile for a Volta V100 (32 GB) NVIDIA graphics card in a DGX Station.

    active_cycles_pm
    active_warps_pm
    shared_ld_transactions
    shared_st_transactions
    elapsed_cycles_sm
    elapsed_cycles_pm
    inst_executed_fp16_pipe_s0
    inst_executed_fp16_pipe_s1
    inst_executed_fp16_pipe_s2
    inst_executed_fp16_pipe_s3
    inst_executed_fp64_pipe_s0
    inst_executed_fp64_pipe_s1
    inst_executed_fp64_pipe_s2
    inst_executed_fp64_pipe_s3
    inst_executed_fma_pipe_s0
    inst_executed_fma_pipe_s1
    inst_executed_fma_pipe_s2
    inst_executed_fma_pipe_s3
    shared_ld_bank_conflict
    shared_st_bank_conflict
    tensor_pipe_active_cycles_s0
    tensor_pipe_active_cycles_s1
    tensor_pipe_active_cycles_s2
    tensor_pipe_active_cycles_s3
    fb_subp0_read_sectors
    fb_subp1_read_sectors
    fb_subp0_write_sectors
    fb_subp1_write_sectors
    active_cycles
    active_warps
    prof_trigger_00
    prof_trigger_01
    prof_trigger_02
    prof_trigger_03
    prof_trigger_04
    prof_trigger_05
    prof_trigger_06
    prof_trigger_07
    inst_issued0
    inst_issued1
    inst_executed
    thread_inst_executed
    not_predicated_off_thread_inst_executed
    generic_load
    generic_store
    atom_count
    global_atom_cas
    gred_count
    global_load
    global_store
    local_load
    local_store
    shared_atom
    shared_atom_cas
    shared_load
    shared_store
    warps_launched
    sm_cta_launched
    l2_subp0_write_sector_misses
    l2_subp1_write_sector_misses
    l2_subp0_read_sector_misses
    l2_subp1_read_sector_misses
    l2_subp0_read_tex_sector_queries
    l2_subp0_write_tex_sector_queries
    l2_subp0_read_tex_hit_sectors
    l2_subp0_write_tex_hit_sectors
    l2_subp0_read_sysmem_sector_queries
    l2_subp0_write_sysmem_sector_queries
    l2_subp0_total_read_sector_queries
    l2_subp0_total_write_sector_queries
    l2_subp1_read_tex_sector_queries
    l2_subp1_write_tex_sector_queries
    l2_subp1_read_tex_hit_sectors
    l2_subp1_write_tex_hit_sectors
    l2_subp1_read_sysmem_sector_queries
    l2_subp1_write_sysmem_sector_queries
    l2_subp1_total_read_sector_queries
    l2_subp1_total_write_sector_queries
    pcie_tx_active_pulse
    pcie_rx_active_pulse
    elapsed_cycles_sys
    active_cycles_sys
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment