h3-blackwell-runtime/benchmarks/gb10-fc2-nvfp4-baseline-20260825.csv
2026-08-25 22:32:48 +07:00

160 KiB

1IDProcess IDProcess NameHost NameKernel NameContextStreamBlock SizeGrid SizeDeviceCCc2clink__enabled_maskc2clink__presentderived__avg_thread_executedderived__avg_thread_executed_truederived__avg_thread_unexecuted_truederived__derivative_avg_thread_executed_truederived__l1tex__lsu_writeback_bytes_mem_lgds.sum.peak_sustainedderived__l1tex__lsu_writeback_bytes_mem_lgds.sum.per_secondderived__local_spilling_requestsderived__local_spilling_requests_pctderived__lts__lts2xbar_bytes.sum.peak_sustainedderived__lts__lts2xbar_bytes.sum.per_secondderived__memory_l1_conflicts_shared_nwayderived__memory_l1_wavefronts_shared_excessivederived__memory_l2_theoretical_sectors_global_excessivederived__pct_occupancy_per_barrier_countderived__pct_occupancy_per_block_sizederived__pct_occupancy_per_register_countderived__pct_occupancy_per_shared_mem_sizederived__sm__sass_thread_inst_executed_op_dfma_pred_on_x2derived__sm__sass_thread_inst_executed_op_ffma_pred_on_x2derived__sm__sass_thread_inst_executed_op_hfma_pred_on_x4derived__smsp__inst_executed_op_branch_pctderived__smsp__sass_thread_inst_executed_op_dfma_pred_on_x2derived__smsp__sass_thread_inst_executed_op_ffma_pred_on_x2derived__smsp__sass_thread_inst_executed_op_hadd_pred_on_x2derived__smsp__sass_thread_inst_executed_op_hfma_pred_on_x4derived__smsp__sass_thread_inst_executed_op_hmul_pred_on_x2derived_tempMetric0derived_tempMetric1derived_tempMetric2derived_tempMetric3derived_tempMetric4derived_tempMetric5device__attribute_architecturedevice__attribute_async_engine_countdevice__attribute_can_flush_remote_writesdevice__attribute_can_map_host_memorydevice__attribute_can_tex2d_gatherdevice__attribute_can_use_64_bit_stream_mem_opsdevice__attribute_can_use_64_bit_stream_mem_ops_v1device__attribute_can_use_host_pointer_for_registered_memdevice__attribute_can_use_stream_mem_ops_v1device__attribute_can_use_stream_wait_value_nordevice__attribute_can_use_stream_wait_value_nor_v1device__attribute_chipdevice__attribute_clock_ratedevice__attribute_cluster_launchdevice__attribute_compute_capability_majordevice__attribute_compute_capability_minordevice__attribute_compute_modedevice__attribute_compute_preemption_supporteddevice__attribute_concurrent_kernelsdevice__attribute_concurrent_managed_accessdevice__attribute_confidential_computing_modedevice__attribute_cooperative_launchdevice__attribute_cooperative_multi_device_launchdevice__attribute_deferred_mapping_cuda_array_supporteddevice__attribute_device_indexdevice__attribute_direct_managed_mem_access_from_hostdevice__attribute_display_namedevice__attribute_dma_buf_supporteddevice__attribute_ecc_enableddevice__attribute_fb_bus_widthdevice__attribute_fbp_countdevice__attribute_generic_compression_supporteddevice__attribute_global_l1_cache_supporteddevice__attribute_global_memory_bus_widthdevice__attribute_gpu_direct_rdma_flush_writes_optionsdevice__attribute_gpu_direct_rdma_supporteddevice__attribute_gpu_direct_rdma_with_cuda_vmm_supporteddevice__attribute_gpu_direct_rdma_writes_orderingdevice__attribute_gpu_overlapdevice__attribute_gpu_pci_device_iddevice__attribute_gpu_pci_ext_device_iddevice__attribute_gpu_pci_ext_downstream_link_ratedevice__attribute_gpu_pci_ext_downstream_link_widthdevice__attribute_gpu_pci_ext_gendevice__attribute_gpu_pci_ext_gpu_gendevice__attribute_gpu_pci_ext_gpu_link_ratedevice__attribute_gpu_pci_ext_gpu_link_widthdevice__attribute_gpu_pci_revision_iddevice__attribute_gpu_pci_sub_system_iddevice__attribute_handle_type_fabric_supporteddevice__attribute_handle_type_posix_file_descriptor_supporteddevice__attribute_handle_type_win32_handle_supporteddevice__attribute_handle_type_win32_kmt_handle_supporteddevice__attribute_host_native_atomic_supporteddevice__attribute_host_numa_iddevice__attribute_host_register_supporteddevice__attribute_implementationdevice__attribute_integrateddevice__attribute_ipc_event_supporteddevice__attribute_kernel_exec_timeoutdevice__attribute_l2_cache_sizedevice__attribute_l2s_countdevice__attribute_limits_max_cta_per_smdevice__attribute_limits_num_tpcsdevice__attribute_local_l1_cache_supporteddevice__attribute_managed_memorydevice__attribute_max_access_policy_window_sizedevice__attribute_max_block_dim_xdevice__attribute_max_block_dim_ydevice__attribute_max_block_dim_zdevice__attribute_max_blocks_per_multiprocessordevice__attribute_max_gpu_frequency_khzdevice__attribute_max_grid_dim_xdevice__attribute_max_grid_dim_ydevice__attribute_max_grid_dim_zdevice__attribute_max_ipc_per_multiprocessordevice__attribute_max_ipc_per_schedulerdevice__attribute_max_mem_frequency_khzdevice__attribute_max_persisting_l2_cache_sizedevice__attribute_max_pitchdevice__attribute_max_registers_per_blockdevice__attribute_max_registers_per_multiprocessordevice__attribute_max_registers_per_threaddevice__attribute_max_shared_memory_per_blockdevice__attribute_max_shared_memory_per_block_optindevice__attribute_max_shared_memory_per_multiprocessordevice__attribute_max_threads_per_blockdevice__attribute_max_threads_per_multiprocessordevice__attribute_max_warps_per_multiprocessordevice__attribute_max_warps_per_schedulerdevice__attribute_maximum_surface1d_layered_layersdevice__attribute_maximum_surface1d_layered_widthdevice__attribute_maximum_surface1d_widthdevice__attribute_maximum_surface2d_heightdevice__attribute_maximum_surface2d_layered_heightdevice__attribute_maximum_surface2d_layered_layersdevice__attribute_maximum_surface2d_layered_widthdevice__attribute_maximum_surface2d_widthdevice__attribute_maximum_surface3d_depthdevice__attribute_maximum_surface3d_heightdevice__attribute_maximum_surface3d_widthdevice__attribute_maximum_surfacecubemap_layered_layersdevice__attribute_maximum_surfacecubemap_layered_widthdevice__attribute_maximum_surfacecubemap_widthdevice__attribute_maximum_texture1d_layered_layersdevice__attribute_maximum_texture1d_layered_widthdevice__attribute_maximum_texture1d_linear_widthdevice__attribute_maximum_texture1d_mipmapped_widthdevice__attribute_maximum_texture1d_widthdevice__attribute_maximum_texture2d_gather_heightdevice__attribute_maximum_texture2d_gather_widthdevice__attribute_maximum_texture2d_heightdevice__attribute_maximum_texture2d_layered_heightdevice__attribute_maximum_texture2d_layered_layersdevice__attribute_maximum_texture2d_layered_widthdevice__attribute_maximum_texture2d_linear_heightdevice__attribute_maximum_texture2d_linear_pitchdevice__attribute_maximum_texture2d_linear_widthdevice__attribute_maximum_texture2d_mipmapped_heightdevice__attribute_maximum_texture2d_mipmapped_widthdevice__attribute_maximum_texture2d_widthdevice__attribute_maximum_texture3d_depthdevice__attribute_maximum_texture3d_depth_alternatedevice__attribute_maximum_texture3d_heightdevice__attribute_maximum_texture3d_height_alternatedevice__attribute_maximum_texture3d_widthdevice__attribute_maximum_texture3d_width_alternatedevice__attribute_maximum_texturecubemap_layered_layersdevice__attribute_maximum_texturecubemap_layered_widthdevice__attribute_maximum_texturecubemap_widthdevice__attribute_mem_sync_domain_countdevice__attribute_memory_clock_ratedevice__attribute_memory_pools_supporteddevice__attribute_mempool_supported_handle_typesdevice__attribute_mps_enableddevice__attribute_multi_gpu_boarddevice__attribute_multi_gpu_board_group_iddevice__attribute_multicast_supporteddevice__attribute_multiprocessor_countdevice__attribute_num_l2s_per_fbpdevice__attribute_num_schedulers_per_multiprocessordevice__attribute_num_tex_per_multiprocessordevice__attribute_numa_configdevice__attribute_pageable_memory_accessdevice__attribute_pageable_memory_access_uses_host_page_tablesdevice__attribute_pci_bus_iddevice__attribute_pci_device_iddevice__attribute_pci_domain_iddevice__attribute_ram_locationdevice__attribute_ram_typedevice__attribute_reserved_shared_memory_per_blockdevice__attribute_sass_leveldevice__attribute_single_to_double_precision_perf_ratiodevice__attribute_sparse_cuda_array_supporteddevice__attribute_stream_priorities_supporteddevice__attribute_surface_alignmentdevice__attribute_tcc_driverdevice__attribute_tensor_map_access_supporteddevice__attribute_texture_alignmentdevice__attribute_texture_pitch_alignmentdevice__attribute_total_constant_memorydevice__attribute_total_memorydevice__attribute_unified_addressingdevice__attribute_unified_function_pointersdevice__attribute_virtual_address_management_supporteddevice__attribute_warp_sizegcc__cache_requests_type_constant.sumgcc__cache_requests_type_constant.sum.pct_of_peak_sustained_elapsedgcc__cache_requests_type_instruction.sumgcc__cache_requests_type_instruction.sum.pct_of_peak_sustained_elapsedgcc__xbar2gcc_sectors.sumgcc__xbar2gcc_sectors.sum.pct_of_peak_sustained_elapsedgpc__cycles_elapsed.avggpc__cycles_elapsed.avg.per_secondgpc__cycles_elapsed.maxgpc__cycles_elapsed.max.per_secondgpc__cycles_elapsed.mingpc__cycles_elapsed.min.per_secondgpc__cycles_elapsed.sumgpc__cycles_elapsed.sum.per_secondgpu__compute_memory_access_throughput.avg.pct_of_peak_sustained_elapsedgpu__compute_memory_access_throughput.max.pct_of_peak_sustained_elapsedgpu__compute_memory_access_throughput.min.pct_of_peak_sustained_elapsedgpu__compute_memory_access_throughput.sum.pct_of_peak_sustained_elapsedgpu__compute_memory_access_throughput_internal_activity.avg.pct_of_peak_sustained_elapsedgpu__compute_memory_access_throughput_internal_activity.max.pct_of_peak_sustained_elapsedgpu__compute_memory_access_throughput_internal_activity.min.pct_of_peak_sustained_elapsedgpu__compute_memory_access_throughput_internal_activity.sum.pct_of_peak_sustained_elapsedgpu__compute_memory_request_throughput.avg.pct_of_peak_sustained_elapsedgpu__compute_memory_request_throughput.max.pct_of_peak_sustained_elapsedgpu__compute_memory_request_throughput.min.pct_of_peak_sustained_elapsedgpu__compute_memory_request_throughput.sum.pct_of_peak_sustained_elapsedgpu__compute_memory_request_throughput_internal_activity.avg.pct_of_peak_sustained_elapsedgpu__compute_memory_request_throughput_internal_activity.max.pct_of_peak_sustained_elapsedgpu__compute_memory_request_throughput_internal_activity.min.pct_of_peak_sustained_elapsedgpu__compute_memory_request_throughput_internal_activity.sum.pct_of_peak_sustained_elapsedgpu__compute_memory_throughput.avg.pct_of_peak_sustained_elapsedgpu__compute_memory_throughput.max.pct_of_peak_sustained_elapsedgpu__compute_memory_throughput.min.pct_of_peak_sustained_elapsedgpu__compute_memory_throughput.sum.pct_of_peak_sustained_elapsedgpu__time_duration.avggpu__time_duration.maxgpu__time_duration.mingpu__time_duration.sumgr__workids_granted.avggr__workids_granted.maxgr__workids_granted.mingr__workids_granted.sumgr__workids_granted_as_ctas.avggr__workids_granted_as_ctas.maxgr__workids_granted_as_ctas.mingr__workids_granted_as_ctas.sumgr__workids_requested.avggr__workids_requested.maxgr__workids_requested.mingr__workids_requested.sumidc__request_cycles_active.avg.pct_of_peak_sustained_elapsedidc__request_cycles_active.max.pct_of_peak_sustained_elapsedidc__request_cycles_active.min.pct_of_peak_sustained_elapsedidc__request_cycles_active.sum.pct_of_peak_sustained_elapsedidc__request_hit_rate.pctidc__requests.sumidc__requests.sum.pct_of_peak_sustained_elapsedinst_executedl1tex__cycles_active.avgl1tex__cycles_active.maxl1tex__cycles_active.minl1tex__cycles_active.suml1tex__cycles_elapsed.avgl1tex__cycles_elapsed.avg.per_secondl1tex__cycles_elapsed.maxl1tex__cycles_elapsed.max.per_secondl1tex__cycles_elapsed.minl1tex__cycles_elapsed.min.per_secondl1tex__cycles_elapsed.suml1tex__cycles_elapsed.sum.per_secondl1tex__data_bank_conflicts_pipe_lsu_mem_shared.suml1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_atom.suml1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.suml1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ldgsts.suml1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.suml1tex__data_bank_reads.avg.pct_of_peak_sustained_elapsedl1tex__data_bank_reads.max.pct_of_peak_sustained_elapsedl1tex__data_bank_reads.min.pct_of_peak_sustained_elapsedl1tex__data_bank_reads.sum.pct_of_peak_sustained_elapsedl1tex__data_bank_writes.avg.pct_of_peak_sustained_elapsedl1tex__data_bank_writes.max.pct_of_peak_sustained_elapsedl1tex__data_bank_writes.min.pct_of_peak_sustained_elapsedl1tex__data_bank_writes.sum.pct_of_peak_sustained_elapsedl1tex__data_pipe_lsu_wavefronts.avg.pct_of_peak_sustained_elapsedl1tex__data_pipe_lsu_wavefronts.max.pct_of_peak_sustained_elapsedl1tex__data_pipe_lsu_wavefronts.min.pct_of_peak_sustained_elapsedl1tex__data_pipe_lsu_wavefronts.sum.pct_of_peak_sustained_elapsedl1tex__data_pipe_lsu_wavefronts_mem_shared.suml1tex__data_pipe_lsu_wavefronts_mem_shared.sum.pct_of_peak_sustained_elapsedl1tex__data_pipe_lsu_wavefronts_mem_shared_op_atom.suml1tex__data_pipe_lsu_wavefronts_mem_shared_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__data_pipe_lsu_wavefronts_mem_shared_op_ld.suml1tex__data_pipe_lsu_wavefronts_mem_shared_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__data_pipe_lsu_wavefronts_mem_shared_op_st.suml1tex__data_pipe_lsu_wavefronts_mem_shared_op_st.sum.pct_of_peak_sustained_elapsedl1tex__data_pipe_tex_wavefronts.avg.pct_of_peak_sustained_elapsedl1tex__data_pipe_tex_wavefronts.max.pct_of_peak_sustained_elapsedl1tex__data_pipe_tex_wavefronts.min.pct_of_peak_sustained_elapsedl1tex__data_pipe_tex_wavefronts.sum.pct_of_peak_sustained_elapsedl1tex__f_wavefronts.avg.pct_of_peak_sustained_elapsedl1tex__f_wavefronts.max.pct_of_peak_sustained_elapsedl1tex__f_wavefronts.min.pct_of_peak_sustained_elapsedl1tex__f_wavefronts.sum.pct_of_peak_sustained_elapsedl1tex__lsu_writeback_active.avg.pct_of_peak_sustained_elapsedl1tex__lsu_writeback_active.max.pct_of_peak_sustained_elapsedl1tex__lsu_writeback_active.min.pct_of_peak_sustained_elapsedl1tex__lsu_writeback_active.sum.pct_of_peak_sustained_elapsedl1tex__lsu_writeback_active_mem_lgds.suml1tex__lsu_writeback_active_mem_lgds.sum.pct_of_peak_sustained_elapsedl1tex__lsu_writeback_active_mem_lgds.sum.peak_sustainedl1tex__lsu_writeback_active_mem_lgds.sum.per_secondl1tex__lsuin_requests.avg.pct_of_peak_sustained_elapsedl1tex__lsuin_requests.max.pct_of_peak_sustained_elapsedl1tex__lsuin_requests.min.pct_of_peak_sustained_elapsedl1tex__lsuin_requests.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_req_cycles_active.avg.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_req_cycles_active.max.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_req_cycles_active.min.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_req_cycles_active.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_bytes.suml1tex__m_l1tex2xbar_write_bytes.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_bytes.sum.per_secondl1tex__m_l1tex2xbar_write_bytes_mem_dshared.suml1tex__m_l1tex2xbar_write_bytes_mem_dshared.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_bytes_mem_dshared.sum.per_secondl1tex__m_l1tex2xbar_write_bytes_mem_global_op_tma_red.suml1tex__m_l1tex2xbar_write_bytes_mem_global_op_tma_red.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_bytes_mem_global_op_tma_red.sum.per_secondl1tex__m_l1tex2xbar_write_bytes_mem_global_op_tma_st.suml1tex__m_l1tex2xbar_write_bytes_mem_global_op_tma_st.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_bytes_mem_global_op_tma_st.sum.per_secondl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_atom.suml1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_atom.sum.per_secondl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_ld.suml1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_ld.sum.per_secondl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_redas.suml1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_redas.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_redas.sum.per_secondl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_st.suml1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_st.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_st.sum.per_secondl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_tma_red.suml1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_tma_red.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_tma_st.suml1tex__m_l1tex2xbar_write_sectors_mem_dshared_op_tma_st.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_global_op_atom.suml1tex__m_l1tex2xbar_write_sectors_mem_global_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_global_op_red.suml1tex__m_l1tex2xbar_write_sectors_mem_global_op_red.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_global_op_tma_red.suml1tex__m_l1tex2xbar_write_sectors_mem_global_op_tma_red.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_global_op_tma_red.sum.per_secondl1tex__m_l1tex2xbar_write_sectors_mem_global_op_tma_st.suml1tex__m_l1tex2xbar_write_sectors_mem_global_op_tma_st.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_global_op_tma_st.sum.per_secondl1tex__m_l1tex2xbar_write_sectors_mem_lg_op_st.suml1tex__m_l1tex2xbar_write_sectors_mem_lg_op_st.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_surface_op_atom.suml1tex__m_l1tex2xbar_write_sectors_mem_surface_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_surface_op_red.suml1tex__m_l1tex2xbar_write_sectors_mem_surface_op_red.sum.pct_of_peak_sustained_elapsedl1tex__m_l1tex2xbar_write_sectors_mem_surface_op_st.suml1tex__m_l1tex2xbar_write_sectors_mem_surface_op_st.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_bytes.suml1tex__m_xbar2l1tex_read_bytes.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_bytes.sum.per_secondl1tex__m_xbar2l1tex_read_bytes_mem_dshared.suml1tex__m_xbar2l1tex_read_bytes_mem_dshared.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_bytes_mem_dshared.sum.per_secondl1tex__m_xbar2l1tex_read_bytes_mem_global_op_tma_ld.suml1tex__m_xbar2l1tex_read_bytes_mem_global_op_tma_ld.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_bytes_mem_global_op_tma_ld.sum.per_secondl1tex__m_xbar2l1tex_read_sectors.avg.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors.max.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors.min.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_atom.suml1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_atom.sum.per_secondl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_ld.suml1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_ld.sum.per_secondl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_redas.suml1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_redas.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_redas.sum.per_secondl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_st.suml1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_st.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_st.sum.per_secondl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_tma_red.suml1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_tma_red.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_tma_st.suml1tex__m_xbar2l1tex_read_sectors_mem_dshared_op_tma_st.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_global_op_atom.suml1tex__m_xbar2l1tex_read_sectors_mem_global_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_global_op_tma_ld.suml1tex__m_xbar2l1tex_read_sectors_mem_global_op_tma_ld.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_global_op_tma_ld.sum.per_secondl1tex__m_xbar2l1tex_read_sectors_mem_lg_op_ld.suml1tex__m_xbar2l1tex_read_sectors_mem_lg_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_surface_op_atom.suml1tex__m_xbar2l1tex_read_sectors_mem_surface_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_surface_op_ld.suml1tex__m_xbar2l1tex_read_sectors_mem_surface_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__m_xbar2l1tex_read_sectors_mem_texture.suml1tex__m_xbar2l1tex_read_sectors_mem_texture.sum.pct_of_peak_sustained_elapsedl1tex__t_bytes_pipe_lsu_mem_global_op_ldgsts_cache_access.suml1tex__t_bytes_pipe_lsu_mem_global_op_ldgsts_cache_access.sum.pct_of_peak_sustained_elapsedl1tex__t_bytes_pipe_lsu_mem_global_op_ldgsts_cache_access.sum.per_secondl1tex__t_output_wavefronts_pipe_lsu_mem_dshared_op_atom.suml1tex__t_output_wavefronts_pipe_lsu_mem_dshared_op_ld.suml1tex__t_output_wavefronts_pipe_lsu_mem_dshared_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_lsu_mem_dshared_op_redas.suml1tex__t_output_wavefronts_pipe_lsu_mem_dshared_op_redas.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_lsu_mem_dshared_op_st.suml1tex__t_output_wavefronts_pipe_lsu_mem_dshared_op_st.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_lsu_mem_global_op_atom.suml1tex__t_output_wavefronts_pipe_lsu_mem_global_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_lsu_mem_global_op_ld.suml1tex__t_output_wavefronts_pipe_lsu_mem_global_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_lsu_mem_global_op_red.suml1tex__t_output_wavefronts_pipe_lsu_mem_global_op_red.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_lsu_mem_global_op_st.suml1tex__t_output_wavefronts_pipe_lsu_mem_global_op_st.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_lsu_mem_local_op_ld.suml1tex__t_output_wavefronts_pipe_lsu_mem_local_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_lsu_mem_local_op_st.suml1tex__t_output_wavefronts_pipe_lsu_mem_local_op_st.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_tex_mem_surface_op_atom.suml1tex__t_output_wavefronts_pipe_tex_mem_surface_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_tex_mem_surface_op_ld.suml1tex__t_output_wavefronts_pipe_tex_mem_surface_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_tex_mem_surface_op_red.suml1tex__t_output_wavefronts_pipe_tex_mem_surface_op_red.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_tex_mem_surface_op_st.suml1tex__t_output_wavefronts_pipe_tex_mem_surface_op_st.sum.pct_of_peak_sustained_elapsedl1tex__t_output_wavefronts_pipe_tex_mem_texture.suml1tex__t_output_wavefronts_pipe_tex_mem_texture.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_dshared_op_atom.suml1tex__t_requests_pipe_lsu_mem_dshared_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_dshared_op_ld.suml1tex__t_requests_pipe_lsu_mem_dshared_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_dshared_op_redas.suml1tex__t_requests_pipe_lsu_mem_dshared_op_redas.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_dshared_op_st.suml1tex__t_requests_pipe_lsu_mem_dshared_op_st.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_global_op_atom.suml1tex__t_requests_pipe_lsu_mem_global_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_global_op_ld.suml1tex__t_requests_pipe_lsu_mem_global_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_global_op_red.suml1tex__t_requests_pipe_lsu_mem_global_op_red.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_global_op_st.suml1tex__t_requests_pipe_lsu_mem_global_op_st.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_local_op_ld.suml1tex__t_requests_pipe_lsu_mem_local_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_lsu_mem_local_op_st.suml1tex__t_requests_pipe_lsu_mem_local_op_st.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_tex_mem_surface_op_atom.suml1tex__t_requests_pipe_tex_mem_surface_op_atom.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_tex_mem_surface_op_ld.suml1tex__t_requests_pipe_tex_mem_surface_op_ld.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_tex_mem_surface_op_red.suml1tex__t_requests_pipe_tex_mem_surface_op_red.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_tex_mem_surface_op_st.suml1tex__t_requests_pipe_tex_mem_surface_op_st.sum.pct_of_peak_sustained_elapsedl1tex__t_requests_pipe_tex_mem_texture.suml1tex__t_requests_pipe_tex_mem_texture.sum.pct_of_peak_sustained_elapsedl1tex__t_sector_hit_rate.pctl1tex__t_sector_pipe_lsu_mem_global_op_atom_hit_rate.pctl1tex__t_sector_pipe_lsu_mem_global_op_ld_hit_rate.pctl1tex__t_sector_pipe_lsu_mem_global_op_red_hit_rate.pctl1tex__t_sector_pipe_lsu_mem_global_op_st_hit_rate.pctl1tex__t_sector_pipe_lsu_mem_local_op_ld_hit_rate.pctl1tex__t_sector_pipe_lsu_mem_local_op_st_hit_rate.pctl1tex__t_sector_pipe_tex_mem_surface_op_atom_hit_rate.pctl1tex__t_sector_pipe_tex_mem_surface_op_ld_hit_rate.pctl1tex__t_sector_pipe_tex_mem_surface_op_red_hit_rate.pctl1tex__t_sector_pipe_tex_mem_surface_op_st_hit_rate.pctl1tex__t_sector_pipe_tex_mem_texture_op_tex_hit_rate.pctl1tex__t_sectors_pipe_lsu_mem_dshared_op_atom.suml1tex__t_sectors_pipe_lsu_mem_dshared_op_atom_lookup_miss.suml1tex__t_sectors_pipe_lsu_mem_dshared_op_ld.suml1tex__t_sectors_pipe_lsu_mem_dshared_op_ld_lookup_miss.suml1tex__t_sectors_pipe_lsu_mem_dshared_op_redas.suml1tex__t_sectors_pipe_lsu_mem_dshared_op_redas_lookup_miss.suml1tex__t_sectors_pipe_lsu_mem_dshared_op_st.suml1tex__t_sectors_pipe_lsu_mem_dshared_op_st_lookup_miss.suml1tex__t_sectors_pipe_lsu_mem_global_op_atom.suml1tex__t_sectors_pipe_lsu_mem_global_op_atom_lookup_hit.suml1tex__t_sectors_pipe_lsu_mem_global_op_atom_lookup_miss.suml1tex__t_sectors_pipe_lsu_mem_global_op_ld.suml1tex__t_sectors_pipe_lsu_mem_global_op_ld_lookup_hit.suml1tex__t_sectors_pipe_lsu_mem_global_op_ld_lookup_miss.suml1tex__t_sectors_pipe_lsu_mem_global_op_red.suml1tex__t_sectors_pipe_lsu_mem_global_op_red_lookup_hit.suml1tex__t_sectors_pipe_lsu_mem_global_op_red_lookup_miss.suml1tex__t_sectors_pipe_lsu_mem_global_op_st.suml1tex__t_sectors_pipe_lsu_mem_global_op_st_lookup_hit.suml1tex__t_sectors_pipe_lsu_mem_global_op_st_lookup_miss.suml1tex__t_sectors_pipe_lsu_mem_local_op_ld.suml1tex__t_sectors_pipe_lsu_mem_local_op_ld_lookup_hit.suml1tex__t_sectors_pipe_lsu_mem_local_op_ld_lookup_miss.suml1tex__t_sectors_pipe_lsu_mem_local_op_st.suml1tex__t_sectors_pipe_lsu_mem_local_op_st_lookup_hit.suml1tex__t_sectors_pipe_lsu_mem_local_op_st_lookup_miss.suml1tex__t_sectors_pipe_tex_mem_surface_op_atom.suml1tex__t_sectors_pipe_tex_mem_surface_op_atom_lookup_hit.suml1tex__t_sectors_pipe_tex_mem_surface_op_atom_lookup_miss.suml1tex__t_sectors_pipe_tex_mem_surface_op_ld.suml1tex__t_sectors_pipe_tex_mem_surface_op_ld_lookup_hit.suml1tex__t_sectors_pipe_tex_mem_surface_op_ld_lookup_miss.suml1tex__t_sectors_pipe_tex_mem_surface_op_red.suml1tex__t_sectors_pipe_tex_mem_surface_op_red_lookup_hit.suml1tex__t_sectors_pipe_tex_mem_surface_op_red_lookup_miss.suml1tex__t_sectors_pipe_tex_mem_surface_op_st.suml1tex__t_sectors_pipe_tex_mem_surface_op_st_lookup_hit.suml1tex__t_sectors_pipe_tex_mem_surface_op_st_lookup_miss.suml1tex__t_sectors_pipe_tex_mem_texture.suml1tex__t_sectors_pipe_tex_mem_texture_lookup_hit.suml1tex__t_sectors_pipe_tex_mem_texture_lookup_miss.suml1tex__tex_writeback_active.avg.pct_of_peak_sustained_elapsedl1tex__tex_writeback_active.max.pct_of_peak_sustained_elapsedl1tex__tex_writeback_active.min.pct_of_peak_sustained_elapsedl1tex__tex_writeback_active.suml1tex__tex_writeback_active.sum.pct_of_peak_sustained_elapsedl1tex__texin_sm2tex_req_cycles_active.avg.pct_of_peak_sustained_elapsedl1tex__texin_sm2tex_req_cycles_active.max.pct_of_peak_sustained_elapsedl1tex__texin_sm2tex_req_cycles_active.min.pct_of_peak_sustained_elapsedl1tex__texin_sm2tex_req_cycles_active.sum.pct_of_peak_sustained_elapsedl1tex__throughput.avg.pct_of_peak_sustained_activel1tex__throughput.avg.pct_of_peak_sustained_elapsedl1tex__throughput.max.pct_of_peak_sustained_activel1tex__throughput.max.pct_of_peak_sustained_elapsedl1tex__throughput.min.pct_of_peak_sustained_activel1tex__throughput.min.pct_of_peak_sustained_elapsedl1tex__throughput.sum.pct_of_peak_sustained_activel1tex__throughput.sum.pct_of_peak_sustained_elapsedlaunch__barrier_countlaunch__block_dim_xlaunch__block_dim_ylaunch__block_dim_zlaunch__block_sizelaunch__cluster_dim_xlaunch__cluster_dim_ylaunch__cluster_dim_zlaunch__cluster_max_activelaunch__cluster_max_potential_sizelaunch__cluster_scheduling_policylaunch__cluster_sizelaunch__context_idlaunch__device_idlaunch__func_cache_configlaunch__function_pcslaunch__grid_dim_xlaunch__grid_dim_ylaunch__grid_dim_zlaunch__grid_sizelaunch__kernel_namelaunch__occupancy_cluster_gpu_pctlaunch__occupancy_cluster_pctlaunch__occupancy_limit_barrierslaunch__occupancy_limit_blockslaunch__occupancy_limit_registerslaunch__occupancy_limit_shared_memlaunch__occupancy_limit_warpslaunch__occupancy_per_barrier_countlaunch__occupancy_per_block_sizelaunch__occupancy_per_cluster_sizelaunch__occupancy_per_register_countlaunch__occupancy_per_shared_mem_sizelaunch__persisting_l2_cache_sizelaunch__preferred_cluster_dim_xlaunch__preferred_cluster_dim_ylaunch__preferred_cluster_dim_zlaunch__preferred_cluster_sizelaunch__registers_per_threadlaunch__registers_per_thread_allocatedlaunch__shared_mem_config_sizelaunch__shared_mem_per_blocklaunch__shared_mem_per_block_allocatedlaunch__shared_mem_per_block_driverlaunch__shared_mem_per_block_dynamiclaunch__shared_mem_per_block_staticlaunch__sm_countlaunch__stack_sizelaunch__stream_idlaunch__thread_countlaunch__tpc_countlaunch__tpc_enabledlaunch__uses_cdplaunch__uses_green_contextlaunch__uses_mpslaunch__uses_nvlink_centric_schedulinglaunch__uses_vgpulaunch__waves_per_multiprocessorlrc__average_ilc_input_sector_success_rate.pctlrc__ilc_input_sectors.sumlts__average_gcomp_input_sector_success_rate.pctlts__average_gcomp_output_sector_compression_achieved_rate.ratiolts__average_t_sectors_requested_srcunit_tex_op_read_vs_returned_sectors_realtime.ratiolts__average_xcomp_gxc_sector_input_compression_rate.ratiolts__cycles_active.avglts__cycles_active.maxlts__cycles_active.minlts__cycles_active.sumlts__cycles_elapsed.avglts__cycles_elapsed.avg.per_secondlts__cycles_elapsed.maxlts__cycles_elapsed.max.per_secondlts__cycles_elapsed.minlts__cycles_elapsed.min.per_secondlts__cycles_elapsed.sumlts__cycles_elapsed.sum.per_secondlts__d_atomic_input_cycles_active.avg.pct_of_peak_sustained_elapsedlts__d_atomic_input_cycles_active.max.pct_of_peak_sustained_elapsedlts__d_atomic_input_cycles_active.min.pct_of_peak_sustained_elapsedlts__d_atomic_input_cycles_active.sum.pct_of_peak_sustained_elapsedlts__d_decomp_input_sectors.avg.pct_of_peak_sustained_elapsedlts__d_decomp_input_sectors.max.pct_of_peak_sustained_elapsedlts__d_decomp_input_sectors.min.pct_of_peak_sustained_elapsedlts__d_decomp_input_sectors.sum.pct_of_peak_sustained_elapsedlts__d_sectors.avg.pct_of_peak_sustained_elapsedlts__d_sectors.max.pct_of_peak_sustained_elapsedlts__d_sectors.min.pct_of_peak_sustained_elapsedlts__d_sectors.sum.pct_of_peak_sustained_elapsedlts__d_sectors_fill_sysmem.sumlts__d_sectors_fill_sysmem.sum.pct_of_peak_sustained_elapsedlts__d_sectors_fill_sysmem.sum.per_secondlts__gcomp_input_sectors.avglts__gcomp_input_sectors.maxlts__gcomp_input_sectors.minlts__gcomp_input_sectors.sumlts__lts2xbar_cycles_active.avg.pct_of_peak_sustained_elapsedlts__lts2xbar_cycles_active.avg.peak_sustainedlts__lts2xbar_cycles_active.avg.per_secondlts__lts2xbar_cycles_active.max.pct_of_peak_sustained_elapsedlts__lts2xbar_cycles_active.max.peak_sustainedlts__lts2xbar_cycles_active.max.per_secondlts__lts2xbar_cycles_active.min.pct_of_peak_sustained_elapsedlts__lts2xbar_cycles_active.min.peak_sustainedlts__lts2xbar_cycles_active.min.per_secondlts__lts2xbar_cycles_active.sum.pct_of_peak_sustained_elapsedlts__lts2xbar_cycles_active.sum.peak_sustainedlts__lts2xbar_cycles_active.sum.per_secondlts__t_requests.sumlts__t_requests_srcunit_gcc.sumlts__t_requests_srcunit_tex.sumlts__t_requests_srcunit_tex_op_atom_dot_alu.sumlts__t_requests_srcunit_tex_op_atom_dot_cas.sumlts__t_requests_srcunit_tex_op_read.sumlts__t_requests_srcunit_tex_op_red.sumlts__t_requests_srcunit_tex_op_write.sumlts__t_sector_hit_rate.pctlts__t_sector_op_read_hit_rate.pctlts__t_sector_op_write_hit_rate.pctlts__t_sectors.avglts__t_sectors.avg.pct_of_peak_sustained_elapsedlts__t_sectors.avg.peak_sustainedlts__t_sectors.avg.per_cycle_elapsedlts__t_sectors.maxlts__t_sectors.max.pct_of_peak_sustained_elapsedlts__t_sectors.minlts__t_sectors.min.pct_of_peak_sustained_elapsedlts__t_sectors.sumlts__t_sectors.sum.pct_of_peak_sustained_elapsedlts__t_sectors.sum.per_secondlts__t_sectors_aperture_sysmem_op_write.sumlts__t_sectors_aperture_sysmem_op_write.sum.pct_of_peak_sustained_elapsedlts__t_sectors_aperture_sysmem_op_write.sum.per_secondlts__t_sectors_data_ecc.avg.pct_of_peak_sustained_elapsedlts__t_sectors_data_ecc.avg.peak_sustainedlts__t_sectors_data_ecc.avg.per_cycle_elapsedlts__t_sectors_data_ecc.sumlts__t_sectors_data_ecc.sum.per_secondlts__t_sectors_evict_first_lookup_hit.sumlts__t_sectors_evict_first_lookup_miss.sumlts__t_sectors_evict_last_lookup_hit.sumlts__t_sectors_evict_last_lookup_miss.sumlts__t_sectors_evict_normal_demote_lookup_hit.sumlts__t_sectors_evict_normal_demote_lookup_miss.sumlts__t_sectors_evict_normal_lookup_hit.sumlts__t_sectors_evict_normal_lookup_miss.sumlts__t_sectors_lookup_hit.sumlts__t_sectors_lookup_miss.sumlts__t_sectors_requested_srcunit_tex_op_read_realtime.sumlts__t_sectors_requested_srcunit_tex_op_read_realtime.sum.pct_of_peak_sustained_elapsedlts__t_sectors_requested_srcunit_tex_op_read_realtime.sum.per_secondlts__t_sectors_srcunit_gcc.avg.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_gcc.avg.peak_sustainedlts__t_sectors_srcunit_gcc.avg.per_cycle_elapsedlts__t_sectors_srcunit_gcc.sumlts__t_sectors_srcunit_gcc.sum.per_secondlts__t_sectors_srcunit_gcc_lookup_hit.sumlts__t_sectors_srcunit_gcc_lookup_miss.sumlts__t_sectors_srcunit_tex.avg.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex.avg.peak_sustainedlts__t_sectors_srcunit_tex.avg.per_cycle_elapsedlts__t_sectors_srcunit_tex.max.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex.min.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex.sumlts__t_sectors_srcunit_tex.sum.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex.sum.per_secondlts__t_sectors_srcunit_tex_aperture_peer_lookup_miss.avglts__t_sectors_srcunit_tex_aperture_peer_lookup_miss.maxlts__t_sectors_srcunit_tex_aperture_peer_lookup_miss.minlts__t_sectors_srcunit_tex_aperture_peer_lookup_miss.sumlts__t_sectors_srcunit_tex_aperture_sysmem_lookup_miss.avglts__t_sectors_srcunit_tex_aperture_sysmem_lookup_miss.maxlts__t_sectors_srcunit_tex_aperture_sysmem_lookup_miss.minlts__t_sectors_srcunit_tex_aperture_sysmem_lookup_miss.sumlts__t_sectors_srcunit_tex_evict_first_lookup_hit.sumlts__t_sectors_srcunit_tex_evict_first_lookup_miss.sumlts__t_sectors_srcunit_tex_evict_last_lookup_hit.sumlts__t_sectors_srcunit_tex_evict_last_lookup_miss.sumlts__t_sectors_srcunit_tex_evict_normal_demote_lookup_hit.sumlts__t_sectors_srcunit_tex_evict_normal_demote_lookup_miss.sumlts__t_sectors_srcunit_tex_evict_normal_lookup_hit.sumlts__t_sectors_srcunit_tex_evict_normal_lookup_miss.sumlts__t_sectors_srcunit_tex_lookup_hit.sumlts__t_sectors_srcunit_tex_lookup_miss.avglts__t_sectors_srcunit_tex_lookup_miss.maxlts__t_sectors_srcunit_tex_lookup_miss.minlts__t_sectors_srcunit_tex_lookup_miss.sumlts__t_sectors_srcunit_tex_op_atom.sumlts__t_sectors_srcunit_tex_op_atom.sum.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex_op_atom.sum.per_secondlts__t_sectors_srcunit_tex_op_atom_dot_alu.avg.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex_op_atom_dot_alu.avg.peak_sustainedlts__t_sectors_srcunit_tex_op_atom_dot_alu.avg.per_cycle_elapsedlts__t_sectors_srcunit_tex_op_atom_dot_alu.sumlts__t_sectors_srcunit_tex_op_atom_dot_alu.sum.per_secondlts__t_sectors_srcunit_tex_op_atom_dot_alu_lookup_hit.sumlts__t_sectors_srcunit_tex_op_atom_dot_alu_lookup_miss.sumlts__t_sectors_srcunit_tex_op_atom_dot_cas.avg.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex_op_atom_dot_cas.avg.peak_sustainedlts__t_sectors_srcunit_tex_op_atom_dot_cas.avg.per_cycle_elapsedlts__t_sectors_srcunit_tex_op_atom_dot_cas.sumlts__t_sectors_srcunit_tex_op_atom_dot_cas.sum.per_secondlts__t_sectors_srcunit_tex_op_atom_dot_cas_lookup_hit.sumlts__t_sectors_srcunit_tex_op_atom_dot_cas_lookup_miss.sumlts__t_sectors_srcunit_tex_op_atom_evict_first_lookup_hit.sumlts__t_sectors_srcunit_tex_op_atom_evict_first_lookup_miss.sumlts__t_sectors_srcunit_tex_op_atom_evict_last_lookup_hit.sumlts__t_sectors_srcunit_tex_op_atom_evict_last_lookup_miss.sumlts__t_sectors_srcunit_tex_op_atom_evict_normal_lookup_hit.sumlts__t_sectors_srcunit_tex_op_atom_evict_normal_lookup_miss.sumlts__t_sectors_srcunit_tex_op_read.avg.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex_op_read.avg.peak_sustainedlts__t_sectors_srcunit_tex_op_read.avg.per_cycle_elapsedlts__t_sectors_srcunit_tex_op_read.sumlts__t_sectors_srcunit_tex_op_read.sum.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex_op_read.sum.per_secondlts__t_sectors_srcunit_tex_op_read_evict_first_lookup_hit.sumlts__t_sectors_srcunit_tex_op_read_evict_first_lookup_miss.sumlts__t_sectors_srcunit_tex_op_read_evict_last_lookup_hit.sumlts__t_sectors_srcunit_tex_op_read_evict_last_lookup_miss.sumlts__t_sectors_srcunit_tex_op_read_evict_normal_demote_lookup_hit.sumlts__t_sectors_srcunit_tex_op_read_evict_normal_demote_lookup_miss.sumlts__t_sectors_srcunit_tex_op_read_evict_normal_lookup_hit.sumlts__t_sectors_srcunit_tex_op_read_evict_normal_lookup_miss.sumlts__t_sectors_srcunit_tex_op_read_lookup_hit.sumlts__t_sectors_srcunit_tex_op_read_lookup_miss.sumlts__t_sectors_srcunit_tex_op_red.avg.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex_op_red.avg.peak_sustainedlts__t_sectors_srcunit_tex_op_red.avg.per_cycle_elapsedlts__t_sectors_srcunit_tex_op_red.sumlts__t_sectors_srcunit_tex_op_red.sum.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex_op_red.sum.per_secondlts__t_sectors_srcunit_tex_op_red_lookup_hit.sumlts__t_sectors_srcunit_tex_op_red_lookup_miss.sumlts__t_sectors_srcunit_tex_op_write.avg.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex_op_write.avg.peak_sustainedlts__t_sectors_srcunit_tex_op_write.avg.per_cycle_elapsedlts__t_sectors_srcunit_tex_op_write.sumlts__t_sectors_srcunit_tex_op_write.sum.pct_of_peak_sustained_elapsedlts__t_sectors_srcunit_tex_op_write.sum.per_secondlts__t_sectors_srcunit_tex_op_write_evict_first_lookup_hit.sumlts__t_sectors_srcunit_tex_op_write_evict_first_lookup_miss.sumlts__t_sectors_srcunit_tex_op_write_evict_last_lookup_hit.sumlts__t_sectors_srcunit_tex_op_write_evict_last_lookup_miss.sumlts__t_sectors_srcunit_tex_op_write_evict_normal_demote_lookup_hit.sumlts__t_sectors_srcunit_tex_op_write_evict_normal_demote_lookup_miss.sumlts__t_sectors_srcunit_tex_op_write_evict_normal_lookup_hit.sumlts__t_sectors_srcunit_tex_op_write_evict_normal_lookup_miss.sumlts__t_sectors_srcunit_tex_op_write_lookup_hit.sumlts__t_sectors_srcunit_tex_op_write_lookup_miss.sumlts__t_tag_requests.avg.pct_of_peak_sustained_elapsedlts__t_tag_requests.max.pct_of_peak_sustained_elapsedlts__t_tag_requests.min.pct_of_peak_sustained_elapsedlts__t_tag_requests.sum.pct_of_peak_sustained_elapsedlts__throughput.avg.pct_of_peak_sustained_elapsedlts__throughput.max.pct_of_peak_sustained_elapsedlts__throughput.min.pct_of_peak_sustained_elapsedlts__throughput.sum.pct_of_peak_sustained_elapsedlts__xbar2lts_cycles_active.avg.pct_of_peak_sustained_elapsedlts__xbar2lts_cycles_active.max.pct_of_peak_sustained_elapsedlts__xbar2lts_cycles_active.min.pct_of_peak_sustained_elapsedlts__xbar2lts_cycles_active.sum.pct_of_peak_sustained_elapsedlts__xcomp_gxc_sectors_input.sumlts__xcomp_gxc_sectors_input.sum.pct_of_peak_sustained_elapsedlts__xcomp_gxc_sectors_input.sum.per_secondlts__xcomp_gxc_sectors_output.sumlts__xcomp_gxc_sectors_output.sum.pct_of_peak_sustained_elapsedlts__xcomp_gxc_sectors_output.sum.per_secondmemory_access_size_typememory_access_typememory_l1_tag_requests_globalmemory_l1_wavefronts_sharedmemory_l1_wavefronts_shared_idealmemory_l2_theoretical_sectors_globalmemory_l2_theoretical_sectors_global_idealmemory_l2_theoretical_sectors_localmemory_typenuma__cpu_affinitynuma__dev_display_name_allnuma__id_cpunuma__id_memorynvlink__bandwidthnvlink__count_logicalnvlink__count_physicalnvlink__destination_portsnvlink__dev0Idnvlink__dev0typenvlink__dev1Idnvlink__dev1typenvlink__dev_display_name_allnvlink__enabled_masknvlink__is_direct_linknvlink__is_nvswitch_connectednvlink__max_countnvlink__peer_accessnvlink__peer_atomicnvlink__source_portsnvlink__system_accessnvlink__system_atomicpmsampling:gr__ctas_launched_queue_sync_realtime.sumpmsampling:l1tex__data_pipe_lsu_wavefronts.avgpmsampling:l1tex__lsu_writeback_active.avgpmsampling:l1tex__t_sector_hit_rate.pctpmsampling:lts__average_t_sector_hit_rate_realtime.pctpmsampling:sm__average_thread_inst_executed_pred_on_per_inst_executed_realtime.pctpmsampling:sm__cycles_active.avgpmsampling:sm__inst_executed_pipe_alu_realtime.avg.pct_of_peak_sustained_elapsedpmsampling:sm__inst_executed_realtime.avg.per_cycle_activepmsampling:sm__pipe_tensor_cycles_active_realtime.avg.pct_of_peak_sustained_elapsedpmsampling:smsp__inst_executed_pipe_fmaheavy.avg.pct_of_peak_sustained_elapsedpmsampling:smsp__inst_executed_pipe_fmalite.avg.pct_of_peak_sustained_elapsedpmsampling:tpc__warps_active_realtime.avg.per_cycle_activepmsampling:tpc__warps_active_realtime.sum.per_cycle_activeprofiler__perfworks_session_reuseprofiler__pmsampler_buffer_size_bytesprofiler__pmsampler_ctxsw_0profiler__pmsampler_ctxsw_1profiler__pmsampler_interval_timeprofiler__pmsampler_merged_samplesprofiler__pmsampler_pass_groupsprofiler__replayer_bytes_mem_accessible.avgprofiler__replayer_bytes_mem_accessible.maxprofiler__replayer_bytes_mem_accessible.minprofiler__replayer_bytes_mem_accessible.sumprofiler__replayer_bytes_mem_backed_up.avgprofiler__replayer_bytes_mem_backed_up.maxprofiler__replayer_bytes_mem_backed_up.minprofiler__replayer_bytes_mem_backed_up.sumprofiler__replayer_passesprofiler__replayer_passes_type_warmupprofiler__timestamp_workload_end_0profiler__timestamp_workload_end_1profiler__timestamp_workload_start_0profiler__timestamp_workload_start_1sass__inst_executed_global_loadssass__inst_executed_global_storessass__inst_executed_local_loadssass__inst_executed_local_storessass__inst_executed_per_opcodesass__inst_executed_per_opcode_categorysass__inst_executed_per_opcode_with_modifier_allsass__inst_executed_per_opcode_with_modifier_selectivesass__inst_executed_register_spillingsass__inst_executed_register_spilling_mem_localsass__inst_executed_register_spilling_mem_sharedsass__inst_executed_register_spilling_op_readsass__inst_executed_register_spilling_op_writesass__inst_executed_shared_loadssass__inst_executed_shared_storessass__thread_inst_executed_per_opcode_categorysass__thread_inst_executed_true_per_opcodesass__thread_inst_executed_true_per_opcode_with_modifier_allsass__thread_inst_executed_true_per_opcode_with_modifier_selectivesm__cycles_active.avgsm__cycles_active.maxsm__cycles_active.minsm__cycles_active.sumsm__cycles_elapsed.avgsm__cycles_elapsed.avg.per_secondsm__cycles_elapsed.maxsm__cycles_elapsed.max.per_secondsm__cycles_elapsed.minsm__cycles_elapsed.min.per_secondsm__cycles_elapsed.sumsm__cycles_elapsed.sum.per_secondsm__dcc_request_hit_rate.pctsm__dcc_requests.sumsm__dcc_requests.sum.pct_of_peak_sustained_elapsedsm__dcc_requests_lookup_hit.sumsm__icc_request_hit_rate.pctsm__icc_requests.sumsm__icc_requests.sum.pct_of_peak_sustained_elapsedsm__inst_executed.avg.pct_of_peak_sustained_elapsedsm__inst_executed.avg.per_cycle_activesm__inst_executed.avg.per_cycle_elapsedsm__inst_executed.max.pct_of_peak_sustained_elapsedsm__inst_executed.max.per_cycle_activesm__inst_executed.max.per_cycle_elapsedsm__inst_executed.min.pct_of_peak_sustained_elapsedsm__inst_executed.min.per_cycle_activesm__inst_executed.min.per_cycle_elapsedsm__inst_executed.sum.pct_of_peak_sustained_elapsedsm__inst_executed.sum.per_cycle_activesm__inst_executed.sum.per_cycle_elapsedsm__inst_executed_pipe_adu.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_adu.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_adu.max.pct_of_peak_sustained_activesm__inst_executed_pipe_adu.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_adu.min.pct_of_peak_sustained_activesm__inst_executed_pipe_adu.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_adu.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_adu.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_alu.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_alu.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_alu.max.pct_of_peak_sustained_activesm__inst_executed_pipe_alu.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_alu.min.pct_of_peak_sustained_activesm__inst_executed_pipe_alu.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_alu.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_alu.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_cbu.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_cbu.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_cbu.max.pct_of_peak_sustained_activesm__inst_executed_pipe_cbu.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_cbu.min.pct_of_peak_sustained_activesm__inst_executed_pipe_cbu.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_cbu.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_cbu.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_cbu_pred_on_any.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_cbu_pred_on_any.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_cbu_pred_on_any.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_cbu_pred_on_any.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fma.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_fma.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fma.max.pct_of_peak_sustained_activesm__inst_executed_pipe_fma.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fma.min.pct_of_peak_sustained_activesm__inst_executed_pipe_fma.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fma.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_fma.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fma_type_fp16.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_fma_type_fp16.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64.max.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64.min.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64_op_dmma.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64_op_dmma.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64_op_dmma.max.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64_op_dmma.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64_op_dmma.min.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64_op_dmma.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64_op_dmma.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64_op_dmma.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64_op_fp64.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64_op_fp64.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64_op_fp64.max.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64_op_fp64.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64_op_fp64.min.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64_op_fp64.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_fp64_op_fp64.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_fp64_op_fp64.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_ipa.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_ipa.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_ipa.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_ipa.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_lsu.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_lsu.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_lsu.max.pct_of_peak_sustained_activesm__inst_executed_pipe_lsu.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_lsu.min.pct_of_peak_sustained_activesm__inst_executed_pipe_lsu.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_lsu.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_lsu.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tensor_subpipe_hmma.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_tensor_subpipe_hmma.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tensor_subpipe_imma.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_tensor_subpipe_imma.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tex.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_tex.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tex.max.pct_of_peak_sustained_activesm__inst_executed_pipe_tex.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tex.min.pct_of_peak_sustained_activesm__inst_executed_pipe_tex.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tex.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_tex.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tma.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_tma.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tma.max.pct_of_peak_sustained_activesm__inst_executed_pipe_tma.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tma.min.pct_of_peak_sustained_activesm__inst_executed_pipe_tma.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_tma.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_tma.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_uniform.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_uniform.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_uniform.max.pct_of_peak_sustained_activesm__inst_executed_pipe_uniform.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_uniform.min.pct_of_peak_sustained_activesm__inst_executed_pipe_uniform.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_uniform.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_uniform.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_workid.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_workid.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_workid.max.pct_of_peak_sustained_activesm__inst_executed_pipe_workid.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_workid.min.pct_of_peak_sustained_activesm__inst_executed_pipe_workid.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_workid.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_workid.sum.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_xu.avg.pct_of_peak_sustained_activesm__inst_executed_pipe_xu.avg.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_xu.max.pct_of_peak_sustained_activesm__inst_executed_pipe_xu.max.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_xu.min.pct_of_peak_sustained_activesm__inst_executed_pipe_xu.min.pct_of_peak_sustained_elapsedsm__inst_executed_pipe_xu.sum.pct_of_peak_sustained_activesm__inst_executed_pipe_xu.sum.pct_of_peak_sustained_elapsedsm__inst_issued.avg.pct_of_peak_sustained_elapsedsm__inst_issued.avg.per_cycle_activesm__inst_issued.max.pct_of_peak_sustained_elapsedsm__inst_issued.max.per_cycle_activesm__inst_issued.min.pct_of_peak_sustained_elapsedsm__inst_issued.min.per_cycle_activesm__inst_issued.sum.pct_of_peak_sustained_elapsedsm__inst_issued.sum.per_cycle_activesm__instruction_throughput.avg.pct_of_peak_sustained_elapsedsm__instruction_throughput.max.pct_of_peak_sustained_elapsedsm__instruction_throughput.min.pct_of_peak_sustained_elapsedsm__instruction_throughput.sum.pct_of_peak_sustained_elapsedsm__instruction_throughput_internal_activity.avg.pct_of_peak_sustained_elapsedsm__instruction_throughput_internal_activity.max.pct_of_peak_sustained_elapsedsm__instruction_throughput_internal_activity.min.pct_of_peak_sustained_elapsedsm__instruction_throughput_internal_activity.sum.pct_of_peak_sustained_elapsedsm__issue_active.avg.pct_of_peak_sustained_elapsedsm__issue_active.max.pct_of_peak_sustained_elapsedsm__issue_active.min.pct_of_peak_sustained_elapsedsm__issue_active.sum.pct_of_peak_sustained_elapsedsm__maximum_warps_avg_per_active_cyclesm__maximum_warps_per_active_cycle_pctsm__memory_throughput.avg.pct_of_peak_sustained_elapsedsm__memory_throughput.max.pct_of_peak_sustained_elapsedsm__memory_throughput.min.pct_of_peak_sustained_elapsedsm__memory_throughput.sum.pct_of_peak_sustained_elapsedsm__memory_throughput_internal_activity.avg.pct_of_peak_sustained_elapsedsm__memory_throughput_internal_activity.max.pct_of_peak_sustained_elapsedsm__memory_throughput_internal_activity.min.pct_of_peak_sustained_elapsedsm__memory_throughput_internal_activity.sum.pct_of_peak_sustained_elapsedsm__mio2rf_writeback_active.avg.pct_of_peak_sustained_elapsedsm__mio2rf_writeback_active.max.pct_of_peak_sustained_elapsedsm__mio2rf_writeback_active.min.pct_of_peak_sustained_elapsedsm__mio2rf_writeback_active.sum.pct_of_peak_sustained_elapsedsm__mio_inst_issued.avg.pct_of_peak_sustained_elapsedsm__mio_inst_issued.max.pct_of_peak_sustained_elapsedsm__mio_inst_issued.min.pct_of_peak_sustained_elapsedsm__mio_inst_issued.sum.pct_of_peak_sustained_elapsedsm__mio_pq_read_cycles_active.avg.pct_of_peak_sustained_elapsedsm__mio_pq_read_cycles_active.max.pct_of_peak_sustained_elapsedsm__mio_pq_read_cycles_active.min.pct_of_peak_sustained_elapsedsm__mio_pq_read_cycles_active.sum.pct_of_peak_sustained_elapsedsm__mio_pq_write_cycles_active.avg.pct_of_peak_sustained_elapsedsm__mio_pq_write_cycles_active.max.pct_of_peak_sustained_elapsedsm__mio_pq_write_cycles_active.min.pct_of_peak_sustained_elapsedsm__mio_pq_write_cycles_active.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.avgsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.avg.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.maxsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.max.peak_sustainedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.max.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.minsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.min.peak_sustainedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.min.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.sumsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_off.sum.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.avgsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.avg.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.maxsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.max.peak_sustainedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.max.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.minsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.min.peak_sustainedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.min.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.sumsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_bf16_dst_fp32_sparsity_on.sum.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.avgsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.avg.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.maxsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.max.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.max.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.minsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.min.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.min.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.sumsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_off.sum.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.avgsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.avg.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.maxsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.max.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.max.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.minsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.min.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.min.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.sumsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp16_sparsity_on.sum.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.avgsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.avg.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.maxsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.max.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.max.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.minsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.min.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.min.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.sumsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_off.sum.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.avgsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.avg.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.maxsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.max.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.max.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.minsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.min.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.min.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.sumsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_fp16_dst_fp32_sparsity_on.sum.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.avgsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.avg.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.maxsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.max.peak_sustainedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.max.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.minsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.min.peak_sustainedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.min.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.sumsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_off.sum.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.avgsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.avg.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.maxsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.max.peak_sustainedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.max.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.minsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.min.peak_sustainedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.min.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.sumsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_op_hmma_src_tf32_dst_fp32_sparsity_on.sum.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_off.avgsm__ops_path_tensor_op_imma_src_int8_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.avg.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_off.maxsm__ops_path_tensor_op_imma_src_int8_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.max.peak_sustainedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.max.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_off.minsm__ops_path_tensor_op_imma_src_int8_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.min.peak_sustainedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.min.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_off.sumsm__ops_path_tensor_op_imma_src_int8_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_off.sum.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_on.avgsm__ops_path_tensor_op_imma_src_int8_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.avg.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_on.maxsm__ops_path_tensor_op_imma_src_int8_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.max.peak_sustainedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.max.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_on.minsm__ops_path_tensor_op_imma_src_int8_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.min.peak_sustainedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.min.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_on.sumsm__ops_path_tensor_op_imma_src_int8_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_op_imma_src_int8_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_op_imma_src_int8_sparsity_on.sum.per_secondsm__ops_path_tensor_src_bf16_dst_fp32.avgsm__ops_path_tensor_src_bf16_dst_fp32.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_bf16_dst_fp32.avg.peak_sustainedsm__ops_path_tensor_src_bf16_dst_fp32.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_bf16_dst_fp32.avg.per_cycle_elapsedsm__ops_path_tensor_src_bf16_dst_fp32.avg.per_secondsm__ops_path_tensor_src_bf16_dst_fp32.maxsm__ops_path_tensor_src_bf16_dst_fp32.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_bf16_dst_fp32.max.peak_sustainedsm__ops_path_tensor_src_bf16_dst_fp32.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_bf16_dst_fp32.max.per_cycle_elapsedsm__ops_path_tensor_src_bf16_dst_fp32.max.per_secondsm__ops_path_tensor_src_bf16_dst_fp32.minsm__ops_path_tensor_src_bf16_dst_fp32.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_bf16_dst_fp32.min.peak_sustainedsm__ops_path_tensor_src_bf16_dst_fp32.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_bf16_dst_fp32.min.per_cycle_elapsedsm__ops_path_tensor_src_bf16_dst_fp32.min.per_secondsm__ops_path_tensor_src_bf16_dst_fp32.sumsm__ops_path_tensor_src_bf16_dst_fp32.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_bf16_dst_fp32.sum.peak_sustainedsm__ops_path_tensor_src_bf16_dst_fp32.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_bf16_dst_fp32.sum.per_cycle_elapsedsm__ops_path_tensor_src_bf16_dst_fp32.sum.per_secondsm__ops_path_tensor_src_fp16_dst_fp16.avgsm__ops_path_tensor_src_fp16_dst_fp16.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp16_dst_fp16.avg.peak_sustainedsm__ops_path_tensor_src_fp16_dst_fp16.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp16_dst_fp16.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp16_dst_fp16.avg.per_secondsm__ops_path_tensor_src_fp16_dst_fp16.maxsm__ops_path_tensor_src_fp16_dst_fp16.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp16_dst_fp16.max.peak_sustainedsm__ops_path_tensor_src_fp16_dst_fp16.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp16_dst_fp16.max.per_cycle_elapsedsm__ops_path_tensor_src_fp16_dst_fp16.max.per_secondsm__ops_path_tensor_src_fp16_dst_fp16.minsm__ops_path_tensor_src_fp16_dst_fp16.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp16_dst_fp16.min.peak_sustainedsm__ops_path_tensor_src_fp16_dst_fp16.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp16_dst_fp16.min.per_cycle_elapsedsm__ops_path_tensor_src_fp16_dst_fp16.min.per_secondsm__ops_path_tensor_src_fp16_dst_fp16.sumsm__ops_path_tensor_src_fp16_dst_fp16.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp16_dst_fp16.sum.peak_sustainedsm__ops_path_tensor_src_fp16_dst_fp16.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp16_dst_fp16.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp16_dst_fp16.sum.per_secondsm__ops_path_tensor_src_fp16_dst_fp32.avgsm__ops_path_tensor_src_fp16_dst_fp32.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp16_dst_fp32.avg.peak_sustainedsm__ops_path_tensor_src_fp16_dst_fp32.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp16_dst_fp32.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp16_dst_fp32.avg.per_secondsm__ops_path_tensor_src_fp16_dst_fp32.maxsm__ops_path_tensor_src_fp16_dst_fp32.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp16_dst_fp32.max.peak_sustainedsm__ops_path_tensor_src_fp16_dst_fp32.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp16_dst_fp32.max.per_cycle_elapsedsm__ops_path_tensor_src_fp16_dst_fp32.max.per_secondsm__ops_path_tensor_src_fp16_dst_fp32.minsm__ops_path_tensor_src_fp16_dst_fp32.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp16_dst_fp32.min.peak_sustainedsm__ops_path_tensor_src_fp16_dst_fp32.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp16_dst_fp32.min.per_cycle_elapsedsm__ops_path_tensor_src_fp16_dst_fp32.min.per_secondsm__ops_path_tensor_src_fp16_dst_fp32.sumsm__ops_path_tensor_src_fp16_dst_fp32.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp16_dst_fp32.sum.peak_sustainedsm__ops_path_tensor_src_fp16_dst_fp32.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp16_dst_fp32.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp16_dst_fp32.sum.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.avgsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.avg.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.maxsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.max.peak_sustainedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.max.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.minsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.min.peak_sustainedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.min.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.sumsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_off.sum.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.avgsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.avg.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.maxsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.max.peak_sustainedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.max.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.minsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.min.peak_sustainedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.min.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.sumsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp4_dst_fp32_sparsity_on.sum.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.avgsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.avg.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.maxsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.max.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.max.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.minsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.min.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.min.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.sumsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_off.sum.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.avgsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.avg.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.maxsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.max.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.max.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.minsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.min.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.min.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.sumsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp16_sparsity_on.sum.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.avgsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.avg.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.maxsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.max.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.max.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.minsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.min.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.min.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.sumsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_off.sum.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.avgsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.avg.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.maxsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.max.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.max.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.minsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.min.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.min.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.sumsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp4_fp6_dst_fp32_sparsity_on.sum.per_secondsm__ops_path_tensor_src_fp64.avgsm__ops_path_tensor_src_fp64.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp64.avg.peak_sustainedsm__ops_path_tensor_src_fp64.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp64.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp64.avg.per_secondsm__ops_path_tensor_src_fp64.maxsm__ops_path_tensor_src_fp64.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp64.max.peak_sustainedsm__ops_path_tensor_src_fp64.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp64.max.per_cycle_elapsedsm__ops_path_tensor_src_fp64.max.per_secondsm__ops_path_tensor_src_fp64.minsm__ops_path_tensor_src_fp64.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp64.min.peak_sustainedsm__ops_path_tensor_src_fp64.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp64.min.per_cycle_elapsedsm__ops_path_tensor_src_fp64.min.per_secondsm__ops_path_tensor_src_fp64.sumsm__ops_path_tensor_src_fp64.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp64.sum.peak_sustainedsm__ops_path_tensor_src_fp64.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp64.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp64.sum.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.avgsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.avg.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.maxsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.max.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.max.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.minsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.min.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.min.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.sumsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_off.sum.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.avgsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.avg.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.maxsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.max.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.max.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.minsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.min.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.min.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.sumsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp16_sparsity_on.sum.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.avgsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.avg.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.avg.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.maxsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.max.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.max.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.max.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.minsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.min.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.min.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.min.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.sumsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.sum.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_off.sum.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.avgsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.avg.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.avg.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.avg.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.maxsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.max.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.max.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.max.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.minsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.min.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.min.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.min.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.sumsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.sum.peak_sustainedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.sum.per_cycle_elapsedsm__ops_path_tensor_src_fp8_dst_fp32_sparsity_on.sum.per_secondsm__ops_path_tensor_src_int8.avgsm__ops_path_tensor_src_int8.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_int8.avg.peak_sustainedsm__ops_path_tensor_src_int8.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_int8.avg.per_cycle_elapsedsm__ops_path_tensor_src_int8.avg.per_secondsm__ops_path_tensor_src_int8.maxsm__ops_path_tensor_src_int8.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_int8.max.peak_sustainedsm__ops_path_tensor_src_int8.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_int8.max.per_cycle_elapsedsm__ops_path_tensor_src_int8.max.per_secondsm__ops_path_tensor_src_int8.minsm__ops_path_tensor_src_int8.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_int8.min.peak_sustainedsm__ops_path_tensor_src_int8.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_int8.min.per_cycle_elapsedsm__ops_path_tensor_src_int8.min.per_secondsm__ops_path_tensor_src_int8.sumsm__ops_path_tensor_src_int8.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_int8.sum.peak_sustainedsm__ops_path_tensor_src_int8.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_int8.sum.per_cycle_elapsedsm__ops_path_tensor_src_int8.sum.per_secondsm__ops_path_tensor_src_tf32_dst_fp32.avgsm__ops_path_tensor_src_tf32_dst_fp32.avg.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_tf32_dst_fp32.avg.peak_sustainedsm__ops_path_tensor_src_tf32_dst_fp32.avg.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_tf32_dst_fp32.avg.per_cycle_elapsedsm__ops_path_tensor_src_tf32_dst_fp32.avg.per_secondsm__ops_path_tensor_src_tf32_dst_fp32.maxsm__ops_path_tensor_src_tf32_dst_fp32.max.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_tf32_dst_fp32.max.peak_sustainedsm__ops_path_tensor_src_tf32_dst_fp32.max.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_tf32_dst_fp32.max.per_cycle_elapsedsm__ops_path_tensor_src_tf32_dst_fp32.max.per_secondsm__ops_path_tensor_src_tf32_dst_fp32.minsm__ops_path_tensor_src_tf32_dst_fp32.min.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_tf32_dst_fp32.min.peak_sustainedsm__ops_path_tensor_src_tf32_dst_fp32.min.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_tf32_dst_fp32.min.per_cycle_elapsedsm__ops_path_tensor_src_tf32_dst_fp32.min.per_secondsm__ops_path_tensor_src_tf32_dst_fp32.sumsm__ops_path_tensor_src_tf32_dst_fp32.sum.pct_of_peak_sustained_elapsedsm__ops_path_tensor_src_tf32_dst_fp32.sum.peak_sustainedsm__ops_path_tensor_src_tf32_dst_fp32.sum.peak_sustained_elapsed.per_secondsm__ops_path_tensor_src_tf32_dst_fp32.sum.per_cycle_elapsedsm__ops_path_tensor_src_tf32_dst_fp32.sum.per_secondsm__pipe_alu_cycles_active.avg.pct_of_peak_sustained_activesm__pipe_alu_cycles_active.avg.pct_of_peak_sustained_elapsedsm__pipe_alu_cycles_active.max.pct_of_peak_sustained_activesm__pipe_alu_cycles_active.max.pct_of_peak_sustained_elapsedsm__pipe_alu_cycles_active.min.pct_of_peak_sustained_activesm__pipe_alu_cycles_active.min.pct_of_peak_sustained_elapsedsm__pipe_alu_cycles_active.sum.pct_of_peak_sustained_activesm__pipe_alu_cycles_active.sum.pct_of_peak_sustained_elapsedsm__pipe_aluheavy_cycles_active.avg.pct_of_peak_sustained_elapsedsm__pipe_aluheavy_cycles_active.max.pct_of_peak_sustained_elapsedsm__pipe_aluheavy_cycles_active.min.pct_of_peak_sustained_elapsedsm__pipe_aluheavy_cycles_active.sum.pct_of_peak_sustained_elapsedsm__pipe_fma_cycles_active.avg.pct_of_peak_sustained_activesm__pipe_fma_cycles_active.avg.pct_of_peak_sustained_elapsedsm__pipe_fma_cycles_active.max.pct_of_peak_sustained_activesm__pipe_fma_cycles_active.max.pct_of_peak_sustained_elapsedsm__pipe_fma_cycles_active.min.pct_of_peak_sustained_activesm__pipe_fma_cycles_active.min.pct_of_peak_sustained_elapsedsm__pipe_fma_cycles_active.sum.pct_of_peak_sustained_activesm__pipe_fma_cycles_active.sum.pct_of_peak_sustained_elapsedsm__pipe_fmaheavy_cycles_active.avg.pct_of_peak_sustained_elapsedsm__pipe_fmaheavy_cycles_active.max.pct_of_peak_sustained_elapsedsm__pipe_fmaheavy_cycles_active.min.pct_of_peak_sustained_elapsedsm__pipe_fmaheavy_cycles_active.sum.pct_of_peak_sustained_elapsedsm__pipe_fp64_cycles_active.avg.pct_of_peak_sustained_activesm__pipe_fp64_cycles_active.avg.pct_of_peak_sustained_elapsedsm__pipe_fp64_cycles_active.max.pct_of_peak_sustained_activesm__pipe_fp64_cycles_active.max.pct_of_peak_sustained_elapsedsm__pipe_fp64_cycles_active.min.pct_of_peak_sustained_activesm__pipe_fp64_cycles_active.min.pct_of_peak_sustained_elapsedsm__pipe_fp64_cycles_active.sum.pct_of_peak_sustained_activesm__pipe_fp64_cycles_active.sum.pct_of_peak_sustained_elapsedsm__pipe_tensor_cycles_active.avg.pct_of_peak_sustained_activesm__pipe_tensor_cycles_active.avg.pct_of_peak_sustained_elapsedsm__pipe_tensor_cycles_active.max.pct_of_peak_sustained_activesm__pipe_tensor_cycles_active.max.pct_of_peak_sustained_elapsedsm__pipe_tensor_cycles_active.min.pct_of_peak_sustained_activesm__pipe_tensor_cycles_active.min.pct_of_peak_sustained_elapsedsm__pipe_tensor_cycles_active.sum.pct_of_peak_sustained_activesm__pipe_tensor_cycles_active.sum.pct_of_peak_sustained_elapsedsm__pipe_tensor_subpipe_hmma_cycles_active.avg.pct_of_peak_sustained_activesm__pipe_tensor_subpipe_hmma_cycles_active.avg.pct_of_peak_sustained_elapsedsm__pipe_tensor_subpipe_imma_cycles_active.avg.pct_of_peak_sustained_activesm__pipe_tensor_subpipe_imma_cycles_active.avg.pct_of_peak_sustained_elapsedsm__pipe_tma_cycles_active.avg.pct_of_peak_sustained_activesm__pipe_tma_cycles_active.avg.pct_of_peak_sustained_elapsedsm__pipe_tma_cycles_active.max.pct_of_peak_sustained_activesm__pipe_tma_cycles_active.max.pct_of_peak_sustained_elapsedsm__pipe_tma_cycles_active.min.pct_of_peak_sustained_activesm__pipe_tma_cycles_active.min.pct_of_peak_sustained_elapsedsm__pipe_tma_cycles_active.sum.pct_of_peak_sustained_activesm__pipe_tma_cycles_active.sum.pct_of_peak_sustained_elapsedsm__sass_inst_executed_op_ldgsts_cache_access.sumsm__sass_inst_executed_op_ldgsts_cache_bypass.sumsm__sass_l1tex_m_xbar2l1tex_read_bytes_mem_global_op_ldgsts_cache_bypass.sumsm__sass_l1tex_m_xbar2l1tex_read_bytes_mem_global_op_ldgsts_cache_bypass.sum.pct_of_peak_sustained_elapsedsm__sass_l1tex_m_xbar2l1tex_read_bytes_mem_global_op_ldgsts_cache_bypass.sum.per_secondsm__sass_l1tex_t_requests_pipe_lsu_mem_global_op_ldgsts.sumsm__sass_l1tex_t_requests_pipe_lsu_mem_global_op_ldgsts.sum.pct_of_peak_sustained_elapsedsm__sass_l1tex_t_requests_pipe_lsu_mem_global_op_ldgsts_cache_access.sumsm__sass_l1tex_t_requests_pipe_lsu_mem_global_op_ldgsts_cache_bypass.sumsm__sass_l1tex_t_sectors_pipe_lsu_mem_global_op_ldgsts_cache_access.sumsm__sass_l1tex_t_sectors_pipe_lsu_mem_global_op_ldgsts_cache_access.sum.pct_of_peak_sustained_elapsedsm__sass_l1tex_t_sectors_pipe_lsu_mem_global_op_ldgsts_cache_bypass.sumsm__sass_l1tex_t_sectors_pipe_lsu_mem_global_op_ldgsts_cache_bypass.sum.pct_of_peak_sustained_elapsedsm__sass_thread_inst_executed_op_dfma_pred_on.avg.peak_sustainedsm__sass_thread_inst_executed_op_dfma_pred_on.max.peak_sustainedsm__sass_thread_inst_executed_op_dfma_pred_on.min.peak_sustainedsm__sass_thread_inst_executed_op_dfma_pred_on.sum.peak_sustainedsm__sass_thread_inst_executed_op_ffma_pred_on.avg.peak_sustainedsm__sass_thread_inst_executed_op_ffma_pred_on.max.peak_sustainedsm__sass_thread_inst_executed_op_ffma_pred_on.min.peak_sustainedsm__sass_thread_inst_executed_op_ffma_pred_on.sum.peak_sustainedsm__sass_thread_inst_executed_op_hfma_pred_on.avg.peak_sustainedsm__sass_thread_inst_executed_op_hfma_pred_on.max.peak_sustainedsm__sass_thread_inst_executed_op_hfma_pred_on.min.peak_sustainedsm__sass_thread_inst_executed_op_hfma_pred_on.sum.peak_sustainedsm__throughput.avg.pct_of_peak_sustained_elapsedsm__throughput.max.pct_of_peak_sustained_elapsedsm__throughput.min.pct_of_peak_sustained_elapsedsm__throughput.sum.pct_of_peak_sustained_elapsedsm__warps_active.avg.pct_of_peak_sustained_activesm__warps_active.avg.per_cycle_activesm__warps_active.max.pct_of_peak_sustained_activesm__warps_active.max.per_cycle_activesm__warps_active.min.pct_of_peak_sustained_activesm__warps_active.min.per_cycle_activesm__warps_active.sum.pct_of_peak_sustained_activesm__warps_active.sum.per_cycle_activesmsp__average_warp_latency_per_inst_issued.ratiosmsp__average_warps_active_per_inst_executed.ratiosmsp__average_warps_issue_stalled_barrier_per_issue_active.ratiosmsp__average_warps_issue_stalled_branch_resolving_per_issue_active.ratiosmsp__average_warps_issue_stalled_dispatch_stall_per_issue_active.ratiosmsp__average_warps_issue_stalled_drain_per_issue_active.ratiosmsp__average_warps_issue_stalled_lg_throttle_per_issue_active.ratiosmsp__average_warps_issue_stalled_long_scoreboard_per_issue_active.ratiosmsp__average_warps_issue_stalled_math_pipe_throttle_per_issue_active.ratiosmsp__average_warps_issue_stalled_membar_per_issue_active.ratiosmsp__average_warps_issue_stalled_mio_throttle_per_issue_active.ratiosmsp__average_warps_issue_stalled_misc_per_issue_active.ratiosmsp__average_warps_issue_stalled_no_instruction_per_issue_active.ratiosmsp__average_warps_issue_stalled_not_selected_per_issue_active.ratiosmsp__average_warps_issue_stalled_selected_per_issue_active.ratiosmsp__average_warps_issue_stalled_short_scoreboard_per_issue_active.ratiosmsp__average_warps_issue_stalled_sleeping_per_issue_active.ratiosmsp__average_warps_issue_stalled_tex_throttle_per_issue_active.ratiosmsp__average_warps_issue_stalled_wait_per_issue_active.ratiosmsp__branch_targets_threads_divergentsmsp__cycles_active.avgsmsp__cycles_active.maxsmsp__cycles_active.minsmsp__cycles_active.sumsmsp__cycles_elapsed.avgsmsp__cycles_elapsed.avg.per_secondsmsp__cycles_elapsed.maxsmsp__cycles_elapsed.max.per_secondsmsp__cycles_elapsed.minsmsp__cycles_elapsed.min.per_secondsmsp__cycles_elapsed.sumsmsp__cycles_elapsed.sum.per_secondsmsp__inst_executed.avgsmsp__inst_executed.maxsmsp__inst_executed.minsmsp__inst_executed.sumsmsp__inst_executed_op_branch.avgsmsp__inst_executed_op_branch.maxsmsp__inst_executed_op_branch.minsmsp__inst_executed_op_branch.sumsmsp__inst_executed_op_generic_atom_dot_alu.sumsmsp__inst_executed_op_generic_atom_dot_alu.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_generic_atom_dot_cas.sumsmsp__inst_executed_op_generic_atom_dot_cas.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_global_red.sumsmsp__inst_executed_op_global_red.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_ldgsts.sumsmsp__inst_executed_op_ldgsts.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_ldsm.sumsmsp__inst_executed_op_ldsm.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_shared_atom.sumsmsp__inst_executed_op_shared_atom.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_shared_stsm.sumsmsp__inst_executed_op_shared_stsm.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_surface_atom_dot_alu.sumsmsp__inst_executed_op_surface_atom_dot_alu.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_surface_atom_dot_cas.sumsmsp__inst_executed_op_surface_atom_dot_cas.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_surface_ld.sumsmsp__inst_executed_op_surface_ld.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_surface_red.sumsmsp__inst_executed_op_surface_red.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_surface_st.sumsmsp__inst_executed_op_surface_st.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_texture.sumsmsp__inst_executed_op_texture.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_tma_ld.sumsmsp__inst_executed_op_tma_ld.sum.pct_of_peak_sustained_elapsedsmsp__inst_executed_op_tma_st.sumsmsp__inst_executed_op_tma_st.sum.pct_of_peak_sustained_elapsedsmsp__inst_issued.avgsmsp__inst_issued.maxsmsp__inst_issued.minsmsp__inst_issued.sumsmsp__issue_active.avg.pct_of_peak_sustained_activesmsp__issue_active.avg.per_cycle_activesmsp__issue_active.max.pct_of_peak_sustained_activesmsp__issue_active.max.per_cycle_activesmsp__issue_active.min.pct_of_peak_sustained_activesmsp__issue_active.min.per_cycle_activesmsp__issue_active.sum.pct_of_peak_sustained_activesmsp__issue_active.sum.per_cycle_activesmsp__issue_inst0.avg.pct_of_peak_sustained_activesmsp__issue_inst0.max.pct_of_peak_sustained_activesmsp__issue_inst0.min.pct_of_peak_sustained_activesmsp__issue_inst0.sum.pct_of_peak_sustained_activesmsp__maximum_warps_avg_per_active_cyclesmsp__pcsamp_aggregated_passessmsp__pcsamp_buffer_size_bytessmsp__pcsamp_dropped_bytessmsp__pcsamp_intervalsmsp__pcsamp_interval_cyclessmsp__pcsamp_sample_countsmsp__pcsamp_warps_issue_stalled_barriersmsp__pcsamp_warps_issue_stalled_barrier_not_issuedsmsp__pcsamp_warps_issue_stalled_branch_resolvingsmsp__pcsamp_warps_issue_stalled_branch_resolving_not_issuedsmsp__pcsamp_warps_issue_stalled_dispatch_stallsmsp__pcsamp_warps_issue_stalled_dispatch_stall_not_issuedsmsp__pcsamp_warps_issue_stalled_drainsmsp__pcsamp_warps_issue_stalled_drain_not_issuedsmsp__pcsamp_warps_issue_stalled_lg_throttlesmsp__pcsamp_warps_issue_stalled_lg_throttle_not_issuedsmsp__pcsamp_warps_issue_stalled_long_scoreboardsmsp__pcsamp_warps_issue_stalled_long_scoreboard_not_issuedsmsp__pcsamp_warps_issue_stalled_math_pipe_throttlesmsp__pcsamp_warps_issue_stalled_math_pipe_throttle_not_issuedsmsp__pcsamp_warps_issue_stalled_membarsmsp__pcsamp_warps_issue_stalled_membar_not_issuedsmsp__pcsamp_warps_issue_stalled_mio_throttlesmsp__pcsamp_warps_issue_stalled_mio_throttle_not_issuedsmsp__pcsamp_warps_issue_stalled_miscsmsp__pcsamp_warps_issue_stalled_misc_not_issuedsmsp__pcsamp_warps_issue_stalled_no_instructionssmsp__pcsamp_warps_issue_stalled_no_instructions_not_issuedsmsp__pcsamp_warps_issue_stalled_not_selectedsmsp__pcsamp_warps_issue_stalled_not_selected_not_issuedsmsp__pcsamp_warps_issue_stalled_selectedsmsp__pcsamp_warps_issue_stalled_selected_not_issuedsmsp__pcsamp_warps_issue_stalled_short_scoreboardsmsp__pcsamp_warps_issue_stalled_short_scoreboard_not_issuedsmsp__pcsamp_warps_issue_stalled_sleepingsmsp__pcsamp_warps_issue_stalled_sleeping_not_issuedsmsp__pcsamp_warps_issue_stalled_tex_throttlesmsp__pcsamp_warps_issue_stalled_tex_throttle_not_issuedsmsp__pcsamp_warps_issue_stalled_waitsmsp__pcsamp_warps_issue_stalled_wait_not_issuedsmsp__sass_average_branch_targets_threads_uniform.pctsmsp__sass_average_data_bytes_per_sector_mem_global_op_ld.max_ratesmsp__sass_average_data_bytes_per_sector_mem_global_op_ld.ratiosmsp__sass_average_data_bytes_per_sector_mem_global_op_st.max_ratesmsp__sass_average_data_bytes_per_sector_mem_global_op_st.ratiosmsp__sass_average_data_bytes_per_sector_mem_local_op_ld.max_ratesmsp__sass_average_data_bytes_per_sector_mem_local_op_ld.ratiosmsp__sass_average_data_bytes_per_sector_mem_local_op_st.max_ratesmsp__sass_average_data_bytes_per_sector_mem_local_op_st.ratiosmsp__sass_branch_targets_threads_divergent.avgsmsp__sass_branch_targets_threads_divergent.maxsmsp__sass_branch_targets_threads_divergent.minsmsp__sass_branch_targets_threads_divergent.sumsmsp__sass_inst_executed_memdesc_explicit_evict_typesmsp__sass_inst_executed_memdesc_explicit_hitprop_evict_firstsmsp__sass_inst_executed_memdesc_explicit_hitprop_evict_lastsmsp__sass_inst_executed_memdesc_explicit_hitprop_evict_normalsmsp__sass_inst_executed_memdesc_explicit_hitprop_evict_normal_demotesmsp__sass_inst_executed_memdesc_explicit_missprop_evict_firstsmsp__sass_inst_executed_memdesc_explicit_missprop_evict_normalsmsp__sass_inst_executed_op_dshared.sumsmsp__sass_inst_executed_op_dshared.sum.pct_of_peak_sustained_elapsedsmsp__sass_inst_executed_op_dshared_atom.sumsmsp__sass_inst_executed_op_dshared_ld.sumsmsp__sass_inst_executed_op_dshared_redas.sumsmsp__sass_inst_executed_op_dshared_st.sumsmsp__sass_inst_executed_op_dshared_stas.sumsmsp__sass_inst_executed_op_dshared_tma_red.sumsmsp__sass_inst_executed_op_dshared_tma_st.sumsmsp__sass_inst_executed_op_global_ld.sumsmsp__sass_inst_executed_op_global_st.sumsmsp__sass_inst_executed_op_local_ld.sumsmsp__sass_inst_executed_op_local_st.sumsmsp__sass_inst_executed_op_shared.sumsmsp__sass_inst_executed_op_shared.sum.pct_of_peak_sustained_elapsedsmsp__sass_inst_executed_op_shared_ld.sumsmsp__sass_inst_executed_op_shared_st.sumsmsp__sass_inst_executed_op_tma_ld.sumsmsp__sass_inst_executed_op_tma_red.sumsmsp__sass_inst_executed_op_tma_st.sumsmsp__sass_l1tex_data_pipe_lsu_wavefronts_mem_shared_op_ldgsts.sumsmsp__sass_l1tex_data_pipe_lsu_wavefronts_mem_shared_op_ldgsts.sum.pct_of_peak_sustained_elapsedsmsp__sass_l1tex_data_pipe_lsu_wavefronts_mem_shared_op_ldgsts_cache_access.sumsmsp__sass_l1tex_data_pipe_lsu_wavefronts_mem_shared_op_ldgsts_cache_access.sum.pct_of_peak_sustained_elapsedsmsp__sass_l1tex_m_xbar2l1tex_read_sectors_mem_global_op_ldgsts_cache_bypass.sumsmsp__sass_l1tex_m_xbar2l1tex_read_sectors_mem_global_op_ldgsts_cache_bypass.sum.pct_of_peak_sustained_elapsedsmsp__sass_thread_inst_executed_op_dadd_pred_on.avg.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dadd_pred_on.max.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dadd_pred_on.min.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dadd_pred_on.sum.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dfma_pred_on.avg.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dfma_pred_on.max.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dfma_pred_on.min.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dfma_pred_on.sum.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dmul_pred_on.avg.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dmul_pred_on.max.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dmul_pred_on.min.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_dmul_pred_on.sum.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_fadd_pred_on.avg.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_fadd_pred_on.max.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_fadd_pred_on.min.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_fadd_pred_on.sum.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_ffma_pred_on.avg.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_ffma_pred_on.max.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_ffma_pred_on.min.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_ffma_pred_on.sum.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_fmul_pred_on.avg.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_fmul_pred_on.max.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_fmul_pred_on.min.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_fmul_pred_on.sum.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hadd_pred_on.avg.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hadd_pred_on.max.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hadd_pred_on.min.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hadd_pred_on.sum.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hfma_pred_on.avg.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hfma_pred_on.max.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hfma_pred_on.min.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hfma_pred_on.sum.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hmul_pred_on.avg.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hmul_pred_on.max.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hmul_pred_on.min.per_cycle_elapsedsmsp__sass_thread_inst_executed_op_hmul_pred_on.sum.per_cycle_elapsedsmsp__thread_inst_executed_per_inst_executed.ratiosmsp__thread_inst_executed_pred_on_per_inst_executed.ratiosmsp__warps_active.avg.peak_sustainedsmsp__warps_active.avg.per_cycle_activesmsp__warps_active.max.peak_sustainedsmsp__warps_active.max.per_cycle_activesmsp__warps_active.min.peak_sustainedsmsp__warps_active.min.per_cycle_activesmsp__warps_active.sum.peak_sustainedsmsp__warps_active.sum.per_cycle_activesmsp__warps_eligible.avg.per_cycle_activesmsp__warps_eligible.max.per_cycle_activesmsp__warps_eligible.min.per_cycle_activesmsp__warps_eligible.sum.per_cycle_activethread_inst_executedthread_inst_executed_true
2threadthreadthreadthread%KbyteGbytebyte%%/register%/Kbytethreadthreadthread%threadthreadthreadthreadthreadrequest%request%%cycleGhzcycleGhzcycleGhzcycleGhz%%%%%%%%%%%%%%%%%%%%msmsmsmsblockblockblockblock%%%%%%instcyclecyclecyclecyclecycleGhzcycleGhzcycleGhzcycleGhz%%%%%%%%%%%%%%%%%%%%%%%%%%%%cycle%Mhz%%%%%%%%Mbyte%Gbyte/sbyte%byte/sbyte%byte/sMbyte%Gbyte/ssector%sector/ssector%sector/ssector%sector/ssector%sector/ssector%sector%sector%sector%sector%sector/ssector%sector/ussector%sector%sector%sector%Gbyte%Gbyte/sbyte%byte/sGbyte%Gbyte/s%%%%sector%sector/ssector%sector/ssector%sector/ssector%sector/ssector%sector%sector%sector%sector/nssector%sector%sector%sector%byte%byte/s%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%sectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsector%%%cycle%%%%%%%%%%%%%blockblockblockclusterblock%%blockblockblockblockblockMbyteregister/threadregister/threadKbyteKbyte/blockKbyte/blockKbyte/blockKbyte/blockbyte/blockSMthread%sector%cyclecyclecyclecyclecycleGhzcycleGhzcycleGhzcycleGhz%%%%%%%%%%%%sector%sector/nssectorsectorsectorsector%Mhz%Mhz%Mhz%Ghzrequestrequestrequestrequestrequestrequestrequestrequest%%%sector%sector/cyclesector/cyclesector%sector%sector%sector/nssector%sector/us%sector/cyclesector/cyclesectorsector/ssectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsector%sector/ns%sector/cyclesector/cyclesectorsector/ussectorsector%sector/cyclesector/cycle%%sector%sector/nssectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsectorsector%sector/s%sector/cyclesector/cyclesectorsector/ssectorsector%sector/cyclesector/cyclesectorsector/ssectorsectorsectorsectorsectorsectorsectorsector%sector/cyclesector/cyclesector%sector/nssectorsectorsectorsectorsectorsectorsectorsectorsectorsector%sector/cyclesector/cyclesector%sector/ssectorsector%sector/cyclesector/cyclesector%sector/ussectorsectorsectorsectorsectorsectorsectorsectorsectorsector%%%%%%%%%%%%sector%sector/ssector%sector/ssectorssectorssectorssectorssectorssectorsblockcycle%%%cycle%inst/cycle%%%warpwarpMbyteussampleGbyteGbyteGbyteGbyteGbyteGbyteGbyteGbytepasspassinstinstinstinstinstinstinstinstinstinstinstcyclecyclecyclecyclecycleGhzcycleGhzcycleGhzcycleGhz%cycle%cycle%cycle%%inst/cycleinst/cycle%inst/cycleinst/cycle%inst/cycleinst/cycle%inst/cycleinst/cycle%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%inst/cycle%inst/cycle%inst/cycle%inst/cycle%%%%%%%%%%%%warp%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%instinstbyte%byte/s%sector%sector%inst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycle%%%%%warp%warp%warp%warpcyclecycleinstinstinstinstinstinstinstinstinstinstinstinstinstinstinstinstinstbranchescyclecyclecyclecyclecycleGhzcycleGhzcycleGhzcycleGhzinstinstinstinstinstinstinstinstinst%inst%inst%inst%inst%inst%inst%inst%inst%inst%inst%inst%inst%inst%inst%instinstinstinst%%%%%%%%warppassMbytebytecyclewarpwarpbranchesbrancheswarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpinstinstwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarp%byte/sectorbyte/sectorbyte/sectorbyte/sectorbyte/sectorbyte/sectorbyte/sectorbyte/sectorbranchesbranchesbranchesbranchesinstinstinstinstinstinstinst%instinstinstinstinstinstinstinstinstinstinstinst%instinstinstinstinst%%sector%inst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cycleinst/cyclewarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpwarpinstinst
3073python3.12127.0.0.1void at::vectorized_elementwise_kernel<4, at::BinaryFunctor<float, float, float, at::MulFunctor<float>>, std::array<char *, 3>>(int, T2, T3)17(128, 1, 1)(1, 1, 1)012.101380220783874.0000001694614434334763.9500.0000001.0240003.3261800006925270.00000010876.0000001.959000192.00000012288.00000012288.0000000.07566500.00000000.12880503748900nan04321011101010443241800011210111No-CC11100NVIDIA GB1000256411256100100177293590211794320001604250016161431801001014431112516582424242411134217728102410246424241800021474836476553565535418533000188743682147483647655366553625549152101376102400102415364812204832768327686553632768204832768131072163841638416384204632768327682048327682684354563276813107232768327686553632768204832768650002097120131072327683276813107216384327681638481921638481922046327683276848533000110000486410111015101024126411512015123265536130661769216111324.0000000.00628930.0000000.0471706720.52830215900.0000002.13251115903.0000002.13291315897.0000002.13210863600.0000008.5300430.2642630.8610430.0140010.2642630.1461320.4480220.0140010.1461320.2515750.9182390.0566040.25157500000.2642630.9182390.0566040.2642630.0074560.0074560.0074560.00745600000.0000000.0000000.0000000.00000000000.0264681.2704400.0000000.02646853.623188690.01808248946.6250002238.0000000.0000002238.00000015900.0000002.13251115903.0000002.13291315897.0000002.132108763200.000000102.360515000000.0000080.0003930.0000000.0000080.0000370.0017690.0000000.0000370.0095650.4591190.0000000.009565700.0091720000.00000000.000000000000000.0007860.0377360.0000000.0007862.0000000.000262480.2682400.0191300.9182390.0000000.0191300.0129720.0314470.0125790.0129720.0000320.0001310.0042920000000.0000000.0000000.000000000000000000000000000000.0000000.0000000.0000001.0000000.0001310000000.0000000.0002620.0085840000.0000000.0000000.0000000.0002620.0125790.0000000.0002620000000000000000000.0000000.0000000.0000002.0000000.00026200000000000000000020.0002620010.00013100.00000000.0000000000000000000000000020.0002620010.00013100.00000000.00000000000000000.00000000.000000000.0000000.00000000000000000000002.0000000.0000002.0000000001.00000001.0000000.0000000.00000000.0000000.0000000.000000000000000000000000000.0566040.0566040.0566040.05660419.3029490.056604313.1367290.91823919.3029490.05660419.3029490.05660401281112800008PolicySpread010CachePreferNone111110024.00000024.00000012.00000032.00000012.0000003362540052649564.71859200004040.00000032.7680001.0240001.0240001.0240000.0000000481024712824all000000.00100000001253.8750003557.000000149.00000020062.00000014285.0000001.91590714285.0000001.91590714285.0000001.915907228560.00000030.654506000000000.1697580.4340220.0000000.169758185.0000000.0809420.02481200000.16954026.4964460.700035226.8240340.00700020.2682400.169540320.103943301.000000176.0000003.000000002.00000001.00000048.75827873.6842111.99501275.5000000.2642632.0000000.005285246.0000000.8610432.0000000.0070001208.0000000.2642630.162017401.0000000.17544653.78218908.00000000057.000000284.0000000000549.000000193.000000589.000000535.0000000.0000000.0000000.0000000.3080151.0000000.003080704.00000094.420601533.000000171.0000000.0006562.0000000.0000130.0035000.0000003.0000000.0006560.00040200000.1875001.0000000.0000003.0000000000000.0000003.0000000.0000000.1875001.0000000.0000003.00000000001.0000000000001.000000000000000000.0004382.0000000.0000092.0000000.0004380.0002680000000.0000002.0000000.0000002.00000001.0000000000000.0004381.0000000.0000041.0000000.0004380.13412000000001.00000001.0000000.1391320.4690230.0000000.1391320.2642630.8610430.0140010.2642630.2515750.6020300.0140010.25157500000000300330011110000000010000000000.0000001.520.125000641.2291670.0000550.1541190.0000000.0001170.0000230.28646913.75053204.194304113.0000000225.18585625.18585625.185856957.06254125.18585625.18585625.185856957.06254138.000000011112.0000001.0000000.0000000.0000004894894894890no datano data000.0000000.000000833183318331833146.6250002238.0000000.0000002238.00000015900.0000002.13251115903.0000002.13291315897.0000002.132108763200.000000102.3605150.0000008.0000000.0010480.00000073.333333120.0000000.0314470.0160180.2184990.0006410.76886810.4879360.0307550.0000000.0000000.0000000.01601810.4879360.0307559.7408400.028564467.5603221.3710690.0000000.0000009.7408400.0285641.8431640.00540588.4718500.2594340.0000000.0000001.8431640.0054050.2904380.00085213.9410190.0408810.0000000.0000000.2904380.0008520.0034070.1635220.0000000.0034071.3516530.00396464.8793570.1902520.0000000.0000001.3516530.0039640.3574620.00104800000000000000000000000000006.5236820.019130313.1367290.9182390.0000000.0000006.5236820.0191300.0000000.00000000000000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000000000000.0160510.2189450.77044010.5093830.0000000.0000000.01605110.5093830.0160510.7704400.0000000.01605100000.0160510.7704400.0000000.01605148.000000100.0000000.0285641.3710690.0000000.0285640.0010480.0503140.0000000.0010480.0025880.1242140.0000000.0025880.0158980.7631030.0000000.0158980.0003930.0188680.0000000.0003930.0003930.0188680.0000000.0003930010242183690987124.46000010242183690987124.46000010242183690987124.46000049152104817167381974.25000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.50000010242183690987124.46000010242183690987124.46000010242183690987124.46000049152104817167381974.25000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.50000010242183690987124.46000010242183690987124.46000010242183690987124.46000049152104817167381974.25000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.5000005121091845493562.2300005121091845493562.2300005121091845493562.2300002457652408583690987.12000010242183690987124.46000010242183690987124.46000010242183690987124.46000049152104817167381974.25000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.50000040968734763948497.85000040968734763948497.85000040968734763948497.850000196608419268669527897000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.50000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.50000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.500000.00000040968734763948497.850000.00000040968734763948497.850000.00000040968734763948497.850000.0000001966084192686695278970000819217469527896995.710000819217469527896995.710000819217469527896995.710000393216838537339055794000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.50000040968734763948497.85000040968734763948497.85000040968734763948497.850000196608419268669527897000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.50000040968734763948497.85000040968734763948497.85000040968734763948497.85000019660841926866952789700003.517478393791.5200003.517478393791.5200003.517478393791.520000168.33358962901993.06000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.50000040968734763948497.85000040968734763948497.85000040968734763948497.850000196608419268669527897000020484367381974248.93000020484367381974248.93000020484367381974248.93000098304209634334763948.50000040968734763948497.85000040968734763948497.85000040968734763948497.850000196608419268669527897000040968734763948497.85000040968734763948497.85000040968734763948497.850000196608419268669527897000010242183690987124.46000010242183690987124.46000010242183690987124.46000049152104817167381974.25001.8431640.00540588.4718500.2594340.0000000.0000001.8431640.0054050.0064200.3081760.0000000.0064200.8042900.00235838.6058980.1132080.0000000.0000000.8042900.0023580.0157890.7578620.0000000.015789000000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.000000000.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00000000000000000002.0000002.0000002.00000096.000000128.000000128.000000128.0000006144.00000064.00000064.00000064.0000003072.0000000.0285641.3710690.0000000.02856432.53090615.6148351561.483467749.5120640.0000000.00000032.530906749.51206412.93877612.9652350.0000000.3816330.0081630.01632701.8224490.02244900.0000000.01224590.1387760.0000001.0000002.0734690.00000002.055102133.0520832259.0000000.0000006346.00000015900.0000002.13251115903.0000002.13291315897.0000002.1321083052800.000000409.4420602.546875132.0000000.000000489.0000000.19270813.0000000.00000037.000000000000000.0000000.000000000.0000000.0000000000000000000.0000000.0000000.0000000.0000002.552083133.0000000.000000490.0000007.7213990.08402.3952104.020.00000007.72139914.8392.2786016432.2722980.00000092.27860112.000000233.554432051024.00000016000000000088000000006600002200000094.73684232.0000004.00000032.0000004.00000032.0000000.00000032.0000000.0000000.0052081.00000001.00000000000000000000002.0000001.0000000.0000000.0000000.0000000.0000000.0000000.0000000.00000000.00000000000000000000000000000.0000000.0000000.0000000.0000000.0002940.01408800.05635200000.0001680.00805000.032201000031.1517.0412.0000000.99905512.00000069.28458912.0000000.0000002304.000000191.8184680.0772144.0239520.00000014.825087152338331
4173python3.12127.0.0.1cutlass3x_sm120_bstensorop_s16864gemm_block_scaled_ue4m3xe2m1_ue4m3xe2m1_f32_bf16_bf16_128x128x256_1x1x1_0_tnn_align32_o_vs16_bias_bf16_relu_stream_k17(384, 1, 1)(42, 296, 1)012.1015616752394354166.000000759861441620772988.98696768100.0000001.024000466.239645294445562880625316.0000004225.0000004.975000192.00000012288.00000012288.0000000.03318003.44326200.0000000429966141295861238576696768114321011101010443241800011210111No-CC11100NVIDIA GB1000256411256100100177293590211794320001604250016161431801001014431112516582424242411134217728102410246424241800021474836476553565535418533000188743682147483647655366553625549152101376102400102415364812204832768327686553632768204832768131072163841638416384204632768327682048327682684354563276813107232768327686553632768204832768650002097120131072327683276813107216384327681638481921638481922046327683276848533000110000486410111015101024126411512015123265536130661769216111322798544.0000000.5913599028.0000000.001908107120.001132118309837.7500002.148848118334635.0000002.149298118285340.0000002.148403473239351.0000008.59539023.97468623.99390123.96153223.97468612.55926912.62896212.48990712.55926923.59883323.61692723.58328923.598833000023.97468623.99390123.96153223.97468655.05734455.05734455.05734455.0573441238412384123841238412384.00000012384.00000012384.00000012384.000000124321243212432124320.0703230.0703260.0703100.07032399.72163019912320.0701281259175041118776167.583333118805817.000000118739425.0000005701256044.000000118309837.7500002.148848118334635.0000002.149298118285340.0000002.1484035678872212.000000103.1446824481329004456651402507545.3246395.3246885.3246325.3246391.7934561.7934571.7934551.79345612.73743912.73804012.73693212.73743971980860312.6752030071315773312.55808734406630.0605870000000011.78744911.78744911.78744911.787449697152.0000000.0122764812.6622897.9997177.9997177.9997177.9997173.5607433.5634083.5597833.560743406.7573760.2238337.387886000000406.6836480.2237927.3865470000000000000000000000012708864.0000000.223792230.8295872304.0000000.00004100000025.66442514.122756466.13990200025.66442214.122755466.13984714.12275614.12275614.12275614.122756000000000000000000802013184.00000014.12275514.56687096.0000000.0000020000000000000000009600.0000170000.0000006961920.0122595760.000010000000000000000000009600.0000170000.0000006961920.0122595760.000010000000000099.979413090.00000000100.00000097.9166670000000000000000960.000000864.00000096.0000000000.00000000.000000696192.000000696192.00000002304.0000002256.00000048.000000000000000000000000000.0116380.0116780.0115890.01163814.06730914.12275614.06730914.12275614.06730914.12275614.06730914.12275683841138400008PolicySpread010CachePreferNone142296112432003.00000024.0000001.0000001.0000004.0000003001570202823884.7185920000168168.000000102.40000089.08800089.0880001.02400088.06400004810247477388824all000002591000001.000107113733.250000107135103.000000107088888.0000001713819732.000000106226770.0000001.929384106226770.0000001.929384106226770.0000001.9293841699628320.00000030.8701470000000017.58403917.59497717.57352317.584039367742418.00000021.6366376.679262000023.5988332910.62430623.6169272911.32252923.5832892910.02451923.5988333214.569989203788027.0000002832.000000203681184.00000000200503392.00000003177792.00000053.31540254.1571220.39031450935069.43750023.9746862.0000000.47949450975893.00000023.99390150907123.00000023.961532814961111.00000023.97468614.80204212769216.0000000.751295231.92575408.00000000063635.000000209527.0000000000434448305.000000380287608.000000434499795.000000380523451.000000802013280.0000005.89844614.5668720.0006661.0000000.00000711328.0000000.2057498632.0000002688.00000023.9677242.0000000.47935423.98264623.954898814724448.00000023.96772414.797743000023767776.12500023784480.00000023750968.000000380284418.000000000000434439826.000000380285022.000000434440114.00000023767813.87500023784508.00000023750980.000000380285022.00000000001.0000000000001.0000000000000000023.5937842.0000000.471876802013280.00000023.59378414.566872000000434439462.000000367573666.000000434439462.000000367573666.00000001.0000000000000.7478791.0000000.00747912711168.0000000.747879230.871435000000012711168.000000012711168.00000011.99016012.00833511.98227711.99016023.97468623.99390123.96153223.97468611.92053411.94549611.91452811.920534000000009607163322726717759849609606984960111100000000100000000032.00000015070513.8513945712.000000116848615.0625001.4425121048.19873524.9164590.7167180.02782545312.8753052175018.014626028.7703041112.0000000225.18585625.18585625.185856957.06254125.18585625.18585625.185856957.06254138.00000001111960.0000000.000000696192.000000576.0000001259175041125917504112591750411259175041696768no datano data69619257689236896.000000432.00000031879588511318795885113187958851131879588511118776167.583333118805817.000000118739425.0000005701256044.000000118309837.7500002.148848118334635.0000002.149298118285340.0000002.1484035678872212.000000103.14468299.6226521476887.0000000.0260071471314.00000099.94529451933628.0000001.8290125.7047470.2272940.2281905.7058240.2273370.2282335.7035840.2272480.2281435.70474710.91011210.9531151.3679791.3733711.3708391.3762421.3648951.3702751.3679791.3733711.4479091.4536161.4480261.4537331.4477431.4534491.4479091.4536160.0572680.0574940.0574340.0576600.0571060.0573310.0572680.0574940.2290030.2297220.2281820.2290030.1591910.1598180.1591910.1598180.1591910.1598180.1591910.1598180.0000000.00000000000000000000000000000000007.9683097.9997177.9683097.9997177.9683097.9997177.9683097.99971725.00854625.10711900000000000.1570140.1576330.1570140.1576330.1570140.1576330.1570140.1576331.0464021.0505271.0464021.0505271.0464021.0505271.0464021.0505270.0002180.0002190.0002180.0002190.0002180.0002190.0002180.000219000000005.7483620.2290325.7495500.2290795.7470260.2289785.74836210.99352425.10711925.10711925.10711925.10711900005.7483625.7495505.7470265.74836212.00000025.0000007.9997177.9997177.9997177.9997170.0260060.0260060.0260060.0260062.9556282.9556282.9556282.9556283.1593923.1603493.1583603.1593921.3294331.3341151.3248261.3294331.3294411.3341221.3248331.3294410010242200419872342.55000010242200419872342.55000010242200419872342.55000049152105620153872442.52000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.03000010242200419872342.55000010242200419872342.55000010242200419872342.55000049152105620153872442.52000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.03000010242200419872342.55000010242200419872342.55000010242200419872342.55000049152105620153872442.52000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.0300005121100209936171.2800005121100209936171.2800005121100209936171.2800002457652810076936221.26000010242200419872342.55000010242200419872342.55000010242200419872342.55000049152105620153872442.52000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.03000040968801679489370.21000040968801679489370.21000040968801679489370.210000196608422480615489770.06000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.03000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.03000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.030012166837043225.10711940968801679489370.211028.392209848161800.1812166837043225.10711940968801679489370.211028.392209848161800.1812166837043225.10711940968801679489370.211028.392209848161800.18584008178073625.107119196608422480615489770.0649362.60106072711766408.5000819217603358978740.420000819217603358978740.420000819217603358978740.420000393216844961230979540.12000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.03000040968801679489370.21000040968801679489370.21000040968801679489370.210000196608422480615489770.06000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.03000040968801679489370.21000040968801679489370.21000040968801679489370.210000196608422480615489770.0600003.517535684494.3200003.517535684494.3200003.517535684494.320000168.33361712855727.54000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.03000040968801679489370.21000040968801679489370.21000040968801679489370.210000196608422480615489770.06000020484400839744685.10000020484400839744685.10000020484400839744685.10000098304211240307744885.03000040968801679489370.21000040968801679489370.21000040968801679489370.210000196608422480615489770.06000040968801679489370.21000040968801679489370.21000040968801679489370.210000196608422480615489770.06000010242200419872342.55000010242200419872342.55000010242200419872342.55000049152105620153872442.52001.4478991.4536061.4480201.4537281.4477141.4534201.4478991.4536062.4766142.4768842.4762472.4766140.2390300.2399720.2394970.2404410.2385740.2395140.2390300.2399720.7230770.7231260.7230300.7230770000000025.00854625.10711925.00854625.10711925.00854625.10711925.00854625.10711925.00854625.107119000.1570140.1576330.1570140.1576330.1570140.1576330.1570140.15763300000000000002.0000002.0000002.00000096.000000128.000000128.000000128.0000006144.00000064.00000064.00000064.0000003072.00000025.10711925.10711925.10711925.10711920.7494779.95974920.7555419.96266020.7423869.95634520.749477478.06795843.77283444.1074940.2068730.1624190.0674450.00000200.6532413.78190300.0229190.0181410.0893130.2788721.0000020.10534833.71565103.74484612480118853673.520833118890151.000000118818410.00000022819905316.000000118309837.7500002.148848118334635.0000002.149298118285340.0000002.14840322715488848.000000412.5787266749277.2812507300353.0000006518321.0000001295861238.000000223940.697917308958.000000174699.00000042996614.00000000000000133668864.0000000.588448001591296.0000000.0070050000000000002784768.0000000.01225999456.0000000.0004386800878.1510427388883.0000006547928.0000001305768605.0000005.7220600.066.2167900.065.5092350.065.72206010.9994.27794093.81390194.46109594.2779403.000000233.554432051024.0000003262109323253063111408961352612048110059347550502947252481950021762043175514657581662321812077232077326612245023424182520029052028291499.93709832.0000004.00000032.0000000.00000032.0000004.00000032.0000001.00000065.000000307.000000012480.0000000000000000000000960.0000000.000000696192.000000576.000000224497488.0000000.98830189236896.000000432.0000002784768.000000099456.00000000000000000000000000000.0089670.0105940.0077201.7216310.0000000.00000000.00000000000.0000000.00000000.000000000031.1825.4412.0000002.50470812.0000003.00637112.0000002.0033032304.000000480.9038770.0731790.0787450.07083114.0503743930698084831879588511