问Nsight计算中使用的术语

EN

在CC7.5 GPU上的Nsight计算

SM%由sm__throughput定义，内存%由gpu__compute_memory_throughtput定义

sm_throughput是下列指标的最大值：

• sm__instruction_throughput
  • sm__inst_executed
  • sm__issue_active
  • sm__mio_inst_issued
  • sm__pipe_alu_cycles_active
  • sm__inst_executed_pipe_cbu_pred_on_any
  • sm__pipe_fp64_cycles_active
  • sm__pipe_tensor_cycles_active
  • sm__inst_executed_pipe_xu
  • sm__pipe_fma_cycles_active
  • sm__inst_executed_pipe_fp16
  • sm__pipe_shared_cycles_active
  • sm__inst_executed_pipe_uniform
  • sm__instruction_throughput_internal_activity

• sm__memory_throughput
  • idc__request_cycles_active
  • sm__inst_executed_pipe_adu
  • sm__inst_executed_pipe_ipa
  • sm__inst_executed_pipe_lsu
  • sm__inst_executed_pipe_tex
  • sm__mio_pq_read_cycles_active
  • sm__mio_pq_write_cycles_active
  • sm__mio2rf_writeback_active
  • sm__memory_throughput_internal_activity

gpu__compute_memory_throughput是下列指标的最大值：

• gpu__compute_memory_access_throughput
  • l1tex__data_bank_reads
  • l1tex__data_bank_writes
  • l1tex__data_pipe_lsu_wavefronts
  • l1tex__data_pipe_tex_wavefronts
  • l1tex__f_wavefronts
  • lts__d_atomic_input_cycles_active
  • lts__d_sectors
  • lts__t_sectors
  • lts__t_tag_requests
  • gpu__compute_memory_access_throughput_internal_activity

• gpu__compute_memory_access_throughput
• l1tex__lsuin_requests
  • l1tex__texin_sm2tex_req_cycles_active
  • l1tex__lsu_writeback_active
  • l1tex__tex_writeback_active
  • l1tex__m_l1tex2xbar_req_cycles_active
  • l1tex__m_xbar2l1tex_read_sectors
  • lts__lts2xbar_cycles_active
  • lts__xbar2lts_cycles_active
  • lts__d_sectors_fill_device
  • lts__d_sectors_fill_sysmem
  • gpu__dram_throughput
  • gpu__compute_memory_request_throughput_internal_activity

在您的例子中，限制器是sm__inst_executed_pipe_lsu，这是一个指令吞吐量。如果查看区段/SpeedOfLight.py延迟绑定，则定义为sm__throughput和gpu__compute_memory_throuhgput都小于60%。

一些指令管道的吞吐量较低，如fp64、xu和lsu (随芯片而异)。管道使用是sm__throughput的一部分。为了提高业绩，可选办法如下：

1. 将指令减少到超额订阅的管道，或者
2. 发出不同类型的指令以使用空的发布周期。

生成击穿

在Nsight Compute 2020.1中，没有一个简单的命令行可以在不运行分析会话的情况下生成列表。现在，您可以使用breakdown:<throughput metric>avg.pct_of_peak_sustained.elapsed收集一个吞吐量度量，并解析输出以获得子度量名称。

例如：

ncu.exe --csv --metrics breakdown:sm__throughput.avg.pct_of_peak_sustained_elapsed --details-all -c 1 cuda_application.exe

生成：

"ID","Process ID","Process Name","Host Name","Kernel Name","Kernel Time","Context","Stream","Section Name","Metric Name","Metric Unit","Metric Value"
"0","33396","cuda_application.exe","127.0.0.1","kernel()","2020-Aug-20 13:26:26","1","7","Command line profiler metrics","gpu__dram_throughput.avg.pct_of_peak_sustained_elapsed","%","0.38"
"0","33396","cuda_application.exe","127.0.0.1","kernel()","2020-Aug-20 13:26:26","1","7","Command line profiler metrics","l1tex__data_bank_reads.avg.pct_of_peak_sustained_elapsed","%","0.05"
"0","33396","cuda_application.exe","127.0.0.1","kernel()","2020-Aug-20 13:26:26","1","7","Command line profiler metrics","l1tex__data_bank_writes.avg.pct_of_peak_sustained_elapsed","%","0.05"
...

关键字breakdown可以在Nsight计算部分文件中使用，以扩展吞吐量度量。这在SpeedOfLight.section中使用。