GPUperf：Nsight GPU Profiler教程-ORNL峰会

[{"title":"（ 44 个子文件 332KB ） GPUperf：Nsight GPU Profiler教程-ORNL峰会","children":[{"title":"GPUperf-main","children":[{"title":"project","children":[{"title":"tutorial","children":[{"title":"Nsight_Summit","children":[{"title":"README.rst <span style='color:#111;'> 264B </span>","children":null,"spread":false},{"title":"3.NsightTools_Practice","children":[{"title":"README.rst <span style='color:#111;'> 109B </span>","children":null,"spread":false},{"title":"miniWeather_ver0","children":[{"title":"miniWeather_ver0.f90 <span style='color:#111;'> 60B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 690B </span>","children":null,"spread":false}],"spread":true},{"title":"miniWeather_collapse","children":[{"title":"Makefile <span style='color:#111;'> 702B </span>","children":null,"spread":false},{"title":"miniWeather_collapse.f90 <span style='color:#111;'> 64B </span>","children":null,"spread":false}],"spread":true},{"title":"miniWeather_collapse_present","children":[{"title":"miniWeather_collapse_present.f90 <span style='color:#111;'> 72B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 726B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"0.Prerequisite","children":[{"title":"README.rst <span style='color:#111;'> 949B </span>","children":null,"spread":false}],"spread":true},{"title":"2.NsightTools_Basics","children":[{"title":"README.rst <span style='color:#111;'> 272B </span>","children":null,"spread":false},{"title":"vecadd_acc","children":[{"title":"vecadd_acc.f90 <span style='color:#111;'> 49B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 285B </span>","children":null,"spread":false}],"spread":true},{"title":"vecadd_cuda","children":[{"title":"vecadd_nvtx.cu <span style='color:#111;'> 43B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 262B </span>","children":null,"spread":false}],"spread":true},{"title":"matmul_acc","children":[{"title":"matmul_acc.f90 <span style='color:#111;'> 53B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 221B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"interactive_summit.sh <span style='color:#111;'> 253B </span>","children":null,"spread":false},{"title":"envs.sh <span style='color:#111;'> 208B </span>","children":null,"spread":false},{"title":"Makefile.inc <span style='color:#111;'> 2.64KB </span>","children":null,"spread":false},{"title":"5.Further_Study","children":[{"title":"README.rst <span style='color:#111;'> 102B </span>","children":null,"spread":false}],"spread":true},{"title":"nvtx.f90 <span style='color:#111;'> 1.94KB </span>","children":null,"spread":false},{"title":"4.Optimization_Practice","children":[{"title":"README.rst <span style='color:#111;'> 110B </span>","children":null,"spread":false},{"title":"DG","children":[{"title":"README.rst <span style='color:#111;'> 79B </span>","children":null,"spread":false},{"title":"dg_acc.F90 <span style='color:#111;'> 46B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 204B </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"1.Optimization_Essentials","children":[{"title":"README.rst <span style='color:#111;'> 249B </span>","children":null,"spread":false},{"title":"vecadd_cuda","children":[{"title":"vecadd_cuda.ncu-rep <span style='color:#111;'> 95.98KB </span>","children":null,"spread":false},{"title":"vecadd_cuda.qdrep <span style='color:#111;'> 436.22KB </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 226B </span>","children":null,"spread":false},{"title":"vecadd.cu <span style='color:#111;'> 43B </span>","children":null,"spread":false}],"spread":false}],"spread":false}],"spread":false}],"spread":true}],"spread":true},{"title":"README.rst <span style='color:#111;'> 69B </span>","children":null,"spread":false},{"title":"code","children":[{"title":"Fortran","children":[{"title":"DG_NCAR","children":[{"title":"CESM_Kernel_License_091118.docx <span style='color:#111;'> 13.54KB </span>","children":null,"spread":false},{"title":"README.rst <span style='color:#111;'> 169B </span>","children":null,"spread":false},{"title":"dg_acc.F90 <span style='color:#111;'> 3.46KB </span>","children":null,"spread":false}],"spread":true},{"title":"vecadd_acc","children":[{"title":"vecadd.f90 <span style='color:#111;'> 1.01KB </span>","children":null,"spread":false}],"spread":true},{"title":"matmul_acc","children":[{"title":"matmul_acc.f90 <span style='color:#111;'> 3.88KB </span>","children":null,"spread":false}],"spread":true},{"title":"miniWeather","children":[{"title":"README.rst <span style='color:#111;'> 194B </span>","children":null,"spread":false},{"title":"miniWeather_collapse_present.f90 <span style='color:#111;'> 42.32KB </span>","children":null,"spread":false},{"title":"miniWeather_ver0.f90 <span style='color:#111;'> 41.62KB </span>","children":null,"spread":false},{"title":"miniWeather_collapse.f90 <span style='color:#111;'> 41.69KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"C","children":[{"title":"vecadd_nvtx","children":[{"title":"vecadd.cu <span style='color:#111;'> 2.25KB </span>","children":null,"spread":false}],"spread":true},{"title":"vecadd_cuda","children":[{"title":"vecadd.cu <span style='color:#111;'> 1.91KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 11.09KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 57B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]