Windows
Launch application AMDTClassicMatMul.exe and collect the samples
for CYCLES_NOT_IN_HALT and RETIRED_INST events
C:\> AMDuProfCLI.exe collect -e cycles-not-in-halt -e retired-inst --interval 1000000
-o c:\Temp\cpuprof-custom AMDTClassicMatMul.exe
$ ./AMDuProfCLI.exe collect -e event=cycles-not-in-halt,interval=250000
-e event=retired-inst,interval=500000 -o c:\Temp\cpuprof-custom AMDTClassicMatMul.exeLaunch the application AMDTClassicMatMul.exe and collect the Time-Based Profile (TBP) samples
C:\> AMDuProfCLI.exe collect -o c:\Temp\cpuprof-tbp AMDTClassicMatMul.exeLaunch AMDTClassicMatMul.exe and do Assess Performance profile for 10 seconds
C:\> AMDuProfCLI.exe collect --config assess -o c:\Temp\cpuprof-assess -d 10 AMDTClassicMatMul.exeLaunch AMDTClassicMatMul.exe and collect the IBS samples in the SWP mode
C:\> AMDuProfCLI.exe collect --config ibs -a -o c:\Temp\cpuprof-ibs-swp AMDTClassicMatMul.exeCollect the TBP samples in SWP mode for 10 seconds
C:\> AMDuProfCLI.exe collect -a -o c:\Temp\cpuprof-tbp-swp -d 10Launch AMDTClassicMatMul.exe and collect TBP with callstack sampling
C:\> AMDuProfCLI.exe collect --config tbp -g -o c:\Temp\cpuprof-tbp AMDTClassicMatMul.exeLaunch AMDTClassicMatMul.exe and collect TBP with callstack sampling (unwind FPO optimized stack)
C:\> AMDuProfCLI.exe collect --config tbp --call-graph 1:64:user:fpo -o c:\Temp\cpuprof-tbp AMDTClassicMatMul.exe
C:\> AMDuProfCLI.exe collect --config tbp --call-graph-mode fpo --call-graph-type user -o c:\Temp\cpuprof-tbp AMDTClassicMatMul.exeC:\> AMDuProfCLI.exe collect --config tbp --call-graph-mode fp -o c:\Temp\cpuprof-tbp AMDTClassicMatMul.exeLaunch AMDTClassicMatMul.exe and collect the samples for PMCx076 and PMCx0C0
C:\> AMDuProfCLI.exe collect -e event=pmcx76,interval=250000 -e event=pmcxc0,user=1,os=0,interval=250000 -o c:\Temp\cpuprof-
tbp AMDTClassicMatMul.exeLaunch AMDTClassicMatMul.exe and collect the samples for IBS OP with an interval of 50000
C:\> AMDuProfCLI.exe collect -e event=ibs-op,interval=50000 -o c:\Temp\cpuprof-tbp AMDTClassicMatMul.exeLaunch AMDTClassicMatMul.exe and do TBP samples profile for thread concurrency, name
C:\> AMDuProfCLI.exe collect --config tbp --thread thread=concurrency,name -o c:\Temp\cpuprof- tbp AMDTClassicMatMul.exeCollect samples for PMCx076 and PMCx0C0, but collect the call graph info only for PMCx0C0
C:\> AMDuProfCLI.exe collect -e event=pmcx76,interval=250000 -e event=pmcxc0,interval=250000,call-graph -o c:\Temp\cpuprof-pmc AMDTClassicMatMul-binLaunch AMDTClassicMatMul.exe and collect the samples for predefined event RETIRED_INST and L1_DC_REFILLS.ALL events
C:\> AMDuProfCLI.exe collect -e event=RETIRED_INST,interval=250000 -e event=L1_DC_REFILLS.ALL,user=1,os=0,interval=250000 -o
c:\Temp\cpuprof-pmc AMDTClassicMatMul.exeLaunch AMDTClassicMatMul.exe, collect the TBP and Assess Performance samples
C:\> AMDuProfCLI.exe collect --config tbp --config assess -o c:\Temp\cpuprof-tbp-assess AMDTClassicMatMul.exeLaunch AMDTClassicMatMul.exe and collect the samples for PMCx076 and PMCx0C0 events with count-mask enabled
C:\> AMDuProfCLI.exe collect -e event=pmcx076,cmask=0x0, -e event=pmcx0c0,cmask=0x7f,interval=250000 -o c:\Temp\cpuprof-pmc
AMDTClassicMatMul-binLinux
Launch application AMDTClassicMatMul.bin and collect the samples
for CYCLES_NOT_IN_HALT and RETIRED_INST events
$ ./AMDuProfCLI collect -e cycles-not-in-halt -e retired-inst
--interval 1000000 -o /tmp/cpuprof-custom AMDTClassicMatMul-bin
$ ./AMDuProfCLI collect -e event=cycles-not-in-halt,interval=250000
-e event=retired-inst,interval=500000 -o /tmp/cpuprof-custom AMDTClassicMatMul-binLaunch the application AMDTClassicMatMul-bin and collect the TBP samples
$ ./AMDuProfCLI collect -o /tmp/cpuprof-tbp AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and do Assess Performance profile for 10 seconds
$ ./AMDuProfCLI collect --config assess -o /tmp/cpuprof-assess -d 10 AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and collect the IBS samples in the SWP mode
$ ./AMDuProfCLI collect --config ibs -a -o /tmp/cpuprof-ibs-swp AMDTClassicMatMul-binCollect the TBP samples in SWP mode for 10 seconds
$ ./AMDuProfCLI collect -a -o /tmp/cpuprof-tbp-swp -d 10Launch AMDTClassicMatMul-bin and collect TBP with callstack sampling
$ ./AMDuProfCLI collect --config tbp -g -o /tmp/cpuprof-tbp AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and collect TBP with callstack sampling (unwind FPO optimized stack)
$ .AMDuProfCLI collect --config tbp --call-graph-mode fpo --call-graph-size 512 -o /tmp/cpuprof-tbp AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and collect the samples for PMCx076 and PMCx0C0
$ ./AMDuProfCLI collect -e event=pmcx76,interval=250000 -e event=pmcxc0,user=1,os=0,interval=250000 -o /tmp/cpuprof-tbp AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and collect the samples for IBS OP with interval 50000
$ ./AMDuProfCLI collect -e event=ibs-op,interval=50000 -o /tmp/cpuprof-tbp AMDTClassicMatMul- binAttach to a thread and collect TBP samples for 10 seconds
$ AMDuProfCLI collect --config tbp -o /tmp/cpuprof-tbp-attach -d 10 --tid <TID>Collect basic OpenMP trace info of an OpenMP application compiled with GCC OpenMP library
$ AMDuProfCLI collect --trace openmp --openmp-impl omplib -o /tmp/cpuprof-omp <path-to-openmp-exe>Launch AMDTClassicMatMul-bin and collect the memory accesses for false cache sharing
$ AMDuProfCLI collect --config memory -o /tmp/cpuprof-mem AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and collect the threading configuration to analyze hotspots, thread state, and wait object analysis among threads
$ AMDuProfCLI collect --config threading -o /tmp/cpuprof-threading AMDTClassicMatMul-binCollect MPI profiling information
$ mpirun -np 4 ./AMDuProfCLI collect --config assess --mpi --output-dir /tmp/cpuprof-mpi /tmp/ namd <parameters>Collect the samples for PMCx076 and PMCx0C0, but collect the call graph info only for PMCx0C0
$ AMDuProfCLI collect -e event=pmcx76,interval=250000 -e event=pmcxc0,interval=250000,call- graph -o /tmp/cpuprof-pmc
AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and collect the samples for predefined event RETIRED_INST and L1_DC_REFILLS.ALL events
$ AMDuProfCLI collect -e event=RETIRED_INST,interval=250000 -e event=L1_DC_REFILLS.ALL,user=1,os=0,interval=250000 -o /tmp/cpuprof-pmc AMDTClassicMatMul-bin$ AMDuProfCLI collect --trace osrt --osrt-event pthread -o /tmp/cpuprof-os AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and collect syscall taking more than or equal to 1µs
$ AMDuProfCLI collect --trace osrt --osrt-event syscall --osrt-threshold syscall:1000000 -o /tmp/cpuprof-os AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and collect the GPU Traces for hip and hsa domain
$ AMDuProfCLI collect --trace gpu -o /tmp/cpuprof-gpu AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin, collect the TBP samples and GPU Traces for hip and hsa domain
$ AMDuProfCLI collect --config tbp --trace gpu -o /tmp/cpuprof-gpu AMDTClassicMatMul-binLaunch AMDTClassicMatMul-bin and collect the GPU samples
$ AMDuProfCLI collect --config gpu -o /tmp/cpuprof-gpu AMDTClassicMatMul-binLaunch 'AMDTClassicMatMul-bin' and collect 'GPU' samples for 'SQ' Block
$ AMDuProfCLI collect --config gpu --ip-block SQ -o /tmp/gpuprof-gpu AMDTClassicMatMul-binLaunch 'AMDTClassicMatMul-bin' and collect trace data for all functions in 'AMDTClassicMatMul-bin'
$ AMDuProfCLI collect --trace osrt --osrt-event function --osrt-funcs AMDTClassicMatMul-bin:* -o /tmp/cpuprof-os AMDTClassicMatMul-binLaunch 'AMDTClassicMatMul-bin' and collect trace data for all functions in 'AMDTClassicMatMul-bin' which has size greater than or equals to 64
$ AMDuProfCLI collect --trace osrt --osrt-event function --osrt-func-size 64 --osrt-threshold function:10000 --osrt-funcs AMDTClassicMatMul-bin:* -o /tmp/cpuprof-os AMDTClassicMatMul-binLaunch AMDTClassMatMul-bin and perform branch analysis with the default filter type
$ AMDuProfCLI collect --branch-filter -o /tmp/cpuprof-ebp-branch AMDTClassicMatMul-binLaunch AMDTClassMatMul-bin and collect samples for the event PMCXC0
$ AMDuProfCLI collect -e event=pmcxc0,interval=250000 --branch-filter u,k,any -o /tmp/cpuprof- ebp-branch AMDTClassicMatMul-
bin