2
0
Gráfico de cometimentos

278 Cometimentos

Autor(a) SHA1 Mensagem Data
Karl W. Schulz c55508dfe6 Addition of new files to demonstrate top-level data structure refactoring for
2.x version.  Introduces an Omniperf class as the primary structure to organize
work elements and allows for a simple main() which is highlighted in a
omniperf2 example. Demonstrates desired logger functionality including a custom
trace loglevel that can be used to provide more verbosity beyond the debug
level. Also introduces three abstract base classes to organize flexibility for
alternative implementations of key elements within omniperf:

  * underlying profiler tool (e.g. rocprof, rocscope, etc)
  * supported GPU architectures (SoC)
  * analysis environments (e.g. CLI, web-based, etc)

Stub examples for child classes relevant to currently supported options within
omniperf are included in separate files.

Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>
2023-10-04 09:52:50 -05:00
colramos-amd 95f886ef5a Consistent useage of -p/--path option in profile mode
Signed-off-by: colramos-amd <colramos@amd.com>
2023-10-04 09:50:30 -05:00
coleramos425 d3341905f8 Fix verbose mode in analyze mode
Signed-off-by: coleramos425 <colramos@amd.com>
2023-09-20 14:15:18 -05:00
Nicholas Curtis a0955c293d fix for stoichastic kernel dispatch selection
Signed-off-by: Nicholas Curtis <nicurtis@amd.com>
2023-09-11 10:17:20 -04:00
Cole Ramos 1289682045 Merge pull request #168 from JoseSantosAMD/cpp_filt
uses c++filt instead of llvm-cxxfilt
2023-09-05 09:21:02 -05:00
JoseSantosAMD 56e497fd62 Update src/utils/csv_processor.py
Co-authored-by: Cole Ramos <colramos@amd.com>
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>
2023-08-30 17:03:39 -05:00
coleramos425 6461df96e8 Adding color code thresholds to standalone GUI to match Grafana
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-30 16:24:42 -05:00
coleramos425 8936966e81 Standardizing headers. Will use 'avg' instead of 'mean'
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-30 16:20:45 -05:00
coleramos425 0694400618 Merge branch 'main' of github.com:AMDResearch/omniperf into dev 2023-08-29 16:07:14 -05:00
coleramos425 4d9baa07e1 Update docs
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-29 10:56:25 -05:00
coleramos425 50fd968f51 Removing kernelVerbose from database mode
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-24 18:57:26 -05:00
josantos 256ada088d uses c++filt instead of llvm-cxxfilt
Signed-off-by: josantos <josantos@amd.com>
2023-08-24 16:43:45 -05:00
coleramos425 7d457b5096 Replacing subprocess with shutil
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-24 15:54:00 -05:00
coleramos425 7187218ed9 Patch llvm-cxxfilt detection in atypical rocm installs
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-22 11:25:06 -05:00
coleramos425 064debf356 Documentation enhancements
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-17 09:50:38 -05:00
Cole Ramos eec0323945 Merge branch 'main' into dev 2023-08-16 14:29:29 -07:00
coleramos425 3ae0198f8e Renaming csv_converter to make more succinct
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-16 16:16:46 -05:00
coleramos425 f27142160c Remove debug logging
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-16 15:34:55 -05:00
coleramos425 5d74b142b6 Prevent users from ipblock filtering in standalone GUI
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-16 14:16:50 -05:00
coleramos425 74f816ed47 Add a -d option to analyze mode for consistency with profile
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-16 13:48:31 -05:00
Cole Ramos abd424beea Merge pull request #160 from JoseSantosAMD/pct_of_peak
Pct of peak
2023-08-15 13:56:38 -07:00
Cole Ramos 6f6bca1383 Merge pull request #158 from JoseSantosAMD/instr_mix_min_max_avg
Instr mix min max avg
2023-08-15 13:55:22 -07:00
JoseSantosAMD 6d39955708 add simple_bar styling
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-08-15 15:14:20 -05:00
JoseSantosAMD 132cb37d69 add pct of peak to tables
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-08-15 15:04:23 -05:00
coleramos425 dc849b264c Conform to Python formatting
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-15 14:09:38 -05:00
coleramos425 4aa33848de Fixing several bugs on original PR
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-15 14:00:36 -05:00
coleramos425 30cc862667 Adding more details to Grafana setup in docs (#135)
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-14 12:58:33 -05:00
JoseSantosAMD b82f033bf9 Added min/max/avg to VALU Arithmetic Instr Mix
-  gui now runs on archconfigs from sys_info

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-08-11 15:46:46 -05:00
coleramos425 2699460592 Updating docs for filtering with examples (#136) (#137)
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-11 12:33:13 -05:00
JoseSantosAMD 5dac9042e0 Update 1000_compute-unit-instruction-mix.yaml
Signed-off-by: JoseSantosAMD <87447437+JoseSantosAMD@users.noreply.github.com>
2023-08-10 15:15:42 -05:00
JoseSantosAMD bfbd5bbb3a Adding min/max/avg breakdown across dispatches for instruction mix panels
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-08-10 15:09:01 -05:00
josantos 802308cd28 use llvm-cxxfilt in /opt/rocm
Signed-off-by: josantos <josantos@amd.com>
2023-08-10 13:23:52 -05:00
josantos bbb254ef43 reformatting
Signed-off-by: josantos <josantos@amd.com>
2023-08-10 11:16:50 -05:00
josantos 59d77f9d81 Names shortened/demangled after join_prof
-  Added kernelVerbose flag in profile_group
-  Added KernelVerbose flag in analyze_group
-  Analyze replaces csv with shortened/demangled name
-  csv_converter uses llvm-cxxfilt

Signed-off-by: josantos <josantos@amd.com>
2023-08-10 11:13:27 -05:00
josantos 2948f73ae8 keep converter in csv_converter.py
Signed-off-by: josantos <josantos@amd.com>
2023-08-09 10:46:57 -05:00
JoseSantosAMD 76da2a9ed5 Merge branch 'dev' of https://github.com/AMDResearch/omniperf into kernel_name_mappings 2023-08-08 14:49:59 -05:00
JoseSantosAMD 4e51c122d1 removing calls to kernel_name_shortener in mongo
shortening now in profile

Signed-off-by: JoseSantosAMD <josantos@amd.com>
2023-08-08 12:06:39 -05:00
JoseSantosAMD 11b5f65c1c Fix yaml syntax errors
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-08-08 11:04:35 -05:00
JoseSantosAMD d6fb0183a4 Fixing yaml syntax errors
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-08-07 12:41:15 -05:00
JoseSantosAMD ef8ef2291b Fix syntax error in yaml
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-08-07 12:31:27 -05:00
Nicholas Curtis 428d07a379 fix max BF16 flop rate on CDNA2
Signed-off-by: Nicholas Curtis <nicurtis@amd.com>
2023-08-07 11:42:21 -05:00
coleramos425 b1a7a26848 Only load required archs into ArchConfig datastruct (#144)
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-07 11:42:21 -05:00
coleramos425 db9cc25be1 Fix incorrect ordering of args in perfagg func
Signed-off-by: coleramos425 <colramos@amd.com>
2023-08-07 11:42:21 -05:00
colramos-amd a61d509739 New simple_charts utility
Signed-off-by: colramos-amd <colramos@amd.com>
2023-08-07 11:42:21 -05:00
colramos-amd 424dd6a4a8 Add figure styling to YML configs
Signed-off-by: colramos-amd <colramos@amd.com>
2023-08-07 11:42:21 -05:00
colramos-amd e6ca8e0361 Enable join_prof() merge util to be called from outside Omniperf
Signed-off-by: colramos-amd <colramos@amd.com>
2023-08-07 11:42:21 -05:00
colramos-amd 626fc7f18f Filter additional ops in gen_counter_list fucn
Signed-off-by: colramos-amd <colramos@amd.com>
2023-08-07 11:42:21 -05:00
colramos-amd 35daf8c120 Comply to Python formatting
Signed-off-by: colramos-amd <colramos@amd.com>
2023-08-07 11:42:21 -05:00
colramos-amd 2c2b384ca2 Abstract perfmon coalesing for useage in rocomni plugin
Signed-off-by: colramos-amd <colramos@amd.com>
2023-08-07 11:42:21 -05:00
colramos-amd 33ad9ffca3 Rearranging build_df func to optimize ArchConfig for rocomni plugin
Signed-off-by: colramos-amd <colramos@amd.com>
2023-08-07 11:42:21 -05:00