[rocprofv3-benchmark] SDK and rocprofv3 Benchmarking Suite (#157)
* Adding Benchmarking Stg1
* config fix
* reset
* add jpeg and decode traces in iteration
* address comments benchmark config files.
* address comments.
* address comments.
* address comments: revert cntrl ctx.
* address comments: revert csv output.
* resolve merge conflits.
* format.
* build fix.
* fix hip runtime api traces.
* loop cb services.
* format.
* bug fix.
* Fix operator>
- public C++ comparison operator
* Update configuration options
- support selected regions (--selected-regions)
- support writing output config json (--output-config)
- update serialization data
* rocprofv3 tool library misc updates
- lambda for starting context
- support for writing config json
* Tool library updates
- Finished support for all benchmarking modes
- Added build spec support to config json
* Fix ROCPROFILER_SOVERSION
- this value should not be multiplied by 10,000
* Minor tweak to rocprofv3
* Benchmarking scripts
* formatting
* Fix duplicate include
* Add reproducible-dispatch-count test app
- used in benchmarking
* registration logging
- report number of registered contexts and active contexts after client initialization
* Serialize environment in rocprofv3 output config
* ROCPROFILER_BUILD_BENCHMARK CMake option
* Update benchmark SQL schema
- hash_id is text
- add md5sum to benchmarked_app
- remove app_id from benchmarked_sdk
- add sdk_id to benchmark_config
- separate hip_trace into hip_runtime_trace and hip_compiler_trace
- use INT instead of INTEGER for MySQL compatibility
- add count column in benchmark_statistics
- allow std_dev to be NULL in benchmark_statistics
* Update rocprofv3-benchmark.py
- use md5 instead of python hash (which includes random seed)
- use args.mysql_database
- compute md5sum of executable
- fix insert_benchmark_config
- marker trace fixes
- memory allocation fixes
- split hip_trace into hip_{runtime,compiler}_trace
- remove app_id from benchmarked_sdk
- support warmup runs
- count field in benchmark_statistics
* Support launcher and environment in YAML
* Update reproducible-dispatch-count.cpp
- support mode which doesn't use hip event timing
* Misc rocprofv3-benchmark.py updates
- fix some MySQL support
- remove some unnecessary logging
* support mysql db.
* Format.
* Updated SQL input files
- moved benchmark_schema.sql to benchmark_table.sql
- added benchmark_views.sql
- uses {{metric}} syntax for variable substitution
* cmake formatting
* update rocprofv3-benchmark.py
- benchmark config labels
- overhead views
* Encode rocprofv3-benchmark PID in rocprofv3 and timem output files
* Minor tweak to benchmark_views.sql
- include count
- reorder fields for readability
* split statements and use IS if values is NONE.
* use backtick instead of double quotes and add IS before NOT NULL.:
* Adding Mandelbrot Benchmark App
* Adding Dockerfile example
* Update dockerfile
* Update dockerfile
* [SDK] rocprofiler_query_external_correlation_id_request_kind_name
* Execution-profile benchmark mode
* Execution profile SQL support
* Rename mandlebrot folder + misc clang-tidy
* [rocprofv3-benchmark] Execution profile support
* Update installation
* add work dir when setting git revision, useful when building outside src.
* Set FULL_VERSION_STRING and ROCPROFILER_SDK_GIT_REVISION
- when benchmark folder is top-level
* Remove unused python packages from requirements.txt
* Use ldd/pyelftools to include linked libs for md5sum
- also add --filter-benchmark and --filter-rocprofv3 options
- support labeling the rocprofv3 options
- use more argparse groups
- more generic application of filters
- support variable substitution in environment, e.g. PATH=/some/path:$PATH
* Environment improvements
- improve reproducibility when env set via input file vs. shell
- support "environment-ignore" to remove environment variables
* Misc formatting
* Misc. fix
* use backticks for defining new columns name
* Support shuffling the order of benchmark modes/rocprofv3 args
* Address review comments
* Update Dockerfile
- rename to Dockerfile
- reduce to one layer
* Support docker build arg BRANCH
---------
Co-authored-by: Ammar ELWazir <aelwazir@amd.com>
Co-authored-by: Kandula, Venkateshwar reddy <Venkateshwarreddy.Kandula@amd.com>
Co-authored-by: Venkateshwar Reddy Kandula <vkandula@amd.com>
Co-authored-by: Madsen, Jonathan <Jonathan.Madsen@amd.com>
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
This commit is contained in:
43 files changed
+5206
-280
No files matched your search
@@ -0,0 +1,5 @@
|
||||
#
|
||||
#
|
||||
#
|
||||
|
||||
add_subdirectory(rocprofiler-sdk)
|
||||
@@ -0,0 +1,12 @@
|
||||
#
|
||||
#
|
||||
#
|
||||
|
||||
set(DATA_FILES benchmark_tables.sql benchmark_views.sql)
|
||||
|
||||
foreach(_FILE ${DATA_FILES})
|
||||
configure_file(${_FILE} ${CMAKE_DATAROOT_OUTPUT_DIRECTORY}/rocprofiler-sdk/${_FILE}
|
||||
COPYONLY)
|
||||
endforeach()
|
||||
|
||||
install(FILES ${DATA_FILES} DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/rocprofiler-sdk)
|
||||
@@ -0,0 +1,137 @@
|
||||
-- Application used for benchmarking
|
||||
-- Columns such "hip_compiler_api", ..., "scratch_memory" are
|
||||
-- the number of events in the given category, e.g. kernel_dispatch
|
||||
-- represents the number of kernel dispatches in the app. These
|
||||
-- can be approximate since for a given application, the exact
|
||||
-- count may vary.
|
||||
CREATE TABLE IF NOT EXISTS
|
||||
`benchmarked_app` (
|
||||
id INT PRIMARY KEY AUTO_INCREMENT UNIQUE,
|
||||
hash_id TEXT NOT NULL,
|
||||
md5sum TEXT NOT NULL,
|
||||
revision INT DEFAULT 0,
|
||||
command JSON NOT NULL,
|
||||
compiler_id TEXT,
|
||||
compiler_version TEXT,
|
||||
library_arch TEXT,
|
||||
system_name TEXT,
|
||||
system_processor TEXT,
|
||||
system_version TEXT,
|
||||
threads INT,
|
||||
hip_compiler_api INT,
|
||||
hip_runtime_api INT,
|
||||
hsa_api INT,
|
||||
kernel_dispatch INT,
|
||||
marker_api INT,
|
||||
memory_allocation INT,
|
||||
memory_copy INT,
|
||||
ompt INT,
|
||||
rccl_api INT,
|
||||
rocdecode_api INT,
|
||||
rocjpeg_api INT,
|
||||
scratch_memory INT,
|
||||
environment JSON DEFAULT ("{}")
|
||||
);
|
||||
|
||||
-- rocprofiler-sdk used for benchmarking
|
||||
CREATE TABLE IF NOT EXISTS
|
||||
`benchmarked_sdk` (
|
||||
id INT PRIMARY KEY AUTO_INCREMENT UNIQUE,
|
||||
hash_id TEXT NOT NULL,
|
||||
version_major INT NOT NULL,
|
||||
version_minor INT NOT NULL,
|
||||
version_patch INT NOT NULL,
|
||||
soversion INT NOT NULL,
|
||||
compiler_id TEXT NOT NULL,
|
||||
compiler_version TEXT NOT NULL,
|
||||
git_revision TEXT NOT NULL,
|
||||
library_arch TEXT NOT NULL,
|
||||
system_name TEXT NOT NULL,
|
||||
system_processor TEXT NOT NULL,
|
||||
system_version TEXT NOT NULL
|
||||
);
|
||||
|
||||
-- rocprofiler-sdk used for benchmarking
|
||||
CREATE TABLE IF NOT EXISTS
|
||||
`benchmark_config` (
|
||||
id INT PRIMARY KEY AUTO_INCREMENT UNIQUE,
|
||||
hash_id TEXT NOT NULL,
|
||||
sdk_id INT,
|
||||
label TEXT, -- name identifier
|
||||
benchmark_mode TEXT CHECK (
|
||||
benchmark_mode IN (
|
||||
"baseline",
|
||||
"disabled-sdk-contexts",
|
||||
"sdk-buffer-overhead",
|
||||
"sdk-callback-overhead",
|
||||
"tool-runtime-overhead"
|
||||
)
|
||||
) NOT NULL,
|
||||
kernel_rename INT,
|
||||
group_by_queue INT,
|
||||
kernel_trace INT,
|
||||
hsa_trace INT,
|
||||
hip_runtime_trace INT,
|
||||
hip_compiler_trace INT,
|
||||
marker_trace INT,
|
||||
memory_copy_trace INT,
|
||||
memory_allocation_trace INT,
|
||||
scratch_memory_trace INT,
|
||||
dispatch_counter_collection INT,
|
||||
rccl_trace INT,
|
||||
rocdecode_trace INT,
|
||||
rocjpeg_trace INT,
|
||||
pmc_counters JSON DEFAULT ("[]"),
|
||||
pc_sampling_host_trap INT,
|
||||
pc_sampling_stocastic INT,
|
||||
advanced_thread_trace INT,
|
||||
--
|
||||
-- Eventually, we will create tables for storing the subconfigurations for pc sampling and ATT
|
||||
--
|
||||
-- pc_sampling_host_trap_config_id INT,
|
||||
-- pc_sampling_stocastic_config_id INT,
|
||||
-- advanced_thread_trace_config_id INT,
|
||||
-- FOREIGN KEY (pc_sampling_host_trap_config_id) REFERENCES benchmark_pc_sampling_host_trap_config (id) ON UPDATE CASCADE,
|
||||
-- FOREIGN KEY (pc_sampling_stocastic_config_id) REFERENCES benchmark_pc_sampling_stocastic_config (id) ON UPDATE CASCADE,
|
||||
-- FOREIGN KEY (advanced_thread_trace_config_id) REFERENCES benchmark_advanced_thread_trace_config (id) ON UPDATE CASCADE
|
||||
FOREIGN KEY (sdk_id) REFERENCES benchmarked_sdk (id) ON UPDATE CASCADE
|
||||
);
|
||||
|
||||
-- metrics for the benchmark
|
||||
CREATE TABLE IF NOT EXISTS
|
||||
`benchmark_metrics` (
|
||||
id INT PRIMARY KEY AUTO_INCREMENT UNIQUE,
|
||||
app_id INT NOT NULL,
|
||||
cfg_id INT NOT NULL,
|
||||
sdk_id INT,
|
||||
executed_at TIMESTAMP NOT NULL,
|
||||
wall_time DOUBLE NOT NULL,
|
||||
cpu_time DOUBLE NOT NULL,
|
||||
cpu_util DOUBLE NOT NULL,
|
||||
peak_rss DOUBLE NOT NULL,
|
||||
page_rss DOUBLE NOT NULL,
|
||||
virtual_memory DOUBLE NOT NULL,
|
||||
major_page_faults BIGINT NOT NULL,
|
||||
minor_page_faults BIGINT NOT NULL,
|
||||
priority_context_switches BIGINT NOT NULL,
|
||||
voluntary_context_switches BIGINT NOT NULL,
|
||||
FOREIGN KEY (app_id) REFERENCES benchmarked_app (id) ON UPDATE CASCADE,
|
||||
FOREIGN KEY (cfg_id) REFERENCES benchmark_config (id) ON UPDATE CASCADE,
|
||||
FOREIGN KEY (sdk_id) REFERENCES benchmarked_sdk (id) ON UPDATE CASCADE
|
||||
);
|
||||
|
||||
CREATE TABLE IF NOT EXISTS
|
||||
`benchmark_statistics` (
|
||||
id INT PRIMARY KEY AUTO_INCREMENT UNIQUE,
|
||||
app_id INT NOT NULL,
|
||||
cfg_id INT NOT NULL,
|
||||
sdk_id INT,
|
||||
metric_name TEXT NOT NULL,
|
||||
metric_unit TEXT NOT NULL,
|
||||
count INT NOT NULL,
|
||||
sum DOUBLE NOT NULL,
|
||||
mean DOUBLE NOT NULL,
|
||||
min DOUBLE NOT NULL,
|
||||
max DOUBLE NOT NULL,
|
||||
std_dev DOUBLE
|
||||
);
|
||||
@@ -0,0 +1,75 @@
|
||||
-- Analysis views used for benchmarking
|
||||
CREATE VIEW IF NOT EXISTS
|
||||
`benchmark_analysis_{{metric}}` AS
|
||||
WITH
|
||||
baseline AS (
|
||||
SELECT
|
||||
*
|
||||
FROM
|
||||
benchmark_statistics BL
|
||||
WHERE
|
||||
BL.sdk_id IS NULL
|
||||
AND BL.metric_name = "{{metric}}"
|
||||
)
|
||||
SELECT
|
||||
ST.id,
|
||||
ST.app_id,
|
||||
ST.cfg_id,
|
||||
ST.sdk_id,
|
||||
BS.git_revision,
|
||||
BA.command,
|
||||
ST.metric_name,
|
||||
ST.metric_unit,
|
||||
ST.count,
|
||||
ST.mean,
|
||||
ST.std_dev AS `+/-`,
|
||||
BL.mean AS baseline_mean,
|
||||
BL.std_dev AS `+/- (baseline)`,
|
||||
((ST.mean - BL.mean) / BL.mean) * 100 AS `overhead (%)`,
|
||||
BC.benchmark_mode,
|
||||
BC.label AS benchmark_label
|
||||
FROM
|
||||
benchmark_statistics ST
|
||||
JOIN benchmark_config BC ON BC.id = ST.cfg_id
|
||||
JOIN benchmarked_sdk BS ON BS.id = ST.sdk_id
|
||||
JOIN benchmarked_app BA ON BA.id = ST.app_id
|
||||
JOIN baseline BL ON (
|
||||
BL.app_id = ST.app_id
|
||||
AND BL.metric_name = ST.metric_name
|
||||
)
|
||||
WHERE
|
||||
ST.metric_name = "{{metric}}"
|
||||
AND ST.sdk_id IS NOT NULL
|
||||
ORDER BY
|
||||
`overhead (%)` DESC;
|
||||
|
||||
-- benchmarked_app without environment info
|
||||
CREATE VIEW IF NOT EXISTS
|
||||
`benchmarked_app_without_env` AS
|
||||
SELECT
|
||||
id,
|
||||
hash_id,
|
||||
md5sum,
|
||||
revision,
|
||||
command,
|
||||
compiler_id,
|
||||
compiler_version,
|
||||
library_arch,
|
||||
system_name,
|
||||
system_processor,
|
||||
system_version,
|
||||
threads,
|
||||
hip_compiler_api,
|
||||
hip_runtime_api,
|
||||
hsa_api,
|
||||
kernel_dispatch,
|
||||
marker_api,
|
||||
memory_allocation,
|
||||
memory_copy,
|
||||
ompt,
|
||||
rccl_api,
|
||||
rocdecode_api,
|
||||
rocjpeg_api,
|
||||
scratch_memory
|
||||
FROM
|
||||
benchmarked_app;
|
||||
Reference in new issue
Block a user