issue 40 typos fix
Change-Id: I486301c42bc5691a4d8a852e0ce168f8ca7776a0
[ROCm/rocprofiler commit: 1a63cba43d]
This commit is contained in:
committed by
Giovanni Baraldi
parent
f731ae7593
commit
b363586f82
@@ -124,7 +124,7 @@ Info API:
|
||||
- rocprofiler_info_query_t - profiling info query
|
||||
- rocprofiler_info_data_t - profiling info data
|
||||
- rocprofiler_get_info - return the info for a given info kind
|
||||
- rocprofiler_iterote_inf_ - iterate over the info for a given info kind
|
||||
- rocprofiler_iterate_inf_ - iterate over the info for a given info kind
|
||||
- rocprofiler_query_info - iterate over the info for a given info query
|
||||
|
||||
Context API:
|
||||
|
||||
@@ -38,7 +38,7 @@ ROCProfiler: input from "/tmp/rpl_data_191018_011134_9695/input0.xml"
|
||||
Device name Ellesmere [Radeon RX 470/480/570/570X/580/580X]
|
||||
PASSED!
|
||||
|
||||
ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_191018_011134_9695/input0_results_191018_011134
|
||||
ROCprofiler: 1 contexts collected, output directory /tmp/rpl_data_191018_011134_9695/input0_results_191018_011134
|
||||
RPL: '/…./MatrixTranspose/input.csv' is generated
|
||||
```
|
||||
#### 2.1.1. Counters and metrics
|
||||
@@ -94,7 +94,7 @@ Derived metrics:
|
||||
TCC_HIT_sum = sum(TCC_HIT,16)
|
||||
gpu-agent0 : TCC_MISS_sum : Number of cache misses. Sum over TCC instances.
|
||||
TCC_MISS_sum = sum(TCC_MISS,16)
|
||||
gpu-agent0 : TCC_MC_RDREQ_sum : Number of 32-byte reads. Sum over TCC instaces.
|
||||
gpu-agent0 : TCC_MC_RDREQ_sum : Number of 32-byte reads. Sum over TCC instances.
|
||||
TCC_MC_RDREQ_sum = sum(TCC_MC_RDREQ,16)
|
||||
. . .
|
||||
```
|
||||
@@ -199,7 +199,7 @@ hsa: hsa_queue_create hsa_amd_memory_pool_allocate
|
||||
#### 3.2.2. Tracing time period
|
||||
Trace can be dumped periodically with initial delay, dumping period length and rate:
|
||||
```
|
||||
--trace-period <dealy:length:rate>
|
||||
--trace-period <delay:length:rate>
|
||||
```
|
||||
### 3.3. Concurrent kernels
|
||||
Currently concurrent kernels profiling is not supported which is a planned feature. Kernels are serialized.
|
||||
@@ -268,12 +268,12 @@ Options:
|
||||
|
||||
-o <output file> - output CSV file [<input file base>.csv]
|
||||
-d <data directory> - directory where profiler store profiling data including traces [/tmp]
|
||||
The data directory is renoving autonatically if the directory is matching the temporary one, which is the default.
|
||||
The data directory is removed automatically if the directory is matching the temporary one, which is the default.
|
||||
-t <temporary directory> - to change the temporary directory [/tmp]
|
||||
By changing the temporary directory you can prevent removing the profiling data from /tmp or enable removing from not '/tmp' directory.
|
||||
|
||||
--basenames <on|off> - to turn on/off truncating of the kernel full function names till the base ones [off]
|
||||
--timestamp <on|off> - to turn on/off the kernel disoatches timestamps, dispatch/begin/end/complete [off]
|
||||
--timestamp <on|off> - to turn on/off the kernel dispatches timestamps, dispatch/begin/end/complete [off]
|
||||
--ctx-wait <on|off> - to wait for outstanding contexts on profiler exit [on]
|
||||
--ctx-limit <max number> - maximum number of outstanding contexts [0 - unlimited]
|
||||
--heartbeat <rate sec> - to print progress heartbeats [0 - disabled]
|
||||
@@ -297,11 +297,11 @@ Options:
|
||||
</trace>
|
||||
|
||||
--trace-start <on|off> - to enable tracing on start [on]
|
||||
--trace-period <dealy:length:rate> - to enable trace with initial delay, with periodic sample length and rate
|
||||
--trace-period <delay:length:rate> - to enable trace with initial delay, with periodic sample length and rate
|
||||
Supported time formats: <number(m|s|ms|us)>
|
||||
|
||||
Configuration file:
|
||||
You can set your parameters defaults preferences in the configuration file 'rpl_rc.xml'. The search path sequence: .:/home/evgeny:<package path>
|
||||
You can set your parameters defaults preferences in the configuration file 'rpl_rc.xml'. The search path sequence: .:/home/user:<package path>
|
||||
First the configuration file is looking in the current directory, then in your home, and then in the package directory.
|
||||
Configurable options: 'basenames', 'timestamp', 'ctx-limit', 'heartbeat', 'obj-tracking'.
|
||||
An example of 'rpl_rc.xml':
|
||||
|
||||
@@ -51,7 +51,7 @@ The user has two options for building:
|
||||
./build.sh --clean-build OR ./build.sh -cb
|
||||
```
|
||||
|
||||
- Option 2 (Where ROCM_PATH envronment need to be set with the current installation directory of rocm), run the following:
|
||||
- Option 2 (Where ROCM_PATH environment need to be set with the current installation directory of rocm), run the following:
|
||||
```bash
|
||||
# Creating the build directory
|
||||
mkdir build && cd build
|
||||
@@ -121,7 +121,7 @@ The user has two options for building:
|
||||
pmc: SQ_WAVES GRBM_COUNT GRBM_GUI_ACTIVE SQ_INSTS_VALU
|
||||
```
|
||||
|
||||
- Application Trace Support: Differnt trace options are available while profiling an app:
|
||||
- Application Trace Support: Different trace options are available while profiling an app:
|
||||
```bash
|
||||
# HIP API & asynchronous activity tracing
|
||||
rocprofv2 --hip-api <app_relative_path> ## For synchronous HIP API Activity tracing
|
||||
@@ -202,7 +202,7 @@ The user has two options for building:
|
||||
|
||||
- unittests (Gtest Based) : These includes tests for core classes. Any newly added functionality should have a unit test written to it.
|
||||
|
||||
- featuretests (standalone and Gtest Based): These includes both API tests and tool tests. Tool is tested against different applications to make sure we have right output in evry run.
|
||||
- featuretests (standalone and Gtest Based): These includes both API tests and tool tests. Tool is tested against different applications to make sure we have right output in every run.
|
||||
|
||||
- memorytests (standalone): This includes running address sanitizer for memory leaks, corruptions.
|
||||
|
||||
@@ -267,7 +267,7 @@ samples can be run as independent executables once installed
|
||||
- plugin
|
||||
- file: File Plugin
|
||||
- perfetto: Perfetto Plugin
|
||||
- att: Adavced thread tracer Plugin
|
||||
- att: Advanced thread tracer Plugin
|
||||
- ctf: CTF Plugin
|
||||
- samples: Samples of how to use the API, and also input.txt input file samples for counter collection and ATT.
|
||||
- script: Scripts needed for tracing
|
||||
|
||||
Reference in New Issue
Block a user