Restructure PTI repo, improve testing

jfedorov · Apr 16, 2021 · 7bad721 · 7bad721
1 parent df968c9
commit 7bad721
Show file tree

Hide file tree

Showing 102 changed files with 737 additions and 479 deletions.
diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-0.21.0
+0.22.0
diff --git a/samples/build_utils/CMakeLists.txt → build_utils/CMakeLists.txt b/samples/build_utils/CMakeLists.txt → build_utils/CMakeLists.txt
diff --git a/samples/build_utils/build_utils.py → build_utils/build_utils.py b/samples/build_utils/build_utils.py → build_utils/build_utils.py
diff --git a/samples/build_utils/get_cl_headers.py → build_utils/get_cl_headers.py b/samples/build_utils/get_cl_headers.py → build_utils/get_cl_headers.py
diff --git a/...les/build_utils/get_cl_tracing_headers.py → build_utils/get_cl_tracing_headers.py b/...les/build_utils/get_cl_tracing_headers.py → build_utils/get_cl_tracing_headers.py
diff --git a/samples/build_utils/get_gmm_headers.py → build_utils/get_gmm_headers.py b/samples/build_utils/get_gmm_headers.py → build_utils/get_gmm_headers.py
diff --git a/samples/build_utils/get_gtpin_headers.py → build_utils/get_gtpin_headers.py b/samples/build_utils/get_gtpin_headers.py → build_utils/get_gtpin_headers.py
diff --git a/samples/build_utils/get_gtpin_libs.py → build_utils/get_gtpin_libs.py b/samples/build_utils/get_gtpin_libs.py → build_utils/get_gtpin_libs.py
diff --git a/samples/build_utils/get_iga_headers.py → build_utils/get_iga_headers.py b/samples/build_utils/get_iga_headers.py → build_utils/get_iga_headers.py
diff --git a/samples/build_utils/get_igc_headers.py → build_utils/get_igc_headers.py b/samples/build_utils/get_igc_headers.py → build_utils/get_igc_headers.py
diff --git a/samples/build_utils/get_itt.py → build_utils/get_itt.py b/samples/build_utils/get_itt.py → build_utils/get_itt.py
diff --git a/samples/build_utils/get_md_headers.py → build_utils/get_md_headers.py b/samples/build_utils/get_md_headers.py → build_utils/get_md_headers.py
diff --git a/chapters/device_activity_tracing/LevelZero.md b/chapters/device_activity_tracing/LevelZero.md
@@ -138,4 +138,8 @@ Event pool profiling does not require any additional environment variables to be
 
 ## Samples
 - [Level Zero GEMM](../../samples/ze_gemm)
-- [Level Zero Hot Kernels](../../samples/ze_hot_kernels)
+- [Level Zero Hot Kernels](../../samples/ze_hot_kernels)
+
+## Tools
+- [Level Zero Tracer](../../tools/ze_tracer)
+- [Tracing and Profiling Tool for Data Parallel C++ (DPC++)](../../tools/onetrace)
diff --git a/chapters/runtime_api_tracing/LevelZero.md b/chapters/runtime_api_tracing/LevelZero.md
@@ -97,4 +97,8 @@ ZE_ENABLE_TRACING_LAYER=1 ./<application>
 - [Level Zero Hot Functions](../../samples/ze_hot_functions)
 - [Level Zero Hot Kernels](../../samples/ze_hot_kernels)
 - [Level Zero Debug Info](../../samples/ze_debug_info)
-- [Level Zero Metric Query](../../samples/ze_metric_query)
+- [Level Zero Metric Query](../../samples/ze_metric_query)
+
+## Tools
+- [Level Zero Tracer](../../tools/ze_tracer)
+- [Tracing and Profiling Tool for Data Parallel C++ (DPC++)](../../tools/onetrace)
diff --git a/samples/loader/init.cc → loader/init.cc b/samples/loader/init.cc → loader/init.cc
diff --git a/samples/loader/loader.cc → loader/loader.cc b/samples/loader/loader.cc → loader/loader.cc
diff --git a/samples/loader/loader.h → loader/loader.h b/samples/loader/loader.h → loader/loader.h
diff --git a/samples/loader/tool.h → loader/tool.h b/samples/loader/tool.h → loader/tool.h
diff --git a/samples/cl_debug_info/CMakeLists.txt b/samples/cl_debug_info/CMakeLists.txt
@@ -1,4 +1,4 @@
-include("../build_utils/CMakeLists.txt")
+include("../../build_utils/CMakeLists.txt")
 SetRequiredCMakeVersion()
 cmake_minimum_required(VERSION ${REQUIRED_CMAKE_VERSION})
 
@@ -8,9 +8,9 @@ SetBuildType()
 
 # Tool Library
 
-add_library(clt_debug_info SHARED "${PROJECT_SOURCE_DIR}/../loader/init.cc" tool.cc)
+add_library(clt_debug_info SHARED "${PROJECT_SOURCE_DIR}/../../loader/init.cc" tool.cc)
 target_include_directories(clt_debug_info
-  PRIVATE "${PROJECT_SOURCE_DIR}/../utils")
+  PRIVATE "${PROJECT_SOURCE_DIR}/../../utils")
 if(CMAKE_INCLUDE_PATH)
   target_include_directories(clt_debug_info
     PUBLIC "${CMAKE_INCLUDE_PATH}")
@@ -30,9 +30,9 @@ GetGmmHeaders(clt_debug_info)
 # Loader
 
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DTOOL_NAME=clt_debug_info")
-add_executable(cl_debug_info "${PROJECT_SOURCE_DIR}/../loader/loader.cc")
+add_executable(cl_debug_info "${PROJECT_SOURCE_DIR}/../../loader/loader.cc")
 target_include_directories(cl_debug_info
-  PRIVATE "${PROJECT_SOURCE_DIR}/../utils")
+  PRIVATE "${PROJECT_SOURCE_DIR}/../../utils")
 if(UNIX)
   target_link_libraries(cl_debug_info
     dl)

diff --git a/samples/cl_gemm/CMakeLists.txt b/samples/cl_gemm/CMakeLists.txt
@@ -1,4 +1,4 @@
-include("../build_utils/CMakeLists.txt")
+include("../../build_utils/CMakeLists.txt")
 SetRequiredCMakeVersion()
 cmake_minimum_required(VERSION ${REQUIRED_CMAKE_VERSION})
 
@@ -8,7 +8,7 @@ SetBuildType()
 
 add_executable(cl_gemm main.cc)
 target_include_directories(cl_gemm
-  PRIVATE "${PROJECT_SOURCE_DIR}/../utils")
+  PRIVATE "${PROJECT_SOURCE_DIR}/../../utils")
 if(CMAKE_INCLUDE_PATH)
   target_include_directories(cl_gemm
     PUBLIC "${CMAKE_INCLUDE_PATH}")

diff --git a/samples/cl_gemm_inst/CMakeLists.txt b/samples/cl_gemm_inst/CMakeLists.txt
@@ -1,4 +1,4 @@
-include("../build_utils/CMakeLists.txt")
+include("../../build_utils/CMakeLists.txt")
 SetRequiredCMakeVersion()
 cmake_minimum_required(VERSION ${REQUIRED_CMAKE_VERSION})
 
@@ -8,7 +8,7 @@ SetBuildType()
 
 add_executable(cl_gemm_inst main.cc)
 target_include_directories(cl_gemm_inst
-  PRIVATE "${PROJECT_SOURCE_DIR}/../utils")
+  PRIVATE "${PROJECT_SOURCE_DIR}/../../utils")
 if(CMAKE_INCLUDE_PATH)
   target_include_directories(cl_gemm_inst
     PUBLIC "${CMAKE_INCLUDE_PATH}")

diff --git a/samples/cl_gemm_itt/CMakeLists.txt b/samples/cl_gemm_itt/CMakeLists.txt
@@ -1,4 +1,4 @@
-include("../build_utils/CMakeLists.txt")
+include("../../build_utils/CMakeLists.txt")
 SetRequiredCMakeVersion()
 cmake_minimum_required(VERSION ${REQUIRED_CMAKE_VERSION})
 
@@ -8,7 +8,7 @@ SetBuildType()
 
 add_executable(cl_gemm_itt main.cc ittnotify.cc)
 target_include_directories(cl_gemm_itt
-  PRIVATE "${PROJECT_SOURCE_DIR}/../utils")
+  PRIVATE "${PROJECT_SOURCE_DIR}/../../utils")
 if(CMAKE_INCLUDE_PATH)
   target_include_directories(cl_gemm_itt
     PUBLIC "${CMAKE_INCLUDE_PATH}")

diff --git a/samples/cl_gpu_metrics/CMakeLists.txt b/samples/cl_gpu_metrics/CMakeLists.txt
@@ -1,4 +1,4 @@
-include("../build_utils/CMakeLists.txt")
+include("../../build_utils/CMakeLists.txt")
 SetRequiredCMakeVersion()
 cmake_minimum_required(VERSION ${REQUIRED_CMAKE_VERSION})
 
@@ -9,10 +9,10 @@ SetBuildType()
 # Tool Library
 
 add_library(clt_gpu_metrics SHARED
-  "${PROJECT_SOURCE_DIR}/../loader/init.cc"
+  "${PROJECT_SOURCE_DIR}/../../loader/init.cc"
   tool.cc)
 target_include_directories(clt_gpu_metrics
-  PRIVATE "${PROJECT_SOURCE_DIR}/../utils"
+  PRIVATE "${PROJECT_SOURCE_DIR}/../../utils"
   PRIVATE "${PROJECT_SOURCE_DIR}/../cl_hot_kernels")
 if(CMAKE_INCLUDE_PATH)
   target_include_directories(clt_gpu_metrics
@@ -34,9 +34,9 @@ CheckForMDLibrary()
 # Loader
 
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DTOOL_NAME=clt_gpu_metrics")
-add_executable(cl_gpu_metrics "${PROJECT_SOURCE_DIR}/../loader/loader.cc")
+add_executable(cl_gpu_metrics "${PROJECT_SOURCE_DIR}/../../loader/loader.cc")
 target_include_directories(cl_gpu_metrics
-  PRIVATE "${PROJECT_SOURCE_DIR}/../utils")
+  PRIVATE "${PROJECT_SOURCE_DIR}/../../utils")
 if(UNIX)
   target_link_libraries(cl_gpu_metrics
     dl)

diff --git a/samples/cl_hot_functions/CMakeLists.txt b/samples/cl_hot_functions/CMakeLists.txt
@@ -1,4 +1,4 @@
-include("../build_utils/CMakeLists.txt")
+include("../../build_utils/CMakeLists.txt")
 SetRequiredCMakeVersion()
 cmake_minimum_required(VERSION ${REQUIRED_CMAKE_VERSION})
 
@@ -9,10 +9,10 @@ SetBuildType()
 # Tool Library
 
 add_library(clt_hot_functions SHARED
-  "${PROJECT_SOURCE_DIR}/../loader/init.cc"
+  "${PROJECT_SOURCE_DIR}/../../loader/init.cc"
   tool.cc)
 target_include_directories(clt_hot_functions
-  PRIVATE "${PROJECT_SOURCE_DIR}/../utils")
+  PRIVATE "${PROJECT_SOURCE_DIR}/../../utils")
 if(CMAKE_INCLUDE_PATH)
   target_include_directories(clt_hot_functions
     PUBLIC "${CMAKE_INCLUDE_PATH}")
@@ -26,9 +26,9 @@ GetOpenCLTracingHeaders(clt_hot_functions)
 # Loader
 
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DTOOL_NAME=clt_hot_functions")
-add_executable(cl_hot_functions "${PROJECT_SOURCE_DIR}/../loader/loader.cc")
+add_executable(cl_hot_functions "${PROJECT_SOURCE_DIR}/../../loader/loader.cc")
 target_include_directories(cl_hot_functions
-  PRIVATE "${PROJECT_SOURCE_DIR}/../utils")
+  PRIVATE "${PROJECT_SOURCE_DIR}/../../utils")
 if(UNIX)
   target_link_libraries(cl_hot_functions
     dl)

diff --git a/samples/cl_hot_functions/README.md b/samples/cl_hot_functions/README.md
@@ -1,30 +1,43 @@
 # OpenCL(TM) Hot Functions
 ## Overview
-This is a simple LD_PRELOAD based tool that allows to collect all called OpenCL(TM) API functions within an application along with their total execution time and call count for GPU device.
+This is a simple LD_PRELOAD based tool that allows to collect all called OpenCL(TM) API functions within an application along with their total execution time and call count.
 
 As a result, table like the following will be printed.
 ```
-                          Function,       Calls,           Time (ns),        Average (ns)
-                    clBuildProgram,           1,           183549198,           183549198
-                    clCreateBuffer,          12,              108285,                9023
-clCreateCommandQueueWithProperties,           1,                1265,                1265
-                   clCreateContext,           1,                9322,                9322
-                    clCreateKernel,           1,                3428,                3428
-         clCreateProgramWithSource,           1,                3219,                3219
-            clEnqueueNDRangeKernel,           4,             2237845,              559461
-               clEnqueueReadBuffer,           4,             2358133,              589533
-              clEnqueueWriteBuffer,           8,             5719781,              714972
-                          clFinish,           4,           174064236,            43516059
-                    clGetDeviceIDs,           2,                 362,                 181
-                   clGetDeviceInfo,           2,                 354,                 177
-           clGetEventProfilingInfo,           8,               14198,                1774
-                   clGetKernelInfo,           4,                2411,                 602
-             clReleaseCommandQueue,           1,                1046,                1046
-                  clReleaseContext,           1,                 173,                 173
-                   clReleaseKernel,           1,                2741,                2741
-                clReleaseMemObject,          12,              110922,                9243
-                  clReleaseProgram,           1,               11561,               11561
-                    clSetKernelArg,          16,               75282,                4705
+=== API Timing Results: ===
+
+Total Execution Time (ns): 363687486
+Total API Time for CPU backend (ns): 524
+Total API Time for GPU backend (ns): 355355363
+
+== CPU Backend: ==
+
+      Function,       Calls,           Time (ns),  Time (%),        Average (ns),            Min (ns),            Max (ns)
+clGetDeviceIDs,           1,                 524,    100.00,                 524,                 524,                 524
+
+== GPU Backend: ==
+
+                          Function,       Calls,           Time (ns),  Time (%),        Average (ns),            Min (ns),            Max (ns)
+                    clBuildProgram,           1,           173888026,     48.93,           173888026,           173888026,           173888026
+                          clFinish,           4,           172908147,     48.66,            43227036,            42711785,            44318785
+              clEnqueueWriteBuffer,           8,             4636256,      1.30,              579532,              207825,             1864890
+               clEnqueueReadBuffer,           4,             2051244,      0.58,              512811,              498662,              542971
+            clEnqueueNDRangeKernel,           4,             1623139,      0.46,              405784,              236120,              609050
+                clReleaseMemObject,          12,               95182,      0.03,                7931,                3525,               16436
+                    clCreateBuffer,          12,               81056,      0.02,                6754,                2511,               16990
+                    clSetKernelArg,          16,               24515,      0.01,                1532,                 141,                7038
+           clGetEventProfilingInfo,           8,               13139,      0.00,                1642,                 103,                3288
+                   clCreateContext,           1,               12680,      0.00,               12680,               12680,               12680
+                  clReleaseProgram,           1,                9503,      0.00,                9503,                9503,                9503
+         clCreateProgramWithSource,           1,                3880,      0.00,                3880,                3880,                3880
+                    clCreateKernel,           1,                2941,      0.00,                2941,                2941,                2941
+                   clReleaseKernel,           1,                1679,      0.00,                1679,                1679,                1679
+                   clGetKernelInfo,           4,                1617,      0.00,                 404,                 190,                 552
+clCreateCommandQueueWithProperties,           1,                1388,      0.00,                1388,                1388,                1388
+                    clGetDeviceIDs,           2,                 311,      0.00,                 155,                 138,                 173
+             clReleaseCommandQueue,           1,                 270,      0.00,                 270,                 270,                 270
+                   clGetDeviceInfo,           2,                 227,      0.00,                 113,                 103,                 124
+                  clReleaseContext,           1,                 163,      0.00,                 163,                 163,                 163
 ```
 ## Supported OS
 - Linux
@@ -35,7 +48,8 @@ clCreateCommandQueueWithProperties,           1,                1265,
 - [Git](https://git-scm.com/) (version 1.8 and above)
 - [Python](https://www.python.org/) (version 2.7 and above)
 - [OpenCL(TM) ICD Loader](https://github.com/KhronosGroup/OpenCL-ICD-Loader)
-- [Intel(R) Graphics Compute Runtime for oneAPI Level Zero and OpenCL(TM) Driver](https://github.com/intel/compute-runtime)
+- [Intel(R) Graphics Compute Runtime for oneAPI Level Zero and OpenCL(TM) Driver](https://github.com/intel/compute-runtime) to run on GPU
+- [Intel(R) Xeon(R) Processor / Intel(R) Core(TM) Processor (CPU) Runtimes](https://software.intel.com/en-us/articles/opencl-drivers#cpu-section) to run on CPU
 
 ## Build and Run
 ### Linux
@@ -51,9 +65,10 @@ Use this command line to run the tool:
 ```sh
 ./cl_hot_functions <target_application>
 ```
-One may use [cl_gemm](../cl_gemm) as target application:
+One may use [cl_gemm](../cl_gemm) or [dpc_gemm](../dpc_gemm) as target application:
 ```sh
 ./cl_hot_functions ../../cl_gemm/build/cl_gemm
+./cl_hot_functions ../../dpc_gemm/build/dpc_gemm cpu
 ```
 ### Windows
 Use Microsoft* Visual Studio x64 command prompt to run the following commands and build the sample:
@@ -68,7 +83,8 @@ Use this command line to run the tool:
 ```sh
 cl_hot_functions.exe <target_application>
 ```
-One may use [cl_gemm](../cl_gemm) as target application:
+One may use [cl_gemm](../cl_gemm) or [dpc_gemm](../dpc_gemm) as target application:
 ```sh
 cl_hot_functions.exe ..\..\cl_gemm\build\cl_gemm.exe
+cl_hot_functions.exe ..\..\dpc_gemm\build\dpc_gemm.exe cpu
 ```