AI/rocm-systems
2
0
Derivar 0
Código Questões Pedidos de integração Operações Pacotes Planeamentos Lançamentos Wiki Trabalho

HIP API Tracing (#357)

Ver a proveniência 
* Update include/rocprofiler-sdk/hip*

- updates for intercept table

* Update lib/common/units.hpp

- clang-tidy fixes

* Add lib/rocprofiler-sdk/hip

- tracing implementation for the HIP intercept table

* Update source/lib/rocprofiler-sdk/CMakeLists.txt

- add_subdirectory(hip)

* Update source/lib/rocprofiler-sdk/hsa

- offset function in hsa_api_info<Idx>
- remove report_activity, set_callback
- Tweak HSA_API_TABLE_LOOKUP_DEFINITION

* Update lib/rocprofiler-sdk/hip

- rocprofiler::hip::copy_table
- stringize_impl print dereferenced pointers when possible

* Update lib/rocprofiler-sdk/hsa/utils.hpp

- stringize_impl print dereferenced pointers when possible

* Update lib/rocprofiler-sdk/tests/intercept_table.cpp

- remove failures for intercepting HIP API tables

* Update include/rocprofiler-sdk/fwd.h

- add ROCPROFILER_HIP_RUNTIME_LIBRARY (== ROCPROFILER_HIP_LIBRARY)
- add ROCPROFILER_HIP_COMPILER_LIBRARY

* Update lib/rocprofiler-sdk/buffer_tracing.cpp

- Support ROCPROFILER_BUFFER_TRACING_HIP_API in rocprofiler_query_buffer_tracing_kind_operation_name
- Support ROCPROFILER_BUFFER_TRACING_HIP_API in rocprofiler_iterate_buffer_tracing_kind_operations

* Update lib/rocprofiler-sdk/callback_tracing.cpp

- Support ROCPROFILER_CALLBACK_TRACING_HIP_API in rocprofiler_query_callback_tracing_kind_operation_name
- Support ROCPROFILER_CALLBACK_TRACING_HIP_API in rocprofiler_iterate_callback_tracing_kind_operations
- Support ROCPROFILER_CALLBACK_TRACING_HIP_API in rocprofiler_iterate_callback_tracing_kind_operation_args

* Update lib/rocprofiler-sdk/intercept_table.cpp

- support HipDispatchTable and HipCompilerDispatchTable

* Update lib/rocprofiler-sdk/internal_threading.cpp

- Support ROCPROFILER_HIP_COMPILER_LIBRARY

* Update lib/rocprofiler-sdk/registration.cpp

- Support "hip" and "hip_compiler" in rocprofiler_set_api_table
- Added some extra logging

* Update samples/api_{buffered,callback}_tracing

- Modifications to demonstrate HIP API tracing

* Update tests/kernel-tracing

- Modifications to handle/test HIP API tracing

* Separate HIP tracing from HIP compiler tracing

* Fix installation of include/rocprofiler-sdk/hip/*

- add compiler and table headers to install

* Fixes to HIP interception

- hip_api_trace.hpp was updated a bit
  - removed hipGetDeviceProperties (generic)
  - added hipGetDevicePropertiesR0600
  - added hipGetDevicePropertiesR0000
  - removed hipRegisterTracerCallback
  - reordered hipCreateChannelDesc, hipExtModuleLaunchKernel, hipHccModuleLaunchKernel
  - added hipDrvGraphAddMemsetNode
- static asserts in hsa_api_info ensuring ordering of pointers

* Update lib/rocprofiler-sdk/hip/hip.*

- use size_t instead of rocprofiler_hip_table_api_id_t as non-type template parameter (smaller binary)
- separated out population of callback_context_data and buffered_context_data into non-template function (significantly smaller binary)

* Update lib/rocprofiler-sdk/hsa/hsa.*

- separated out population of callback_context_data and buffered_context_data into non-template function (significantly smaller binary)

* Update test/kernel-tracing/validate.py

- does not expect any hip_api_traces until libamdhip.so actually starts using rocprofiler-register

* Update tests/tools/json-tool.cpp

- fix context associated with "HIP_API_CALLBACK"

* Update external/CMakeLists.txt

- move misc variables to top of CMakeLists.txt so they apply to all external subprojects
  - BUILD_TESTING (OFF)
  - BUILD_SHARED_LIBS (OFF)
  - BUILD_OBJECT_LIBS (OFF)
  - BUILD_STATIC_LIBS (ON)
  - CMAKE_POSITION_INDEPENDENT_CODE (ON)
  - CMAKE_VISIBILITY_INLINES_HIDDEN (ON)
  - CMAKE_CXX_VISIBILITY_PRESET (hidden)
- disable using libunwind in glog

* Update lib/rocprofiler-{sdk,sdk-tool}/CMakeLists.txt

- remove explicit setting of SKIP_BUILD_RPATH

* Update CMakeLists.txt

- set high-level CMAKE_BUILD_RPATH and CMAKE_INSTALL_RPATH_USE_LINK_PATH

* Update tests/CMakeLists.txt

- include(GNUInstallDirs)

* Update samples/CMakeLists.txt

- include(GNUInstallDirs)

* Update include/rocprofiler-sdk/hip/{compiler_api,api}_args.h

- remove extern "C" due to incompatibility b/t empty struct in C (size 0) vs. empty struct in C++ (size 1)

* Update lib/rocprofiler-sdk/hip/details/ostream.hpp

- clang-tidy fixes

* Update cmake/rocprofiler_linting.cmake

- add a feature for clang tidy exe

* Update lib/rocprofiler-sdk/hip/hip.cpp

- use recursion instead of fold expression due to clang-tidy errors (maximum nesting level exceeded)

* Update lib/rocprofiler-sdk/buffer_tracing.cpp

- fix merge

* Update lib/rocprofiler-sdk/callback_tracing.cpp

- fix merge

* Update bin/rocprofv3

- args for marker, HIP runtime, and HIP compiler tracing

* Update tests/apps/simple-transpose

- use roctx

* Update tests/rocprofv3/tracing

- validate marker API data

* Update lib/rocprofiler-sdk-tool

- support for HIP runtime, HIP compiler, marker API

* Update queue/queue_controller/registration/utility

- call hsa::queue_controller_fini() during finalization
- add a yield function to common/utility.hpp
  - implements a thread yield + sleep
- add a sync function to Queue class
- add a iterate_queues member function to QueueController
  - this is used to sync each queue during queue_controller_fini()

* Fix data races: queue/context/stable_vector

- stable_vector::emplace_back returns reference
- correlation id map uses stable_vector
- queue_info_session has explicit fields for queue id, hsa agent, rocp agent
- use hsa::get_table() in AsyncSignalHandler
- WriteInterceptor does not use TLS for context array

* Update lib/rocprofiler-sdk/hsa/hsa.*

- static object for API subtables
- accessors for API subtables
- google tests for HSA API subtables

* Update lib/rocprofiler-sdk/hsa/{queue,async_copy}.cpp

- use HSA subtable accessors

* Update rocprofiler_memcheck and CI workflow

- use GCC 13 instead of GCC 11 due to suspected false positives in thread sanitizer
  - GCC 13 uses libtsan.so.2

* Update CI workflow

* Update lib/rocprofiler-sdk/counters/{metrics,counters}

- fix possibly dangling reference to a temporary from gcc-13

* Update thread-sanitizer-suppr.txt

- Ignore data races originating in hsa-runtime library

* Update cmake/rocprofiler_memcheck.cmake

- Deduce the sanitizer library to preload by compiling an application and extracting the linked sanitizer library

* Update tests/rocprofv3/tracing/CMakeLists.txt

- add csv files to REQUIRED_FILES and ATTACH_ON_FAIL in validate test

* Update lib/common/container/record_header_buffer.hpp

- fix data race identified by gcc v13 and libtsan.so.2

* Update hip API id, args, and def

- remove hipDrvGraphAddMemsetNode (not part of ROCm 6.0

* Update lib/common/container/record_header_buffer.hpp

- fix deadlock in save/read/reset

* Update source/docs/CMakeLists.txt

- remove COMMAND_ERROR_IS_FATAL ANY to allow for printing of stdout/stderr

* Update lib/rocprofiler-sdk/hip/details/ostream.hpp

- remove overloads for HIP_MEMSET_NODE_PARAMS

* Update docs/CMakeLists.txt

- use find_program for shell instead of hardcoded /bin/bash
Este cometimento está contido em:
Jonathan R. Madsen
2024-01-24 16:32:54 -06:00
cometido por GitHub
ascendente f84c2f4386
cometimento c641749fe6
74 ficheiros modificados com 10091 adições e 729 eliminações
Descarregar ficheiro patch Descarregar ficheiro diff Expandir todos os ficheiros Colapsar todos os ficheiros
source/include/rocprofiler-sdk/hip/api_args.h
+590 -105
Ver ficheiro
@@ -22,68 +22,100 @@
#pragma once
#include <rocprofiler-sdk/defines.h>
#include <hip/hip_runtime.h>
#include <hip/hip_runtime_api.h>
#include <hip/hip_version.h>
// must be included after
#include <hip/hip_deprecated.h>
typedef union rocprofiler_hip_api_retval_u
{
int int_retval;
const char* const_charp_retval;
hipError_t hipError_t_retval;
int int_retval;
const char* const_charp_retval;
hipError_t hipError_t_retval;
hipChannelFormatDesc hipChannelFormatDesc_retval;
} rocprofiler_hip_api_retval_t;
typedef union rocprofiler_hip_api_args_u
{
struct
{
dim3* gridDim;
dim3* blockDim;
size_t* sharedMem;
hipStream_t* stream;
} __hipPopCallConfiguration;
uint32_t id;
} hipApiName;
struct
{
dim3 gridDim;
dim3 blockDim;
size_t sharedMem;
hipStream_t stream;
} __hipPushCallConfiguration;
struct
{
hipArray** array;
hipArray_t* array;
const HIP_ARRAY3D_DESCRIPTOR* pAllocateArray;
} hipArray3DCreate;
struct
{
HIP_ARRAY3D_DESCRIPTOR* pArrayDescriptor;
hipArray* array;
hipArray_t array;
} hipArray3DGetDescriptor;
struct
{
hipArray** pHandle;
hipArray_t* pHandle;
const HIP_ARRAY_DESCRIPTOR* pAllocateArray;
} hipArrayCreate;
struct
{
hipArray* array;
hipArray_t array;
} hipArrayDestroy;
struct
{
HIP_ARRAY_DESCRIPTOR* pArrayDescriptor;
hipArray* array;
hipArray_t array;
} hipArrayGetDescriptor;
struct
{
hipChannelFormatDesc* desc;
hipExtent* extent;
unsigned int* flags;
hipArray* array;
hipArray_t array;
} hipArrayGetInfo;
struct
{
int* device;
const hipDeviceProp_t* prop;
size_t* offset;
const textureReference* tex;
const void* devPtr;
const hipChannelFormatDesc* desc;
size_t size;
} hipBindTexture;
struct
{
size_t* offset;
const textureReference* tex;
const void* devPtr;
const hipChannelFormatDesc* desc;
size_t width;
size_t height;
size_t pitch;
} hipBindTexture2D;
struct
{
const textureReference* tex;
hipArray_const_t array;
const hipChannelFormatDesc* desc;
} hipBindTextureToArray;
struct
{
const textureReference* tex;
hipMipmappedArray_const_t mipmappedArray;
const hipChannelFormatDesc* desc;
} hipBindTextureToMipmappedArray;
struct
{
int* device;
const hipDeviceProp_tR0600* prop;
} hipChooseDevice;
struct
{
int* device;
const hipDeviceProp_tR0000* prop;
} hipChooseDeviceR0000;
struct
{
dim3 gridDim;
dim3 blockDim;
@@ -96,6 +128,13 @@ typedef union rocprofiler_hip_api_args_u
const hipResourceDesc* pResDesc;
} hipCreateSurfaceObject;
struct
{
hipTextureObject_t* pTexObject;
const hipResourceDesc* pResDesc;
const hipTextureDesc* pTexDesc;
const struct hipResourceViewDesc* pResViewDesc;
} hipCreateTextureObject;
struct
{
hipCtx_t* ctx;
unsigned int flags;
@@ -160,6 +199,9 @@ typedef union rocprofiler_hip_api_args_u
hipSharedMemConfig config;
} hipCtxSetSharedMemConfig;
struct
{
} hipCtxSynchronize;
struct
{
hipExternalMemory_t extMem;
} hipDestroyExternalMemory;
@@ -172,6 +214,10 @@ typedef union rocprofiler_hip_api_args_u
hipSurfaceObject_t surfaceObject;
} hipDestroySurfaceObject;
struct
{
hipTextureObject_t textureObject;
} hipDestroyTextureObject;
struct
{
int* canAccessPeer;
int deviceId;
@@ -295,6 +341,9 @@ typedef union rocprofiler_hip_api_args_u
unsigned int flags;
} hipDevicePrimaryCtxSetFlags;
struct
{
} hipDeviceReset;
struct
{
hipFuncCache_t cacheConfig;
} hipDeviceSetCacheConfig;
@@ -319,6 +368,9 @@ typedef union rocprofiler_hip_api_args_u
hipSharedMemConfig config;
} hipDeviceSetSharedMemConfig;
struct
{
} hipDeviceSynchronize;
struct
{
size_t* bytes;
hipDevice_t device;
@@ -328,6 +380,25 @@ typedef union rocprofiler_hip_api_args_u
int* driverVersion;
} hipDriverGetVersion;
struct
{
hipError_t hipError;
const char** errorString;
} hipDrvGetErrorName;
struct
{
hipError_t hipError;
const char** errorString;
} hipDrvGetErrorString;
struct
{
hipGraphNode_t* phGraphNode;
hipGraph_t hGraph;
const hipGraphNode_t* dependencies;
size_t numDependencies;
const HIP_MEMCPY3D* copyParams;
hipCtx_t ctx;
} hipDrvGraphAddMemcpyNode;
struct
{
const hip_Memcpy2D* pCopy;
} hipDrvMemcpy2DUnaligned;
@@ -353,8 +424,8 @@ typedef union rocprofiler_hip_api_args_u
} hipEventCreate;
struct
{
hipEvent_t* event;
unsigned int flags;
hipEvent_t* event;
unsigned flags;
} hipEventCreateWithFlags;
struct
{
@@ -381,10 +452,10 @@ typedef union rocprofiler_hip_api_args_u
} hipEventSynchronize;
struct
{
int device1;
int device2;
unsigned int* linktype;
unsigned int* hopcount;
int device1;
int device2;
uint32_t* linktype;
uint32_t* hopcount;
} hipExtGetLinkTypeAndHopCount;
struct
{
@@ -412,32 +483,15 @@ typedef union rocprofiler_hip_api_args_u
} hipExtMallocWithFlags;
struct
{
hipFunction_t f;
unsigned int globalWorkSizeX;
unsigned int globalWorkSizeY;
unsigned int globalWorkSizeZ;
unsigned int localWorkSizeX;
unsigned int localWorkSizeY;
unsigned int localWorkSizeZ;
size_t sharedMemBytes;
hipStream_t hStream;
void** kernelParams;
void** extra;
hipEvent_t startEvent;
hipEvent_t stopEvent;
unsigned int flags;
} hipExtModuleLaunchKernel;
struct
{
hipStream_t* stream;
unsigned int cuMaskSize;
const unsigned int* cuMask;
hipStream_t* stream;
uint32_t cuMaskSize;
const uint32_t* cuMask;
} hipExtStreamCreateWithCUMask;
struct
{
hipStream_t stream;
unsigned int cuMaskSize;
unsigned int* cuMask;
hipStream_t stream;
uint32_t cuMaskSize;
uint32_t* cuMask;
} hipExtStreamGetCUMask;
struct
{
@@ -451,7 +505,7 @@ typedef union rocprofiler_hip_api_args_u
} hipFree;
struct
{
hipArray* array;
hipArray_t array;
} hipFreeArray;
struct
{
@@ -474,8 +528,8 @@ typedef union rocprofiler_hip_api_args_u
} hipFuncGetAttribute;
struct
{
hipFuncAttributes* attr;
const void* func;
struct hipFuncAttributes* attr;
const void* func;
} hipFuncGetAttributes;
struct
{
@@ -519,9 +573,25 @@ typedef union rocprofiler_hip_api_args_u
} hipGetDeviceFlags;
struct
{
hipDeviceProp_t* props;
hipDevice_t device;
} hipGetDeviceProperties;
hipDeviceProp_tR0600* prop;
int deviceId;
} hipGetDevicePropertiesR0600;
struct
{
hipDeviceProp_tR0000* prop;
int deviceId;
} hipGetDevicePropertiesR0000;
struct
{
hipError_t hip_error;
} hipGetErrorName;
struct
{
hipError_t hipError;
} hipGetErrorString;
struct
{
} hipGetLastError;
struct
{
hipArray_t* levelArray;
@@ -539,6 +609,31 @@ typedef union rocprofiler_hip_api_args_u
const void* symbol;
} hipGetSymbolSize;
struct
{
size_t* offset;
const textureReference* texref;
} hipGetTextureAlignmentOffset;
struct
{
hipResourceDesc* pResDesc;
hipTextureObject_t textureObject;
} hipGetTextureObjectResourceDesc;
struct
{
struct hipResourceViewDesc* pResViewDesc;
hipTextureObject_t textureObject;
} hipGetTextureObjectResourceViewDesc;
struct
{
hipTextureDesc* pTexDesc;
hipTextureObject_t textureObject;
} hipGetTextureObjectTextureDesc;
struct
{
const textureReference** texref;
const void* symbol;
} hipGetTextureReference;
struct
{
hipGraphNode_t* pGraphNode;
hipGraph_t graph;
@@ -1024,22 +1119,6 @@ typedef union rocprofiler_hip_api_args_u
hipGraphicsResource_t resource;
} hipGraphicsUnregisterResource;
struct
{
hipFunction_t f;
unsigned int globalWorkSizeX;
unsigned int globalWorkSizeY;
unsigned int globalWorkSizeZ;
unsigned int blockDimX;
unsigned int blockDimY;
unsigned int blockDimZ;
size_t sharedMemBytes;
hipStream_t hStream;
void** kernelParams;
void** extra;
hipEvent_t startEvent;
hipEvent_t stopEvent;
} hipHccModuleLaunchKernel;
struct
{
void** ptr;
size_t size;
@@ -1116,8 +1195,17 @@ typedef union rocprofiler_hip_api_args_u
unsigned int flags;
} hipIpcOpenMemHandle;
struct
{
hipFunction_t f;
} hipKernelNameRef;
struct
{
const void* hostFunction;
hipStream_t stream;
} hipKernelNameRefByPtr;
struct
{
const void* func;
} hipLaunchByPtr;
struct
{
@@ -1161,14 +1249,14 @@ typedef union rocprofiler_hip_api_args_u
} hipMalloc3D;
struct
{
hipArray_t* array;
const hipChannelFormatDesc* desc;
hipExtent extent;
unsigned int flags;
hipArray_t* array;
const struct hipChannelFormatDesc* desc;
struct hipExtent extent;
unsigned int flags;
} hipMalloc3DArray;
struct
{
hipArray** array;
hipArray_t* array;
const hipChannelFormatDesc* desc;
size_t width;
size_t height;
@@ -1200,11 +1288,11 @@ typedef union rocprofiler_hip_api_args_u
} hipMallocManaged;
struct
{
hipMipmappedArray_t* mipmappedArray;
const hipChannelFormatDesc* desc;
hipExtent extent;
unsigned int numLevels;
unsigned int flags;
hipMipmappedArray_t* mipmappedArray;
const struct hipChannelFormatDesc* desc;
struct hipExtent extent;
unsigned int numLevels;
unsigned int flags;
} hipMallocMipmappedArray;
struct
{
@@ -1474,7 +1562,7 @@ typedef union rocprofiler_hip_api_args_u
} hipMemcpy2DFromArrayAsync;
struct
{
hipArray* dst;
hipArray_t dst;
size_t wOffset;
size_t hOffset;
const void* src;
@@ -1485,7 +1573,7 @@ typedef union rocprofiler_hip_api_args_u
} hipMemcpy2DToArray;
struct
{
hipArray* dst;
hipArray_t dst;
size_t wOffset;
size_t hOffset;
const void* src;
@@ -1497,12 +1585,12 @@ typedef union rocprofiler_hip_api_args_u
} hipMemcpy2DToArrayAsync;
struct
{
const hipMemcpy3DParms* p;
const struct hipMemcpy3DParms* p;
} hipMemcpy3D;
struct
{
const hipMemcpy3DParms* p;
hipStream_t stream;
const struct hipMemcpy3DParms* p;
hipStream_t stream;
} hipMemcpy3DAsync;
struct
{
@@ -1514,10 +1602,10 @@ typedef union rocprofiler_hip_api_args_u
} hipMemcpyAsync;
struct
{
void* dst;
hipArray* srcArray;
size_t srcOffset;
size_t count;
void* dst;
hipArray_t srcArray;
size_t srcOffset;
size_t count;
} hipMemcpyAtoH;
struct
{
@@ -1573,7 +1661,7 @@ typedef union rocprofiler_hip_api_args_u
} hipMemcpyFromSymbolAsync;
struct
{
hipArray* dstArray;
hipArray_t dstArray;
size_t dstOffset;
const void* srcHost;
size_t count;
@@ -1619,7 +1707,7 @@ typedef union rocprofiler_hip_api_args_u
} hipMemcpyPeerAsync;
struct
{
hipArray* dst;
hipArray_t dst;
size_t wOffset;
size_t hOffset;
const void* src;
@@ -1817,7 +1905,7 @@ typedef union rocprofiler_hip_api_args_u
const void* image;
unsigned int numOptions;
hipJitOption* options;
void** optionsValues;
void** optionValues;
} hipModuleLoadDataEx;
struct
{
@@ -1860,14 +1948,14 @@ typedef union rocprofiler_hip_api_args_u
int* numBlocks;
const void* f;
int blockSize;
size_t dynamicSMemSize;
size_t dynSharedMemPerBlk;
} hipOccupancyMaxActiveBlocksPerMultiprocessor;
struct
{
int* numBlocks;
const void* f;
int blockSize;
size_t dynamicSMemSize;
size_t dynSharedMemPerBlk;
unsigned int flags;
} hipOccupancyMaxActiveBlocksPerMultiprocessorWithFlags;
struct
@@ -1879,6 +1967,9 @@ typedef union rocprofiler_hip_api_args_u
int blockSizeLimit;
} hipOccupancyMaxPotentialBlockSize;
struct
{
} hipPeekAtLastError;
struct
{
void* data;
hipPointer_attribute attribute;
@@ -1896,6 +1987,12 @@ typedef union rocprofiler_hip_api_args_u
hipDeviceptr_t ptr;
} hipPointerSetAttribute;
struct
{
} hipProfilerStart;
struct
{
} hipProfilerStop;
struct
{
int* runtimeVersion;
} hipRuntimeGetVersion;
@@ -1905,7 +2002,7 @@ typedef union rocprofiler_hip_api_args_u
} hipSetDevice;
struct
{
unsigned int flags;
unsigned flags;
} hipSetDeviceFlags;
struct
{
@@ -2023,9 +2120,9 @@ typedef union rocprofiler_hip_api_args_u
{
hipStream_t stream;
void* ptr;
unsigned int value;
uint32_t value;
unsigned int flags;
unsigned int mask;
uint32_t mask;
} hipStreamWaitValue32;
struct
{
@@ -2039,7 +2136,7 @@ typedef union rocprofiler_hip_api_args_u
{
hipStream_t stream;
void* ptr;
unsigned int value;
uint32_t value;
unsigned int flags;
} hipStreamWriteValue32;
struct
@@ -2050,11 +2147,48 @@ typedef union rocprofiler_hip_api_args_u
unsigned int flags;
} hipStreamWriteValue64;
struct
{
hipTextureObject_t* pTexObject;
const HIP_RESOURCE_DESC* pResDesc;
const HIP_TEXTURE_DESC* pTexDesc;
const HIP_RESOURCE_VIEW_DESC* pResViewDesc;
} hipTexObjectCreate;
struct
{
hipTextureObject_t texObject;
} hipTexObjectDestroy;
struct
{
HIP_RESOURCE_DESC* pResDesc;
hipTextureObject_t texObject;
} hipTexObjectGetResourceDesc;
struct
{
HIP_RESOURCE_VIEW_DESC* pResViewDesc;
hipTextureObject_t texObject;
} hipTexObjectGetResourceViewDesc;
struct
{
HIP_TEXTURE_DESC* pTexDesc;
hipTextureObject_t texObject;
} hipTexObjectGetTextureDesc;
struct
{
hipDeviceptr_t* dev_ptr;
const textureReference* texRef;
} hipTexRefGetAddress;
struct
{
enum hipTextureAddressMode* pam;
const textureReference* texRef;
int dim;
} hipTexRefGetAddressMode;
struct
{
enum hipTextureFilterMode* pfm;
const textureReference* texRef;
} hipTexRefGetFilterMode;
struct
{
unsigned int* pFlags;
const textureReference* texRef;
@@ -2076,6 +2210,11 @@ typedef union rocprofiler_hip_api_args_u
const textureReference* texRef;
} hipTexRefGetMipMappedArray;
struct
{
enum hipTextureFilterMode* pfm;
const textureReference* texRef;
} hipTexRefGetMipmapFilterMode;
struct
{
float* pbias;
const textureReference* texRef;
@@ -2101,6 +2240,12 @@ typedef union rocprofiler_hip_api_args_u
size_t Pitch;
} hipTexRefSetAddress2D;
struct
{
textureReference* texRef;
int dim;
enum hipTextureAddressMode am;
} hipTexRefSetAddressMode;
struct
{
textureReference* tex;
hipArray_const_t array;
@@ -2112,6 +2257,11 @@ typedef union rocprofiler_hip_api_args_u
float* pBorderColor;
} hipTexRefSetBorderColor;
struct
{
textureReference* texRef;
enum hipTextureFilterMode fm;
} hipTexRefSetFilterMode;
struct
{
textureReference* texRef;
unsigned int Flags;
@@ -2128,6 +2278,11 @@ typedef union rocprofiler_hip_api_args_u
unsigned int maxAniso;
} hipTexRefSetMaxAnisotropy;
struct
{
textureReference* texRef;
enum hipTextureFilterMode fm;
} hipTexRefSetMipmapFilterMode;
struct
{
textureReference* texRef;
float bias;
@@ -2140,15 +2295,19 @@ typedef union rocprofiler_hip_api_args_u
} hipTexRefSetMipmapLevelClamp;
struct
{
textureReference* texRef;
hipMipmappedArray* mipmappedArray;
unsigned int Flags;
textureReference* texRef;
struct hipMipmappedArray* mipmappedArray;
unsigned int Flags;
} hipTexRefSetMipmappedArray;
struct
{
hipStreamCaptureMode* mode;
} hipThreadExchangeStreamCaptureMode;
struct
{
const textureReference* tex;
} hipUnbindTexture;
struct
{
hipUserObject_t* object_out;
void* ptr;
@@ -2173,4 +2332,330 @@ typedef union rocprofiler_hip_api_args_u
unsigned int numExtSems;
hipStream_t stream;
} hipWaitExternalSemaphoresAsync;
struct
{
int x;
int y;
int z;
int w;
hipChannelFormatKind f;
} hipCreateChannelDesc;
struct
{
hipFunction_t f;
uint32_t globalWorkSizeX;
uint32_t globalWorkSizeY;
uint32_t globalWorkSizeZ;
uint32_t localWorkSizeX;
uint32_t localWorkSizeY;
uint32_t localWorkSizeZ;
size_t sharedMemBytes;
hipStream_t hStream;
void** kernelParams;
void** extra;
hipEvent_t startEvent;
hipEvent_t stopEvent;
uint32_t flags;
} hipExtModuleLaunchKernel;
struct
{
hipFunction_t f;
uint32_t globalWorkSizeX;
uint32_t globalWorkSizeY;
uint32_t globalWorkSizeZ;
uint32_t localWorkSizeX;
uint32_t localWorkSizeY;
uint32_t localWorkSizeZ;
size_t sharedMemBytes;
hipStream_t hStream;
void** kernelParams;
void** extra;
hipEvent_t startEvent;
hipEvent_t stopEvent;
} hipHccModuleLaunchKernel;
struct
{
void* dst;
const void* src;
size_t sizeBytes;
hipMemcpyKind kind;
} hipMemcpy_spt;
struct
{
const void* symbol;
const void* src;
size_t sizeBytes;
size_t offset;
hipMemcpyKind kind;
} hipMemcpyToSymbol_spt;
struct
{
void* dst;
const void* symbol;
size_t sizeBytes;
size_t offset;
hipMemcpyKind kind;
} hipMemcpyFromSymbol_spt;
struct
{
void* dst;
size_t dpitch;
const void* src;
size_t spitch;
size_t width;
size_t height;
hipMemcpyKind kind;
} hipMemcpy2D_spt;
struct
{
void* dst;
size_t dpitch;
hipArray_const_t src;
size_t wOffset;
size_t hOffset;
size_t width;
size_t height;
hipMemcpyKind kind;
} hipMemcpy2DFromArray_spt;
struct
{
const struct hipMemcpy3DParms* p;
} hipMemcpy3D_spt;
struct
{
void* dst;
int value;
size_t sizeBytes;
} hipMemset_spt;
struct
{
void* dst;
int value;
size_t sizeBytes;
hipStream_t stream;
} hipMemsetAsync_spt;
struct
{
void* dst;
size_t pitch;
int value;
size_t width;
size_t height;
} hipMemset2D_spt;
struct
{
void* dst;
size_t pitch;
int value;
size_t width;
size_t height;
hipStream_t stream;
} hipMemset2DAsync_spt;
struct
{
hipPitchedPtr pitchedDevPtr;
int value;
hipExtent extent;
hipStream_t stream;
} hipMemset3DAsync_spt;
struct
{
hipPitchedPtr pitchedDevPtr;
int value;
hipExtent extent;
} hipMemset3D_spt;
struct
{
void* dst;
const void* src;
size_t sizeBytes;
hipMemcpyKind kind;
hipStream_t stream;
} hipMemcpyAsync_spt;
struct
{
const hipMemcpy3DParms* p;
hipStream_t stream;
} hipMemcpy3DAsync_spt;
struct
{
void* dst;
size_t dpitch;
const void* src;
size_t spitch;
size_t width;
size_t height;
hipMemcpyKind kind;
hipStream_t stream;
} hipMemcpy2DAsync_spt;
struct
{
void* dst;
const void* symbol;
size_t sizeBytes;
size_t offset;
hipMemcpyKind kind;
hipStream_t stream;
} hipMemcpyFromSymbolAsync_spt;
struct
{
const void* symbol;
const void* src;
size_t sizeBytes;
size_t offset;
hipMemcpyKind kind;
hipStream_t stream;
} hipMemcpyToSymbolAsync_spt;
struct
{
void* dst;
hipArray_const_t src;
size_t wOffsetSrc;
size_t hOffset;
size_t count;
hipMemcpyKind kind;
} hipMemcpyFromArray_spt;
struct
{
hipArray_t dst;
size_t wOffset;
size_t hOffset;
const void* src;
size_t spitch;
size_t width;
size_t height;
hipMemcpyKind kind;
} hipMemcpy2DToArray_spt;
struct
{
void* dst;
size_t dpitch;
hipArray_const_t src;
size_t wOffsetSrc;
size_t hOffsetSrc;
size_t width;
size_t height;
hipMemcpyKind kind;
hipStream_t stream;
} hipMemcpy2DFromArrayAsync_spt;
struct
{
hipArray_t dst;
size_t wOffset;
size_t hOffset;
const void* src;
size_t spitch;
size_t width;
size_t height;
hipMemcpyKind kind;
hipStream_t stream;
} hipMemcpy2DToArrayAsync_spt;
struct
{
hipStream_t stream;
} hipStreamQuery_spt;
struct
{
hipStream_t stream;
} hipStreamSynchronize_spt;
struct
{
hipStream_t stream;
int* priority;
} hipStreamGetPriority_spt;
struct
{
hipStream_t stream;
hipEvent_t event;
unsigned int flags;
} hipStreamWaitEvent_spt;
struct
{
hipStream_t stream;
unsigned int* flags;
} hipStreamGetFlags_spt;
struct
{
hipStream_t stream;
hipStreamCallback_t callback;
void* userData;
unsigned int flags;
} hipStreamAddCallback_spt;
struct
{
hipEvent_t event;
hipStream_t stream;
} hipEventRecord_spt;
struct
{
const void* f;
dim3 gridDim;
dim3 blockDim;
void** kernelParams;
uint32_t sharedMemBytes;
hipStream_t hStream;
} hipLaunchCooperativeKernel_spt;
struct
{
const void* function_address;
dim3 numBlocks;
dim3 dimBlocks;
void** args;
size_t sharedMemBytes;
hipStream_t stream;
} hipLaunchKernel_spt;
struct
{
hipGraphExec_t graphExec;
hipStream_t stream;
} hipGraphLaunch_spt;
struct
{
hipStream_t stream;
hipStreamCaptureMode mode;
} hipStreamBeginCapture_spt;
struct
{
hipStream_t stream;
hipGraph_t* pGraph;
} hipStreamEndCapture_spt;
struct
{
hipStream_t stream;
hipStreamCaptureStatus* pCaptureStatus;
} hipStreamIsCapturing_spt;
struct
{
hipStream_t stream;
hipStreamCaptureStatus* pCaptureStatus;
unsigned long long* pId;
} hipStreamGetCaptureInfo_spt;
struct
{
hipStream_t stream;
hipStreamCaptureStatus* captureStatus_out;
unsigned long long* id_out;
hipGraph_t* graph_out;
const hipGraphNode_t** dependencies_out;
size_t* numDependencies_out;
} hipStreamGetCaptureInfo_v2_spt;
struct
{
hipStream_t stream;
hipHostFn_t fn;
void* userData;
} hipLaunchHostFunc_spt;
struct
{
hipStream_t stream;
} hipGetStreamDeviceId;
// struct
// {
// hipGraphNode_t* phGraphNode;
// hipGraph_t hGraph;
// const hipGraphNode_t* dependencies;
// size_t numDependencies;
// const HIP_MEMSET_NODE_PARAMS* memsetParams;
// hipCtx_t ctx;
// } hipDrvGraphAddMemsetNode;
} rocprofiler_hip_api_args_t;