1c68c74bb7
SWDEV-349226 - Add the hipDataTypes mapping to cudaDataTypes
...
Change-Id: Iadeb2675adf314c02dcc5d722581678ec36f8632
2022-10-14 06:44:30 -04:00
1b902e1809
SWDEV-355727 - Change in AMDGCN format in bitcode.
...
Change-Id: Ic32a3e7b866b35a321d8ececc2f6c63f9b23121d
2022-10-13 14:19:03 -04:00
da88091ba4
SWDEV-359548 - Enqueue marker if fence is dirty
...
The marker would flush any caches.
Change-Id: I5f990285fb3c3a3e8d5d0b2a2d5a9f1fdcea435c
2022-10-13 07:53:01 -04:00
039e26ee0f
SWDEV-357759, SWDEV-360041, SWDEV-361145 Fix Stream end capture on forked streams
...
Change-Id: If0dc6242d2d3ca680e37e14a5dea5cf68dc295df
2022-10-12 13:00:05 -04:00
56e7c8b3a0
SWDEV-318349 - Remove sync for null stream
...
Remove sync for null stream in hipGraphExec::Run()
Change-Id: Ieaaed1c15b4d258193d8341d4b17d9f03a9e4783
2022-10-12 09:46:18 -04:00
88c399a43d
SWDEV-356570, SWDEV-356571, SWDEV-356572, SWDEV-356575 -
...
updating with current status of hipNotSupported and null checks
Change-Id: I3b1ce3d3e5ce9b69d1f5dacda35f5aa586714f5c
2022-10-11 23:45:27 -04:00
be80bf5406
SWDEV-353548 - assert with different behavior for Release vs Debug
...
assert statement behavior
-Debug: crashes tests with SIGABORT
-Release: continues silently without
Change-Id: I7578eb16a7391ff7f9d68f1cae3bcea7f8225579
2022-10-11 14:00:28 -04:00
7ef4eada54
SWDEV-356551 - Add support for device attributes.
...
Change-Id: Ic0f2b9cb510b027e0b8d1b3fb6d984e0d2600b15
2022-10-11 12:06:44 -04:00
0d67bd3f09
SWDEV-360001 - Add hipLaunchHostFunc in Nvidia path
...
Change-Id: I5c733b416642174a089a86c420b03e8775e206d6
2022-10-11 06:18:52 -04:00
0a3e89c0cb
SWDEV-356314 - Init managed vars on device kernel is launched
...
Change-Id: I9c30b7d0e2a490dbb2bd9c02dccaae17d76874ef
2022-10-11 00:18:30 -04:00
c3a340c21b
Fix a build error when compiling with clang
...
Fix the following error:
hip_intercept.cpp:52:7: error: reinterpret_cast from 'const void *' to 'decltype(activity_prof::report_activity.load())' (aka 'int (*)(activity_domain_t, unsigned int, void *)') casts away qualifiers
reinterpret_cast<decltype(activity_prof::report_activity.load())>(function),
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
by replacing the 'const void *function' argument with the correct type.
Change-Id: I859d45ee01b7aaa1e46563cdc37de57b4159d330
2022-10-10 12:30:36 -04:00
8b391ef18c
SWDEV-351969 - TLS Optimization
...
- Aggregate all TLS(Thread Local Storage) variables into a single class
- This is to improve cache accesses per thread
Change-Id: Ic8361eaeae290fff00254684e309471958365eb9
2022-10-09 22:08:14 -04:00
f83ba8cd23
SWDEV-318349 - Fix hipGraphKernelNode and hipGraphMemcpyNode
...
For hipGraphKernelNode, remove func_;
and reorganize functions to naturely support mGPU;
For hipGraphMemcpyNode, make EnqueueCommands() support different
queues' sync
Change-Id: I22708923f454adf4456ff99d25559daffed8c20d
2022-10-07 09:07:56 -04:00
aeeab1c975
SWDEV-357246 - Fixes to return with a error code instead of segfault in alloc failure case
...
Change-Id: Ie18d50f2f7ef3f4b2c0153152fca057232c1f8a2
2022-10-04 09:38:42 -04:00
47a29c748a
SWDEV-359838 - Add a phase data pointer to the hip_api_data_t
...
To avoid using the thread local std::stack to remember the phase enter
timestamp, the tracer tool uses the phase data to store the timestamp.
Change-Id: I9e95637b41d6f0b2bd61016062ca07d6ba897652
2022-09-30 14:55:01 -07:00
b425e27230
SWDEV-357250 - hiprtc support with AMD_LOG_LEVEL when linked as separate library
...
Change-Id: Ieda83af85a9344b4e09d4fe85acc65386db79c39
2022-09-23 05:50:07 -04:00
ab89a70f5d
SWDEV-356651 - Merge hipJit options between hiprtc and hip runtime.
...
Change-Id: I73b66eaf081ce63b6b7ce45f71880877953cf81c
2022-09-22 12:53:58 -04:00
835b7578dc
Revert "SWDEV-351980 - Update hip_prof_str.h"
...
This reverts commit f296e42803
2022-09-21 13:04:38 -04:00
d870bdb9b1
SWDEV-355727 - Added more rules to target ID comparison in hiprtc.
...
Change-Id: I56137375c3eb47dd604c7a02bb88f7e3dbe6c04d
2022-09-21 12:18:13 -04:00
f296e42803
SWDEV-351980 - Update hip_prof_str.h
...
Change-Id: Ied27c137aff54e69dc14129e6daad9196479edf9
2022-09-21 11:38:59 +00:00
0b1ea7e075
SWDEV-351980 - Remove the ROCtracer private interface from the public header
...
Change-Id: I51d45cca5051f04d3c1b59ca2a9cf1db5fd1ebd4
2022-09-21 02:41:47 -04:00
82bce811ee
SWDEV-351980 - Consolidate registration tables in the roctracer library
...
Remove the api_callbacks_table_t that was holding the API activities and
user callbacks. Instead use a single roctracer callback (TracerCallback)
used to report both API activities and callbacks.
Remove the hipInitActivityCallback that was setting the ROCtracer
callback and memory pool for asynchronous activities as it did not
allow disctinct pools to be used for each activity. Instead, use
hipRegisterTracerCallback to set the single roctracer callback.
Change-Id: I4c10f04f29a6e4cce8caf15db3016c3f72c86b04
2022-09-21 02:41:39 -04:00
eeddffc1b1
SWDEV-351980 - Remove IS_PROFILER_ON
...
The CallbacksTable::is_enabled() can simply be implemented by checking
if enabled_api_count is > 0. The ROCclr does not use IS_PROFILER_ON
to report asynchronous activities.
Change-Id: Iab3d034357e51282bf2c453b2ac5c9726786b9eb
2022-09-21 02:41:29 -04:00
85fd969253
SWDEV-351980 - Move hip_api_data and record to the HIP function's stack
...
Since the hip_api_data and record are only needed at the HIP function's
scope, there is no need to allocate/free them in the ROCtracer activity
callback, they can reside on the HIP function's stack frame.
This solves an issue with the thread local stacks of records the tracer
maintains that are destroyed first (before any global destructor) on
process exit, making it impossible to use HIP functions in global
destructors when the profiler is enabled.
Change-Id: Ib1d70124d009a44dc1f08d41edff95e5f9f84369
2022-09-21 02:41:15 -04:00
42b5a6d5af
SWDEV-356554 - updated hipDeviceGetDefaultMemPool
...
updated the error check/messages
Change-Id: I518d497a82a14862d5168cc423aeaa20075336b8
2022-09-20 16:42:48 -04:00
f1d8a02122
SWDEV-356582 - set the parent node in Graph Clone
...
Change-Id: I9b685ca9827b0a0dddc3ef6a0394b298d1031f04
2022-09-20 16:42:29 -04:00
2801e4fe63
SWDEV-357334 - hipEventRecord_spt() to take optional stream arg
...
Change-Id: I19540c577e2c3635a00379f814350ada41020af2
2022-09-19 20:28:13 +00:00
df278887fe
SWDEV-301667 - Pass all params to API Init
...
- Correct return for ihipLaunchKernel
Change-Id: I66e81fa635473e6e728936e4cfba9f1bc7f018ad
2022-09-15 22:20:02 -07:00
1ee3a6d5c6
SWDEV-340649 - Removes a check to limit the size of allocation that was capped to the size of device memory available
...
Change-Id: Ia99264cc85a1e76293e4fad0734f544351c82809
2022-09-14 12:58:33 -04:00
8e10332ff1
Revert "SWDEV-339488 - Address HIPRT tests failure with spaces in the include path"
...
This reverts commit 89355fb586
2022-09-13 23:06:23 -04:00
39fc6605ec
SWDEV-351274 - add proper checks for set attribute
...
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I9243e6180f3040341396b7159622f2b96e143ac2
2022-09-09 10:49:33 -04:00
52a22a1263
SWDEV-350025 - Added hipLaunchHostFunc functionality
...
Change-Id: I6b9d547f7ddf84e617e35ff5d5a490ff458272ef
2022-09-07 17:53:26 +00:00
e5dff9a140
SWDEV-351054 - Move validation for w & h to hipMemAllocPitch.
...
Change-Id: Ia624fc99e797baf88dc029d7e36bb80df1bd7d12
2022-09-07 01:00:49 -04:00
3b530b5676
SWDEV-354138 - Fixed SPT functions linking issue
...
Change-Id: I738ccdfd6db8cfa8c29f93bb6061e83795df382b
2022-09-05 06:22:08 -04:00
b7716825c8
SWDEV-344342 - hiprtc-config-version.cmake should be generated in build directory
...
Change-Id: I7becaa64873c5e8ba95e814421c1f700a0997a8b
2022-09-05 00:05:18 -04:00
7f4c711ac1
SWDEV-354717 - Fix hipExtLaunchKernel as part of stream capture
...
Change-Id: Ic29d7403dfa38f01bec423aa1df7aa75c60a86e2
2022-09-01 19:26:14 +00:00
2b322a9087
SWDEV-354717 - Add support for hipExtLaunchKernel as part of stream capture
...
Change-Id: I22708923f454a0f4456ff99d25559daffe08c208
2022-09-01 05:02:20 +00:00
c72942964d
SWDEV-352951 - Add capture support for hipModuleLaunchKernel
...
Change-Id: Iced0846c9f753ecbb87e3f7aec2bfd72137d8c00
2022-08-31 22:15:02 -04:00
c833a19284
SWDEV-352582 - Updated warning message
...
Using wrapper header file will generate warning message during build time.
Updated the message content to make it more meaningful
Change-Id: I4e0c5e3d845946d9b493d98879ea8e75a92506ee
2022-08-31 11:58:26 -07:00
9f37acc55f
SWDEV-341326 - removing sigabrt for NoBinaryForGpu
...
Change-Id: Ia30fb3efec7f71b870e6a35d5ce51a4aa61fad28
2022-08-31 09:39:59 -04:00
1ea4d588ef
SWDEV-301667 - Pretty print logs
...
Change-Id: Ide95a5f8d35d81d4a9eb658f40ae2e82ffa3d97f
2022-08-30 12:32:11 -04:00
da47e7184e
SWDEV-353672 - add missing defines for cuda
...
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I8e2e0a3b8845d1920e6a40e3ed676c657ab90276
2022-08-29 08:59:23 -04:00
fd8647807d
SWDEV-325711: move the API under correct hip version
...
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: Ia4e1588da7d21b2cb617c374d846ce5e05b1f4f8
2022-08-26 15:59:30 -04:00
89355fb586
SWDEV-339488 - Address HIPRT tests failure with spaces in the include path
...
Change-Id: Ic9ed57e44fcfdf82a0d066483bc73e1d59c39e30
2022-08-26 06:47:56 -04:00
d9f002c36f
SWDEV-351055 - changed isParent() to checking directly for parent's pointer. image should not be released for test types in Unit_hipMallocArray_happy
...
Change-Id: I8e4fae8c9188ee68c392237cb824a790ad7c9563
2022-08-25 10:11:54 -04:00
ab112eaf1d
SWDEV-344342 - Expose hiprtc target via cmake config interface
...
Change-Id: I1f19c4792665b078c2799c0c3c9e2d5b28c906de
2022-08-25 00:29:23 -04:00
a10df01f81
SWDEV-352290 - correct params checks
...
- correct condition for flags
- remove check for num of dependency
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I6efd918e203b57c840d74ee0243f24b0c2c80e21
2022-08-24 14:09:51 -04:00
cf57f20407
SWDEV-351282 - Null check for desc.
...
Change-Id: I69d534b6f97442c69b66154476a2637e99c3df77
2022-08-24 13:04:56 -04:00
ce5103ac97
SWDEV-352290 - remove the static list for user obj
...
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com >
Change-Id: I8d7542ad5aacdda4e817c6aaed78c9cac4562efd
2022-08-24 12:01:41 -04:00
97741fe5d4
SWDEV-333471 - Remove HIP_FORCE_QUEUE_PROFILING
...
HIP_FORCE_QUEUE_PROFILING has been replaced by GPU_FORCE_QUEUE_PROFILING.
Change-Id: Ic8dec4407ef79c27094cb3954e48869075b4732f
2022-08-24 11:53:16 -04:00
Satyanvesh Dittakavi
kjayapra-amd
Saleel Kudchadker
Anusha GodavarthySurya
Tao Sang
pghafari
Ajay
Jaydeep Patel
Laurent Morichetti
Rakesh Roy
Sourabh Betigeri
Maneesh Gupta
sdashmiz
Sarbojit Sarkar
Ranjith Ramakrishnan
Jiabao Xie
Jason Tang