76333 Commity
Autor SHA1 Wiadomość Data
jujiang ba2cd19726 SWDEV-242207-Update deprecated APIs
Change-Id: I0c1c7f33f75232b210495241d0e5e7e6b90d45f0
2020-07-08 15:23:52 -04:00
Wenkai Du 47dfed5f01 Revert "Split primitive class to smaller structures" (#230)
This reverts commit 622b49e80a.

[ROCm/rccl commit: 5215130168]
2020-07-08 11:06:50 -07:00
Wenkai Du 5215130168 Revert "Split primitive class to smaller structures" (#230)
This reverts commit 486fd436af.
2020-07-08 11:06:50 -07:00
jujiang da470ad95f SWDEV-241903-Add document HIP_logging.md
Change-Id: I348218218b305e845b7e26afaeb4e287bf0387de


[ROCm/clr commit: e73e0d2fb3]
2020-07-08 11:19:33 -04:00
jujiang e73e0d2fb3 SWDEV-241903-Add document HIP_logging.md
Change-Id: I348218218b305e845b7e26afaeb4e287bf0387de
2020-07-08 11:19:33 -04:00
jujiang cdb345a3f9 SWDEV-241903-Add document HIP_logging.md
Change-Id: I348218218b305e845b7e26afaeb4e287bf0387de


[ROCm/hip commit: f9f0580829]
2020-07-08 11:19:33 -04:00
jujiang f9f0580829 SWDEV-241903-Add document HIP_logging.md
Change-Id: I348218218b305e845b7e26afaeb4e287bf0387de
2020-07-08 11:19:33 -04:00
Chris Freehill 001aa0b825 Fix docs + cmake_utils path issues
This corrects issues that arose after OAM reorganization.
It should address SWDEV-243294.

Also, fix some compile warnings that show up on RHEL.

Change-Id: Id14d444905da35cd7346bcfbcd82b6d0572708c4


[ROCm/rocm_smi_lib commit: c2ef9a6879]
2020-07-08 09:47:25 -05:00
Chris Freehill c2ef9a6879 Fix docs + cmake_utils path issues
This corrects issues that arose after OAM reorganization.
It should address SWDEV-243294.

Also, fix some compile warnings that show up on RHEL.

Change-Id: Id14d444905da35cd7346bcfbcd82b6d0572708c4
2020-07-08 09:47:25 -05:00
Chris Freehill ca36d70cee Fix docs + cmake_utils path issues
This corrects issues that arose after OAM reorganization.
It should address SWDEV-243294.

Also, fix some compile warnings that show up on RHEL.

Change-Id: Id14d444905da35cd7346bcfbcd82b6d0572708c4


[ROCm/amdsmi commit: c2ef9a6879]
2020-07-08 09:47:25 -05:00
Chauncey Hui 153229ec2a SWDEV-2 - Change OpenCL version number from 3172 to 3173
[ROCm/clr commit: 1b69c85913]
2020-07-08 03:00:03 -04:00
Chauncey Hui 1b69c85913 SWDEV-2 - Change OpenCL version number from 3172 to 3173 2020-07-08 03:00:03 -04:00
Rahul Garg 6d8419f433 Bump version to 3.7
Change-Id: Id077c317573e95833c8bc7f16951df776de2a273


[ROCm/clr commit: 27002fd792]
2020-07-08 01:54:05 -04:00
Rahul Garg 27002fd792 Bump version to 3.7
Change-Id: Id077c317573e95833c8bc7f16951df776de2a273
2020-07-08 01:54:05 -04:00
Rahul Garg 63b52034a3 Bump version to 3.7
Change-Id: Id077c317573e95833c8bc7f16951df776de2a273


[ROCm/hip commit: 6a277dea45]
2020-07-08 01:54:05 -04:00
Rahul Garg 6a277dea45 Bump version to 3.7
Change-Id: Id077c317573e95833c8bc7f16951df776de2a273
2020-07-08 01:54:05 -04:00
Jatin Chaudhary 260a83c546 Replacing deprecated HSA API calls with newer ones
Change-Id: Iebe2c00e717ab0e47c61611752b717966c719994


[ROCm/clr commit: cd1e364911]
2020-07-08 00:32:24 -04:00
Jatin Chaudhary cd1e364911 Replacing deprecated HSA API calls with newer ones
Change-Id: Iebe2c00e717ab0e47c61611752b717966c719994
2020-07-08 00:32:24 -04:00
Yong Zhao 76a6781c2d kfdtest: Add gfx1030 support
Change-Id: I5fd0d9af09cbefc0acbe24397a7e2f3aa14a7c97
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
2020-07-07 18:09:56 -04:00
Yong Zhao 69159934ae kfdtest: Add gfx1030 support
Change-Id: I5fd0d9af09cbefc0acbe24397a7e2f3aa14a7c97
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>


[ROCm/ROCR-Runtime commit: 76a6781c2d]
2020-07-07 18:09:56 -04:00
Yong Zhao 58ca2b745c libhsakmt: Support gfx90a
Change-Id: I1ad594eab093f5aa30143ade4e72f2379c9e3616
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
2020-07-07 15:55:28 -05:00
Yong Zhao 9f0c092c5d libhsakmt: Support gfx90a
Change-Id: I1ad594eab093f5aa30143ade4e72f2379c9e3616
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>


[ROCm/ROCR-Runtime commit: 58ca2b745c]
2020-07-07 15:55:28 -05:00
Sean Keely f6e6eae86d Remove unnecessary HSA_API declarations.
The excess declarations mark implemenation functions as default
visibility.  Normally this is not an issue since our linker script
will specify which visible symbols will be permitted into the dynamic
symbol table.  However, for static linking methods which apply linker
directives during incremental linking symbol visibility must be correct
in the (non-dynamic) symbol table.

Change-Id: I13dc8dd1019368e8943920d36335a91f0c555a92
2020-07-07 16:41:34 -04:00
Sean Keely 8f366634af Remove unnecessary HSA_API declarations.
The excess declarations mark implemenation functions as default
visibility.  Normally this is not an issue since our linker script
will specify which visible symbols will be permitted into the dynamic
symbol table.  However, for static linking methods which apply linker
directives during incremental linking symbol visibility must be correct
in the (non-dynamic) symbol table.

Change-Id: I13dc8dd1019368e8943920d36335a91f0c555a92


[ROCm/ROCR-Runtime commit: f6e6eae86d]
2020-07-07 16:41:34 -04:00
Wenkai Du 4a3b58ac3a Match RCCL package name to API version (#229)
[ROCm/rccl commit: 1addf4f196]
2020-07-07 13:30:39 -07:00
Wenkai Du 1addf4f196 Match RCCL package name to API version (#229) 2020-07-07 13:30:39 -07:00
Aryan Salmanpour 8d083a3c61 Always print error message with the returned error code before abort
Change-Id: I8479abc586937a50c90b2785c4ce7364e6e9732b


[ROCm/clr commit: 4a901f3dd3]
2020-07-07 16:28:30 -04:00
Aryan Salmanpour 4a901f3dd3 Always print error message with the returned error code before abort
Change-Id: I8479abc586937a50c90b2785c4ce7364e6e9732b
2020-07-07 16:28:30 -04:00
Aryan Salmanpour c69f88fe04 add an error message before aborting if a wrong GPU target was used for compilation
Change-Id: I7b41e93d420dbc47978238a681f2956a0def01cb


[ROCm/clr commit: 8f862becd0]
2020-07-07 14:50:44 -04:00
Aryan Salmanpour 8f862becd0 add an error message before aborting if a wrong GPU target was used for compilation
Change-Id: I7b41e93d420dbc47978238a681f2956a0def01cb
2020-07-07 14:50:44 -04:00
Aryan Salmanpour 7a2961fc57 add an error message before aborting if a wrong GPU target was used for compilation
Change-Id: I7b41e93d420dbc47978238a681f2956a0def01cb


[ROCm/hip commit: 9121a74ac1]
2020-07-07 14:50:44 -04:00
Aryan Salmanpour 9121a74ac1 add an error message before aborting if a wrong GPU target was used for compilation
Change-Id: I7b41e93d420dbc47978238a681f2956a0def01cb
2020-07-07 14:50:44 -04:00
Riatre Foo e791f8c8c7 Fix build action order
Add $(INCTARGETS) to build dependencies of %.o and $(DEVICELIB).
As there were no dep files during the first build, Make may kick off source
compilation before nccl.h got generated, which leads to occasional build
failures on systems with high core count. The build failure could be
reproduced reliably with a `sleep 5` in $(INCDIR)/nccl.h rule.


[ROCm/rccl commit: 2d8601701d]
2020-07-07 10:20:51 -07:00
Riatre Foo 2d8601701d Fix build action order
Add $(INCTARGETS) to build dependencies of %.o and $(DEVICELIB).
As there were no dep files during the first build, Make may kick off source
compilation before nccl.h got generated, which leads to occasional build
failures on systems with high core count. The build failure could be
reproduced reliably with a `sleep 5` in $(INCDIR)/nccl.h rule.
2020-07-07 10:20:51 -07:00
Yong Zhao 7c74069d6a libhsakmt: Prepare for gfx1030 support
PCI IDs have yet to be added later.

Change-Id: Iac303fc1346f4ed5c4da5300b1e311c1c6938ee2
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
2020-07-07 11:07:14 -04:00
Yong Zhao 430c7be7e0 libhsakmt: Prepare for gfx1030 support
PCI IDs have yet to be added later.

Change-Id: Iac303fc1346f4ed5c4da5300b1e311c1c6938ee2
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>


[ROCm/ROCR-Runtime commit: 7c74069d6a]
2020-07-07 11:07:14 -04:00
Chauncey Hui bf3fd89566 SWDEV-2 - Change OpenCL version number from 3171 to 3172
[ROCm/clr commit: 5c2e64a43c]
2020-07-07 03:00:03 -04:00
Chauncey Hui 5c2e64a43c SWDEV-2 - Change OpenCL version number from 3171 to 3172 2020-07-07 03:00:03 -04:00
Rachida Kebichi 37231cd00d Fix for ptr type unknown
Change-Id: I17674c689e7051b79d15cc4cae9676c86a8c46ae
2020-07-07 01:16:16 -04:00
Rachida Kebichi e6ab54a04c Fix for ptr type unknown
Change-Id: I17674c689e7051b79d15cc4cae9676c86a8c46ae


[ROCm/rocprofiler commit: 37231cd00d]
2020-07-07 01:16:16 -04:00
Lakhan singh Thakur 4bf371401d [dtest] Enhancing hipStreamAddCallback() api test
-Scenario-1:: This test case is used to verify if the callback function
              called through  hipStreamAddCallback() api completes the
	      execution in order as hipStreamAddCallback() api queued
	      in their respective streams: hipStreamACb_AltEnqueue.cpp
-Scenario-2:: This test case tests if Host thread continues with next
              command after hipStreamAddCallback() api or wait for
	      callback() call to finish. Ideally Host thread should not
              wait for callback to
              finish: hipStreamACb_ThrdBehaviour.cpp
-Scenario-3:: Streams are launched in individual GPUs with different
              kernel Verify that all the kernels queued are executed
	      before the callback is hit: hipStreamACb_MStrm_Mgpu.cpp
-Scenario-4:: Checks the callback execution in the same order it was
              added. Also, it checks if the number of callbacks
	      executed are same as the number of callbacks added:
	      hipStreamACb_order.cpp
-Scenario-5:: This test case checks whether hipStreamSynchronize() is
              taking less time than the time taken by Callback()
	      function launched by hipStreamAddCallback() api :
	      hipStreamACb_StrmSyncTiming.cpp
-Scenario-6:: This test case is used to check if the runtime is ok when
              hipStreamAddCallback() is called back to back multiple
	      calls: hipStreamACb_MultiCalls.cpp
-Scenario-7:: This test case is used to check the behaviour of HIP when
              multiple hipStreaAddCallback() are called over multiple
	      Threads:hipStreamACb_MultiThread.cpp
              (Currently disabled)

SWDEV-238517 for enhancing hip unit tests

Change-Id: I9c7b7df6766c728b2b201df18726b9fbdd434c06


[ROCm/clr commit: 18f8b15523]
2020-07-07 00:43:32 -04:00
Lakhan singh Thakur 18f8b15523 [dtest] Enhancing hipStreamAddCallback() api test
-Scenario-1:: This test case is used to verify if the callback function
              called through  hipStreamAddCallback() api completes the
	      execution in order as hipStreamAddCallback() api queued
	      in their respective streams: hipStreamACb_AltEnqueue.cpp
-Scenario-2:: This test case tests if Host thread continues with next
              command after hipStreamAddCallback() api or wait for
	      callback() call to finish. Ideally Host thread should not
              wait for callback to
              finish: hipStreamACb_ThrdBehaviour.cpp
-Scenario-3:: Streams are launched in individual GPUs with different
              kernel Verify that all the kernels queued are executed
	      before the callback is hit: hipStreamACb_MStrm_Mgpu.cpp
-Scenario-4:: Checks the callback execution in the same order it was
              added. Also, it checks if the number of callbacks
	      executed are same as the number of callbacks added:
	      hipStreamACb_order.cpp
-Scenario-5:: This test case checks whether hipStreamSynchronize() is
              taking less time than the time taken by Callback()
	      function launched by hipStreamAddCallback() api :
	      hipStreamACb_StrmSyncTiming.cpp
-Scenario-6:: This test case is used to check if the runtime is ok when
              hipStreamAddCallback() is called back to back multiple
	      calls: hipStreamACb_MultiCalls.cpp
-Scenario-7:: This test case is used to check the behaviour of HIP when
              multiple hipStreaAddCallback() are called over multiple
	      Threads:hipStreamACb_MultiThread.cpp
              (Currently disabled)

SWDEV-238517 for enhancing hip unit tests

Change-Id: I9c7b7df6766c728b2b201df18726b9fbdd434c06
2020-07-07 00:43:32 -04:00
Lakhan singh Thakur 2ac9c18acf [dtest] Enhancing hipStreamAddCallback() api test
-Scenario-1:: This test case is used to verify if the callback function
              called through  hipStreamAddCallback() api completes the
	      execution in order as hipStreamAddCallback() api queued
	      in their respective streams: hipStreamACb_AltEnqueue.cpp
-Scenario-2:: This test case tests if Host thread continues with next
              command after hipStreamAddCallback() api or wait for
	      callback() call to finish. Ideally Host thread should not
              wait for callback to
              finish: hipStreamACb_ThrdBehaviour.cpp
-Scenario-3:: Streams are launched in individual GPUs with different
              kernel Verify that all the kernels queued are executed
	      before the callback is hit: hipStreamACb_MStrm_Mgpu.cpp
-Scenario-4:: Checks the callback execution in the same order it was
              added. Also, it checks if the number of callbacks
	      executed are same as the number of callbacks added:
	      hipStreamACb_order.cpp
-Scenario-5:: This test case checks whether hipStreamSynchronize() is
              taking less time than the time taken by Callback()
	      function launched by hipStreamAddCallback() api :
	      hipStreamACb_StrmSyncTiming.cpp
-Scenario-6:: This test case is used to check if the runtime is ok when
              hipStreamAddCallback() is called back to back multiple
	      calls: hipStreamACb_MultiCalls.cpp
-Scenario-7:: This test case is used to check the behaviour of HIP when
              multiple hipStreaAddCallback() are called over multiple
	      Threads:hipStreamACb_MultiThread.cpp
              (Currently disabled)

SWDEV-238517 for enhancing hip unit tests

Change-Id: I9c7b7df6766c728b2b201df18726b9fbdd434c06


[ROCm/hip commit: d613d1d58b]
2020-07-07 00:43:32 -04:00
Lakhan singh Thakur d613d1d58b [dtest] Enhancing hipStreamAddCallback() api test
-Scenario-1:: This test case is used to verify if the callback function
              called through  hipStreamAddCallback() api completes the
	      execution in order as hipStreamAddCallback() api queued
	      in their respective streams: hipStreamACb_AltEnqueue.cpp
-Scenario-2:: This test case tests if Host thread continues with next
              command after hipStreamAddCallback() api or wait for
	      callback() call to finish. Ideally Host thread should not
              wait for callback to
              finish: hipStreamACb_ThrdBehaviour.cpp
-Scenario-3:: Streams are launched in individual GPUs with different
              kernel Verify that all the kernels queued are executed
	      before the callback is hit: hipStreamACb_MStrm_Mgpu.cpp
-Scenario-4:: Checks the callback execution in the same order it was
              added. Also, it checks if the number of callbacks
	      executed are same as the number of callbacks added:
	      hipStreamACb_order.cpp
-Scenario-5:: This test case checks whether hipStreamSynchronize() is
              taking less time than the time taken by Callback()
	      function launched by hipStreamAddCallback() api :
	      hipStreamACb_StrmSyncTiming.cpp
-Scenario-6:: This test case is used to check if the runtime is ok when
              hipStreamAddCallback() is called back to back multiple
	      calls: hipStreamACb_MultiCalls.cpp
-Scenario-7:: This test case is used to check the behaviour of HIP when
              multiple hipStreaAddCallback() are called over multiple
	      Threads:hipStreamACb_MultiThread.cpp
              (Currently disabled)

SWDEV-238517 for enhancing hip unit tests

Change-Id: I9c7b7df6766c728b2b201df18726b9fbdd434c06
2020-07-07 00:43:32 -04:00
Wenkai Du 99d8ddc145 Change scatter and gather bandwidth calculation to match alltoall (#7)
[ROCm/rccl-tests commit: 346cb16442]
2020-07-06 17:12:50 -07:00
Wenkai Du 346cb16442 Change scatter and gather bandwidth calculation to match alltoall (#7) 2020-07-06 17:12:50 -07:00
Tao Sang 7591ff8172 Fix static lib crash by setting top init_priority
Set top init_priority on affecting global variables so that
they will be created firstly and destroyed lastly.

Change-Id: Ied59fbecab66ba8195c4a7a02b6bef9fa2fad3af


[ROCm/clr commit: f7bf882981]
2020-07-06 16:54:10 -04:00
Tao Sang f7bf882981 Fix static lib crash by setting top init_priority
Set top init_priority on affecting global variables so that
they will be created firstly and destroyed lastly.

Change-Id: Ied59fbecab66ba8195c4a7a02b6bef9fa2fad3af
2020-07-06 16:54:10 -04:00
Vlad Sytchenko 0611a0502a Add ability to run each ocltst test individually
Now one can run a single test by invoking `make test.ocltst.${module_name}.${test_name}`. Invoking `make test.ocltst.${module_name}` will still run all of the modules tests.

Change-Id: I31b384576cb09800e580e41c12528a276899b6c2
Signed-off-by: Vlad Sytchenko <Vladislav.Sytchenko@amd.com>


[ROCm/clr commit: 3be244fb34]
2020-07-06 15:56:46 -04:00
Vlad Sytchenko 3be244fb34 Add ability to run each ocltst test individually
Now one can run a single test by invoking `make test.ocltst.${module_name}.${test_name}`. Invoking `make test.ocltst.${module_name}` will still run all of the modules tests.

Change-Id: I31b384576cb09800e580e41c12528a276899b6c2
Signed-off-by: Vlad Sytchenko <Vladislav.Sytchenko@amd.com>
2020-07-06 15:56:46 -04:00