SWDEV-79445 - OCL generic changes and code clean-up
- Don't disable the trace if start occurred on a queue, which didn't generate a preparation. That should fix random timeouts and still keep trace commands in order.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.cpp#10 edit
[ROCm/clr commit: 697488de5b]
SWDEV-79445 - OCL generic changes and code clean-up
- Don't disable the trace if start occurred on a queue, which didn't generate a preparation. That should fix random timeouts and still keep trace commands in order.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.cpp#10 edit
[Reasons]
+ Simplify the support
+ Optimize compilation and code generation time
[Additionally]
+ Update minimum required version of cmake
+ Fix MSVC compile options force update
[ROCm/clr commit: 75972cb51d]
[Reasons]
+ Simplify the support
+ Optimize compilation and code generation time
[Additionally]
+ Update minimum required version of cmake
+ Fix MSVC compile options force update
[Reasons]
+ Simplify the support
+ Optimize compilation and code generation time
[Additionally]
+ Update minimum required version of cmake
+ Fix MSVC compile options force update
[ROCm/hip commit: 5d1255272b]
[Reasons]
+ Simplify the support
+ Optimize compilation and code generation time
[Additionally]
+ Update minimum required version of cmake
+ Fix MSVC compile options force update
SWDEV-79445 - OCL generic changes and code clean-up
- Remove detection of the global memory usage, based on the names of variables
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#82 edit
[ROCm/clr commit: 8a8f11369e]
SWDEV-79445 - OCL generic changes and code clean-up
- Remove detection of the global memory usage, based on the names of variables
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#82 edit
SWDEV-2 - Change OpenCL version number from 2762 to 2763.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2510 edit
[ROCm/clr commit: dacfc65a68]
SWDEV-2 - Change OpenCL version number from 2762 to 2763.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2510 edit
Debug agent requires handles to internal queues for single step debugging.
Added tools only API hsa_amd_runtime_queue_create_register for reporting.
hsa_amd_runtime_queue_create_register sets a callback which is invoked
when internal queues are created.
Change-Id: Ia5190ae724fadba686c15f25b2cd085350eeff0e
Debug agent requires handles to internal queues for single step debugging.
Added tools only API hsa_amd_runtime_queue_create_register for reporting.
hsa_amd_runtime_queue_create_register sets a callback which is invoked
when internal queues are created.
Change-Id: Ia5190ae724fadba686c15f25b2cd085350eeff0e
[ROCm/ROCR-Runtime commit: 757502ccd6]
Required for debug agent requires copy API and trap handler to be initalized
prior to loading. Existing tools do not make use of internal queue or scratch
memory intercept which is what PostToolsInit allows.
PostToolsInit() will be removed in a following cleanup change.
Change-Id: If43377843808e3eff0defd9204910a67a852902f
Required for debug agent requires copy API and trap handler to be initalized
prior to loading. Existing tools do not make use of internal queue or scratch
memory intercept which is what PostToolsInit allows.
PostToolsInit() will be removed in a following cleanup change.
Change-Id: If43377843808e3eff0defd9204910a67a852902f
[ROCm/ROCR-Runtime commit: 5975c465ad]
On gfx900+, the test sometimes timeout due to cp fw bug.
Blacklist it until we address the root cause and have a fix.
Change-Id: Iff600a6f6dbd86c56e034f530484205520bced32
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
On gfx900+, the test sometimes timeout due to cp fw bug.
Blacklist it until we address the root cause and have a fix.
Change-Id: Iff600a6f6dbd86c56e034f530484205520bced32
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
[ROCm/ROCR-Runtime commit: 7a13bb4d66]
We observe this test fails on gfx900+. Looks like the sdma packets are not
executed at all after we submit sometimes.
Run it with timeout 2s on gfx900.
[ RUN ] KFDQMTest.SdmaEventInterrupt
[----------] SDMACopyData FAIL! 1485262707170 VS 1485262747814
[----------] Event On Queue 1:0 Timeout, try to resubmit packets!
[----------] The timeout event is signaled!
[ ] Time Consumption (ns)
[ ] 1: 1859427148
[ ] 2: 680148
[ ] 3: 6370
[ ] 4: 5481
/home/pp/code/compute/libhsakmt/tests/kfdtest/src/KFDQMTest.cpp:1670: Failure
Value of: (ret)
Actual: 31
Expected: HSAKMT_STATUS_SUCCESS
Which is: 0
[----------] SDMACopyData FAIL! 1485367669958 VS 1485367750022
[----------] Event On Queue 2:1 Timeout, try to resubmit packets!
[----------] The timeout event is signaled!
[ ] Time Consumption (ns)
[ ] 1: 1881615148
[ ] 2: 673629
[ ] 3: 6074
[ ] 4: 5481
/home/pp/code/compute/libhsakmt/tests/kfdtest/src/KFDQMTest.cpp:1670: Failure
Value of: (ret)
Actual: 31
Expected: HSAKMT_STATUS_SUCCESS
Which is: 0
[----------] SDMACopyData FAIL! 1485427671250 VS 1485427751238
[----------] Event On Queue 2:1 Timeout, try to resubmit packets!
[----------] The timeout event is signaled!
[ ] Time Consumption (ns)
[ ] 1: 1881508777
[ ] 2: 741629
[ ] 3: 6074
[ ] 4: 5481
/home/pp/code/compute/libhsakmt/tests/kfdtest/src/KFDQMTest.cpp:1670: Failure
Value of: (ret)
Actual: 31
Expected: HSAKMT_STATUS_SUCCESS
Which is: 0
[ FAILED ] KFDQMTest.SdmaEventInterrupt (23675 ms)
Change-Id: I7c1b752537d89782570df20838bf976578614f75
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
We observe this test fails on gfx900+. Looks like the sdma packets are not
executed at all after we submit sometimes.
Run it with timeout 2s on gfx900.
[ RUN ] KFDQMTest.SdmaEventInterrupt
[----------] SDMACopyData FAIL! 1485262707170 VS 1485262747814
[----------] Event On Queue 1:0 Timeout, try to resubmit packets!
[----------] The timeout event is signaled!
[ ] Time Consumption (ns)
[ ] 1: 1859427148
[ ] 2: 680148
[ ] 3: 6370
[ ] 4: 5481
/home/pp/code/compute/libhsakmt/tests/kfdtest/src/KFDQMTest.cpp:1670: Failure
Value of: (ret)
Actual: 31
Expected: HSAKMT_STATUS_SUCCESS
Which is: 0
[----------] SDMACopyData FAIL! 1485367669958 VS 1485367750022
[----------] Event On Queue 2:1 Timeout, try to resubmit packets!
[----------] The timeout event is signaled!
[ ] Time Consumption (ns)
[ ] 1: 1881615148
[ ] 2: 673629
[ ] 3: 6074
[ ] 4: 5481
/home/pp/code/compute/libhsakmt/tests/kfdtest/src/KFDQMTest.cpp:1670: Failure
Value of: (ret)
Actual: 31
Expected: HSAKMT_STATUS_SUCCESS
Which is: 0
[----------] SDMACopyData FAIL! 1485427671250 VS 1485427751238
[----------] Event On Queue 2:1 Timeout, try to resubmit packets!
[----------] The timeout event is signaled!
[ ] Time Consumption (ns)
[ ] 1: 1881508777
[ ] 2: 741629
[ ] 3: 6074
[ ] 4: 5481
/home/pp/code/compute/libhsakmt/tests/kfdtest/src/KFDQMTest.cpp:1670: Failure
Value of: (ret)
Actual: 31
Expected: HSAKMT_STATUS_SUCCESS
Which is: 0
[ FAILED ] KFDQMTest.SdmaEventInterrupt (23675 ms)
Change-Id: I7c1b752537d89782570df20838bf976578614f75
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
[ROCm/ROCR-Runtime commit: ab4610cff7]
SWDEV-2 - Change OpenCL version number from 2761 to 2762.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2509 edit
[ROCm/clr commit: 0cad7593a1]
SWDEV-2 - Change OpenCL version number from 2761 to 2762.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2509 edit
When compiling with Early Finalization enabled in HCC,
the resulting .kernel section of the host object now may
contain more than one device code bundles. This is to
teach the HIP runtime to correctly extract all the
bundles from the .kernel section.
[ROCm/clr commit: f39873c584]
When compiling with Early Finalization enabled in HCC,
the resulting .kernel section of the host object now may
contain more than one device code bundles. This is to
teach the HIP runtime to correctly extract all the
bundles from the .kernel section.
When compiling with Early Finalization enabled in HCC,
the resulting .kernel section of the host object now may
contain more than one device code bundles. This is to
teach the HIP runtime to correctly extract all the
bundles from the .kernel section.
[ROCm/hip commit: 30ce25e627]
When compiling with Early Finalization enabled in HCC,
the resulting .kernel section of the host object now may
contain more than one device code bundles. This is to
teach the HIP runtime to correctly extract all the
bundles from the .kernel section.
SWDEV-2 - Change OpenCL version number from 2760 to 2761.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2508 edit
[ROCm/clr commit: eac5cfc736]
SWDEV-2 - Change OpenCL version number from 2760 to 2761.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2508 edit
SWDEV-145570 - [HIP] Track last used event and use last enqueued command in a stream rather than creating a new event
ReviewBoardURL = http://ocltc.amd.com/reviews/r/15996/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_context.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_event.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_stream.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.hpp#20 edit
[ROCm/clr commit: 8526ed9b96]
SWDEV-145570 - [HIP] Track last used event and use last enqueued command in a stream rather than creating a new event
ReviewBoardURL = http://ocltc.amd.com/reviews/r/15996/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_context.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_event.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_stream.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.hpp#20 edit
SWDEV-145570 - [HIP] Track last used event and use last enqueued command in a stream rather than creating a new event
ReviewBoardURL = http://ocltc.amd.com/reviews/r/15996/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_context.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_event.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_stream.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.hpp#20 edit
[ROCm/hip commit: 133447a412]
SWDEV-145570 - [HIP] Track last used event and use last enqueued command in a stream rather than creating a new event
ReviewBoardURL = http://ocltc.amd.com/reviews/r/15996/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_context.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_event.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_stream.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.hpp#20 edit
foreman
Evgeny Mankov
Evgeny Mankov
Evgeny
Yaxun Sam Liu
Sean Keely
xinhui pan
Jenkins
Maneesh Gupta
Siu Chi Chan