Move hidden heap creation to the kernel launch to make sure it's
allocated on the actual first usage.
Change-Id: I1b65a82fc06d9129ed45a69765bf14ea3d945b04
[ROCm/clr commit: 4975f69337]
Move hidden heap creation to the kernel launch to make sure it's
allocated on the actual first usage.
Change-Id: I1b65a82fc06d9129ed45a69765bf14ea3d945b04
The init version includes the amd_smi.h header, an example uses the
amd_smi, folder structure and CMake files.
Add the support to libdrm.
Change-Id: I779e55e4cf9491c61dc226a30d24e96be9bc6016
The init version includes the amd_smi.h header, an example uses the
amd_smi, folder structure and CMake files.
Add the support to libdrm.
Change-Id: I779e55e4cf9491c61dc226a30d24e96be9bc6016
[ROCm/amdsmi commit: 91ad08aa65]
Move StartLateDeviceInit() and FinishDeviceInit() calls in RGP
server to avoid a timeout
Change-Id: Ifd681859c7dc76259d7296aa8cc15305d563c9b2
[ROCm/clr commit: ecea224bcf]
* Fix the main library stop routine for timemory
- the main pop_timemory function was popping too many calls
- this primarily affected recursive calls
* Lengthen the timeout for the Configure CMake step
* Fix python tests
- new validate-timemory-json.py script
* Documentation update
- Call-counts in timemory output examples in documentation were affected by the changes
* Fix the per-thread metrics during finalization
- pthread_create_mutex starts/stops the per-thread data
- removed unintentional continue statement
* Docs tweaks
* Fix lap counter on per-thread metrics
[ROCm/rocprofiler-systems commit: a142b2029d]
* Fix the main library stop routine for timemory
- the main pop_timemory function was popping too many calls
- this primarily affected recursive calls
* Lengthen the timeout for the Configure CMake step
* Fix python tests
- new validate-timemory-json.py script
* Documentation update
- Call-counts in timemory output examples in documentation were affected by the changes
* Fix the per-thread metrics during finalization
- pthread_create_mutex starts/stops the per-thread data
- removed unintentional continue statement
* Docs tweaks
* Fix lap counter on per-thread metrics
This env variable sets the max VA alignment order size as
"PAGE_SIZE * 2^alignment order" during mapping. By default the order
size is set to 9(2MB).
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I01ae4e0963f4d21c7c367464e60f865bc58d7fac
This env variable sets the max VA alignment order size as
"PAGE_SIZE * 2^alignment order" during mapping. By default the order
size is set to 9(2MB).
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I01ae4e0963f4d21c7c367464e60f865bc58d7fac
[ROCm/ROCR-Runtime commit: 0e908f05bb]
This issue happens when we have slices that have overlapping
timestamp values (i.e. start_ts + dur = start_ts of next slice)
and the flow event references that shared timestamp value.
The google chrome parser sorts all the events
and just taking the most recent one.
Rocprof is outputting flow attachment points as start+dur;
the end ts of the slice that can overlap with the next slice
if no gap between them.
Solution proposal by Michael Steffen (Michael.Steffen@amd.com)
Change-Id: Ifcde142144033c9012b01a78c95f047384f972dd
This issue happens when we have slices that have overlapping
timestamp values (i.e. start_ts + dur = start_ts of next slice)
and the flow event references that shared timestamp value.
The google chrome parser sorts all the events
and just taking the most recent one.
Rocprof is outputting flow attachment points as start+dur;
the end ts of the slice that can overlap with the next slice
if no gap between them.
Solution proposal by Michael Steffen (Michael.Steffen@amd.com)
Change-Id: Ifcde142144033c9012b01a78c95f047384f972dd
[ROCm/rocprofiler commit: 93a79eb99a]
Add blacklist for tests on GFX11 that are under debug/not functional.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I32f375f29036a2fc1a54f2792b31ebc45f4d668b
Add blacklist for tests on GFX11 that are under debug/not functional.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I32f375f29036a2fc1a54f2792b31ebc45f4d668b
[ROCm/ROCR-Runtime commit: 852d29bca2]
There seems to be in an incompatibility between the python installation
used in the CI and pytest. Update pytest before running CI.
[ROCm/rccl-tests commit: 67544e2c34]
New API function to report available memory per GPU
Signed-off-by: Daniel Phillips <Daniel.Phillips@amd.com>
Change-Id: I63c1e4ca0020c657977ab3635947ab0ed0a81440
New API function to report available memory per GPU
Signed-off-by: Daniel Phillips <Daniel.Phillips@amd.com>
Change-Id: I63c1e4ca0020c657977ab3635947ab0ed0a81440
[ROCm/ROCR-Runtime commit: 6da6058d4a]
- Memcpy1D node type is not complying with cuda
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: If8113f5e699de0c62d98effc4580a2e0fee9a950
[ROCm/hipother commit: 9583567388]
- Memcpy1D node type is not complying with cuda
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: If8113f5e699de0c62d98effc4580a2e0fee9a950
[ROCm/clr commit: 13c875eaf0]
Saleel Kudchadker
Sourabh Betigeri
ROCm CI Service Account
haoyuan2
Jonathan R. Madsen
German Andryeyev
Bill(Shuzhou) Liu
Alex Sierra
Ammar ELWazir
Graham Sider
Edgar Gabriel
Edgar
Wenkai Du
Daniel Phillips
sdashmiz