- Fixes -0.0 and +0.0 comparison. For atomicMax if the value on
address is -0.0 and on val is +0.0, gfx90a's unsafe atomics will swap
them. This behavior should be consistent with cas loop as well.
- _system variants of atomicMax and atomicMin are resulting in
incorrect output. Updated these to use the similar implementation as
atomicMax and atomicMin.
Change-Id: I20df36ee29ae0434a6b564f2ba71193fe41cfa59
[ROCm/clr commit: d69cc35750]
- Fixes -0.0 and +0.0 comparison. For atomicMax if the value on
address is -0.0 and on val is +0.0, gfx90a's unsafe atomics will swap
them. This behavior should be consistent with cas loop as well.
- _system variants of atomicMax and atomicMin are resulting in
incorrect output. Updated these to use the similar implementation as
atomicMax and atomicMin.
Change-Id: I20df36ee29ae0434a6b564f2ba71193fe41cfa59
This fixes issues like:
1.
/run/lock/rdcd.lock: Bad file descriptor
Failed to determine owner of lock file.: Numerical result out of range
2.
rdc.service: Failed to determine group credentials: No such process
rdc.service: Failed at step GROUP spawning rdcd: No such process
Change-Id: I0ef5eb6ab72d036a3ea8dcb81f7a9108d279f7d6
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
This fixes issues like:
1.
/run/lock/rdcd.lock: Bad file descriptor
Failed to determine owner of lock file.: Numerical result out of range
2.
rdc.service: Failed to determine group credentials: No such process
rdc.service: Failed at step GROUP spawning rdcd: No such process
Change-Id: I0ef5eb6ab72d036a3ea8dcb81f7a9108d279f7d6
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
[ROCm/rdc commit: c015f0fcaa]
Previously we relied on "render" to be enough and only used "video" as a
fallback. On some systems like SLES this might not be sufficient.
One issue happened when starting rocprofiler as part of RDC
initialization:
what(): hsa error code: 4104 HSA_STATUS_ERROR_OUT_OF_RESOURCES
The issue only happened when RDC was started with systemd.
Turns out "rdc" user (under which systemctl starts RDC) only had render
but not video group. Adding video group solved the issue.
Change-Id: Idf6a9521ae72a0b28a428869aa7ab1edde3ae259
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
Previously we relied on "render" to be enough and only used "video" as a
fallback. On some systems like SLES this might not be sufficient.
One issue happened when starting rocprofiler as part of RDC
initialization:
what(): hsa error code: 4104 HSA_STATUS_ERROR_OUT_OF_RESOURCES
The issue only happened when RDC was started with systemd.
Turns out "rdc" user (under which systemctl starts RDC) only had render
but not video group. Adding video group solved the issue.
Change-Id: Idf6a9521ae72a0b28a428869aa7ab1edde3ae259
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
[ROCm/rdc commit: 4ebc34095c]
rocprofv2 does not support the "kernel:" attribute in
input files. This commit adds support for this attribute
for cli/csv output. This is requested by Alibaba/Omniperf
to have compatible execution with both v1/v2 (JSON and CTF
are not supported here and not needed).
Filtering can also be enabled by the flag ROCPROFILER_KERNEL_FILTER.
Change-Id: I376382d9e5b10a8356df8d175b1a56396b5b51d3
rocprofv2 does not support the "kernel:" attribute in
input files. This commit adds support for this attribute
for cli/csv output. This is requested by Alibaba/Omniperf
to have compatible execution with both v1/v2 (JSON and CTF
are not supported here and not needed).
Filtering can also be enabled by the flag ROCPROFILER_KERNEL_FILTER.
Change-Id: I376382d9e5b10a8356df8d175b1a56396b5b51d3
[ROCm/rocprofiler commit: b32eb2bda9]
Compiler has changed to match the device side struct layout with
the host side and hence the test is updated to verify if struct sizes
of both host and device are equal instead of checking for hardcoded
struct sizes
Change-Id: Idd9ea1f04b413b7aa30f03555fd8e0ee11cd0f75
[ROCm/hip-tests commit: 5f1dfc3851]
Compiler has changed to match the device side struct layout with
the host side and hence the test is updated to verify if struct sizes
of both host and device are equal instead of checking for hardcoded
struct sizes
Change-Id: Idd9ea1f04b413b7aa30f03555fd8e0ee11cd0f75
Current DMABUF implemenation is unstable. Switch back to legacy
support for now.
Change-Id: I3be871f38c6524b0bcc9225bab61de4e57771efb
[ROCm/ROCR-Runtime commit: ea646cf958]
When configuring the otf2 dependency, CFLAGS, CXXFLAGS, CC and CXX are
explicitly specified, but LDFLAGS is not. As a consequence, LDFLAGS is
picked up from the environment (if set). In some build configurations,
the LDFLAG from the environment is not compatible with the rest of the
compiler/linker configuration options specified in CMakeLists.txt,
resulting in the configure script failing.
This patch make sure to specify an empty LDFLAGS when configuring otf2
build to avoid such issues.
Bug: SWDEV-477693
[ROCm/rocprofiler-sdk commit: 9f3cffc39a]
When configuring the otf2 dependency, CFLAGS, CXXFLAGS, CC and CXX are
explicitly specified, but LDFLAGS is not. As a consequence, LDFLAGS is
picked up from the environment (if set). In some build configurations,
the LDFLAG from the environment is not compatible with the rest of the
compiler/linker configuration options specified in CMakeLists.txt,
resulting in the configure script failing.
This patch make sure to specify an empty LDFLAGS when configuring otf2
build to avoid such issues.
Bug: SWDEV-477693
* remove leftover css
Signed-off-by: Peter Jun Park <peter.park@amd.com>
* fix link to panel_config_template.yaml
Signed-off-by: Peter Jun Park <peter.park@amd.com>
* add note in archived docs pointing to latest
Signed-off-by: Peter Jun Park <peter.park@amd.com>
rm repetition
---------
Signed-off-by: Peter Jun Park <peter.park@amd.com>
[ROCm/rocprofiler-compute commit: e8fc341345]
* remove leftover css
Signed-off-by: Peter Jun Park <peter.park@amd.com>
* fix link to panel_config_template.yaml
Signed-off-by: Peter Jun Park <peter.park@amd.com>
* add note in archived docs pointing to latest
Signed-off-by: Peter Jun Park <peter.park@amd.com>
rm repetition
---------
Signed-off-by: Peter Jun Park <peter.park@amd.com>
* Add `amd-staging` and `amd-mainline` to workflow.
* Update branch names in documentation
* Change `dev` to `amd-staging` and `main` to `amd-mainline` in documentation.
* Remove references from 2.x from workflows.
* Convert the link to LICENSE to a relative path in CONTRIBUTING.
---------
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-compute commit: e176d8eec8]
* Add `amd-staging` and `amd-mainline` to workflow.
* Update branch names in documentation
* Change `dev` to `amd-staging` and `main` to `amd-mainline` in documentation.
* Remove references from 2.x from workflows.
* Convert the link to LICENSE to a relative path in CONTRIBUTING.
---------
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
amd-jmacaran
Satyanvesh Dittakavi
Rakesh Roy
gobhardw
Galantsev, Dmitrii
SrirakshaNag
Marko Arandjelovic
Saleel Kudchadker
Benjamin Welton
Jonathan Kim
Branislav Brzak
Ajay
lancesix
Jeffrey Novotny
xuchen-amd
benrichard-amd
Peter Park
David Galiffi