The change is made temporarily for testing the ASAN jenkins build.
Need to revert this change after testing
Change-Id: Icbfcfec423170114becdc82696afcf54b6d79d48
[ROCm/rocm-core commit: 8ce1529027]
The change is made temporarily for testing the ASAN jenkins build.
Need to revert this change after testing
Change-Id: Icbfcfec423170114becdc82696afcf54b6d79d48
Updates:
* [rocm-smi] Provide a thread-safe logging feature
* [rocm-smi] Adding logrotation into install/upgrade/remove
scripts
* [rocm-smi] Updated cmake lists to include rocm_smi_logger
* [rocm-smi] Updated DEB/RPM install/remove logging file &
folder with all users having r/w privledges for
/var/log/rocm_smi_lib/ROCm-SMI-lib.log
* [rocm-smi] Added ability to do a glob search for multiple files
(globFileExists), assists doing file searches with * strings
* [rocm-smi] Added ability to log system details when RSMI_LOGGING
is turned on (getSystemDetails())
* [rocm-smi] Added logging to provide which ROCm API is being called
when RSMI_LOGGING is on
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added environment variable RSMI_LOGGING to control
when logging is enabled or disabled. By default, by not
setting this env. variable, logging is turned off. When
setting RSMI_LOGGING=<any value>, logging is enabled
which is placed in /var/log/rocm_smi_lib/ROCm-SMI-lib.log file.
Setting RSMI_LOGGING is allowed in both debug and release builds.
* [rocm-smi] Removed an initialize procedure which keeps
debug_inf_loop. Seems this feature is not being used.
Change-Id: I79b48387609c6233c6f05b04fb8bba66b68c2399
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: c3a095a180]
Updates:
* [rocm-smi] Provide a thread-safe logging feature
* [rocm-smi] Adding logrotation into install/upgrade/remove
scripts
* [rocm-smi] Updated cmake lists to include rocm_smi_logger
* [rocm-smi] Updated DEB/RPM install/remove logging file &
folder with all users having r/w privledges for
/var/log/rocm_smi_lib/ROCm-SMI-lib.log
* [rocm-smi] Added ability to do a glob search for multiple files
(globFileExists), assists doing file searches with * strings
* [rocm-smi] Added ability to log system details when RSMI_LOGGING
is turned on (getSystemDetails())
* [rocm-smi] Added logging to provide which ROCm API is being called
when RSMI_LOGGING is on
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added environment variable RSMI_LOGGING to control
when logging is enabled or disabled. By default, by not
setting this env. variable, logging is turned off. When
setting RSMI_LOGGING=<any value>, logging is enabled
which is placed in /var/log/rocm_smi_lib/ROCm-SMI-lib.log file.
Setting RSMI_LOGGING is allowed in both debug and release builds.
* [rocm-smi] Removed an initialize procedure which keeps
debug_inf_loop. Seems this feature is not being used.
Change-Id: I79b48387609c6233c6f05b04fb8bba66b68c2399
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Updates:
* [rocm-smi] Provide a thread-safe logging feature
* [rocm-smi] Adding logrotation into install/upgrade/remove
scripts
* [rocm-smi] Updated cmake lists to include rocm_smi_logger
* [rocm-smi] Updated DEB/RPM install/remove logging file &
folder with all users having r/w privledges for
/var/log/rocm_smi_lib/ROCm-SMI-lib.log
* [rocm-smi] Added ability to do a glob search for multiple files
(globFileExists), assists doing file searches with * strings
* [rocm-smi] Added ability to log system details when RSMI_LOGGING
is turned on (getSystemDetails())
* [rocm-smi] Added logging to provide which ROCm API is being called
when RSMI_LOGGING is on
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added environment variable RSMI_LOGGING to control
when logging is enabled or disabled. By default, by not
setting this env. variable, logging is turned off. When
setting RSMI_LOGGING=<any value>, logging is enabled
which is placed in /var/log/rocm_smi_lib/ROCm-SMI-lib.log file.
Setting RSMI_LOGGING is allowed in both debug and release builds.
* [rocm-smi] Removed an initialize procedure which keeps
debug_inf_loop. Seems this feature is not being used.
Change-Id: I79b48387609c6233c6f05b04fb8bba66b68c2399
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/amdsmi commit: c3a095a180]
Add support for HSA_ENABLE_PEER_SDMA env variable that can be used to
disable use of SDMA engines for device-to-device transfers. Note that
setting HSA_ENABLE_SDMA=0 will disable all SDMA transfers and override
HSA_ENABLE_PEER_SDMA values.
Change-Id: I737b3c2b2efcf3ff237f98bc748f49b8252ed24a
Add support for HSA_ENABLE_PEER_SDMA env variable that can be used to
disable use of SDMA engines for device-to-device transfers. Note that
setting HSA_ENABLE_SDMA=0 will disable all SDMA transfers and override
HSA_ENABLE_PEER_SDMA values.
Change-Id: I737b3c2b2efcf3ff237f98bc748f49b8252ed24a
[ROCm/ROCR-Runtime commit: a397373cea]
Previously, we used the following approach and Comgr actions
for device lib linking:
AMD_COMGR_COMPILE_SOURCE_TO_BC (compile with clang driver)
AMD_COMGR_ADD_DEVICE_LIBRARIES (link in device libs with
llvm-link API)
However, the clang driver can link in device libraries as part
of compilation, assuming a --rocm-path is set. In this context,
this is accomplished by using the following Comgr action instead:
AMD_COMGR_COMPILE_SOURCE_WITH_DEVICE_LIBS_TO_BC (compile and
link in device libs with clang driver)
Change-Id: I661465865365afecc44aa15d4df91bfab361af8d
[ROCm/clr commit: a4c5c44008]
Previously, we used the following approach and Comgr actions
for device lib linking:
AMD_COMGR_COMPILE_SOURCE_TO_BC (compile with clang driver)
AMD_COMGR_ADD_DEVICE_LIBRARIES (link in device libs with
llvm-link API)
However, the clang driver can link in device libraries as part
of compilation, assuming a --rocm-path is set. In this context,
this is accomplished by using the following Comgr action instead:
AMD_COMGR_COMPILE_SOURCE_WITH_DEVICE_LIBS_TO_BC (compile and
link in device libs with clang driver)
Change-Id: I661465865365afecc44aa15d4df91bfab361af8d
For aqua_vanjaram APU mode, KFDEvictTest and KFDSVMEvictTest are
skipped. Those tests passed on dGPU mode with memory reporting partition
support on GFX 9.4.3.
Change-Id: I56357843c6743b01b807359dbb37b32391fd9a25
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
For aqua_vanjaram APU mode, KFDEvictTest and KFDSVMEvictTest are
skipped. Those tests passed on dGPU mode with memory reporting partition
support on GFX 9.4.3.
Change-Id: I56357843c6743b01b807359dbb37b32391fd9a25
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
[ROCm/ROCR-Runtime commit: 5df82e3d14]
Add support functions to remap the first page of device memory (GPU/GTT)
to share host ASAN logic.
Signed-off-by: David Yat Sin <David.YatSin@amd.com>
Change-Id: I4c27d5417ba80a172dccb0a079a597c5dc1c8f85
Add support functions to remap the first page of device memory (GPU/GTT)
to share host ASAN logic.
Signed-off-by: David Yat Sin <David.YatSin@amd.com>
Change-Id: I4c27d5417ba80a172dccb0a079a597c5dc1c8f85
[ROCm/ROCR-Runtime commit: 1e6d728730]
Added a RCCL_MSCCL_ENABLE_DONE_EVENT env var, set it be 0 by default.
The env var is to control whether to use doneEvent when invoking MSCCL
kernels.
Skipping doneEvent would cause the firmware to skip L2 cache flush,
resulting in overall performance improvement.
[ROCm/rccl commit: 12dba425de]
Added a RCCL_MSCCL_ENABLE_DONE_EVENT env var, set it be 0 by default.
The env var is to control whether to use doneEvent when invoking MSCCL
kernels.
Skipping doneEvent would cause the firmware to skip L2 cache flush,
resulting in overall performance improvement.
RUNPATH in libraries will be : $ORIGIN
RUNPATH in binaries will be : $ORIGIN/../lib
Change-Id: Iafa66a8e02cc8c5783903d40927b63652042d2f1
[ROCm/ROCR-Runtime commit: ad002f1e7b]
Update documentation for hsa_amd_pointer_info to clarify which fields
are invalid when the allocation type is HSA_EXT_POINTER_TYPE_UNKNOWN.
Change-Id: Idaed985962c4a98d281ebe01bef8ec2459da3985
Update documentation for hsa_amd_pointer_info to clarify which fields
are invalid when the allocation type is HSA_EXT_POINTER_TYPE_UNKNOWN.
Change-Id: Idaed985962c4a98d281ebe01bef8ec2459da3985
[ROCm/ROCR-Runtime commit: 39feb83b88]
hipcc and clang++ both have logic to detect the installed hardware
and to automatically select the appropriate AMDGPU target when it is
left unspecified. When the AMDGPU_TARGETS property is initialized with
a set of default values, it results in the addition of an explicit set
of --offload-arch flags being passed. These explicit architecture flags
disable the architecture autodetection in the compiler.
The resulting behaviour from setting fixed defaults makes it unpleasant
to compile with CMake because they increase the build times for projects
unless they are overriden (as most users do not need to build for all
five default architectures). The fixed defaults are also troublesome for
users with hardware not included in the default set (e.g., gfx1011,
gfx1031, gfx1100).
A possible alternative might be to detect the architecture within
hip-config.cmake rather than running the detection logic on each
compiler invocation. However, this approach is simpler.
Change-Id: I9495d766b7eed03852eb4dc72b0aabe4100bc32c
Signed-off-by: Cordell Bloor <Cordell.Bloor@amd.com>
[ROCm/clr commit: e1bed6f354]
hipcc and clang++ both have logic to detect the installed hardware
and to automatically select the appropriate AMDGPU target when it is
left unspecified. When the AMDGPU_TARGETS property is initialized with
a set of default values, it results in the addition of an explicit set
of --offload-arch flags being passed. These explicit architecture flags
disable the architecture autodetection in the compiler.
The resulting behaviour from setting fixed defaults makes it unpleasant
to compile with CMake because they increase the build times for projects
unless they are overriden (as most users do not need to build for all
five default architectures). The fixed defaults are also troublesome for
users with hardware not included in the default set (e.g., gfx1011,
gfx1031, gfx1100).
A possible alternative might be to detect the architecture within
hip-config.cmake rather than running the detection logic on each
compiler invocation. However, this approach is simpler.
Change-Id: I9495d766b7eed03852eb4dc72b0aabe4100bc32c
Signed-off-by: Cordell Bloor <Cordell.Bloor@amd.com>
sdashmiz
Ranjith Ramakrishnan
gobhardw
Jaydeep Patel
Charis Poag
David Yat Sin
pghafari
Jacob Lambert
Philip Yang
Wen-Heng (Jack) Chung
Bing Ma
AravindanC
Ammar ELWazir
Dalibor Stanisavljevic
Cordell Bloor
Cole Ramos