The PCI ID backup method in rocm_agent_enumerator, where the
tool uses lspci to find all AMD GPU devices in the system and
manaully match them to gfx version, is extremely outdated. The
PCI ID list did not include anything after Vega 10, and the
actual call to lspci no longer returned anything due to some
missing conversions.
The patch adds all GPUs that might be needed by ROCr up through
Navy Flounder. The PCI ID to gfx matching pulls from the amdgpu
driver and libhsakmt.
Change-Id: I58b77bb6aa631f575352fc444d2542f265909706
rocminfo uses lsmod to check for loaded drivers. Use of sysfs is
possible but sysfs' stable interface does not allow for easy parsing.
Use of lsmod avoids needing to walk the sysfs tree and avoids issues
of permissions to examine sysfs.
Both Debian and Fedora list lsmod under kmod. Presumption is that
CentOS and RHEL also follow this.
Change-Id: Ic5033e0b780100c54d2fe0b4f501c40acbc237fb
Package should depend on hsa-rocr, not hsa-rocr-dev. Also
Remove negative path for dependency rocm-core (unconditional add +
conditional remove simplified to conditional add).
Change-Id: I6ead202f4f3f2f77b1da2ffed77feee956caf2e9
Cmake manages CMAKE_CXX_FLAGS in standard ways from user inputs,
env vars, and target properties. Use target properties for our
options and let cmake handle the rest.
Change-Id: I20ef738e4df7880258d770f4ec13c09d8b323fba
JIRA : SWDEV-234471
With this change rocminfo exe shall be created using using hsa-runtime64::hsa-runtime64 which
internally decides whether static or shared libs based on its cmake build options
S. Keely:
Update patch to use find_package for rocr dependency.
Removed deadcode now supported by find_package.
Removed "hsa/" prefix from include statements since find_package
points to the target (ie rocr) include directory.
Removed typedef on structs due to new clang-11 warning.
Adapting to the comments : Removed PATHS for hsa find_package
Change-Id: I1ec65cdbce3085e44f1839da196eb4ae5c9ff30d
On Ubuntu 20.04, there is no more python or python2. Currently I get
this: /usr/bin/env: ‘python’: No such file or directory
Change-Id: Ib310b8aa7c1bd62973ef3cc8bcaf571831ad4435
On newer kernels, it seems the group was changed from "video" to
"render". The check for video group misled me for quite some time, so
relax this check. Rather than specifically checking for video group
ownership, first see if /dev/kfd can be open as read-write. Then
diagnose whether the user belongs to the group that owns it, rather
than hardcoding the video group.
Change-Id: I9e65427363e9a5cdba802e09cee2f40fb80520ed
CACHE variables allow for variables to be documented, and
ROCR_LIB_DIR/ROCR_INC_DIR should be overridable as they'll
have different values on different Linux distributions.
Change-Id: I0bba633c184df2da55bdbe6aabbd53346d098b83
* Continue with rocminfo even if video and kfd check fail.
* Color code informational lines (white) and warnings (red)
Change-Id: I739034c932fffca0924abc93ae9a929664a3e182
This is a python port of rocm_agent_enumerator, which is used by HIP/HCC to
determine available AMDGPU targets on a system.
Its previous implementation was written in C++ which makes it somewhat hard to
deploy onto different distros / architectures. A python port should remove such
issue.