Using "PROGRAMS" and "FILES" without specifying permissions will
automatically select the right permissions.
PROGRAMS is used for executables, FILES is used for data files
Change-Id: I0fb6eff257a8f936848bd648cf877da6dc0b6906
Fix segfault on p2p copies when 2 agents cannot access each other's
memory (usually because the PCI BAR's are out of range). The
AcquireAsyncCopyAccess function should return NULL in that case, so that
the test can be skipped.
Change-Id: If018f3609dd21a01c56eaec94de3bca52c385c4d
Remove KFD-specific Allocate/Free calls from the AMD::MemoryRegion.
The KFD-driver-specific Allocate/Free calls are now implemented in
the KfdDriver. Future changes will migrate the remaining KFD-specific
calls out of AMD::MemoryRegion.
This allows the MemoryRegion to be used across AMD drivers like the
XDNA driver.
Change-Id: Ib6a2a9e5e1a15e61644d2592beb3a8e6578c3010
Adds the initial KFD driver interface and use it to open the
KFD from amd_topology.cpp.
This change is to show the direction of the Driver interface for
initially supporting the KFD and to get feedback on the approach.
For now we wrap relevant ROCt calls behind this generic driver
interface so that we can generalize core ROCr components like
MemoryRegion, Runtime, etc.
Now that ROCt is incorporated into ROCr, we can more fully integrate
ROCt into the Driver interface. Ideally, we get to a point where
the generic Driver interface can support KFD, XDNA, and potential
future drivers.
Change-Id: I4573fd6af1f8398233ee9d3814d9f3139dd0279c
If some agents cannot access the memory buffer directly, this will cause
the hsa_amd_interop_map_buffer API call to fail
Change-Id: If2f0e1735c2926440d657831de50775d7f304c8e
Enum type for compute AQL is defined as larger then targeted SDMAs
enum types. We should only deny legacy calls for SDMA queues that
require targeted engines.
Change-Id: I6386a8700b3b18af825b6f0d2be27052cc8de0f5
This change adds the initial classes for the AIE agent and AIE AQL
queue.
An AIE agent list is added to the core runtime object.
Change-Id: I84b02f52171b80726dfb2c8431582a3ea2986eb3
Updates:
- [CLI] Previously --showfw displayed fw that
does not exist on systems. This change removes
that extra output.
Change-Id: If8b063001b80b03579ea1378dfd890c60f62ccd7
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
In centos-7, python2 is used for cpack bytecompile. Using f strings in code will result in syntax error.
Setting _python_bytecompile_errors_terminate_build to 0 will ignore the errors
Change-Id: I43ecc99ae16627f4f5f91d0cca0398f6a003fa3c
Rewriting logic to fix issue where pthread_create would return errors
other than EINVAL, and these errors would be ignored.
Change-Id: I573958724dcf886c20e8c14e6a9182303b3ffa06
Core dump support relies on debugger related KFD ioctl which have been
introduced in version 1.13 of the interface. However, the code checks
for KFD_IOCTL_MINOR_VERSION (currently 17), making it impossible to
produce core dumps when using some drivers that should support it.
Update the CHECK_KFD_MINOR_VERSION calls in the debugger related ioctl
wrappers and look for KFD 1.13 or above.
Change-Id: I10a7fd03bf8f678b6318d7c25d6a7ded804dac67
A recent patch introduced a build failure when building with Clang:
[ 65%] Building CXX object runtime/hsa-runtime/CMakeFiles/hsa-runtime64.dir/libamdhsacode/amd_core_dump.cpp.o
[…]/runtime/hsa-runtime/libamdhsacode/amd_core_dump.cpp:271:29: error: arithmetic on a pointer to void
271 | read = pread(fd_, buf + done, buf_size - done,
| ~~~ ^
1 error generated.
This patch fixes this by making sure the "void *" pointer is converting
to "char *" before doing arithmetic on it.
Change-Id: Ib1663ed30abce76e05f06d042975eccd7d729823
Recommended SDMA engines for DMA copies are now exposed for better
GPU-GPU performance. ROCr can now select those DMA engines.
Also lock-in host-device copies to SDMA0 and device-host copies to
SDMA1 for better stability and performance.
Change-Id: Ideff2e13daf537104efecb8b837bd49ee5096cb5
Extend the current Thunk implementation of queue creation to target
specific SDMA engine IDs.
Also expose the new recommend SDMA engines per IO link from the KFD
sysfs.
Change-Id: I51f9a0d83c0f1fc4d5dc837f879a7ae332e7d7e9
When HSA_OVERRIDE_GFX_VERSION is used, save the overrided GFX
version to OverrideEngineId instead of original EngineId. There
are places where real GFX properties still needed, e.g. CWSR size
calculation.
Change-Id: I9d9149bae465b7cfe55604fc19e7ca34e48b7b1c
Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
* Update HSA ABI checks for tracing
* Update lib/common/abi.hpp
- perform ABI versioning checks even when `ROCPROFILER_CI` is not defined (or ROCPROFILER_CI=0)
* Enforce versioning size for various HSA AmdExt step versions + hsa_amd_enable_logging support
* Minor HIP abi.cpp updates
- ROCPROFILER_API after function
- use rocprofiler_tracing_operation_t in lieu of uint32_t where appropriate
- rocprofiler_tracing_operation_t is not int32_t typedef (formerly uint32_t)
- use const T* instead of T* where appropriate
The current trap handler has 2 limitations:
1) If it receives a HOST_TRAP, it clears the corresponding bit
and notifies the host, when it should not.
2) When it is entered because of a debug trap (s_trap 3) and the
debugger is not attached, it returns unconditionally. However,
if another exception is reported at the same time as the trap
handler is entered for the debug trap (a memory violation for
example), that other exception ends-up being ignored.
This patch addresses both of those issues. It makes it so host traps
and debug traps are ignored when necessary. If any other exception is
reported to the wave, we halt the wave and notify the host, and if no
other exception is reported (i.e. we entered the trap handler because of
host trap or debug trap), we return to shader code.
Other minor defects are also fixed during this refactor:
- Fixed SQ_WAVE_EXCP_FLAG_PRIV_XNACK_ERROR_SHIFT which had an incorrect
value
- Host traps can be sent at any time, including after we have halted a
wave. In such case, the old approach would have:
1) cleared the trap ID saved in ttmp6
2) clobbered ttmp10 where part of the actual wave's PC is saved.
Change-Id: I9ecd341f4967e686233dec182b3e5b0388ef19bd
* Add kernel profiling time info to counter collection records
- lib/rocprofiler-sdk/kernel_dispatch
- added profiling_time.{hpp,cpp}
- restructured tracing.cpp
- updated queue.cpp AsyncSignalHandler
- gets kernel dispatch profiling time and passes to dispatch_complete and signal callbacks
- structured some header includes to reduce cyclic include probability
- originally, including kernel_dispatch/tracing.hpp in hsa/queue.hpp created a lot of cyclic includes
* Fix kernel_dispatch.cpp includes
* Fix kernel_dispatch.cpp
- include <cstring>
- replace use of ROCPROFILER_HSA_AMD_EXT_API_ID_NONE with ROCPROFILER_KERNEL_DISPATCH_LAST
This fixes an issue for missing HW events when out of HW events.
We cannot determine whether a HW event has occurred unless we call the
underlying drivers with hsaKmtWaitOnMultipleEvents_Ext. Previous logic
in Signal::WaitAny would switch to ACTIVE_WAIT state if we run out of
hardware events (signal->EopEvent() == NULL) and this would cause the
hsaKmtWaitOnMultipleEvents_Ext call to be skipped. But also, when we
have some signals without hardware events, calling
hsaKmtWaitOnMultipleEvents_Ext with a timeout of 0 so that we can poll
for remaining signals adds overhead with an IOCTL call and may cause
extra delay. Separating AsyncEventLoop into two separate threads so
that:
1. We can have a new Signal::WaitAnyExceptions to wait for HW events
This function can be simpler as it does not have to perform all the
timer calculations because it is expected to be always waiting on
hsaKmtWaitOnMultipleEvents_Ext through the lifetime of a process.
2. Signal::WaitAny does not need to have extra code to check for HW
exceptions as it only needs to handle HSA_EVENTTYPE_SIGNAL events. It
can also skip the calls to hsaKmtWaitOnMultipleEvents_Ext if needed.
Change-Id: I52ba99fd6e483e0cb477b7931a0dcc03520aa523
Signed-off-by: David Yat Sin <David.YatSin@amd.com>
Delete queues used internally in agent destructor to make sure any
memory allocated by the queue objects are freed before the agent memory
regions are destroyed.
Change-Id: I4768c9cf66f77ac00a5a355f373f7f22dc266e47
Joseph Greathouse
Jeremy Newton
David Yat Sin
Giovanni LB
Zhang Ava
Tony Gutierrez
Shweta Khatri
Jonathan Kim
Ammar ELWazir
David Galiffi
Charis Poag
jamesxu2
Galantsev, Dmitrii
Maisam Arif
Ranjith Ramakrishnan
Joseph Macaranas
Lancelot SIX
Bill(Shuzhou) Liu
Gopesh Bhardwaj
Yifan Zhang
Jonathan R. Madsen