Fixes hang due to change in order of initialization of libraries
that have cyclical dependencies and they call hsa_init() during their
initialization phase.
This implementation looks for a symbol called "HSA_AMD_TOOL_PRIORITY"
across all loaded shared libraries using dynamic section entries of the
loaded lib instead of using dlopen and dlsym for the same purpose.
Change-Id: I4865f2fd18dd186ec311a432ec38fbb5583805d2
[ROCm/ROCR-Runtime commit: 8aac885318]
Simplified the callback method. Also fixed the way, loaded shared object were getting appended into a string vector,
which was not being passed to this callback method.
Change-Id: I68661dd73f61a11c42fa92f670e8e7b6ffcb5711
[ROCm/ROCR-Runtime commit: 8751e65b79]
New environment variable HSA_OVERRIDE_CPU_AFFINITY_DEBUG to
enable/disable overriding CPU affinity.
Default value is enabled(1).
This is a temporary variable and may be removed in the future.
Change-Id: Id6a7c611730471ddc276ca333fde1e57046bf32a
[ROCm/ROCR-Runtime commit: df3fe8c2fb]
Mostly a demo at this point. Logs SVM (aka HMM) info to
HSA_SVM_PROFILE if set.
Example: HSA_SVM_PROFILE=log.txt SomeApp
Change-Id: Ib6fd688f661a21b2c695f586b833be93662a15f4
[ROCm/ROCR-Runtime commit: 965df6eef7]
During hsa initializing stage, ROCr now searches all the loaded libraries
for a symbol "HSA_AMD_TOOL_PRIORITY" and adds all those libraries to
the tools library init list. Tools libraries listed in HSA_TOOLS_LIB
env variable are also loaded in the given order and take priority
over HSA_AMD_TOOL_PRIORITY.
Change-Id: I739af42bbd777c44a9152c11e17dd69979b65e82
[ROCm/ROCR-Runtime commit: e7fc301aa7]
Add support for AMD Agent to return amount of memory available
Change-Id: I5c32e2cebbaa2993b044250aefe434e4cc02d8c2
Signed-off-by: David Yat Sin <david.yatsin@amd.com>
[ROCm/ROCR-Runtime commit: 4ac840269c]
Discards all user provided async copy agent info and relies on
pointer info discovery.
Change-Id: Ife3e708a49ffccbede4983ab47d5ed0032970857
[ROCm/ROCR-Runtime commit: 3ebe99f96d]
This is consistent with KFD and has significantly better latency.
KFD is taking this as the definition of the SystemClockCounter.
Change-Id: I4c1b3bc58c738206265c55ebefd41356c013bfe5
[ROCm/ROCR-Runtime commit: 0ee82742a7]
__x86_64__ and __AMD64__ should be already defined by the compiler to
specify the compilation target and shouldn't be defined manually.
I fixed two x86_64 checks to include VS variables, as removing this
might cause it to fail to compile on that compiler.
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
Change-Id: I600ff449af85bf7d83ecab167d97933922e2d917
[ROCm/ROCR-Runtime commit: 178a7a5cfa]
Each time delay is grown we need to reset elapsed. We want to take
the most accurate sample from the set at fixed delay.
Without this we will hang if there is ever an insufficiently accurate,
high unit clock read.
Change-Id: Ic65f364067789ac85a6572d67af2d77528e265bb
[ROCm/ROCR-Runtime commit: 4e9849034d]
With asym. harvest hw does not issue groups equally to each SE,
occasionally hw will skip an SE so that the distribution reflects
each SE's CU count. Scratch resources must be allocated to reflect
this asymmetric distribution of groups.
Change-Id: I65e26206500483ea18e6e8796e65ecba5354b029
[ROCm/ROCR-Runtime commit: 552dcead93]
discardBlock may be called multiple times on the same block.
We must not discard the block multiple times or we will corrupt
in-use memory accounting.
Change-Id: Ife9f3162785965a795dcf81887d4d447cc096e62
[ROCm/ROCR-Runtime commit: b9a0c1d313]
On gfx90a only a reduced number of CUs must be used for cooperative
dispatches due to CWSR and launcher interactions with asymetric
harvest. We must use one fewer CUs per SE than the lowest count of
CUs on any SE.
Also adds env var HSA_COOP_CU_COUNT which enables the cooperative
CU count computation. Set to 1 to enable the new computation.
This is an opt-in feature that will become enabled by default (opt-out)
in a future release.
Change-Id: Ifbb75ced3bbc15876eef44922c6a4f6fde8c4c28
[ROCm/ROCR-Runtime commit: 37942c982a]
ROCM_VISIBLE_DEVICES was used where ROCR_VISIBLE_DEVICES was
intended.
Change-Id: I644a546f3c9dd0b50898ef8a21dbb8f5c3a36926
[ROCm/ROCR-Runtime commit: fce6ba052e]
Prior solution used a single global lock to protect the memory tracking structures.
This change protects the memory tracking structure with a shared mutex (rw lock) in
shared (r) mode for memory allocations and frees so that long duration processes,
calling to kfd, can be done in parallel. Operations which must modify the memory map
take the mutex in exclusive mode (w) and must not call to the thunk while holding
the mutex.
The fragment allocator now requires separate protection and is protected with a
mutex at the device level. Protecting at the device level, rather than pool,
allows retention of the current recursive design and allows calling Trim from
withing Allocate. This could be made finer (pool level locks) but would
require backing out of Allocate entirely to call Trim. Trim and any retried
Allocation must be done in isolation (per device) or we may report OOM when
memory is actually available in some pool's fragment cache. So some device
level serialization is required in at least some paths.
Change-Id: I7c1e94d6965ffcc602b12fefdd3a6e97b84b5e00
[ROCm/ROCR-Runtime commit: df55cb0450]
This omission did not cause problems earlier due to having not been
instanced.
Change-Id: I7a54f82e06c299902f3bf6b4d3737cc5e30961ad
[ROCm/ROCR-Runtime commit: 322588a60e]
KFD topology has been corrected and the defaults used by this
workaround are no longer true for all chips.
Change-Id: I0242d8077e9666ed1cf0dc3985244258ae5c0924
[ROCm/ROCR-Runtime commit: 19c1e92b4c]
Delay parsing until after GPU discovery. Use the surfaced
GPU count and maximum phyiscal CU count to limit parsed bit masks.
This prevents pathological input such as
HSA_CU_MASK=0-8000000:0-8000000 from attempting to consume 7TiB.
Change-Id: I3773d2db3740c2023b0f6275d1818b69119b0495
[ROCm/ROCR-Runtime commit: 2aa0795b33]
New environment variable HSA_CU_MASK allows users to
specify a cu mask to every queue allocated from any
GPU. hsa_amd_queue_cu_set_mask is restricted from
escaping this mask.
A new API hsa_amd_queue_cu_get_mask is added to query
the current cu mask.
Change-Id: I846c03a5faaca9b95067c31db84b59cc9fce2f03
[ROCm/ROCR-Runtime commit: 4455250be1]
Enables the fragment allocator to handle >2MB allocations, maintaining
good TLB alignment. Prior code contained a bug that caused the effective
API granule for vram allocations >2MB to be bumped to 2MB.
Also adjusts the block cache's block retention heuristic to not
count discarded blocks as in use. This will reduce block retention
when a significant amount of large blocks or IPC is in use.
Change-Id: I30bd85eb87951df822211f799d9cfe579ab109c6
[ROCm/ROCR-Runtime commit: 8adbda1c18]
Add macro debug_warning_n to stop printing a message after
N instances.
Change-Id: Id5f84b11eb63b3a20bd2bcb2ea8f10a066b457ef
[ROCm/ROCR-Runtime commit: ca8387768e]
Includes some workarounds and HMM.
Conflicts:
opensrc/hsa-runtime/core/runtime/amd_topology.cpp
opensrc/hsa-runtime/core/util/flag.h
Change-Id: I22976f07964a43dbb228a6231777dbd599112b8d
[ROCm/ROCR-Runtime commit: 7333c77e22]
Sramecc is misreported in kfd 4.0 and prior. To prevent possible
corruption due to d16 instructions, deny use of gfx906 with older
kfds and correct misreport for gfx908. Denial of gfx906 may be
overridden by setting HSA_IGNORE_SRAMECC_MISREPORT=1.
Change-Id: I7d5c3a716fad01c348f8b88cd508cedbf914c989
[ROCm/ROCR-Runtime commit: 45fbe5b192]
For small copies cache flush latency is larger than data transfer
latency in local VRAM. Select SDMA for small copies.
Environment key HSA_FORCE_SDMA_SIZE is added for easy adjustment
of the small copy size. This may be removed after tuning is done.
Change-Id: I733fa0ae01c616617c5de50e71226b51fd589ef2
[ROCm/ROCR-Runtime commit: 2a0c6774fb]
- Make code object reader use mmap when loading from a file on Linux.
- Support computing code object URI for memory either fro the loaded
host executables, or from all mmapped files. Define the environment
variable HSA_LOADER_ENABLE_MMAP_URI to non 0 to search the mmap
files, otherwise only the loaded executables will be seatched.
- For mmap search, determine file size and ommit offset and size URI
fragment when the code object is the whole file even when specifying
a file size explicitly or specifying memory that has been mmaped.
- Always return a non-empty code object URI.
- When a code object reader is created, complete all fields to ensure
it can be used in a multi-threaded manner using only const
operations.
- Add missing exception handlers in the AMD vendor extentions.
- More rigorous checking for errors.
Change-Id: I07797b1dc60c5c64245142d77becf9f7c9643395
[ROCm/ROCR-Runtime commit: 91cb98dab6]
Memory from the suballocator may be exported via IPC. If this
happens then the allocating process should not reuse that memory
since it would still be connected to the remote process. IPC exported
memory must be released back to the driver.
Change-Id: I2ab0c814f63191f753fc3640cc4140ee144bf07f
[ROCm/ROCR-Runtime commit: 29b660c91e]
Contructor function must not be attempted twice even if the construction
attempt returns nullptr.
Change-Id: I75353e5e511769a96e4332f7f60887f6559c1cd5
[ROCm/ROCR-Runtime commit: 2fbacccaed]
Setting to 1 prevents the scratch handler from reducing peak occupancy.
Scratch allocations that would normally reduce peak occupancy will
instead fail.
Diagnostic for TF and PyTorch.
Change-Id: I2d7ea47077eb5cf708251c8aa3fd183ad4261be0
[ROCm/ROCR-Runtime commit: dc165c92bc]
Joined threads can not be joined more than once nor can they be detached.
Thread library wait and close allows multiple waits and separate close so
this fixes the pthread implementation.
Change-Id: I0019271a438f11ed4c6c11854011f5c4f6e16b65
[ROCm/ROCR-Runtime commit: a913549190]
Shweta Khatri
David Yat Sin
Sean Keely
skhatri
Jeremy Newton
Tony
Ramesh Errabolu
Christian Sigg