- Retrieve the list of devices linked to each branch using stream ID x.
- Identify the necessary streams for each device to facilitate graph execution.
- Create the necessary streams for each device to ensure successful graph execution.
- Implement support for launching a multi-device, single-branch graph.
Co-authored-by: Anusha GodavarthySurya <Anusha.GodavarthySurya@amd.com>
- Updated kernel arg manager to support allocating kernel args on multiple devices for single graph.
- Updated AQL path to capture on the device where graph node is added.
Co-authored-by: Anusha GodavarthySurya <Anusha.GodavarthySurya@amd.com>
The build of ROCR backend will be enabled by default in Windows.
It requires the dll loader until ROCR dll will be always available in Windows for any configuration.
*Lay foundation to batch packets efficiently for graphs
*Dynamically copy packets with max threshold set with
DEBUG_HIP_GRAPH_BATCH_SIZE, if not stagger packet copy with pow2
*Default threshold for DEBUG_HIP_GRAPH_BATCH_SIZE is 256
*If TS are not collected for a signal for reuse, create a new signal.
This can potentially increase signal footprint if the handler doesn't run
fast enough.
- Refactor deviceLocalAlloc arguments
- Refactor hostAlloc code, have cleaner interface
- Kern args buffer need to have execute flag set as CP enforces this on
certain newer HW.
* SWDEV-465041 - Add support for user events with DD
User events can be replaced with HSA signals. Add the interface
to allocate HSA signal for user events and update the status on
CL_COMPLETE.
Force pinned path with DD to avoid blocking calls. Pinned memory
can be released only when the command is complete.
Simplify device enqueue path to use generic kernel arg buffer and
signals
* Fix notifyCmdQueue() logic for OCL
* Avoid blocking calls in OCL with DD
* Add event destruciton in a case of the failure.
[ROCm/clr commit: 2305f8ae56]
- When doing device/stream sync, we can submit a handler which may
introduce some host side delays. Use DEBUG_CLR_BATCH_CPU_SYNC_SIZE to
batch commands for host wait. Default for HIP is 8 commands.
- Investigation is underway in ROCr but need to address this for now in
HIP runtime.
[ROCm/clr commit: 9b045922a8]
The split path for blit kernels are no longer necessary, since the new blit kernels
don't use the copy size as the global workload
[ROCm/clr commit: da198ac5b2]
* SWDEV-520352 - Remove HostThread and legacy monitor
Remove HostThread, semaphore and legacy monitor.
Make original logics of thread and command queue stricker.
Add more comments to make logics clearer.
Some other minor improvement.
Also part of SWDEV-458943.
[ROCm/clr commit: 96cadbc9e9]
- When a command may possibly have two packets(like device heap
initializer), and if there is no signal on the main kernel packet the
tracking was broken as it marked HW event of the command as the first
packet signal.
- Make sure if no completion signal is attached to the second packet
then clear the HW event for the command.
[ROCm/clr commit: 072fb0804e]
- This change tries to save extra synchronization packets we may insert
as we didnt track the completion signals for every command. We track
the current enqueued command until it exits the enqueue stage. We also
record the exit scope to know if we flushed the caches
- Handle correct release scopes and store completion signal as HW events
- Use a new finishCommand implementation to only wait for the command
passed as the argument
Change-Id: Ie4350c5dd24f5d48dfa6ccbabd892f0544caadcc
[ROCm/clr commit: e03e4f3b5d]
Since hipMemMap can be called for multiple device handles on the same virtual memory, the same is true for hipMemUnmap, meaning that virtual memory can be "partially unmapped".
This means that the unmap function can be called for a specific part of the reserved address, meaning that only the designated subbuffer should be released. If unmap is called on the entire reserved memory, then all subbuffers should be released.
The main point is that for every hsa_amd_vmem_map, there should be a corresponding hsa_amd_vmem_unmap. Otherwise, if entire memory is unmapped by a single unmap call, then HSA will report the memory as "in use" if an attempt is made to delete it.
Change-Id: I039308eafb820decfb1c09f60347f26cdad1a362
[ROCm/clr commit: 3ec1d2d2f1]
- If any kernel uses device heap, the launch needs to be preceeded by an
init kernel, Save on the extra barrier packet launch/flush between the
init heap kernel and user kernel
Change-Id: I8ebc6246188200e5f673dc464bc76a53bcb8b7c6
[ROCm/clr commit: ca530c660b]
- Resolve signal dependencies for barrier value packet if there are > 1
depenent signals. Barrier Value packet accounts for only 1 dep signal
- Better log
Change-Id: Ia506ad5d80b91d598f92e7b539f41756e9b4b64b
[ROCm/clr commit: 2d450e8b06]
The logic can analyze the AQL queue state and
find a failed AQL packet with the kernel's name
Change-Id: I1a478fa2c25462cd07a194784958bdf22454b897
[ROCm/clr commit: ea0b092af8]
This change fixes random segfaults in graph tests that
are seen after the change make internal callbacks non-blocking.
The callback thread that decreases the GraphExec ref count
may now run after the runtime shutdown. This can cause a segfault
because the hip::device that is accessed in GraphExec destructor
is already destroyed during runtime shutdown. This patch ensures
that the hip::device object stays alive until after the
callback thread completes.
Change-Id: I75a6ac01f27a0b2250bbd10ed389ebfb322927af
[ROCm/clr commit: 21c223f8df]
- Added DEBUG_CLR_SKIP_RELEASE_SCOPE flag to force release scope to
SCOPE_NONE in AQL packet header
Change-Id: Ife02cddb9d5cd4749103ce585d3d5fe9024c6868
[ROCm/clr commit: 8155943c5f]
- added wptr and rptr to ClPrint in dispatchBarrierPacket and dispatchBarrierValuePacket
Change-Id: I8a62289deb23c9f657a9b0ac6138bb55eafecba2
[ROCm/clr commit: 078fe7e5de]
Use hsa_amd_signal_create() if settings.system_scope_signal_ is true.
Change-Id: I6d440155dfbcd5bf03658583a93827cb1c56537c
[ROCm/clr commit: 14f58fc74d]
SaleelK
Ioannis Assiouras
Pengda Xie
Godavarthy Surya, Anusha
German Andryeyev
Danylo Lytovchenko
Andryeyev, German
Betigeri, Sourabh
Xie, Pengda
Sang, Tao
Patel, Jaydeepkumar
Arandjelovic, Marko
Jimbo Xie
kjayapra-amd
Ioannis Assiouras
Anusha GodavarthySurya