* clr: Update signal count and pool size for staging buffer
* Change to naming of variables etc
---------
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
This change resolves some of the warnings generated during clr builds.
Quiet regular output of doxygen.
Disable non-documented warnings of doxygen.
Signed-off-by: Sebastian Luzynski <Sebastian.Luzynski@amd.com>
* clr: Implement dynamic stream to HW queue assignment
This change implements dynamic stream to hardware queue (HWq) mapping
with the following features:
* Queue depth heuristics with weights for optimal HWq assignment
* Make last used queue sticky for better locality
* Use pipe HWq to pipe mapping - gfx9 follows a round-robin queue to
pipe mapping based on creation order (single process per device only,
as pipe ID is statically assigned by runtime)
* More aggressive heuristic usage for better queue distribution
* Extend dynamic queues support for all stream priorities
Environment variables:
* DEBUG_HIP_DYNAMIC_QUEUE: 0 - disabled, 1 - Depth heuristics 2 -
Depth+Pipe heuristics
* DEBUG_HIP_IGNORE_STREAM_PRIORITY=1: ignore priority stream creation
* clr: Clean up last_used_queue_
Problem:
The existing SDMA engine selection logic had several issues:
1. Same VirtualGPU/stream could use different SDMA engines for consecutive
async copies since copy_engine_status may report engines as busy
2. Busy and Preferred engine check for every copy
3. No global tracking of which VirtualGPU uses which engine, leading to
suboptimal resource allocation
Solution:
Implemented a global SDMA engine allocator with per-stream affinity:
- Added Device::SdmaEngineAllocator to manage VirtualGPU → engine assignments
* Maintains global map of active assignments
* Enforces exclusivity: different streams use different engines (except
inter-GPU copies where preferred engines are prioritized for optimal
hardware paths like XGMI links)
* Thread-safe allocation/release with Monitor lock
- Modified VirtualGPU to cache assigned engine locally (assigned_sdma_engine_)
for fast lookup without map access on hot path
- Refactored rocrCopyBuffer() to:
1. Check local cached engine first → use if assigned
2. Call AllocateSdmaEngine() if not assigned → cache result
- Moved HSA API queries (memory_copy_engine_status, memory_get_preferred_copy_engine)
into AllocateEngine() for cleaner separation of concerns
- Engine release on HostQueue::finish() instead of only VirtualGPU destruction
* Improves engine utilization by releasing earlier
* Added virtual ReleaseSdmaEngines() method to device::VirtualDevice
- Added future path for simple round-robin allocation (kUseSimpleRR) for
next-gen GPUs with uniform SDMA bandwidth (disabled by default)
Cleanup:
- Removed selectSdmaEngine() helper (logic moved to allocator)
- Removed getSdmaRWMasks() (allocator accesses maxSdmaReadMask_/WriteMask_ directly)
- Removed unused sdmaEngineReadMask_/WriteMask_ member variables from DmaBlitManager
Benefits:
- Ensures consistent per-stream SDMA engine usage
- Prevents cross-stream contention and engine thrashing
- Prioritizes hardware-optimal paths for inter-GPU transfers
- Better resource utilization through earlier release
- Cleaner, more maintainable code structure
* When writing bulk packets always invalidate packet headers, Its
possible that the CP fetcher can have multiple packets in flight. In
such cases we may end up with a malformed packet because the writes are
not complete yet CP finds a valid header.
* While reusing signals, its possible we can come across a timestamp
that can contain several signals, like when profiling a graph. Reading
timestamps from all signals can make the call severely CPU bound.
Instead cache only that signal so as to avoid the overhead for critical
path.
* clr: Use graph segment scheduling to process HIP Graphs
* Add a broader path to use capture packet capture for all topologies
* Refactor code
* Use DEBUG_HIP_GRAPH_SEGMENT_SCHEDULING to toggle new vs classic path,
Enabled by default
* clr: Few fixes and improvements
* clr: Detect complex graphs to take classic path
* Use DEBUG_HIP_GRAPH_SEGMENT_SCHEDULING=2 to force segment scheduling
path
* clr: Fix a cornercase stack corruption
* clr: Track commands of segments instead of snapshots
* clr: Fix Batch dispatch logic
* Track fence_dirty_ flag for command of other streams
* Dependency resolution markers can now accomodate dirty fence on cross
streams
---------
Co-authored-by: Ioannis Assiouras <Ioannis.Assiouras@amd.com>
Co-authored-by: Godavarthy Surya, Anusha <agodavar@amd.com>
- 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]
Rahul Manocha
sluzynsk-amd
SaleelK
Ioannis Assiouras
German Andryeyev
Sourabh U Betigeri
systems-assistant[bot]
Pengda Xie
Godavarthy Surya, Anusha
Danylo Lytovchenko
Andryeyev, German
Betigeri, Sourabh
Xie, Pengda
Sang, Tao
Patel, Jaydeepkumar
Arandjelovic, Marko