Pass active queue for transfers in the cache coherency layer.
That will allow to use device transfer queue only for
cases when active queue isn't available, because using device
transfer queue from another active queue may cause a deadlock
Change-Id: Ifbe7e0303b77dbf6eeda3939ffbc25a3df7472de
[ROCm/clr commit: 95d55fdfa8]
If GlobalMemCacheLine reported is 0, runtime may run into an
infinite loop as the KernelSegmentAlignment is chosen as size of the
cache line.
Change-Id: Ide547940cc0407f16fab10ee210b4fd3ae4eaafc
[ROCm/clr commit: 041ddc0c1c]
OCL2.2 requires SPIR-V and runtime doesn't support it.
Make sure PAL backend doesn't report any SPIR-V support.
Change-Id: I8d179069674205b54f7d20d149bcb675bee5cdb0
[ROCm/clr commit: 0bf395af39]
Metadata in Codeobject version 5 is the extension of CO3 and CO4.
Add the detection of the new fields and program them in
the setup of the kernel arguments.
Change-Id: I27e58df77320ad00f4f16d35912668db803826af
[ROCm/clr commit: be6a06384e]
Use HSA_AMD_AGENT_INFO_COOPERATIVE_COMPUTE_UNIT_COUNT to get compute
units. This is needed to work around assymentric CU harvesting bug on
gfx90a. Add a new device property to get the max available CUs on the
device.
Change-Id: I878f38f14f16c1af01fc0a77157aea1e816a63b8
[ROCm/clr commit: 33aca5a4a6]
Report proper target id for xnack in HSAIL path. Runtime
will use ISA table and report hsailName().
Fix offline compilation path for PAL.
Change-Id: Ic0250bf6b9c193d867aec9800a319da1bf00c3ee
[ROCm/clr commit: a543d4a860]
When OCL failed to obtain function pointer from GL, we should not call it.
Change-Id: I50f69d270ce445386906a286e44c4e8c83722302
[ROCm/clr commit: 15101e704b]
Add a state indicator to retain ExternalSignals when needed.
Co-operative group launch uses external signals to indicate a dependency
to the next command.
Change-Id: I6d0daa006e2377c3bbf4aeca0fd5b63c7ac8fbbb
[ROCm/clr commit: 1fbd75b825]
Crash was due to the fact that external signal structure was stale even
after destroyign the command. That is because we skipped wait due to a
missing check.
Detect external signals and dispatch a barrier in ReleaseGpuMemoryFence.
Also clear external_signals_ at ProfilingBegin.
Change-Id: I991387edcfe928b511bf5e780988ee131321ed5a
[ROCm/clr commit: 3239222516]
Add a threshold for ROCR/SDMA P2P transfers. ROCR copy path
requires extra barriers in compute for synchronization. That costs
extra performance with tiny transfers.
Reduce active wait time to 10us. Tensorflow uses extra thread
per GPU with constant hipEventQuery() calls. Longer active waits
in ROCr affect CPU performance.
Change-Id: I9020358438615fa2d4617f862f00a562f0a588e7
[ROCm/clr commit: 008133cf41]
With SAM on, don't force Persistent for allocations
in HIP. This makes ROCCLR go down paths we don't want
for HIP.
Change-Id: If54cc16fa891d4cfdc761c6ab21ad707627e822a
[ROCm/clr commit: 5243552768]
This allows experimenting with env var GPU_PINNED_XFER_SIZE which is
still at a default of 32MB
Change-Id: I85ade700ed58d498eba29d1737601dc74d4c26a4
[ROCm/clr commit: 3f82b99f5d]
Stall in the host thread could occur earlier than the app expects.
Make sure rutnime can grow the signals to the queue size without
any stall. Also adding a new signal to the end of the pool could
break the dependency chain on signal reuse. The new logic will
insert the new signal after current to keep the chain intact.
Change-Id: I9c90b98515907db8b677528263c3e88cd9581a14
[ROCm/clr commit: 102c19adf3]
Reference for the first element can trigger an assert with
_GLIBCXX_ASSERTIONS build
Change-Id: I59c63c052831307edfe5dcc6384798a43e9596dd
[ROCm/clr commit: 6f2e7c3199]
Set affinity to the closest node of the current GPU. This reduces
the latency to fetch kernel args since device would query the CPU cache
of core which did the dispatch. This behavior is controlled with
AMD_CPU_AFFINITY env var(disabled by default)
Change-Id: I65afba62cb818ea25a311b88d1c0dd5c51330292
[ROCm/clr commit: b192beea52]
- Create hash values for binaries
- Add the binaries into RGP trace
- Add corresponding hash value for every dispatch
Change-Id: I2c3ce004d69f37d0d46bc4744e12f24273517f5e
[ROCm/clr commit: 2a298f2ec3]
Just signal check will still submit the marker and then later
runtime will have a timeout, but the barrier packet is still
generated. Hence early timeout will allow to skip the marker.
Change-Id: Ieb7d89becbcff43a4f4c46715354ca65ab4a80b9
[ROCm/clr commit: bbb635bc32]
The optimization is controlled with ROCR_SKIP_KERNEL_ARG_COPY.
This is initial check-in for experiments. Extra changes are
necessary for full support:
- handle graph capture with the original sysmem alloc
- avoid memobject references, otherwise there is a race condition with
reusage of the arg buffer
- Remove arg setup from hip
Change-Id: Ib0af710f93e79834711fa4049a7c66093711e68b
[ROCm/clr commit: 7e12cf6318]
The kernel arg pool will be divided into 8 chunks to avoid long stalls,
when the pool will be reused.
Change-Id: I228e6ca1c09e428c1775f1e5b685220a9a5d71af
[ROCm/clr commit: f78b3a8919]
German Andryeyev
Saleel Kudchadker
Satyanvesh Dittakavi
Todd tiantuo Li
Payam
Alex Xie
haoyuan2
Sarbojit Sarkar
Julia Jiang
Christophe Paquot
anusha GodavarthySurya
kjayapra-amd
pghafari