This change adds a new HIP API `hipExtHostAlloc` which preserves
the functionality of `hipHostMalloc`.
Change-Id: I13504c6fc13465ddd7aed329795bb4f2fef1baff
[ROCm/clr commit: 2c84211b58]
hiprtc and hip APIs use the same file.
Append to file instead of start of file
Change-Id: I2703f9bb67f0c51b557a058daab129679a0b5dd9
[ROCm/clr commit: e07172ff57]
This patch fixes this potential issue that filling AQL header before
filling the AQL body. The hsa spec specifies "Packet processors may
process AQL packets after the packet format field is updated, but
before the doorbell is signaled."
However, the hipGraph AQL package with valid header will be filled
before fill the body, which may have the potential issue that CP
receive invalid AQL body.
Change-Id: I84af798c19ee2b8805ba19732b0eabdea2958a96
[ROCm/clr commit: 3959b5be1e]
Fix random language string that leads to compiling failure
of trap handler and TDR of hipMemset() on VM in release
mode of hip-rt
Change-Id: Ie1d874742b804f62ceda68064fa54f5d39c092b8
[ROCm/clr commit: 857d0d60b9]
- Added the optimized multi stream path in graph execution. It uses a fixed number of async streams in the execution
- Optimize the launch latency, where commands
creation and execution is done at the same time
- Optimize the scheduling to use less barriers and waiting signals if
the same queue can be detected
- The new path is controlled by DEBUG_HIP_FORCE_GRAPH_QUEUES
environment variable, where 0 will use the original path and any other
value will force the number of asynchronous queues for execution
- DEBUG_HIP_FORCE_ASYNC_QUEUE can force single queue async
execution in graphs(applicable for Navi families only)
Change-Id: I7eb40bc15c45f508d6911868a6f6d4c3598d380e
[ROCm/clr commit: 9db52f9a46]
=> Added support to capture multiple AQL Packets.
=> Added Interface to callback to hip runtime from rocclr to allocate
kernel args from the graph kernel arg pool.
=> Enabled Support to capture memset node.
Change-Id: I7e1c2ba06927459e024653058af142bd82192c43
[ROCm/clr commit: bd3a35bde1]
hipDeviceSynchronize called from __hipUnregisterFatBinary
accesses static maps and monitors. This change ensures these ojects
are not destroyed before __hipUnregisterFatBinary is called.
Additionally it disables the teardown process for static build.
Change-Id: I46b58641d60efcf6637a8e99cdd786ffe9e2c77d
[ROCm/clr commit: 9b33db9b24]
If only external signals were provided, then just process it
without adding internal signals
Change-Id: Iaefd65d0f8b0a64b9f6a864a9bd73de20a29dfa4
[ROCm/clr commit: 18187cd8fe]
Capture AQL packets during GraphInstantiation and enqueue AQL packets during graph launch.
Added support to capture single graph memset node.
Capture support for memset node is currently disabled.
Memset capture will be enabled when capture for multiple packets are supported..
Change-Id: I14dfbc41731025cc3a548a730558915def3fa384
[ROCm/clr commit: 346da4bb40]
- HIP path doesn't support resource tracking. Thus, double copy can't be enabled,
because it requires resource tracking.
Change-Id: I0f9c4e185b5b2d2b1abde041fca21bb099db9ccd
[ROCm/clr commit: 4c763e45a1]
Fixes the memory leak with hipExtStreamCreateWithCUMask API.
hsa queues with cumask set are not being reused and created
everytime the API is called, But these queues were not being
destroyed during hipStreamDestroy causing memory leak.
Change-Id: Ibfbe019bbd73604e98eca80461efe53fa64bb701
[ROCm/clr commit: 191869b252]
Remove the redundant copies inside sub folders. This was useful when
these projects were independent but now since they are merged they
should have one single .clang-format file.
Change-Id: I60510d7b78b129c761e84f13403492bd0c5d941a
[ROCm/clr commit: b5b1f639c0]
This change modifies the readback mechanism to use a pointer to volatile
instead of a volatile pointer. This ensures that the compiler does not
optimize away the read operation.
Change-Id: I79ff925d615aa8cc4f950e8ff4b7e608fcb179a4
[ROCm/clr commit: ea50d2c0c2]
Implement std::mutex based monitor that has much
simpler logics than legacy monitor.
Create DEBUG_CLR_USE_STDMUTEX_IN_AMD_MONITOR to
toggle them.
If DEBUG_CLR_USE_STDMUTEX_IN_AMD_MONITOR = false
(by default), use legacy monitor;
If DEBUG_CLR_USE_STDMUTEX_IN_AMD_MONITOR = true,
use std::mutex based monitor.
If no perf drop of stl::mutex based monitor,
legacy one will be removed later.
Change-Id: I1d21368ff462477d3238d71e4e2a1a7d6b9167ad
[ROCm/clr commit: 73c02041e1]
- awaitCompletion code may do a endless spin wait for cases where we
dont submit a handler. One such case can be the hipExt*Launch API which
takes a stop event. In that case we optimize the stop event by attaching
a signal to the dispatch packet but dont submit a handler when we attach
the signal. That means if awaitCompletion() is called after that, we
would keep on waiting on command status on the host rather than simply
checking signal value.
Change-Id: Ie8bf175aeefa3f9e4299b1ae7ae9108dad67e283
[ROCm/clr commit: 561fb8a459]
We must be in protected way to get last command when calling
awaitCompletion() where lastCommand will be released and
possibly destroyed.
This can solve scope lock(notify_lock_) crash in
Event::notifyCmdQueue() with AMD_DIRECT_DISPATCH = true.
Change-Id: I4297166f912a71112f4a8945d993160ba9afdc34
[ROCm/clr commit: 749385155a]
1.Move global amd::monitor listenerLock before global
class runtime_tear_down as it will be referenced in
~RuntimeTearDown() after main(). It should be freed
later than runtime_tear_down.
2.Update Device::~Device() to SVM free coopHostcallBuffer_
before context_ is released and freed.
Change-Id: I1d21378ff463477d3238d71e5e2a1a7d6b9147ad
[ROCm/clr commit: 544c45364f]
If the graph has kernels that does device side allocation, during packet capture, heap is
allocated because heap pointer has to be added to the AQL packet, and initialized during
graph launch.
Handle race with wait when 2 kernels with device heap are enqueued on multiple streams.
Change-Id: I45933b77fcaf7bc8fdf1bc906462e32b5d8d3688
[ROCm/clr commit: 57156c524d]
Adding a safety check prevents an invalid memory access
if timestamps and kernelNames vectors are of different size.
The patch also moves the addKernelNames for the accumulate command
into dispatchAqlPacket function.
Change-Id: Iea0927e1253800403a1ae3f3d72de1e7d96476c3
[ROCm/clr commit: d44f44a5b1]
Fork() duplicates all system memory resources, but runtime can't duplicate
GPU resources. Thus, avoid tearDown() calls for the child process(s).
Change-Id: Id6b12bacd5112b9ad3747c218e09cba98ea1b42c
[ROCm/clr commit: ae2992ea43]
Julia Jiang
kjayapra-amd
Ioannis Assiouras
ksankisa
Ajay
Shane Xiao
Rahul Manocha
taosang2
German Andryeyev
Anusha GodavarthySurya
Saleel Kudchadker
Satyanvesh Dittakavi
Jaydeep Patel
pghafari
Jatin Chaudhary
Sourabh Betigeri
Alex Xie
Jimbo Xie
Jacob Lambert