This change adds a new HIP API `hipExtHostAlloc` which preserves
the functionality of `hipHostMalloc`.
Change-Id: I13504c6fc13465ddd7aed329795bb4f2fef1baff
Integration into pytorch pointed out some issues, value narrowing, to
fix this we are now using unions. Also removed check for -munsafe*
compiler flag. The check is now just on builtin detection.
Change-Id: I49364503fa429bd862952f9b29879072afa6d553
SPT is destroyed with hipDeviceReset(). If a
stream is created right after reset, the same
object id could be reused. Later SPT destructor
incorrectly verifies that the stream is valid
referring to the reused object id causing the
corruption.
Change-Id: I3b1f7ffdf8bab874dca7b8fde22318162997b8f6
This change adds fixes in optimized multistream path for childGraph uses cases.
1) For childgraph nodes, rely on runNodes() only to process
the childgraph and skip calls to createCommand and enqueueCommands.
This ensures that the start/end markers are enqueued correctly
with respect to the childGraph commands.
In addition, the runNodes() for the childgraph should be called after
the dependency walkthrough to make sure that the subgraph is executed once.
2) Nodes with no outgoing edges should be marked
as a leafs regardless of which stream they are assigned to.
This is to ensure that marker dependencies from nodes
that run on non-zero stream to subgraph leafs that run on zero stream
are still set up correctly.
Change-Id: I4a5f4f3b0e0d01e515cdcb045b46c2798f291255
When source or destination pitch is set to zero in hip_Memcpy2D struct
it should default to WidthInBytes + [src/dst]XInBytes
Change-Id: Id57b53cab40ba72ced231258da9356554c4868c3
- Fixes -0.0 and +0.0 comparison. For atomicMax if the value on
address is -0.0 and on val is +0.0, gfx90a's unsafe atomics will swap
them. This behavior should be consistent with cas loop as well.
- _system variants of atomicMax and atomicMin are resulting in
incorrect output. Updated these to use the similar implementation as
atomicMax and atomicMin.
Change-Id: I20df36ee29ae0434a6b564f2ba71193fe41cfa59
Releasing graph exec after wait completes and before delete hip::stream obj
during stream destroy.
Change-Id: I1d68aa8d844f7d3af330c6d09c44af07f8553551
- 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
=> 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
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
This issue was happening because of incorrect usage of getStream call,
if we get the null stream first and then typecast it, and call on
getStream again, we lose the advantage of simply passing "nullptr" to
indicate NULL stream. Thus we enter the waitActiveStream call and add
barriers to sync across streams.
Change-Id: I94dc4e3ec927295b9e1ab6dee4b37d7d3e00b0cc
Also in the scope of SWDEV-467540.
Fix sporadic crash in Unit_hipStreamAddCallback_MultipleThreads by
deferring release() of block_command.
The test will invoke 1000 threads on the same stream thus there
is a chance to free block_command too early in original code.
By deferring release() of block_command we can make sure block_command
is always valid during calling block_command->notifyCmdQueue().
Change-Id: I31555ee18e6958e34b89f04181867fa4e932a38c
Creation of ReferenceCountedObject will increase reference count by 1.
Clear the commands from Node after capture so that they wont be reference later.
Change-Id: I1cc4085939cf65218ec2aa2e25ab6d737f7cacd3
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
Since we made the members public, we can optimize some operations which
do not require redundant conversions to half_raw types.
Change-Id: I31555ef18e695d8e24b89f0418187fa4e932a38a
On some platforms user can ask for extended shared memory for a
particular kernel in some cases. This feature does not exist on HIP at
the moment. So we are setting it to sharedMemPerBlock which is the
maximum user can expect for their kernels.
Change-Id: I81005cf0d1c9fb941e77d34fb8385241ffe5bdd0
For refactoring of childGraph to have its own graphExec,
kernelArgs needs to be separated from the graphExec object.
All the childNodes part of graph should share same kernelArg pool.
Otherwise we endup creating multiple device kernel arg memory chucks
for single graphExec.
Change-Id: I4029a46ebc1fa112d87df64ab1fecbf288fabe5e
In case when the tile size is greater than the number of active threads,
the coalesced group size should be equal to the number of active threads.
Change-Id: I1d41322f2428a07862a590cb5d34b01243383b7c
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