The copies can get blocked if the last SDMA engine is used by another
copy and this can lead to perf drop in some of the tests like Gromacs.
Resetting the last engine by checking the engine status and fetching the
new mask after few copies can avoid this.
Change-Id: I8fe8ea678db508d291c6242f3741fa9215e99921
Currently we force inlining everything for HIP. Now we'd like to enable function
supports. The first step is to remove uses of `-amdgpu-early-inline-all` in
various places. This patch is to remove all of them from clr.
Change-Id: Ib0cad1f586714c9989778b00746aa4c47a4eec95
Mempool has capability to track dependency between streams for
faster memory reuse. Enable that capability.
Change-Id: I28266a7e38d0fc4c5d027b9542d3719653840821
OpenCL printf handling did not process vector of half precision floats properly
(mainly because compiler packs 2 halfs into a dword and runtime failed to extract the
individual parts).
This patch fixes the issue.
Change-Id: Ia1f15ccfb5db52b71c43cfd588dd38f551ee5277
- Using runtime unbundler, no any gfx device can load fat binary,
if there is any device without available code object.
- Extract available code object to corresponding gfx devices. So
users can work ROCm with those ready devices without segmentation
fault.
Change-Id: I9f14c65ecebf2d3c4b127a007cb434a3ae98c450
- Enable Device kernel args for MI300* for now.
- Fix a perf issue which impacts graph instantiate when dev kernel args
are enabled.
Change-Id: I962e58fd9d8dd1a8db95e601cb03a8e9c7bac97f
Node can be enabled/disabled only for kernel, memcpy and memset nodes.
If the node is disabled it becomes empty node.
To maintain ordering just enqueue marker with respective node dependencies.
Change-Id: I710f3e88ab4e76c81f6f86a40a7dc61fd4c7e440
- enforce incrementing the table versioning number when a table size changes outside of ifdef for ROCPROFILER_REGISTER
- add new HIP_ENFORCE_ABI entries
- update the HipDispatchTable size and bump HIP_RUNTIME_API_TABLE_STEP_VERSION to 1
- re-enable rocprofiler-register
Change-Id: Ie0cc1d8491c5640056e5dd393ea243e4dce4e8a9
When kernel does device side malloc, initial heap is allocated with __amd_rocclr_initHeap.
During graph launch kernel __amd_rocclr_initHeap is enqueued followed by actual kernel . So kernel will execute after initHeap kernel.
But with graph optimizations during capture initHeap gets enqueued on device null stream and actual kernel on graph launch stream.
So no proper synchronization. Switch to command creation and enqueue during launch for kernel node with hidden heap.
Change-Id: Iaf600251faef9a448853f19429023c118aa760b9
__amd_streamOpsWrite blitkernel in device-libs has only 3 args.
so getting rid of the 4th unused arg (sizeBytes)
Change-Id: I81cc1107f8b424bf58558c93a2495a1b878aef91
With multiple HIP streams it's possible to have a race condition when
one thread stops the traces, but another still performs submisisons.
That may cause a crash on the barrier callback.
Change-Id: Ic56f8277fcfd2c2142a4821d927b938b9f313add
Check the pointer if its present in the arrayset before trying to dereference
it as it can cause access violation if the pointer is allocated using malloc
Change-Id: Ida72b9015dc22269fc1fbe0728e66e3de29fda3d
- Implement workaround to ensure HDP writes are done by writing and
reading the HDP MMIO register.
- Implement the same workaround for graphs, we no longer need sentinel
write/readback
Change-Id: I0d3027b46a1f61131ec62e3c8c669ff5184fa6b2
When graph is Instantiate on device 0 graph and launch on device1 switch to command creation and enqueue during launch.
Change-Id: Ied34dc99b2a776130d1354ed3830c6ccab9068e4
Add @gargrahul, @rakesroy, and @mangupta as CODEOWNERS.
This is for GitHub upstream.
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Change-Id: I563a7cf860cca56ae5fb5e05dcfaf1751b3692e4
Windows path still uses multi threading implementation. Hence, in graphs
all nodes are executed in a queue thread and that requires to manage
mempool in the queue thread. However, the spec allows to destory memory,
allocated in a graph, outside of the graph's execution. That may cause
mempool management to go out of sync.
Change-Id: I0ffb2244b3cb720455ed44d1b3e2487fa8959a77
Latest VidMM can provide free memory available on the system.
Use PAL interface to report free memory on the system instead
of per process.
Change-Id: I0e78b9d340299c16829177a8c5182d21cc353384
Read and write int bytes sentinal value to dev_ptr or PCIE connected devices at the tail end of the kernarg surface.
Change-Id: I993d552ac872b3cd56aef4746c4d1d92c58d38b4
German Andryeyev
Satyanvesh Dittakavi
sdashmiz
Shilei Tian
Sameer Sahasrabuddhe
Ioannis Assiouras
Jaydeep Patel
Anusha GodavarthySurya
Rahul Manocha
Vikram
cadolphe
Saleel Kudchadker
Jatin Chaudhary
ChingShihLi
jujiang
Sourabh Betigeri
Jonathan R. Madsen
Ajay
kjayapra-amd
Rahul Garg
Todd tiantuo Li
Alex Xie
David Galiffi
Ilya Panfilov