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
[ROCm/clr commit: 2dc6ec68a5]
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
[ROCm/clr commit: 821ae6a103]
- 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
[ROCm/clr commit: f138e0d113]
When graph is Instantiate on device 0 graph and launch on device1 switch to command creation and enqueue during launch.
Change-Id: Ied34dc99b2a776130d1354ed3830c6ccab9068e4
[ROCm/clr commit: 7d09e1abed]
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
[ROCm/clr commit: 4f6b0da028]
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
[ROCm/clr commit: 853abeb75e]
This should be used in place of dlsym or GetProcAddress (linux and windows respectively)
Change-Id: I5501b538e03892e8e5a2282678d848fcaf21d911
[ROCm/clr commit: 0479cdb3dd]
Fetching null stream's logic has changed earlier from amd::HostQueue
to hip::Stream. This seem to cause some timing difference between
checking for null stream and creating it due to which issues are
observed in multithreaded applications using default stream.
Change-Id: Ie02365dec537275d23a1d225de9811e2fd3a9c55
[ROCm/clr commit: 8d265838cb]
If a system has LLVM installed, `find_package` could choose that one
even if we set `HIP_LLVM_ROOT`. `LLVM_ROOT` is ignored because of this
CMake policy is set to `OLD` by default.
Change-Id: I18fa0453afe170c229e92d6ddc386b43eb0c44f6
[ROCm/clr commit: a2a8dad980]
During hipGraphExecKernelNodeSetParams kernel function can also be updated.
Hence size required for kernel parameters differs from what is allocated during graphInstantiation.
So, create new 128KB kernel pool and allocate kernel args from the pool.
If the pool is full create new 128KB pool. Release kernel pools when graph exec object is destroyed.
Change-Id: I9567946d63400c79cbfd4c5439c654c92557ceae
[ROCm/clr commit: e9957151f3]
use AMD_COMGR_ACTION_COMPILE_SOURCE_TO_RELOCATABLE action
to compile source to realoc. Currently we have source->bc,
link->bc and bc->realoc. This new action replaces the
three steps with one.
Change-Id: I8089cbef681e079702fefc2d2085a23bc3578d02
[ROCm/clr commit: f017777a97]
Generic event synchronize can be called from mempool implementation directly.
Change-Id: Id66ab9cdab486390df4dd405a4ac291eb0bb568f
[ROCm/clr commit: 140a075b6a]
The precompiled header files have hard coded paths in comments. Using the disable linemarker option(-P) will skip the generation of comments
Change-Id: Ifb134052996c343f5405e954784b4b2c286c36b1
[ROCm/clr commit: f9545675cb]
Certain build systems such as NMake seem to interpret backslashes as escapes.
Change-Id: Ifc04d9427148e83084efb1af94a1ce85cb2a6c4e
[ROCm/clr commit: cec5f0b704]
use AMD_COMGR_ACTION_COMPILE_SOURCE_TO_RELOCATABLE action
to compile source to realoc. Currently we have source->bc,
link->bc and bc->realoc. This new action replaces the
three steps with one.
Change-Id: I6ba551b8d04c7e06f41c4324026e4dcd2db1970f
[ROCm/clr commit: ea1487d84d]
Anusha GodavarthySurya
kjayapra-amd
Satyanvesh Dittakavi
Ioannis Assiouras
Saleel Kudchadker
Jaydeep Patel
Ilya Panfilov
German Andryeyev
jiabaxie
Rahul Manocha
Shilei Tian
Todd tiantuo Li
Sameer Sahasrabuddhe
Ajay
Jatin Chaudhary
Ranjith Ramakrishnan
Vikram
Lang Yu