Add VmHeapArray class to reduce the pressure on VA reservation, since
multiple memory pools can be active at the same time.
[ROCm/clr commit: e974f7fde1]
Needs further debugging but for now can test the change
Need to verify if this fixes all the below issues-
SWDEV-512754, SWDEV-511675, SWDEV-511055, SWDEV-504085, SWDEV-499503
Also verify original issues
SWDEV-471863, SWDEV-490991
Change-Id: Ic845f851de1b98e8ed9aa0f07afddec3858119e9
[ROCm/clr commit: f1b8ee7b7f]
- For D2H cases avoid passing dependent signals to SDMA, the signals
take a while to resolve on SDMA engine
Change-Id: I569635228af977847f201c82ca897002f8f2f4a8
[ROCm/clr commit: 78d0ff2dbc]
- This change tries to save extra synchronization packets we may insert
as we didnt track the completion signals for every command. We track
the current enqueued command until it exits the enqueue stage. We also
record the exit scope to know if we flushed the caches
- Handle correct release scopes and store completion signal as HW events
- Use a new finishCommand implementation to only wait for the command
passed as the argument
Change-Id: Ie4350c5dd24f5d48dfa6ccbabd892f0544caadcc
[ROCm/clr commit: e03e4f3b5d]
Since hipMemMap can be called for multiple device handles on the same virtual memory, the same is true for hipMemUnmap, meaning that virtual memory can be "partially unmapped".
This means that the unmap function can be called for a specific part of the reserved address, meaning that only the designated subbuffer should be released. If unmap is called on the entire reserved memory, then all subbuffers should be released.
The main point is that for every hsa_amd_vmem_map, there should be a corresponding hsa_amd_vmem_unmap. Otherwise, if entire memory is unmapped by a single unmap call, then HSA will report the memory as "in use" if an attempt is made to delete it.
Change-Id: I039308eafb820decfb1c09f60347f26cdad1a362
[ROCm/clr commit: 3ec1d2d2f1]
- Use getBuffer/releaseBuffer in BlitManager
- Cleanup XferBuffer as we use ManagedBuffer for both reads/writes
Change-Id: I2661b85dd012763b17a38a743fec1b1d79125f67
[ROCm/clr commit: 37d606d193]
- If any kernel uses device heap, the launch needs to be preceeded by an
init kernel, Save on the extra barrier packet launch/flush between the
init heap kernel and user kernel
Change-Id: I8ebc6246188200e5f673dc464bc76a53bcb8b7c6
[ROCm/clr commit: ca530c660b]
- Add custom compare to the map of queues, which will help with
the round-robin selection
Change-Id: Ie67a820bfb1a5b484a1b3edced967eed94228bb8
[ROCm/clr commit: ba8e740be4]
Add initial implementation of virtual memory heap with
dynamic virtual memory mapping support for memory pools.
DEBUG_HIP_MEM_POOL_VMHEAP controls the new method.
Change-Id: I8dc5be2e0f34ab472f1800f43bb6243639a5e500
[ROCm/clr commit: 296dce5570]
Compute doesn't support IB chaining, but RGP may collect
perf counters, which require more space in CB.
Increase CB size if RGP is enabled.
Change-Id: Iaa0a620ead8541a679b0dfe5e5711af5afdba545
[ROCm/clr commit: 63cf3057ba]
There are 2 functional changes to this patch:
* Use GPU timing for internal markers for HIP.
* Measure CPU time closer to GPU timer, to reduce delta between GPU/CPU timestamp measurements.
There are some smaller non-functional updates:
* waifForFence -> waitForFence typo
* Remove unused drmProfiling
Change-Id: I4c5fa600a842ab60e454888779edcac8449a902a
[ROCm/clr commit: 179801a750]
- Fix regression for D2H pinned copies which adds systemscope release.
- Skip cpu wait for D2H unpinned copies as we can pass the signal of the
barrier to rocr copy.
- Fix an old bug in sdmaEngineRetainCount_ logic
- Improve logging
Change-Id: If074bddb05564b15949b0d5f9bf12acd3692174e
[ROCm/clr commit: 4c95ee5e1e]
BatchMemop should be positioned before the image support kernels
because the total number of kernels is determined by BlitLinearTotal,
when there is no image support on the device.
Change-Id: I8e53caf744ba54259ac04bad1762eef21806f3f2
[ROCm/clr commit: 3e01da3dac]
The cl_khr_depth_images associated macro definition is defined twice in
the compiler: in opencl-c.h and automatically by the compiler deduced
from the cl-ext list. These two co-exist and there is no need to remove
cl_khr_depth_images from the cl-ext list.
If we remove cl_khr_depth_images from the cl-ext list, and we do not
include opencl-c.h the macro is not defined.
This fixes conformance test ./test_compiler compiler_defines_for_extensions
when using Comgr with -include opencl-c-base.h -fdeclare-opencl-builtins
without including opencl-c.h.
Before we got the error `ERROR: Supported extension cl_khr_depth_images
not defined in kernel`
This change is needed to eventually get rid of the opencl-c.pch that is embedded in comgr, and that makes implementing a compilation cache in comgr hard.
Change-Id: I76497874ebe7163966420d4ac23a0788b93a36fd
[ROCm/clr commit: 8c9e6d0fa5]
- Resolve signal dependencies for barrier value packet if there are > 1
depenent signals. Barrier Value packet accounts for only 1 dep signal
- Better log
Change-Id: Ia506ad5d80b91d598f92e7b539f41756e9b4b64b
[ROCm/clr commit: 2d450e8b06]
The logic can analyze the AQL queue state and
find a failed AQL packet with the kernel's name
Change-Id: I1a478fa2c25462cd07a194784958bdf22454b897
[ROCm/clr commit: ea0b092af8]
This change fixes random segfaults in graph tests that
are seen after the change make internal callbacks non-blocking.
The callback thread that decreases the GraphExec ref count
may now run after the runtime shutdown. This can cause a segfault
because the hip::device that is accessed in GraphExec destructor
is already destroyed during runtime shutdown. This patch ensures
that the hip::device object stays alive until after the
callback thread completes.
Change-Id: I75a6ac01f27a0b2250bbd10ed389ebfb322927af
[ROCm/clr commit: 21c223f8df]
Adds UberTrace support for pre-dispatch markers and barrier begin/end markers.
Moves shared definitions out of palgpuopen.hpp into shared header
palcapturemgr.hpp.
Change-Id: I9f464c689e7ff12c54eca043fc1ad65e1836a64f
[ROCm/clr commit: 541c449ce2]
- When using shader copy, make sure to use release scope for the AQL
packet. This is a potential bug but is hidden as hipMemcpyAsync always
needs synchronization(which inserts a barrier with release scope). For
hipMemcpy we use a barrier packet to make sure its blocking. Eitherways
a barrier gets always used and hides in some ways a potential bug.
Change-Id: I57fb7f769c3179e76d712471c0905104c801d7ba
[ROCm/clr commit: c9dd95bf6c]
Patel, Jaydeepkumar
Andryeyev, German
MartinezFernandez, Juan
GunaShekar, Ajay
Arandjelovic, Marko
Saleel Kudchadker
Pengda Xie
Branislav Brzak
Rahul Manocha
Jacob Lambert
Julia Jiang
kjayapra-amd
Vladana Stojiljkovic
Aidan Belton-Schure
victzhan
Ioannis Assiouras
taosang2
Juan Manuel Martinez Caamaño
Jimbo Xie
Jatin Chaudhary
Daniel Livingston
Anusha GodavarthySurya
Evgenii Averin
Sourabh Betigeri