The build of ROCR backend will be enabled by default in Windows.
It requires the dll loader until ROCR dll will be always available in Windows for any configuration.
- Refactor deviceLocalAlloc arguments
- Refactor hostAlloc code, have cleaner interface
- Kern args buffer need to have execute flag set as CP enforces this on
certain newer HW.
* Add hipHostMalloc() new flag hipHostMallocUncached which will force to allocate pinned
host memory on extended fine grained system memory pool.
* Add hipHostAlloc() new flag hipHostAllocUncached which will force to allocate pinned
host memory on extended fine grained system memory pool.
* Add hipHostRegister() new flag hipHostRegisterUncached which will force to map
host memory onto extended fine grained system momory pool.
[ROCm/clr commit: a7d7687b8f]
hsa_amd_ipc_memory_detach is called with an invalid mapped pointer.
Changed to pass the svm pointer of the owner memory instead.
Change-Id: I8203c6e2d718efb8ca3b028309bc78caff8d4c7d
[ROCm/clr commit: 5bb30d7718]
hsa_amd_memory_lock_to_pool() and hsa_amd_memory_unlock()
should be called balanced.
Change-Id: I8b1549861bff752aabbb6399d717d1e346079a38
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
[ROCm/clr commit: cc29df873a]
Recent changes disabled system memory allocation
in the abstraciton layer. That requires memory
allocation/destruction in ROCR. Add destruction logic.
Change-Id: I68fe6b0a620ca743fe5850052ea0efa8bb7931c2
[ROCm/clr commit: a6d480e098]
Add a view bit to avoid original resource destruction when parent
dependency doesn't exist with the image view cache
Change-Id: I8277afd575af8f29951c5d1a9f7d94d784251657
[ROCm/clr commit: b49e8e78e1]
Make sure parent_ field is cleared for the internal image views.
The internal image views don't require dependencies tracking.
The issue appeard only when Navi10 pitch workaround was enabled.
Change-Id: I376d212750085a9391f8c32fc2979dcb5d93c89c
[ROCm/clr commit: 6b89980fb2]
Blit manager requires an image view to reduce the amount
of copy kernels. Creation/destruction of a view in ROCr is
an expensive operation. Thus, runtime can cache views for fast access.
Change-Id: Ia67d775b481cc8326d91215ca22d4a73c1dddb59
[ROCm/clr commit: d29755452b]
let ROCr and addrlib decided whether a pitch is supported.
Then, check if we uses workaround.
Also improve image performance for Navi 1x in some cases.
Change-Id: If8bda46648b23c1dcfa26608ca3bb9cd89fef430
[ROCm/clr commit: b961d4a970]
- Make IPC interfaces generic between devices and rely on the IPC buffer
for attach/detach logic
Change-Id: Id3c18d122030329b7ee532bbb6317de9dd6a0bbe
[ROCm/clr commit: 9aa6f25f1c]
Rename VK interop to ExternalMemory object, since it should handle
DX interops also
Change-Id: I536ec46d3e53ece35234a2e29030393ad411b96d
[ROCm/clr commit: 3e5803c4c0]
Remove amdgpu-pro interface for persistent memory,
used in Liquidflash
Change-Id: I7d1720ad0875a62ebb2d7f96cba39601d560a5df
[ROCm/clr commit: 6dad2fc306]
For OCL, keep original control logic
FOr HIP, keep the fix for SWDEV-338781
Change-Id: I89de8d1e73cd103b3b4f62206eed72d45695dd6e
[ROCm/clr commit: 0a43f6bff3]
German Andryeyev
SaleelK
Ajay GunaShekar
Karthik Jayaprakash
Danylo Lytovchenko
Andryeyev, German
Manocha, Rahul
Betigeri, Sourabh
Sang, Tao
Jayaprakash, Karthik
Ioannis Assiouras
Jaydeep Patel
Lang Yu
Alex Xie
Ajay
Anusha GodavarthySurya
Julia Jiang
haoyuan2