- When doing device/stream sync, we can submit a handler which may
introduce some host side delays. Use DEBUG_CLR_BATCH_CPU_SYNC_SIZE to
batch commands for host wait. Default for HIP is 8 commands.
- Investigation is underway in ROCr but need to address this for now in
HIP runtime.
[ROCm/clr commit: 9b045922a8]
Init and fini kernel needs to be launched when we load and unload code object. Avoid looping through all kernels within a code object just to run the init and fini kernels. Compiler currently only generates 1 init and fini kernel.
[ROCm/clr commit: cd46294b31]
Remove duplicated compiler symbols from hip-rt. hip-rt should use symbols such as EF_AMDGPU_MACH_AMDGCN_XXX and
ELFABIVERSION_AMDGPU_HSA_VX defined in compiler header.
[ROCm/clr commit: b15c1657b8]
Clarify some VGPRs terms description.
Fix some wrong query logics of availableVGPRs_ and
availableRegistersPerCU_ in device info.
Add hipDeviceAttributeMaxAvailableVgprsPerThread
attribute query.
Remove hardcoding of following
info_.vgprAllocGranularity_
info_.vgprsPerSimd_
[ROCm/clr commit: 397f303d97]
- Currently runtime just uses the local agent as it did not check for
IPCShared()
- With this fix we query hsa_amd_pointer_info and get the right agent
for the memory to pass it to the HSA copy api
[ROCm/clr commit: 46d766e4e2]
* SWDEV-539414 - Return error status from runtime handler when HIP_SKIP_ABORT_ON_GPU_ERROR is false
* SWDEV-539414 - default handler when GPU core file is generated
* SWDEV-540576 - Abort if user request a core dump
Change-Id: I9e2c640acf559880bd13641de9103e660ef822a3
---------
Co-authored-by: Assiouras, Ioannis <Ioannis.Assiouras@amd.com>
Co-authored-by: agunashe <ajay.gunashekar@amd.com>
[ROCm/clr commit: 9c1bff0ae7]
* 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]
- ROCr now reports preferred engine for copy status. We can leverage
this for max bandwidth for inter-GPU copies
- Cleanup logging
[ROCm/clr commit: 1b0ea080e4]
Fini kernel is executed during the invocation of amd::Program destructor,
but the dispatch logic can retain/release the reference counter and
cause double free. Avoid double free with an extra retain() call
[ROCm/clr commit: bddb8f14d1]
The split path for blit kernels are no longer necessary, since the new blit kernels
don't use the copy size as the global workload
[ROCm/clr commit: da198ac5b2]
Since the sub-buffer(virtual memory that is mapped to device memory) is associated with device memory, it should utilize the device context instead of the host context. The original implementation caused hipMemcpyPeer to not take the P2P path, as the memory object was treated as host memory.
[ROCm/clr commit: a7492c516d]
Fix incorrect edits done when porting the 2nd level trap handler from
the hsa-runtime.
Change-Id: I7bc5160be47b8f669efe05c4d194bc3c47fc0661
[ROCm/clr commit: c35e9643ec]
Convention is to always link against .so.* at runtime.
Having it link against .so will break on systems that package
the .so files in their dev/devel package.
This issue was found when building ROCm 6.4 for Fedora.
Commiting on behalf of GitHub user Mystro256
[ROCm/clr commit: 6b12154583]
GunaShekar, Ajay
Kudchadker, Saleel
Xie, Pengda
Betigeri, Sourabh
Manocha, Rahul
Sang, Tao
Xie, Jiabao(Jimbo)
Belton-Schure, Aidan
Trinh, Ethan
Guan, Zichuan
Lin, Qun
Patel, Jaydeepkumar
Brzak, Branislav
Jayaprakash, Karthik
Harrymanoharan, Jessey
Andryeyev, German
Dittakavi, Satyanvesh
Assiouras, Ioannis
Arandjelovic, Marko
Six, Lancelot
Xie, AlexBin
Lambert, Jacob
Zhang, Victor