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]
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
Display queue base pointer in the log. This can be co-related with AQL
packets
Change-Id: I544f9b6db6ae01c85e57e4b3f0b3fffefcd7c2ed
[ROCm/clr commit: 0567c3b720]
HIP now has bfloat16 types via amd_hip_bf16.h in hipamd, hip_bf16.h in
hip folder.
Change-Id: Ic4d227936c5013e4b5d577725b8f55bebdc15499
[ROCm/clr commit: 43c811bdd2]
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]
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
- The correlation_id had random junk values which we were inserting in
the dispatch AQL packet even when no profiler was attached but if we had
a valid timestamp.
- Also make sure we dont even write the reserved2 field in the AQL
packet if no profiler attached.
Change-Id: Icdb7493198c1bb5e2d786a97e027288660854cd7
[ROCm/clr commit: 9a6ddae7b2]
- The correlation_id had random junk values which we were inserting in
the dispatch AQL packet even when no profiler was attached but if we had
a valid timestamp.
- Also make sure we dont even write the reserved2 field in the AQL
packet if no profiler attached.
Change-Id: Icdb7493198c1bb5e2d786a97e027288660854cd7
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]
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
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]
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
Generic event synchronize can be called from mempool implementation directly.
Change-Id: Id66ab9cdab486390df4dd405a4ac291eb0bb568f
[ROCm/clr commit: 140a075b6a]
Satyanvesh Dittakavi
Ioannis Assiouras
Rahul Manocha
Saleel Kudchadker
Anusha GodavarthySurya
Jatin Chaudhary
Alex Xie
Shilei Tian
Todd tiantuo Li
German Andryeyev
Sameer Sahasrabuddhe
cadolphe
Ajay