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]
- 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]
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]
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]
This reverts commit 1b05247a03.
Reason for revert: Waiting for staging results before finally merging it.
Change-Id: Iaabb510325f50147f368108e98531291217627c0
[ROCm/clr commit: 77be355fd9]
Extension allows to execute the kernels without a wait barrier and L1
invalidation.
Change-Id: I96c485204303f54a0240b93134f4560673e4bd17
[ROCm/clr commit: 13c6f56ca9]
Dont track the status of fence_dirty_ flag on the host, instead clear it
when we submit a barrier on the respective stream.
Change-Id: I4d98dbf20c81379c9c5da9f5b67629a8f9f6dfcd
[ROCm/clr commit: 0b0df605d4]
- Add API table versioning defines to hip_api_trace.hpp
- Add rocprofiler-register implementation in hip_api_trace.cpp
- created ToolInit implementation
- moved some local functions into anonymous namespace
- renamed some function to be overloads
- made most of the initialization code templated (reduced code duplication)
- enforce ABI
- Updated hipamd/src/CMakeLists.txt
- find rocprofiler-register package (enabled by default but not required)
- Address review comments
- simplify size calculation for dispatch table
- remove setting .size field in GetDispatchTableImpl
- Fix windows build
- Do not enforce ABI on Windows
Change-Id: I08766e8a083528a1236996274bf4522e0e8a1b9f
[ROCm/clr commit: 0f1fdc7794]
Use only 16 workgroups for compute P2P copies.
That should be enough to utilize XGMI bandwidth.
Change-Id: I60dfe019279bb95f93c8874244c1738aad1896d8
[ROCm/clr commit: 31101c6219]
The following builtins from the CUDA spec are implemented:
- __all_sync, __any_sync, __ballot_sync and __activemask
- __match_any_sync and __match_all_sync
- __shfl_sync, __shfl_up_sync, __shfl_down_sync, and __shfl_xor_sync
The following builtins are NOT implemented, pending support in the compiler:
- __reduce_add_sync, __reduce_min_sync, __reduce_max_sync
- __reduce_and_sync, __reduce_or_sync, __reduce_xor_sync
Change-Id: I07dedbbfe5449f4b5c9b040bed59f5603ccec8c3
[ROCm/clr commit: c5ab5680b4]
Jatin Chaudhary
Alex Xie
Ioannis Assiouras
Shilei Tian
Saleel Kudchadker
Todd tiantuo Li
German Andryeyev
Sameer Sahasrabuddhe
cadolphe
Satyanvesh Dittakavi
Ajay
Anusha GodavarthySurya
Ranjith Ramakrishnan
Vikram
kjayapra-amd
Lang Yu
Jaydeepkumar Patel
Rahul Manocha
pghafari
Maneesh Gupta
Jonathan R. Madsen
sdashmiz