If AMD event contains a reference to a HW event, then runtime
could check/wait for HW event. CPU status update will occur later
after HSA signal callback, but it's not important for the result.
Change-Id: I591391a953bbdba6a25ac07e2cd98aeb17cd4596
[ROCm/clr commit: 85c70a7495]
Revert back to using the Raven (gfx902) target ID for Raven 2 (gfx909).
This is due to the HSAIL compiler not supporting gfx909.
In theory there should be no issue with running Raven isa on Raven 2.
Change-Id: I425edebc99075799eda5522fad231b8fb3184873
[ROCm/clr commit: 0b1481d4f1]
For DD, send a NOP packet so that we leverage the handler to indicate
completion.
Change-Id: Ie57ea0124a8497d39cc49da1c4575c2cd86b9319
[ROCm/clr commit: 9d0846e732]
Switch HSA_AMD_SVM_ATTRIB_READ_ONLY to
HSA_AMD_SVM_ATTRIB_READ_MOSTLY to match Cuda. The new attribute
was just exposed in ROCr/KFD.
Change-Id: I2ee522d33c347ba52a4e272d2cd7f67960490cf7
[ROCm/clr commit: 89b69638d1]
All KMD/asic_reg/UGL headers are located under the drivers folder. No
need for the AMD_UGL_PATH variable as it essentially is
${AMD_DRIVERS_PATH}/ugl.
Change-Id: I070d737d50f2096493b3e75ef9b9e824cb19d048
[ROCm/clr commit: 1423c1db64]
Add an extension to memory advise to disable cache coherency for
better performance
Change-Id: I283703d81d9c36ddfa2c8fffa15eef60e2195056
[ROCm/clr commit: a9a1e21445]
With HIP API callback runtime has to stall the queue until the
callback is done. Rocclr will introduce SW blocking HSA signal,
which will be released after the callback is done.
Change-Id: I6411f3efab31b468e3b87ebb5c8d155e116b613d
[ROCm/clr commit: d93df7037c]
This change refactors the current ROCclr cmake build to accomodate a
more modular approach. This allows easier support for multiple compiler
and/or multiple runtime backends.
Currently supported compilers:
HSAIL - enabled by ROCCLR_ENABLE_HSAIL (defaults to OFF)
LC - enabled by ROCCLR_ENABLE_LC (defaults to ON)
Currently supported runtimes:
HSA - enabled by ROCCLR_ENABLE_HSA (defaults to ON)
PAL - enabled by ROCCLR_ENABLE_PAL (defaults to OFF)
Any configuration is supported as long as at least one compiler and one
runtime is enabled.
Since ROCclr clients can configure it differently, one cannot reuse the
same ROCclr build artifacts between different clients. To assure this,
this patch assumes that ROCclr will be built as part of the clients
project.
Change-Id: Id4a5c43634296802b8ae87d1ad5984968391ccaf
[ROCm/clr commit: 7f0c18457d]
Terse static_assert is only available starting with c++17. Add the
message argument since HIP is not compiled using c++17.
Change-Id: I77bc7ddb635e50ac3e6744d73c8751dc8299087e
[ROCm/clr commit: 73ee1afb17]
If the texture object was created from an array, then the array owns
the image SRD. Otherwise, if the texture object is a view, or was
created from a buffer, then it owns the image SRD.
The texture object always owns the sampler SRD.
Change-Id: Id88360c23b2b82418c8c3ae2dd569f427574d420
[ROCm/clr commit: 88f6f3d581]
This reverts commit de94f93e57.
Reason for revert: Copyright year to be updated only when a file is getting modified in that year.
Change-Id: Id1ece634dce7e67da9f3f6e10103ef6214e72dab
[ROCm/clr commit: 91df8fc0e9]
make hipIpcOpenEventHandle has the same behavour of cudaIpcOpenEventHandle.
Change-Id: I3fe6dbc35a7b14ba9119df297b7885df83d28149
[ROCm/clr commit: c87a352288]
LINK_LANGUAGE support has some issue in CMake versions from 3.18.0 to
3.19.8 when complex libs' dependence exists. Jump to a known CMake
version 3.20.0 where the issue is fixed.
Change-Id: I3fe6dbc35a7b14baa210df297b7885df83d28178
[ROCm/clr commit: 3452a09975]
DISABLE_DIRECT_DISPATCH flag will control compilation.
Default is OFF.
Change-Id: I7d4207b8a79f5e3eb61440c5fbe5034c6ce75cce
[ROCm/clr commit: a852370a25]
Replace return value of hipPointerGetAttributes() on NV from
hipErrorUnknown to hipErrorInvalidValue if memory has been freed.
Change-Id: I3fe6dbc35a7a14aa9109df297b7885df83d28149
[ROCm/clr commit: 203c4b9b35]
Make hipModuleGetGlobal match cuModuleGetGlobal behavour.
That is, if one of the first two parameters is nullptr, ignore it.
Change-Id: I3fe6dbc35a7b14aa9119df297b7885df83d28048
[ROCm/clr commit: b58355b065]
Use continue instead of break to make sure we process the
whole hip_runtime_api.h file.
Change-Id: Ied2a8df69ed9eb1dc04d6b2d0d7b117ce2a2b6b3
[ROCm/clr commit: 9a510f1cf1]
Christophe Paquot
German Andryeyev
Chauncey Hui
Vladislav Sytchenko
Saleel Kudchadker
kjayapra-amd
cjatin
anusha GodavarthySurya
Payam
Satyanvesh Dittakavi
Julia Jiang
Laurent Morichetti
Ammar ELWazir
Sourabh Betigeri
Rahul Garg
pghafari
Tao Sang
Sarbojit Sarkar