This change makes HSAIL usage similar to that of Comgr. By default, the
runtime will statically link against it, however if HSAIL_DYN_DLL is
defined, then the runtime will try to dynamically load HSAIL.
Currently stick to statically linking to HSAIL. In a feature patch the
dynamic loading behaviour will be enabled.
Change-Id: I6a78a4375975cf847f236b200404c8cf941d012b
[ROCm/clr commit: c7b50bb890]
In adition to removing the HSAIL logic from the ROCm backend, guard all
of the HSAIL includes in the common layer behind the WITH_COMPILER_LIB
define. This is to avoid including HSAIL headers when building with
no support for it.
In common logic replace the use of the aclType enum with the new
Program::file_type_t enum. This is essentially a local copy of the HSAIL
enum to avoid including any HSAIL headers.
Change-Id: Ica0651d1b29dfccc255cc584eb82a5cb35e1b520
[ROCm/clr commit: cbeb372e46]
This is part 2 of the change. This is for PAL backend.
The parent buffer sometimes has newer data than the sub buffer or image.
We always need to copy the data into copybuffer in pitch workaround.
Tests:
clinfo
Conformance tests: all images test, info, API, basic.
Internal runtime tests
Change-Id: I97d876ac75b240e69b48244be4c9e522db24f8ac
[ROCm/clr commit: 0de4b2962c]
This is part 2 of the code change for PAL.
The copy image workaround could be recursively used by ROCclr blit kernel.
Avoid such situation by using stack variable.
Tests:
clinfo.
Conformance tests - basic, API, info, and all images tests.
Internal runtime tests - all passed.
Change-Id: I3c822e55398cdf35c2c4a46ed9fc20fbee7cc908
[ROCm/clr commit: 090cf6c6d3]
Since the majority of the Hostcall implementation now sits in the
commmon layer, the PAL backend simply just needs to invoke it. One thing
that is missing though is HSA signal support.
The newly added pal::Signal class is a light emulaion of what HSA
signals provide. The current implementation is just enough to get
Hostcall working, but it can be expanded in the future if needed to
fully emulate HSA signals.
The major difference for now between PAL and ROCm hostcall
implemenations is that PAL doesn't support blocking signals. This will
be enabled in the near future. For now use active wait for PAL.
Change-Id: I746557354ab9d71a7d4a31f9320fcc2fee5aee7f
[ROCm/clr commit: 99e8ac55cd]
Enabling DebugVMID requires a certain sequence in
PAL initialization. StartLateDeviceInit() must be called before
CommitSettingsAndInit().
Change-Id: I7385a8cc89e7a8ad97a6b56ad6acbd2cf2f29728
[ROCm/clr commit: dee99ca807]
Since the allocation can be a suballocation, we should print both the
VA range for the allocation and the underlying memory object.
Change-Id: Ic9c707bbb78113b366d1b2c688e6fd33bdc8fd94
[ROCm/clr commit: 9e8a2f3266]
The settings need to be populated ASAP, otherwise the dummy context is
not created properly.
Change-Id: Iede0066308bb601dc68164e894775a646a0372f1
[ROCm/clr commit: 263173914f]
This change unifies the hostcall implementation for all the backends,
by pushing the common logic to the device layer. This is done by
replacing the use of hsa_signal_t with device::Signal (a light wrapper
around it).
Change-Id: I7b6fca7930b5a0b199da5d85e2e048354cc04e7b
[ROCm/clr commit: 671778bdd3]
The existing workgroup calculation logic for GWS initialization is
incorrect. It tries to add together workgroups across dimensions,
leading to major under-count in 2D and 3D kernels. An (x,y,z) kernel
uses x * y * z blocks, not x + y + z.
In addition, the previous logic was incorrect for the case of launching
a single-threaded kernel. It calculated 0 workgroups, leading to
initializing GWS to -1.
Change-Id: I1bb20a0d5b6e0cc10ac55901c28d8f93aac61c09
[ROCm/clr commit: 54d1d69c0a]
Remove targetId_, gfxipMajor_, gfxipMinor_ and gfxipStepping_ from
device::Info as they are now available in device::Isa.
Change-Id: I381b1d4798ebf50655740e004a01ac7f86dbf668
[ROCm/clr commit: c2308216dd]
- Correct GSL path to report targets using the TargetID syntax.
- Correct GSL path to check compatibility of code objects when
loading.
- Add concept of an device isa and create a registery used by ROCm,
PAL and GSL.
- Support XNACK and SRAMECC target features consistently for PAL and ROCm.
- Correct logic for NullDevices and asserts to avoid memory coruption.
- Allow all NullDevices to be created for HIP.
- Numerous other code improvements.
Change-Id: I40abf3d2b22249c1492d1af5919665f8184f4e0e
[ROCm/clr commit: c7e8d91e14]
Use strncpy instead of strcpy to ensure the arrays will not be
overflowered. Only copy one less than size of char array to leave a
NUL character at the end even if the copy is truncated provided the
original object is zeroed memory.
Change-Id: I00f7679630cf28dcb9a51cb0aba2810a4f4c72b9
[ROCm/clr commit: e0448535a3]
For roc devices create hsa_agent_t handles using a pointer to the
device::Device. This ensures each device has a different hsa_agent_t
handle. This may be necessary to ensure the loader symbol lookup will
search only symbols for the correct device.
Change-Id: Iee6dd40d68bf22a02ce8c75cbe5ac8f5a0d9e418
[ROCm/clr commit: 76c371d78a]
roc:Settings and pal::Settings are derivations. Allocate them as their
derived class then assign that to the base class member to avoid the
need for a static_cast.
Use device::settings to access the Settings consistently.
Change-Id: I0f85157962fbf6fed176da0caf83b723bcbe1452
[ROCm/clr commit: 583dddf6b6]
- Use std::unique_ptr to levarage RAII for managing the allocation in
the presence of errors.
Change-Id: I55de515bbf72938e1dd09731c5e51f538cf9d34a
[ROCm/clr commit: 682774a09d]
- Add assertions to enforce that objects are of the correct kind and
have been allocated.
- Make destructors check if objects have been allocated before
deleting.
- Operations that require a non-NullDevice return failure if given a
NullDevice.
- Use static_cast rather than reinterpret_cast when cohersing from a
base class to a derived class.
Change-Id: I02ee0ea9d7982fd7ca29d49c9b02cfae111b7127
[ROCm/clr commit: e5431676d4]
Rename functions that access devices to reflect the derived device
they return. This includes the base device::Device and the derived
gpu/pal/roc device classes in both NullDevice and Device forms. Change
to use the least derived versions to clarify what operations will be
available.
Change-Id: I1abb6bfed7efa24852bc8d0d49acaea357d8b5d0
[ROCm/clr commit: 001fd66cac]
On behalf of Tony Tye. The bootleg passes CQE Baffin/Ellesmere test.
Change-Id: I4c21d21b3aaba360682ef15b8a4dda239f8af276
[ROCm/clr commit: d4316141b7]
PAL doesn't perform chunking for system memory allocations, hence we
should fall back to using pinned memory for mapping large buffers.
Change-Id: I1b472616b72d12ed0105fb65532acacdb98ac7b3
[ROCm/clr commit: b4e212a0f9]
Vladislav Sytchenko
Julia Jiang
Jason Tang
Sourabh Betigeri
Alex Xie
pghafari
German Andryeyev
Tao Sang
Ravi C Akkenapally
kjayapra-amd
Joseph Greathouse
Tony Tye