Support hipLaunchCooperativeKernelMultiDevice()
- Add validation logic for MGPU launches to pass a cuda test
Change-Id: Iccca7fde43493fc3bc6685512d39202271ae3e92
[ROCm/clr commit: 8be723e199]
Support hipLaunchCooperativeKernelMultiDevice()
- Add hipCooperativeLaunchMultiDeviceNoPreSync and
hipCooperativeLaunchMultiDeviceNoPostSync support to pass a cuda test
Change-Id: If518f11ef2636a2235e5df9e77f879d8ced68102
[ROCm/clr commit: 74e98ea447]
These fixes address regressions caused by http://gerrit-git.amd.com/c/compute/ec/hip/+/337601
Currently we're converting a 1D offset into a 3D offset, which doesn't make much sense once you consider the fact that this offset is relative to a different origin than our current 3D offset.
I traced through our blit kernels in VDI - the copy buffer rect path is able to handle immediate offsets in the 3D buffer via the amd::BufferRect::start_ parameter.
Instead of adjusting the offset, simply adjust the start of the region.
Change-Id: Ic8797a2c8ac0ad106f246f61ff06ca1ca03d3058
[ROCm/clr commit: a3613cc6da]
If the code object is embedded in an already mapped file, and the
lifetime of the mapped file exceeds the lifetime of the executable,
we do not need to make a copy of the binary.
This allows the ROCR to present the code object URI as
file:///path/to/file#offset=X&size=Y.
[ROCm/clr commit: 67830996a9]
libc++ defines fma as template function for auto promotion of mixed-type
arguments. libc++ does not handle _Float16 as _Float16 is not a supported
type by C++ standard. As such, it is unlikely we can commit our fix for
_Float16 to libc++ trunk.
Therefore we handle _Float16 with a template specialization of
__numeric_type in HIP headers.
Change-Id: If01960a657ebf1a7a67463cdcf66fab7458dff3c
[ROCm/clr commit: 6f439f0232]
Tests that check POSIX specifiers with a single thread:
- hipPrintfSpecifiers.cpp : all conversion specifiers
- hipPrintfFlags.cpp : common flags that modify conversions
- hipPrintfAltForms.cpp : alternate forms ('#')
- hipPrintfStar.cpp : additional arguments ('*')
- hipPrintfWidthPrecision.cpp : floating point details
Tests that check functionality on top of hostcall
- hipPrintfBasic.cpp : divergent calls, series of calls, return value, etc
- hipPrintfManyWaves.cpp : many waves printing together
- hipPrintfManyDevices.cpp : many waves on many devices
Change-Id: I35e069f4c542f896999239996dc89eda0faad7b8
[ROCm/clr commit: 01d4117789]
1. Enable pitch workaround
2. When we use copy image, we don't need to create the custom pitch image
3. wrtBackImageBuffer_ stores device memory object, not amd image object.
Tests:
conformance kernel read / write test pass with this code change.
Change-Id: I7dca3127adde6ac83e78dd270a2256ebed55c60d
[ROCm/clr commit: 43b9863e17]
- Make sure only one GPU barrier is issued per dispatch
when memory tracking is disabled
Change-Id: I974569ab42a8835304a2930eef87b561a3750327
[ROCm/clr commit: 481cecec78]
This adds the missing compilation flags to hip::device so it can compile with hip-clang compiler.
Change-Id: Ie2b30ea606bfca385a0e84ae03ee0a8d828ad16a
[ROCm/clr commit: 631f82ab82]
Even though the runtime and driver texture object API is one to one, the structs used by these APIs are not. See hipResourceDesc vs HIP_RESOURCE_DESC differences.
These differences are not trivial and most likely won't be able to handled by hipify, so we need new API entry points.
Change-Id: Id4bcb1ad0ae15378dbdb5a2ed07e5ea30f320082
[ROCm/clr commit: a09fadecf2]
Don't error when querying the number of devices if there are no devices present in the system.
We should just return 0 for the number of devices in this case and let the application handle this situation.
Change-Id: I20614ade5e649f3ce9ddd970d4b38bfe296f6cdb
[ROCm/clr commit: 2a223ecec6]
Payam
German Andryeyev
Vladislav Sytchenko
Michael LIAO
satyanveshd
Rahul Garg
Sarbojit2019
lmoriche
Jatin Chaudhary
ansurya
Yaxun (Sam) Liu
Sameer Sahasrabuddhe
Chauncey Hui
eshcherb
Alex Xie
Christophe Paquot
Saleel Kudchadker
Aaron En Ye Shi
kjayapra-amd
Paul Fultz II