Modify texture tests to pass on devices that don't support texture.
Add hipDeviceAttributeImageSupport to check image support in runtime
Change-Id: Ia89c494e651a6198a24448b59a91e046a9ebea38
[ROCm/hip commit: 5c8af57480]
Add the new extension to HIP for quering coherency mode.
The new enum hipMemRangeAttributeCoherencyMode can be used in
hipMemRangeGetAttribute(s), which will return one of the following
values:
hipMemRangeCoherencyModeFineGrain, hipMemRangeCoherencyModeCoarseGrain,
hipMemRangeCoherencyModeIndeterminate
Change-Id: I8717873c254888ea69facc1178d3682e8747c3a7
[ROCm/hip commit: 1f53fbea8f]
make hipIpcOpenEventHandle has the same behavour of cudaIpcOpenEventHandle.
Add Api usages.
Change-Id: I4248b2cebd3de156f9d5d427e1797da22fb964eb
[ROCm/hip commit: c053d60282]
Currently hip_prof_str.h does not include any header files. All HIP
declarations are being resolved by accident.
Pushing it to the end of hip_runtime_api.h will allow it to include the
definition of GLuint.
Change-Id: Ibb33b93cc7eab2028ba96f166bcb06f2f079feef
[ROCm/hip commit: d3b06fd5a6]
Enable NV printf DTests as many as possible.
Fix the bugs due to behavour difference between
Hip-Rocclr and Cuda.
Add hipLimitPrintfFifoSize.
Change-Id: I3fe6dbc35a7a140a9919df197b7885df83d28049
[ROCm/hip commit: 586165ebc2]
Add coarse grain memory extension. The new advice will allow HMM
to disable cache coherency policy to improve performance
Change-Id: I3c792d6a96896b983a7ffccddaa0ded06d183212
[ROCm/hip commit: c80955b569]
Temporarily disable __HIPCC_RTC__ in hip_vector_types.h
while the upstream clang headers are outdated on mainline.
Once upstream patch has landed in mainline, revert this
change. This is a workaround for hiprtc testing.
Change-Id: Ib2cf6023b71431bbfbe3c699076caa4f90f7170c
[ROCm/hip commit: 3899687b8d]
Let clock64() read s_memtime to prevent rolling over
Add wall_clock64() to read s_memrealtime
Change-Id: I706387355add75852c570be2656131ef99e8968f
[ROCm/hip commit: 7373112d74]
Windows may expect long and ulong to be 4 bytes, while
Linux expects 8 bytes. Instead, use uint64_t for
unsigned long, and unsigned long long, and use int64_t
for long and long long to be consistent.
Change-Id: I6ed1cdde43721bcaaab0245644d607b1adbf9884
[ROCm/hip commit: 2d6881e26b]
For hipRTC on Windows, add macro __HIPCC_RTC__ to allow
online compilation of with device functions excluding standard
C/C++ headers, system headers, and host HIP APIs.
Change-Id: I1d91f042baf1359856ec83ab7030dc58785e0334
[ROCm/hip commit: 811bc363c8]
On StreamBegincapture captures the parameters passed to APIs and respective node will be created and added to graph
All parameters are passed to STREAM_CAPTURE macro, it checks if stream in capture mode and redirects the call to the capture function and returns
Updated hipStream and hipEvent with capture parameters
Added handling for hipStreamBeginCapture & hipStreamEndCapture
Change-Id: Ic8926a7b4336c2cc81f0b3a9a224aa392c474134
[ROCm/hip commit: c35ba37287]
Selector indices are as follows (the upper 16-bits of the selector are not used): selector[0] = s<2:0> selector[1] = s<6:4> selector[2] = s<10:8> selector[3] = s<14:12>
Change-Id: Ibf76c6ec2374f1f5b9bba8bd9dbd73660f830eea
[ROCm/hip commit: 1cc65c48a2]
Change-Id: I5daeacd9dd5c6ce7f914d6e6e45dd41fb2a675a5
hipMemRangeGetAttributes was returning hipErrorInvalidValue due to improper
mapping of the arguments to cudaMemRangeGetAttributes.
[ROCm/hip commit: c81a7136d2]
The workaround is no longer needed as the compiler emits the macro itself.
Change-Id: I6a06e73353628bcea71f6bd23503ab6d8e42a29d
[ROCm/hip commit: bf6b451ae3]
Add concurrentManagedAccess detection in hipMallocManaged test.
Skip test when device doesn't support concurrentManagedAccess.
Change-Id: Ie54046feef3baba857a7068972ec1fc1a60c2dfd
[ROCm/hip commit: 60e2b1299c]