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]
HIP headers use few structure names as X, Y, and Z. This causes
compilation issues when the apps use similar names as macros.
Renamed the struct names to use reserved names such as
__X, __Y and __Z
Change-Id: I59416c3734f274e853c87d4856b7e616f6cee5f5
[ROCm/hip commit: b26ef8522e]
Add device_id_ in hip::event to match cuda behaviour in
hipEventQuery() and hipEventRecord().
Enable hipEventElapsedTime test on AMD platform.
Workarround sporadic crash of hipEventIpc test due to
some bug of event ipc.
Add missing hipEventDestroy() in some event tests.
Fix some logic code errors.
Fix typo in comment.
Change-Id: I9ec74c475161b3e31df48d193449023e921f2924
[ROCm/hip commit: 38b0c952a6]
This reverts commit f0a9c129a0.
Reverting since this is dependent on a device libs change which is not yet in mainline.
Change-Id: I094781b868f39995d1eecb41488c1a1a0147b787
[ROCm/hip commit: 7998429c21]
The device library now provides functions to specify the host stderr
stream in a hostcall printf message. This change implements an
assert() macro which can construct such a message. The end result is
that assertions on the device are now correctly printed on the host
stderr instead of stdout.
Change-Id: I85ab8f7848bcf28303cb8dbb8a798bc6aece7d75
[ROCm/hip commit: 96be8a7b73]
Define the following for workarround of rocThrust building failure,
HIP_INCLUDE_HIP_HCC_DETAIL_DRIVER_TYPES_H
HIP_INCLUDE_HIP_HCC_DETAIL_HOST_DEFINES_H
Change-Id: I1ae48677eafd749d6c25bca204c1724b026be22f
[ROCm/hip commit: ef8110da22]
This particular cleanup is limited to just two functions defined in
the HIP headers.
Change-Id: Ib529685265f2fda90e009b24e7e756e0cf363012
[ROCm/hip commit: 05cc647684]
Aaron En Ye Shi
pghafari
Anusha Godavarthy Surya
kjayapra-amd
Satyanvesh Dittakavi
Yaxun (Sam) Liu
Tao Sang
Sourabh Betigeri
Julia Jiang
Sarbojit Sarkar
cjatin
Ravi C Akkenapally
Arya.Rafii
Vladislav Sytchenko
Maneesh Gupta
Sameer Sahasrabuddhe
Michael LIAO