tests/src/runtimeApi/module/hipModuleLaunchKernel.cpp doesn't
need hip_ext.h which will fail cuda building. So remove it
Change-Id: Icf5763449ccec839d9efda90ffe3a86fb53bdb85
[ROCm/clr commit: a6176099cf]
HIP_VERSION_GITDATE won't be defined when git isn't
installed. This will lead to building failure of
deviceLib.hipVersion. When git isn't installed, set
HIP_VERSION_GITDATE as 0 by default.
Change-Id: Icf5763449ccec833d9efda90ffe3a86fb53bdb82
[ROCm/clr commit: 1338ebde58]
On Windows, there may be spaces in the directory
location. Therefore, must add quotes when adding
this path with a location in C:/Program Files/.
Change-Id: I63642093092e25a2f6ed73b55a7afd16835ac736
[ROCm/clr commit: e4c1c79b2b]
In pitch workaround, we need to copy the image to copy buffer
when application wants to read image to buffer. After this
patch, we unconditionally copy the image data to the copy buffer.
Change-Id: I71b0d19459542dfbb3ca51a2c8a3a81367fa2fb5
[ROCm/clr commit: 5330679473]
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]
Modify hipconfig and hipcc to properly run Windows compiler
executables. Support Windows Environmental Variables and
AMD Display Adapter info. Update flags to include quotes for
paths that have spaces, such as Program Files.
Change-Id: Ib721b318bd88be7dfa1247a30ce78c7ed6a334e8
[ROCm/clr commit: 31e772adb5]
Modify hip-config.cmake to support building on Windows
using CMake's find_package(hip). Windows CMake will work
with Ninja Generator and inheritEnvironments clang_cl_x64.
Change-Id: I03d76b5f8d695ce50ecaacb449e4eb1c1ca49700
[ROCm/clr commit: db43d7a3ac]
- The logic will trace compute, sdma read/write operations and
apply signals when necessary
- ROC_CPU_WAIT_FOR_SIGNAL, ROC_SYSTEM_SCOPE_SIGNAL
and ROC_SKIP_COPY_SYNC were added to control the tracking
Change-Id: I9e8e6174c63bf7784f7ab00964e2918c8667d364
[ROCm/clr commit: dbc7abaecf]
- ROCR fails the call for some reason, then the signal will
become invalid and can hang on a wait. The logic will reset the
active signal in such cases
Change-Id: Ia131420200f1bbd7c9a162b8f1b06db8cecf41c6
[ROCm/clr commit: ce2e5eba6b]
- There is a performance regression with a HW wait for HSA signal
on ROCr async operation. For now move the logic back to CPU wait.
- Fix profiling issue with multiple HSA signal per single timestamp
object. Some copies require multiple ROCR calls and if profiling is
required, then the execution time is derived from all used signals.
Change-Id: Id003e4abb8c2de378eedc152a7e389500fc6f4ce
[ROCm/clr commit: 5a8946190a]
Tao Sang
Julia Jiang
German Andryeyev
Chauncey Hui
Aaron En Ye Shi
Satyanvesh Dittakavi
Jason Tang
Alex Xie
Joseph Greathouse
agodavar
Saleel Kudchadker
Sarbojit Sarkar
Vladislav Sytchenko
kjayapra-amd
Rahul Garg
Todd tiantuo Li
Jason Tang