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
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
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
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
- 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
- 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
- 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
Remove targetId_, gfxipMajor_, gfxipMinor_ and gfxipStepping_ from
device::Info as they are now available in device::Isa.
Change-Id: I381b1d4798ebf50655740e004a01ac7f86dbf668
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
Alex Xie
Joseph Greathouse
Chauncey Hui
agodavar
Saleel Kudchadker
Sarbojit Sarkar
Vladislav Sytchenko
kjayapra-amd
Satyanvesh Dittakavi
Rahul Garg
Todd tiantuo Li
Aaron En Ye Shi
German Andryeyev
Jason Tang
Jason Tang
Tao Sang
jujiang
Tony Tye
Jatin Chaudhary
Sameer Sahasrabuddhe
David Salinas