There are now two implementations of printf in HIP:
1. The implemenation for HCC is controlled by the HC_FEATURE_PRINTF
macro, and it works only with the HCC compiler used in combination
with the HCC runtime.
2. The implementation for hip-clang requires the VDI runtime, and is
always enabled with that combination.
Fixes SWDEV-218626 and SWDEV-218629
Changes:
- Revert "`static inline` in a header, just like excess sugar in a diet, causes bloat (#1692)"
This reverts commit cf526f5484.
- Revert "Fix rocFFT build failure (#1777)"
This reverts commit cbd8f604ec.
* first cut of the header implementation of cooperative group feature
* add diclarations for device library functions
* fixed various compile time issues in the CG headers
* enabled copy construction and copy assignment
* fixed a minor bug related to conditional compilation macro
* fixed few more CG constructor issues and added a unit testcase
* fixed typo
* extended unit testcase
* compute size of partitioned CG from mask
* bit of code refactoring
* removed boilerplate code
* fixed few of the review comments by Brian
* Changes to the sigantures of few grid and multi-grid related OCKL functions
* changes to declarations of OCKL functions related to CG feature
* removed all the block level support as it is not planned for 2.9
* Have taken care of review comments by Brian
* Have taken care of review comments by Brian
* removed unused functions which were initially intended to use in block level cg support
- It's a common mistake by assuming 1 << shamt would be promoted to
64-bit, if shamt is a 64-bit integer. That's not the case. Replace
that left shift to a 64-bit one to ensure it won't fall into undefined
behavior.
- Fix the host-side implementation as well for device function testing.
Move remaining function definitions from device_util.cpp to hip_runtime.h header. We can now remove the static library completely as device_util.cpp was the last file part of target hip::hip_device .
previous version return a long long valus *as* double, hence we may get the wrong result.
this also affect atomicAdd(double * ...), which use long long pointer to mimic double pointer.
Signed-off-by: carlushuang <carlus.huang@amd.com>
Replace implementation of __any and __all functions using OCKL functions and replaced __ballot implementation to use llvm intrinsic llvm.amdgcn.icmp.i32 instead of calls to __activelanemask_v4_b64_b1 which is not convergent.
Sarbojit2019
Sameer Sahasrabuddhe
Nick Curtis
Sameer Sahasrabuddhe
Maneesh Gupta
Alex Voicu
satyanveshd
mhbliao
mshivama
kpyzhov
Michael LIAO
Aaron Enye Shi
Yaxun Sam Liu
carlushuang
Brian Sumner