_ Use fields from GRID_LAUNCH_20 structure
(See USE_GRID_LAUNCH_20 define, currently set to 0)
"1" will require HCC support.
- Remove old DISABLE_GRID_LAUNCH support.
Change-Id: I584ce648d217251789a6283cf27feb24cb7dc8d1
[ROCm/clr commit: e27b5cc927]
SWDEV-2 - Change OpenCL version number from 2149 to 2150.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1896 edit
[ROCm/clr commit: 047ef6b06e]
SWDEV-2 - Change OpenCL version number from 2148 to 2149.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1895 edit
[ROCm/clr commit: 3457bc143a]
- Add hierarchy. Tests now live in directories, each with its own
CMakeFiles.txt. Reduces merge conflicts.
- Change make_hip_executable -> build_hip_executable.
- Refresh docs.
- Enable some tests that were previously built but not run.
Change-Id: I8c5de3c954400bf233904282b8b42861a2b7c536
[ROCm/clr commit: 3feb13c8f6]
SWDEV-95698 - Complib: set data layout string from the subtarget in codegen
This logic was broken since llvm 3.6 merge and datalayout was not set as supposed.
This results in a different compilation results with complib and llc.
In addition that leads to the suboptimal codegen.
Testing: smoke, precheckin, llc_opt, ocl_features, vec_ldst, ocl_sdk_aoc2_compare_main
Reviewed by Evgeny Mankov
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/codegen.cpp#71 edit
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/ocl/regression/95698/calcweight-nounroll-min.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/tlst/ocl_regression.tlst#37 edit
[ROCm/clr commit: 2300414425]
SWDEV-2 - Change OpenCL version number from 2147 to 2148.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1894 edit
[ROCm/clr commit: 90d81a61cc]
SWDEV-2 - Change OpenCL version number from 2146 to 2147.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1893 edit
[ROCm/clr commit: 32e6cea52f]
- Complete translation tables for cudaError <-> hipError_t.
- Remove some odd errors that were not correctly translated or not used.
- Add HIPCHECK_API to test infrastructure. Used for negative testing
an API ; if a mismatch occurs it shows the expected return error
code. Can also print a warning rather than error.
- Enable hipMemoryAllocate on NV system, and review error coded.
- Add hipErrorName to nvcc.
Change-Id: I680427dcf32a5796d5913cf9e7f3b4c6f6b91599
Conflicts:
tests/src/CMakeLists.txt
Bug fixes and improved docs for hipFree and hipHostFree.
- Passing NULL pointer initialized runtime and return hipSuccess
(not an error like before).
- add negative test for this. (hipMemoryAllocate, improved)
- Match NVCC errors for invalid pointers, add to test.
- Update hipFree and hipHostFree docs.
- hipGetDevicePointer always set *devicePointer=NULL, even for
invalid flags.
- Gate shared memory usage on specific HCC work-week.
Change-Id: I533b4fd3280a3d6cdbf05eb768976f0c7506c012
[ROCm/clr commit: 6a2a140f34]
SWDEV-2 - Change OpenCL version number from 2145 to 2146.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1892 edit
[ROCm/clr commit: ac02a393c2]
SWDEV-95917 - OpenCL on PAL - add device info query to get the number of aysnc queues
- Correct the number of normal compute queues
- Fix concurrency test workloads
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/perf/OCLPerfConcurrency.cpp#19 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/perf/OCLPerfConcurrency.h#5 edit
[ROCm/clr commit: c7522d11c4]
Ben Sander
Aditya Atluri
Maneesh Gupta
foreman