Graf Tiomantas

2209 Tiomáintí

Údar SHA1 Teachtaireacht Dáta
Kent Knox a1abbea28d Disable CUDA build/test while upgrading to nvidia-docker2
This enables us to remove the driver version from startup string
2017-12-21 11:10:55 -06:00
Maneesh Gupta a8e146d0ce Merge pull request #298 from emankov/master
[HIPIFY][cmake] Fix require_program function
2017-12-19 08:42:27 +05:30
Evgeny Mankov eff6831217 [HIPIFY][cmake] Fix require_program function
Function require_program erroneously doesn't report "Can't find program" on any missing program except the first one due to the cached FOUND_PROGRAM value.

Additionally:
+ Do not throw FATAL_ERROR on missing program in order to obtain the whole list of missing programs (if any).
+ Report also found program location.
2017-12-18 19:57:04 +03:00
Maneesh Gupta b0920e3281 Merge pull request #297 from phani544/nvccTests3
[nvccTests] Resubmit hipMemcpyDtoD & inline_asm_vadd
2017-12-18 15:41:19 +05:30
Maneesh Gupta c124899669 Merge pull request #282 from gargrahul/texture_driver_3d_support
Added support for 3D texture driver apis
2017-12-18 15:39:26 +05:30
Phaneendr-kumar Lanka 89bedb74e7 [nvccTests] Resubmit hipMemcpyDtoD & inline_asm_vadd 2017-12-18 14:46:19 +05:30
Maneesh Gupta 1fe07cbbca Merge pull request #295 from mangupta/static_check
[cmake] Added target static_check for static code analysis
2017-12-15 10:25:58 +05:30
Maneesh Gupta b7855e0fc7 Merge pull request #294 from phani544/nvccWarnings
[nvccWarnings] Fix warnings seen with dtests on nvcc path
2017-12-14 15:58:38 +05:30
Phaneendr-kumar Lanka 0ac125e3db [nvccWarnings] Fix warnings seen with dtests on nvcc path 2017-12-14 14:10:37 +05:30
Maneesh Gupta 379cbfedcf [cmake] Added target static_check for static code analysis
- Added static code analysis using cppcheck
- Fixed couple of warnings reported by cppcheck

Change-Id: Ie3b9b06e95ada322e7dc2ce3d6b91831e870198d
2017-12-14 12:16:44 +05:30
Maneesh Gupta f485e8433d Merge pull request #293 from phani544/nvccWarnings
[nvccWarnings] Fix gpu deprecated targets warnings
2017-12-13 09:58:59 +05:30
Phaneendr-kumar Lanka 7a3e0bc5d0 [nvccWarnings] Fix gpu deprecated targets warnings 2017-12-12 16:00:14 +05:30
Maneesh Gupta 123d719f0c Merge pull request #290 from gargrahul/fix_hipPeerToPeer_simple
Fixed hipPeerToPeer_simple test
2017-12-12 12:50:14 +05:30
Maneesh Gupta 574797cdff Merge pull request #286 from gargrahul/fix_hipDeviceGetAttribute_nvcc
Fix hipGetDeviceAttribute dtest for HIP/NVCC
2017-12-12 12:49:23 +05:30
Maneesh Gupta c4192eec7d Merge pull request #285 from aaronenyeshi/fix-ilogb-unreachable
Fix ilogb/ilogbf functions to return int
2017-12-12 10:47:33 +05:30
Rahul Garg 2de0f1cafd Fixed hipPeerToPeer_simple test
- Moved test inside p2p dir
- Updated HIPCHECK to ignore hipErrorPeerAccessAlreadyEnabled
- Added check for mGPUs
2017-12-11 15:23:18 +05:30
Ben Sander f245fe8a6c Merge pull request #283 from emankov/master
[HIPIFY] Disable cudaBuiltin matcher.
2017-12-07 12:38:02 -08:00
Evgeny Mankov 45befb73d3 [HIPIFY] Remove cudaBuiltin matcher 2017-12-06 20:22:14 +03:00
Rahul Garg a62ef42c09 Fix hipGetDeviceAttribute dtest for HIP/NVCC 2017-12-06 15:49:06 +05:30
Aaron En Ye Shi b439b45641 Fix ilogb/ilogbf functions to return int
This patch will fix hipDoublePrecisionMathDevice test on ThinLTO, which uncovered that hip math_function's ilogb/ilogbf should return type int instead of double. This will match rocdl.
2017-12-05 23:14:10 +00:00
Ben Sander faef491778 Merge pull request #281 from mangupta/issue126
[samples] Adds a sample that shows using HIP with cmake
2017-12-05 11:42:11 -06:00
Evgeny Mankov ccc959fdc9 [HIPIFY] Disable cudaBuiltin matcher.
As HIP has started to support vanilla CUDA syntax for threadIdx, blockIdx, blockDim and gridDim.
Other CUDA builtins are not tracked for now.
2017-12-05 20:28:51 +03:00
Evgeny Mankov 43f0a14005 [HIPIFY] remove duplicates from CUDA_IDENTIFIER_MAP 2017-12-05 19:46:53 +03:00
Evgeny Mankov 360702f70a Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP 2017-12-05 18:19:15 +03:00
Maneesh Gupta 5451441fc3 Merge pull request #278 from bensander/update_docs_and_square
Update docs and square
2017-12-05 15:57:36 +05:30
Rahul Garg 105df94cd0 Added support for
- 3D texture driver APIs
- hipMalloc3D
- hipMemcpy3D for destination other than array
2017-12-05 14:11:13 +05:30
Maneesh Gupta ccc3fc1de6 Simplify square sample's Makefile
Change-Id: I44349a880a3c57ca0e833d67d9c380b706655b1e
2017-12-05 11:54:50 +05:30
Maneesh Gupta f52662da24 [samples] Adds a sample that shows using HIP with cmake
Change-Id: Ief983ea0894d7b5d1ea46a755f9134dda0a1bb8f
2017-12-05 10:48:29 +05:30
Ben Sander c7f9dbf789 Merge pull request #279 from AlexVlx/feature_use_module_based_dispatch_instead_of_pfe
Clean up kernel retrieval code / module management
2017-12-03 18:41:27 -06:00
Ben Sander 4dfcd401b0 Merge pull request #276 from bensander/temp_disable_tests
Temporarily disable a couple tests pending some HCC work
2017-12-03 18:33:47 -06:00
Alex Voicu 76614f15af Re-sync with upstream. 2017-12-03 23:14:58 +00:00
Alex Voicu e186bd9533 This is primarily intended as an additional cleanup of the module functionality, in the aftermath of adopting module based dispatch. The main effort was associated with refactoring the questionable ihipModuleGetSymbol. It was quaintly written and misleading, in that it had little to do with getting symbols, and was exactly retrieving a kernel object. Error handling is modified so as to reduce branching depth. Functions which serve as interfaces to the HSA RT are moved in a separate helper header. Code object readers are properly deleted. Some leftover dead functionality pertaining to associating namespace scope variables with their allocated memory is removed. Executable loading is changed to use a string which holds the ELF image of the code object being loaded, thus avoiding some corner cases where using a istream would fail. 2017-12-03 23:09:06 +00:00
Ben Sander 6e2e029b39 Merge pull request #271 from bensander/cppcheck
Cppcheck
2017-12-02 08:36:17 -06:00
Ben Sander a431bf6ba2 Remove coordinate conversions (threadIdx.x -> hipThreadIdx_x)
Since these are now supported directly.
2017-12-02 07:44:54 -06:00
Ben Sander 4192c8b54a Update square sample for recent HIP ease-of-use improvements 2017-12-02 07:44:27 -06:00
Ben Sander a833ec9f7f Merge pull request #277 from AlexVlx/feature_use_module_based_dispatch_instead_of_pfe
Fix hang by purging archaisms
2017-12-02 07:11:55 -06:00
Alex Voicu 954b7dadf7 Remove stray leftover comment. 2017-12-02 00:03:10 +00:00
Alex Voicu b8c80bd0b2 Replace archaic use of homebrew functionality with calls to the HC maths library. This fixes a hang observed when building hipTestDeviceDouble. 2017-12-02 00:01:47 +00:00
Ben Sander 3a1520025d Update RELEASE.md and bugs to reflect HIP infra improvements. 2017-12-01 16:09:24 -06:00
Ben Sander 0534caaa25 Merge pull request #267 from AlexVlx/feature_sanitise_conversions
Fix curious bitwise conversions.
2017-12-01 15:51:08 -06:00
Ben Sander 721d862089 Temporarily disable a couple tests pending some HCC work 2017-12-01 21:46:28 +00:00
Ben Sander 5933ca7300 Fix some cppcheck style issues. 2017-12-01 20:45:34 +00:00
Ben Sander 743c54a012 Fix warning from default cppchek. 2017-12-01 20:45:33 +00:00
Ben Sander 1a6727e2fc Merge pull request #246 from AlexVlx/feature_use_module_based_dispatch_instead_of_pfe
Use natural dispatch syntax
2017-12-01 14:21:25 -06:00
Alex Voicu 33bb425013 Fix legacy mode detection of the address of an agent allocated variable. In this mode, there exist two executables per each code object, one created by HCC and one created by HIP. Since we dispatch through HCC in legacy mode, we should obtain the address for an agent allocated variable from the latter's executable. Also add two omitted validity checks, whose absence could lead to segfaults when the current process had no .kernel section and / or when an invalid or empty blob was extracted from the latter. 2017-11-30 03:29:04 +00:00
Alex Voicu 2e39534377 Add missing space (the final frontier). 2017-11-29 21:50:43 +00:00
Alex Voicu 4966518846 Revert "Revert adoption of CUDA indexing in general - this can only work with later versions of the compiler, just like module based dispatch, and thus must be guarded against usage in earlier (e.g. 1.6) versions."
This reverts commit 4792475
2017-11-29 21:49:10 +00:00
Alex Voicu 92e80f0943 Use a much simpler guard for version 1.6, which allows for direct CUDA indexing to be used. 2017-11-29 21:47:04 +00:00
Alex Voicu 30e4d445b1 Merge branch 'feature_use_module_based_dispatch_instead_of_pfe' of https://github.com/AlexVlx/HIP into feature_use_module_based_dispatch_instead_of_pfe 2017-11-29 21:45:56 +00:00
Alex Voicu 2557000b56 Revert "Revert adoption of CUDA indexing in general - this can only work with later versions of the compiler, just like module based dispatch, and thus must be guarded against usage in earlier (e.g. 1.6) versions."
This reverts commit d2fd1f5
2017-11-29 21:36:29 +00:00