AI/rocm-systems
2
0
Çatalla 0
Kod Konular Değişiklik İstekleri İşlemler Paketler Projeler Sürüm Viki Aktivite
3.159 İşleme 3 Dal 0 Etiketler
7cd4c4e9ac0cb40d1539c45a2ff571630e598dde
İşleme Grafiği

3159 İşleme

Bu Dal
Bu Dal
Tüm Dallar
Yazar SHA1 Mesaj Tarih
Evgeny Mankov 7cd4c4e9ac Merge pull request #834 from emankov/master 
[HIPIFY] LLVM compatibility
 2018-12-28 15:13:36 +03:00
Maneesh Gupta f71b7fb724 Merge pull request #835 from mangupta/ci-remove-roc-1.9.x 
[ci] Remove ROCm 1.9.x from test infrastructure
 2018-12-28 17:07:19 +05:30
Maneesh Gupta d5d6541ad5 [ci] Remove ROCm 1.9.x from test infrastructure 
Change-Id: I58cce7c60f6def22f337bbe15fab2620419e202b
 2018-12-28 11:23:52 +05:30
emankov 208d7cfaf1 [HIPIFY] LLVM compatibility 
+ sys::fs::make_absolute fro LLVM < 5.0
+ sys::fs::real_path for LLVM >= 5.0
 2018-12-28 01:34:35 +03:00
Evgeny Mankov bc1e8684d6 Merge pull request #833 from emankov/master 
[HIPIFY] Use sys::fs::createTemporaryFile without file opening
 2018-12-27 20:16:09 +03:00
emankov 912c4710ed [HIPIFY] Use sys::fs::createTemporaryFile without file creation 
[Reasons]
+ File is opened further by clang
+ There is a regression with LLVM 5.x, when system error occurs: temporary file couldn't be renamed - permission denied.
 2018-12-27 17:00:18 +03:00
Maneesh Gupta 8cbc3c49d2 Merge pull request #817 from aaronenyeshi/fix-rn-intrinsics 
Add *_rn functions back into HIP intrinsics
 2018-12-27 16:07:27 +05:30
Evgeny Mankov 2e99d910c0 Merge pull request #831 from emankov/master 
[HIPIFY] Introduce option -o-dir
 2018-12-27 13:36:12 +03:00
emankov c8d720081f [HIPIFY] Introduce option -o-dir 
Option -o-dir for output directory:
  + if not specified source file(s) directory is used;
  + creates the directory if the directory doesn't exist (only one level in a tree);
  + if -o and -o-dir both are specified the hipified file is placed to "-o-dir" + "-o";
  + reports an error in case of a wrong directory specified, in case of necessity of creating a tree of subfolders, or in case of a filename specified.
 2018-12-26 16:30:41 +03:00
Evgeny Mankov 93e6010efa Merge pull request #829 from emankov/master 
[HIPIFY][#812] Finishing with temps
 2018-12-25 18:39:12 +03:00
emankov cc59af5dbd [HIPIFY][#812] Finishing with temps 
1. Option -temp-dir for temporary directory:
  + if not specified system temp is used;
  + creates the directory if the directory doesn't exist (only one level in a tree);
  + reports an error in case of a wrong directory specified, in case of necessity of creating a tree of subfolders, or in case of a filename specified.
2. Option -save-temps for preserving temporary files:
  + if specified temporary files are not being deleted from system temps and user temps as well.
3. Work with files in terms of calculated absolute paths by collapsing all '.' and '..' patterns, resolving symlinks and expanding '~' expression to the user's home directory:
  + to produce correct include paths;
  + to avoid possible errors on file routines.
 2018-12-22 00:47:19 +03:00
Evgeny Mankov 64c2a7e065 Merge pull request #825 from emankov/master 
[HIPIFY][fix][#824] Fix the bug with -inplace option
 2018-12-21 18:37:15 +03:00
emankov 8bf3b42e7e [HIPIFY][fix][#824] Fix the bug with -inplace option 
+ Do temp file copying instead of renaming
+ Replace all file routine functions with LLVM's
+ Do not output hipified file in case of errors
 2018-12-20 20:43:50 +03:00
Evgeny Mankov e0649d4fa7 Merge pull request #822 from emankov/master 
[HIPIFY] Add the legal right comment to all the sources
 2018-12-20 18:53:09 +03:00
emankov fcaf954998 [HIPIFY] Add the legal right comment to all the sources 2018-12-20 18:47:57 +03:00
Evgeny Mankov 7f10399271 Merge pull request #816 from emankov/master 
[HIPIFY] Temporary files in system temps introducing
 2018-12-20 18:28:53 +03:00
Aaron Enye Shi 58dfeff27a Add *_rn functions back into HIP intrinsics 
Add back the round-to-nearest-even intrinsics back to HIP math
intrinsics as it caused regression.
 2018-12-18 19:31:54 +00:00
Evgeny Mankov da6fdc0397 [HIPIFY] Temporary files in system temps introducing 
+ Files are not being placed near original source before hipification anymore, system tmp is used for them now.
+ Additional include (-I) to absolute original source dir is added
+ Partially implements #812
+ Tested on windows/linux, single/multiple inputs, with and without includes to user header files
 2018-12-17 20:48:48 +03:00
Evgeny Mankov 6596a1825a Merge pull request #809 from emankov/master 
[HIPIFY][fix] Fix for the rest of found bugs in Statistics
 2018-12-14 15:21:53 +03:00
Evgeny Mankov bffacb6c72 [HIPIFY][fix] Fix for the rest of found bugs in Statistics 
+ Signs of the converted file are extended
+ Total converted lines and total elapsed time are fixed
+ Zero rates are excluded from statistics
 2018-12-13 18:35:45 +03:00
Evgeny Mankov 4a58c0480b Merge pull request #802 from emankov/master 
[HIPIFY][fix] Fix for #801
 2018-12-13 14:40:00 +03:00
Evgeny Mankov 9d223f0f65 [HIPIFY][fix] Fixer for #801 
[issue #801] Errors in hipification statistics
 2018-12-12 21:33:00 +03:00
Evgeny Mankov 7741457dea Merge pull request #800 from emankov/master 
[HIPIFY][tests][fix] Add correct CUDA version detection while testing
 2018-12-12 18:30:03 +03:00
Evgeny Mankov 3d528cf491 [HIPIFY][tests][fix] Add correct CUDA version detection while testing 
+ Just do load_config for lit.site.cfg earlier in lit.cfg to get initialized cuda_version
+ Remove lit.cfg.in for CMake variables substitution
+ Return back lit.cfg
+ Exclude CUDA 9.0 tests if CUDA < 9.0
+ Report CUDA version before running tests
 2018-12-12 17:05:01 +03:00
Maneesh Gupta 56ce3e37d5 Merge pull request #797 from gargrahul/fixhipPointerGetAttributes 
Fixed hipPointerGetAttributes for hostmalloced ptr
 2018-12-12 10:16:07 +05:30
Maneesh Gupta 0dd26b4f63 Merge pull request #608 from gargrahul/add_pinned_2d_sdma_copy 
Added support for pinned 2D SDMA copy
 2018-12-12 07:44:16 +05:30
Evgeny Mankov b955e317a7 [HIPIFY][tests][fix] Add correct CUDA version detection while testing 
+ Add lit.cfg.in for CMake variables substitution to now generated lit.cfg
+ Exclude lit.cfg
+ Exclude CUDA 9.0 tests if CUDA < 9.0
+ Report CUDA version before running tests
 2018-12-11 22:03:11 +03:00
Evgeny Mankov f3d8d3d989 Merge pull request #789 from emankov/master 
[HIPIFY] Initial support of translation to ROCm
 2018-12-11 10:56:41 +03:00
Rahul Garg 5f12067708 Fixed hipPointerGetAttributes for hostmalloced ptr 2018-12-08 01:42:08 +05:30
Evgeny Mankov c5ed25da22 [HIPIFY] Initial support of translation to ROCm 
+ Option '-roc' is added to translate to ROCm instead of HIP
+ Update hipification mechanism accordingly
+ Populate all translation maps with additional field for ROCm identifiers
+ There are 4 degrees of CUDA support now: full support, only by HIP, only by ROCm, unsupported
 2018-12-06 21:52:54 +03:00
Evgeny Mankov d3654e12e4 Merge pull request #787 from emankov/master 
[HIPIFY][tests] Reorganization
 2018-12-04 20:48:48 +03:00
Evgeny Mankov 09612ac03f [HIPIFY][tests] Reorganization 2018-12-04 20:47:34 +03:00
Evgeny Mankov e083cc64eb Merge pull request #786 from emankov/master 
[HIPIFY][SPARSE] Add 3 more CUDA 10.0 tests
 2018-12-04 19:30:26 +03:00
Evgeny Mankov 72d40db358 [HIPIFY][SPARSE] Add 3 more CUDA 10.0 tests 
+ lit update
+ fix typos
 2018-12-04 19:24:29 +03:00
Maneesh Gupta 0c8ba46b9f Merge pull request #785 from mangupta/ci-add-rocm_2_0 
[ci] Add rocm-2.0.x to CI test infrastructure
 2018-12-03 10:41:43 +05:30
Maneesh Gupta dc5b0a1fe0 [ci] Add rocm-2.0.x to CI test infrastructure 
Change-Id: I7fc0c40d1bf50a90ce3e210f2c8e83d1f4bf6d5c
 2018-12-03 08:54:13 +05:30
Evgeny Mankov 1ecfec2264 Merge pull request #784 from emankov/master 
[HIPIFY][SPARSE] Matrix Reorderings and Format Conversion Reference
 2018-11-30 15:35:14 +03:00
Evgeny Mankov 116b9191f7 [HIPIFY][SPARSE] Matrix Reorderings and Format Conversion Reference 
+ cuSPARSE is supported up to CUDA 10.0
+ cuSPARSE_08 test (CUDA 10.0)
+ update CUSPARSE_API_supported_by_HIP.md
+ lit: add a rule for CUDA 10.0 tests excluding
 2018-11-30 15:33:57 +03:00
Maneesh Gupta dbe34ac6ac Merge pull request #783 from scchan/revert_metadata_for_kerarg 
Revert metadata for kerarg
 2018-11-30 09:39:42 +05:30
Siu Chi Chan 1fbf639962 Revert "Rely on code object metadat for kernarg arguments alignof and sizeof." 
This reverts commit fe1e963299.
 2018-11-29 11:38:37 -05:00
Siu Chi Chan 71189c10c1 Revert "Handle the very confusing dual encoding of the symbol name." 
This reverts commit bce3de8162.
 2018-11-29 11:38:36 -05:00
Siu Chi Chan 09f87e41d9 Revert "If we've already seen a __global__ function we do not need to re-parse" 
This reverts commit f7ba987038.
 2018-11-29 11:38:35 -05:00
Siu Chi Chan aeca2c8cdc Revert "Handle (odd) corner case of argumentless __global__ function." 
This reverts commit c0bd1a5af8.
 2018-11-29 11:38:34 -05:00
Siu Chi Chan 8eb9b38e76 Revert "Missing handling nullary __global__ functions for mixed arity cases." 
This reverts commit 4ebc229b9a.
 2018-11-29 11:38:31 -05:00
Siu Chi Chan 909609773c Revert "Fix issue in kernarg metadata parsing due to early finalization" 
This reverts commit 19acf86cef.
 2018-11-29 11:35:00 -05:00
Evgeny Mankov c80c6886e2 Merge pull request #782 from emankov/master 
[HIPIFY][SPARSE] Preconditioners Reference: Tridiagonal and Pentadiagonal solves
 2018-11-29 18:49:34 +03:00
Evgeny Mankov 8a84c665e2 [HIPIFY][SPARSE] Preconditioners Reference: Tridiagonal and Pentadiagonal solves 
+ Tridiagonal Solve, Batched Tridiagonal and Pentadiagonal Solve
+ cuSPARSE_07 test
+ update CUSPARSE_API_supported_by_HIP.md
 2018-11-29 18:46:51 +03:00
Evgeny Mankov d09e6dfb68 Merge pull request #781 from emankov/master 
[HIPIFY][SPARSE] Preconditioners Reference: Incomplete LU Factorization: level 0
 2018-11-29 16:01:44 +03:00
Evgeny Mankov 6c085c83a2 [HIPIFY][SPARSE] Preconditioners Reference: Incomplete LU Factorization: level 0 
+ cuSPARSE_06 test
+ update CUSPARSE_API_supported_by_HIP.md
 2018-11-29 15:59:58 +03:00
Evgeny Mankov eafd40f904 Merge pull request #780 from emankov/master 
[HIPIFY][SPARSE] Preconditioners Reference: Incomplete Cholesky Factorization: level 0
 2018-11-28 20:12:21 +03:00