AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,507 Commits 3 Branches 0 Tags
fb427976d7eecb3c19a20fc3c58c387c60a2fe21
Commit Graph

3507 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Maneesh Gupta 0a9a2d030b Merge pull request #817 from aaronenyeshi/fix-rn-intrinsics 
Add *_rn functions back into HIP intrinsics

[ROCm/clr commit: 274db66ff2]
 2018-12-27 16:07:27 +05:30
Evgeny Mankov 6a90c8f2c3 Merge pull request #831 from emankov/master 
[HIPIFY] Introduce option -o-dir

[ROCm/clr commit: 8ffd7e5fa4]
 2018-12-27 13:36:12 +03:00
emankov c65d6a9e7a [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.


[ROCm/clr commit: c65338fbf7]
 2018-12-26 16:30:41 +03:00
Evgeny Mankov de7f819b49 Merge pull request #829 from emankov/master 
[HIPIFY][#812] Finishing with temps

[ROCm/clr commit: 3cf4df4571]
 2018-12-25 18:39:12 +03:00
emankov 0056b8ad20 [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.


[ROCm/clr commit: 7cac7dbfea]
 2018-12-22 00:47:19 +03:00
Evgeny Mankov 5d3f13140a Merge pull request #825 from emankov/master 
[HIPIFY][fix][#824] Fix the bug with -inplace option

[ROCm/clr commit: 33d4018c67]
 2018-12-21 18:37:15 +03:00
emankov 369ac7b6f5 [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


[ROCm/clr commit: cb598445f5]
 2018-12-20 20:43:50 +03:00
Evgeny Mankov 2b5d3ee7f9 Merge pull request #822 from emankov/master 
[HIPIFY] Add the legal right comment to all the sources

[ROCm/clr commit: 10faf729fa]
 2018-12-20 18:53:09 +03:00
emankov 7d9eaec992 [HIPIFY] Add the legal right comment to all the sources 
[ROCm/clr commit: 340550cc56]
 2018-12-20 18:47:57 +03:00
Evgeny Mankov fb7e140e8e Merge pull request #816 from emankov/master 
[HIPIFY] Temporary files in system temps introducing

[ROCm/clr commit: 41867c6753]
 2018-12-20 18:28:53 +03:00
Rahul Garg 489f3ef7ba Remove redundant arguments from hipMemset3D test 
[ROCm/clr commit: 10d2a9a269]
 2018-12-20 06:51:22 +05:30
Stanley Tsang 0af39754f6 Adding support in the hipify-perl tool for the HIP_SYMBOL macro, which is required for hip API calls involving a device symbol. Added more explicit mention of the HIP_SYMBOL macro in the porting guide. 
[ROCm/clr commit: ca56b81ebf]
 2018-12-19 12:21:02 -05:00
Yaxun Sam Liu 51702bed29 Add default arguments for hipConfigureCall 
[ROCm/clr commit: 02deeadaa4]
 2018-12-18 15:48:21 -05:00
Aaron Enye Shi 56262f0970 Add *_rn functions back into HIP intrinsics 
Add back the round-to-nearest-even intrinsics back to HIP math
intrinsics as it caused regression.


[ROCm/clr commit: 2d50392c17]
 2018-12-18 19:31:54 +00:00
Evgeny Mankov 47d5d2cfd7 [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


[ROCm/clr commit: 1180928408]
 2018-12-17 20:48:48 +03:00
Evgeny Mankov c1076d4c05 Merge pull request #809 from emankov/master 
[HIPIFY][fix] Fix for the rest of found bugs in Statistics

[ROCm/clr commit: 637bf7eb6f]
 2018-12-14 15:21:53 +03:00
Evgeny Mankov 882620028c [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


[ROCm/clr commit: 1e30cd3ea7]
 2018-12-13 18:35:45 +03:00
Evgeny Mankov bdb6f9557f Merge pull request #802 from emankov/master 
[HIPIFY][fix] Fix for #801

[ROCm/clr commit: a5d25a9c5d]
 2018-12-13 14:40:00 +03:00
Evgeny Mankov d2e478546b [HIPIFY][fix] Fixer for #801 
[issue #801] Errors in hipification statistics


[ROCm/clr commit: 8d28db9c8d]
 2018-12-12 21:33:00 +03:00
Evgeny Mankov a8980580c0 Merge pull request #800 from emankov/master 
[HIPIFY][tests][fix] Add correct CUDA version detection while testing

[ROCm/clr commit: 80d5861d78]
 2018-12-12 18:30:03 +03:00
Evgeny Mankov 0d92c82f79 [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


[ROCm/clr commit: a5c66018b6]
 2018-12-12 17:05:01 +03:00
Maneesh Gupta f096437107 Merge pull request #797 from gargrahul/fixhipPointerGetAttributes 
Fixed hipPointerGetAttributes for hostmalloced ptr

[ROCm/clr commit: a778f7cdf7]
 2018-12-12 10:16:07 +05:30
Maneesh Gupta 30ce297635 Merge pull request #608 from gargrahul/add_pinned_2d_sdma_copy 
Added support for pinned 2D SDMA copy

[ROCm/clr commit: 6ce99b066c]
 2018-12-12 07:44:16 +05:30
Evgeny Mankov d38bbc99aa [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


[ROCm/clr commit: 2b01f1eb6f]
 2018-12-11 22:03:11 +03:00
Evgeny Mankov b5934ac50b Merge pull request #789 from emankov/master 
[HIPIFY] Initial support of translation to ROCm

[ROCm/clr commit: f2afe92844]
 2018-12-11 10:56:41 +03:00
Rahul Garg 514e5a41e3 Fixed hipPointerGetAttributes for hostmalloced ptr 
[ROCm/clr commit: 77fd517e09]
 2018-12-08 01:42:08 +05:30
amd-stanley 36af63b64b Merge pull request #1 from ROCm-Developer-Tools/master 
Updating fork with latest code from origin

[ROCm/clr commit: 4fc2715252]
 2018-12-06 13:28:25 -07:00
Evgeny Mankov ccad9cbd80 [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


[ROCm/clr commit: 747eb2c11c]
 2018-12-06 21:52:54 +03:00
Evgeny Mankov 008640c8a5 Merge pull request #787 from emankov/master 
[HIPIFY][tests] Reorganization

[ROCm/clr commit: 32455eddaf]
 2018-12-04 20:48:48 +03:00
Evgeny Mankov 27496f1d0d [HIPIFY][tests] Reorganization 
[ROCm/clr commit: b76cf94562]
 2018-12-04 20:47:34 +03:00
Evgeny Mankov 5906596174 Merge pull request #786 from emankov/master 
[HIPIFY][SPARSE] Add 3 more CUDA 10.0 tests

[ROCm/clr commit: f368ab4a32]
 2018-12-04 19:30:26 +03:00
Evgeny Mankov c6efca710f [HIPIFY][SPARSE] Add 3 more CUDA 10.0 tests 
+ lit update
+ fix typos


[ROCm/clr commit: a421aff96d]
 2018-12-04 19:24:29 +03:00
Maneesh Gupta ddcf75e809 Merge pull request #785 from mangupta/ci-add-rocm_2_0 
[ci] Add rocm-2.0.x to CI test infrastructure

[ROCm/clr commit: f6ec2236cd]
 2018-12-03 10:41:43 +05:30
Maneesh Gupta feefdd498b [ci] Add rocm-2.0.x to CI test infrastructure 
Change-Id: I7fc0c40d1bf50a90ce3e210f2c8e83d1f4bf6d5c


[ROCm/clr commit: 94292df570]
 2018-12-03 08:54:13 +05:30
Evgeny Mankov e5ac8b71ef Merge pull request #784 from emankov/master 
[HIPIFY][SPARSE] Matrix Reorderings and Format Conversion Reference

[ROCm/clr commit: 7de2948334]
 2018-11-30 15:35:14 +03:00
Evgeny Mankov d3ffb890c0 [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


[ROCm/clr commit: 424e4c8229]
 2018-11-30 15:33:57 +03:00
Maneesh Gupta 9c38b6da48 Merge pull request #783 from scchan/revert_metadata_for_kerarg 
Revert metadata for kerarg

[ROCm/clr commit: 940c5c2b26]
 2018-11-30 09:39:42 +05:30
Siu Chi Chan bda6edc929 Revert "Rely on code object metadat for kernarg arguments alignof and sizeof." 
This reverts commit 1ec78f6d67.


[ROCm/clr commit: 4251a70bc0]
 2018-11-29 11:38:37 -05:00
Siu Chi Chan b47617dd72 Revert "Handle the very confusing dual encoding of the symbol name." 
This reverts commit 8599d053b4.


[ROCm/clr commit: a41bce5163]
 2018-11-29 11:38:36 -05:00
Siu Chi Chan 9b6b628695 Revert "If we've already seen a __global__ function we do not need to re-parse" 
This reverts commit 58c5dedc16.


[ROCm/clr commit: dc36c49212]
 2018-11-29 11:38:35 -05:00
Siu Chi Chan 732088e131 Revert "Handle (odd) corner case of argumentless __global__ function." 
This reverts commit f843c8dd48.


[ROCm/clr commit: 30a9be5643]
 2018-11-29 11:38:34 -05:00
Siu Chi Chan 44ac74c9db Revert "Missing handling nullary __global__ functions for mixed arity cases." 
This reverts commit 5647e0ae35.


[ROCm/clr commit: c5df445d1f]
 2018-11-29 11:38:31 -05:00
Siu Chi Chan 61785e9d39 Revert "Fix issue in kernarg metadata parsing due to early finalization" 
This reverts commit 0c610f5890.


[ROCm/clr commit: adbf0c444b]
 2018-11-29 11:35:00 -05:00
Evgeny Mankov d46943ca1d Merge pull request #782 from emankov/master 
[HIPIFY][SPARSE] Preconditioners Reference: Tridiagonal and Pentadiagonal solves

[ROCm/clr commit: c0b3e59fcf]
 2018-11-29 18:49:34 +03:00
Evgeny Mankov 1c4d1bf7a6 [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


[ROCm/clr commit: e8054fe485]
 2018-11-29 18:46:51 +03:00
Evgeny Mankov 81a01ef3a5 Merge pull request #781 from emankov/master 
[HIPIFY][SPARSE] Preconditioners Reference: Incomplete LU Factorization: level 0

[ROCm/clr commit: 7317dce7bd]
 2018-11-29 16:01:44 +03:00
Evgeny Mankov 81004dc3ac [HIPIFY][SPARSE] Preconditioners Reference: Incomplete LU Factorization: level 0 
+ cuSPARSE_06 test
+ update CUSPARSE_API_supported_by_HIP.md


[ROCm/clr commit: ef99d6dee4]
 2018-11-29 15:59:58 +03:00
Evgeny Mankov 55fcdefb1d Merge pull request #780 from emankov/master 
[HIPIFY][SPARSE] Preconditioners Reference: Incomplete Cholesky Factorization: level 0

[ROCm/clr commit: df81e8dcd8]
 2018-11-28 20:12:21 +03:00
Evgeny Mankov c0224ff0b9 [HIPIFY][SPARSE] Preconditioners Reference: Incomplete Cholesky Factorization: level 0 
+ cuSPARSE_05 test
+ update CUSPARSE_API_supported_by_HIP.md


[ROCm/clr commit: e90373c927]
 2018-11-28 20:10:30 +03:00
Maneesh Gupta 98548054e9 Merge pull request #776 from yxsamliu/fix-vdi-path 
Let hipcc handle HIP_VDI_HOME without x86_64

[ROCm/clr commit: a2de2a40d9]
 2018-11-28 09:33:03 +05:30