5d83330b47
[HIPIFY][tests][win] Make cudaRegister.cu building on Windows as well
...
[ROCm/hip commit: f9416a0c49
2018-01-24 20:13:23 +03:00
0682fa4c97
Merge pull request #341 from emankov/hipBLAS
...
[HIPIFY][fix] CUDA and cuBLAS main headers correct handling
[ROCm/hip commit: befa8dbbce
2018-01-24 18:09:12 +03:00
369f3aa9fa
[HIPIFY][fix] CUDA and cuBLAS main headers correct handling
...
[ROCm/hip commit: 600d5d7c06
2018-01-23 23:43:36 +03:00
8f478ccf85
[HIPIFY][tests][win] Uncomment @echo off
...
[ROCm/hip commit: c528f4f9c5
2018-01-23 21:46:27 +03:00
974f8022b1
[HIPIFY][tests][win] Fix run_test.bat
...
All checks should not occur in input file for FileCheck. The issue found on CHECK-NOT.
Change removes all lit checks in the hipified file based on regexp, and the resulted stdout is fed as stdin for FileCheck.
[ROCm/hip commit: 368db8bf6c
2018-01-23 21:43:18 +03:00
944e84b9b7
[HIPIFY][tests] remove concurentKernels.cu as it is one of CUDA SDK samples.
...
[ROCm/hip commit: 9c0dc5cfe7
2018-01-16 20:41:08 +03:00
1506ec0d75
Merge pull request #319 from emankov/issue_211
...
[HIPIFY][fix][#211 ] Algorithm for explicit insert of hip include directive
[ROCm/hip commit: 88c5ffee3a
2018-01-16 19:47:15 +03:00
6004963827
Merge pull request #323 from emankov/cudaBuiltins
...
[HIPIFY][tests] Remove checks on cudaBuiltins
[ROCm/hip commit: 51e0c0a981
2018-01-16 19:46:41 +03:00
0b9b9fd98c
Update headers_test_03.cu
...
[ROCm/hip commit: c328e3987c
2018-01-16 19:21:59 +03:00
3fc406ead3
Update headers_test_04.cu
...
[ROCm/hip commit: a784a9c824
2018-01-16 19:21:14 +03:00
1c69f54730
[HIPIFY][tests] Remove checks on cudaBuiltins
...
As HIP has started to support vanilla CUDA syntax for threadIdx, blockIdx, blockDim and gridDim.
Other CUDA builtins are not tracked for now.
[ROCm/hip commit: 74b489b5b2
2018-01-16 17:13:29 +03:00
02bd6e89eb
[HIPIFY][tests] Add more suffixes to lit config
...
[ROCm/hip commit: 58faf1ddc9
2018-01-16 16:40:31 +03:00
504755669b
Merge pull request #302 from phani544/nvccWarnings
...
[nvccWarnings] Fix -Wno-deprecated-declarations in hip_anyall and hip…
[ROCm/hip commit: c46967cdd8
2018-01-16 12:16:51 +05:30
a5cf750452
Merge pull request #301 from gargrahul/fix_hipPeerToPeer_simple_singlegpu
...
Return pass on single gpu in hipPeerToPeer_simple
[ROCm/hip commit: 07ea65d2a7
2018-01-16 12:16:33 +05:30
851e92ef01
Merge pull request #312 from phani544/nvcctests4
...
[nvcc] Enable hipGetDeviceAttribute
[ROCm/hip commit: d12de062af
2018-01-16 11:05:15 +05:30
0e8da085bf
[HIPIFY][fix][ #211 ] Algorithm for explicit insert of hip include directive
...
If in source CUDA file main header (cuda_runtime.h or cuda.h) is not presented, corresponding HIP main header (hip_runtime.h) should be explicitly included in output hipified file.
[Algorithm]
1. If #pragma once is presented, HIP main header should be placed just after it;
2. Otherwise if any other (not CUDA main) header is presented, HIP main header should be placed just before it;
3. Otherwise HIP main header should be placed in the beginning of output file.
P.S.
There might be one more situation when #ifndef #define ... #endif guard for the entire file is presented (make sense for *.h, *.hpp, *.cuh files). In this case HIP main include should be placed just after such #ifdef, or after #pragma once, if it is also presented. This situation will be handled in a separate change.
[ROCm/hip commit: 09655a0853
2018-01-15 21:05:05 +03:00
16d792681a
[HIPIFY][ #311 ][fix] Get rid of socat in run_test.sh
...
[ROCm/hip commit: 6500cce6aa
2018-01-15 14:20:37 +03:00
12ae481f17
[HIPIFY][tests][win] CUDA samples root env. var is changes
...
Env. var NVCUDASAMPLES_ROOT is changed to NVCUDASAMPLESX_Y_ROOT where X - major ver, Y - minor ver.
Reason: NVCUDASAMPLES_ROOT contains path to CUDA SDK installed last, while NVCUDASAMPLESX_Y_ROOT contains samples of the same version as of CUDA_TOOLKIT_ROOT_DIR.
[ROCm/hip commit: 5df3a9bb3b
2018-01-12 17:15:37 +03:00
a6436cb72b
Merge pull request #310 from emankov/win_testing
...
[HIPIFY][tests] Add Windows testing support
[ROCm/hip commit: f11cb396f0
2018-01-12 16:41:56 +03:00
98a7e887a0
[HIPIFY][tests] Add setlocal to batch script
...
[ROCm/hip commit: fdc10f0856
2018-01-10 21:03:02 +03:00
23ca29818d
[nvcc] Enable hipGetDeviceAttribute
...
[ROCm/hip commit: e9f9456166
2018-01-10 10:51:01 +05:30
7eb3ff1638
[HIPIFY][tests] Add Windows testing support
...
[ROCm/hip commit: 3d5b2ef5f6
2018-01-09 20:20:28 +03:00
263cacc1c2
[HIPIFY][FIX][ #306 ] Eliminate second cuda main include directive
...
// hipified to #include<hip/hip_runtime.h>
#include<cuda.h> // 1st cuda main include (Driver API)
// to eliminate
#include<cuda_runtime.h> // 2nd cuda main include (Runtime API)
HIP has one header hip_runtime.h for both CUDA APIs, thus second cuda main include directive is eliminated entirely.
[ROCm/hip commit: 7e7cfa10cc
2017-12-26 20:54:54 +03:00
75dcb768e0
[nvccWarnings] Fix -Wno-deprecated-declarations in hip_anyall and hip_ballot
...
[ROCm/hip commit: bd60ef9031
2017-12-20 12:05:21 +05:30
56f7455515
Return pass on single gpu in hipPeerToPeer_simple
...
[ROCm/hip commit: 9f62283bad
2017-12-20 09:36:00 +05:30
e2487a261e
[nvccTests] Resubmit hipMemcpyDtoD & inline_asm_vadd
...
[ROCm/hip commit: 7cceebd9ed
2017-12-18 14:46:19 +05:30
f8d610cf61
[nvccWarnings] Fix warnings seen with dtests on nvcc path
...
[ROCm/hip commit: eea7d495c7
2017-12-14 14:10:37 +05:30
d25e05ee87
Merge pull request #290 from gargrahul/fix_hipPeerToPeer_simple
...
Fixed hipPeerToPeer_simple test
[ROCm/hip commit: 26764971c5
2017-12-12 12:50:14 +05:30
3676c97982
Fixed hipPeerToPeer_simple test
...
- Moved test inside p2p dir
- Updated HIPCHECK to ignore hipErrorPeerAccessAlreadyEnabled
- Added check for mGPUs
[ROCm/hip commit: b32489700c
2017-12-11 15:23:18 +05:30
89d9f8ae1c
Fix hipGetDeviceAttribute dtest for HIP/NVCC
...
[ROCm/hip commit: 0782c52271
2017-12-06 15:49:06 +05:30
8ef230eaaf
Temporarily disable a couple tests pending some HCC work
...
[ROCm/hip commit: 62cbe22d50
2017-12-01 21:46:28 +00:00
8d51eaafb6
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 1c5096832e11e7dc6
2017-11-29 21:49:10 +00:00
fcc42f035e
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 d2fd1f5fbaf729f88
2017-11-29 21:36:29 +00:00
11f7d895f4
Merge remote-tracking branch 'origin/master' into feature_use_module_based_dispatch_instead_of_pfe
...
# Conflicts:
# src/hip_module.cpp
[ROCm/hip commit: dc67ca3feb
2017-11-28 17:29:11 +00:00
d31ef2b462
Merge pull request #256 from gargrahul/texture_driver_api_support
...
Texture driver APIs support
[ROCm/hip commit: 0da0426f94
2017-11-27 13:52:39 -06:00
499e247586
Merge pull request #262 from ChrisKitching/frontendaction
...
[HIPIFY] Mostly fix preprocessor-or-template induced issues
[ROCm/hip commit: aa05b3d84e
2017-11-27 17:30:11 +03:00
da1e6b14f5
Porting guides update for texture APIs usage
...
[ROCm/hip commit: 04bc5a1d1f
2017-11-24 12:00:55 +05:30
d8db534805
Modify the set component of the memcpy test (unclear why there is a memset component to begin with).
...
[ROCm/hip commit: 4131b47134
2017-11-21 17:52:01 +00:00
3c936777aa
Re-sync with upstream.
...
[ROCm/hip commit: c5f2b22d0d
2017-11-20 15:34:50 +00:00
d807f528e6
Merge pull request #266 from gargrahul/fix_half2_gfx900
...
Fixed half2 issue on gfx900
[ROCm/hip commit: db378fbc9e
2017-11-20 07:28:41 +05:30
2bb78b3a69
Merge pull request #265 from phani544/nvccTests
...
[nvccTests]Enabled inline_asm_vadd on nvcc
[ROCm/hip commit: 1174534e85
2017-11-20 07:28:29 +05:30
1ec5bab716
Fix test on cuda
...
[ROCm/hip commit: 59956a57ca
2017-11-19 15:31:02 -06:00
64a169fd5c
Merge branch 'feature_natural_indexing' of https://github.com/AlexVlx/HIP
...
[ROCm/hip commit: 5a7a28ad29
2017-11-19 15:25:17 -06:00
dde41ae0aa
Temporarily disable P2P on nvidia (fails on dual GPU)
...
[ROCm/hip commit: e0c3f684ae
2017-11-19 15:21:37 -06:00
962bf7bfda
This implements the trivial change needed to move back from the hip{Something}_{x, y, z} macros to the natural CUDA syntax of Something.{x, y, z}. This is contained in lines 384-404 in hip_runtime.h. All of the other changes have to do with changing unit tests to use this syntax. The macros are retained for backwards compatibility.
...
[ROCm/hip commit: cffd0e14eb
2017-11-19 01:54:12 +00:00
5de28551c1
Fixed test case for GFX900
...
[ROCm/hip commit: 9af0f9cbc1
2017-11-16 09:34:52 +05:30
d0ee6e00fe
Fixed half2 issue on gfx900
...
[ROCm/hip commit: fef496d4f1
2017-11-15 18:52:59 +05:30
65a8021933
[nvccTests]Enabled inline_asm_vadd on nvcc
...
[ROCm/hip commit: 18f6e31d1d
2017-11-14 16:37:59 +05:30
9ef5b7a506
Add an explicit check for proper rewriting of CUDA includes
...
[ROCm/hip commit: ab3debb2f9
2017-11-13 21:02:42 +00:00
6e5f80b345
Add a preprocessor conditional to one of the tests
...
Hurrah, we can cope with ifdefs now (except for kernel launches)
[ROCm/hip commit: 2344ca89f3
2017-11-13 20:58:55 +00:00
Evgeny Mankov
Evgeny Mankov
Maneesh Gupta
Phaneendr-kumar Lanka
Phaneendr-kumar Lanka
Rahul Garg
Ben Sander
Alex Voicu
Chris Kitching