Commit Graph

642 Commits

Author SHA1 Message Date
Rahul Garg 5f63267327 Add surface object API 2D test
[ROCm/clr commit: 919eb74a93]
2018-03-04 22:49:23 +05:30
Alex Voicu 4e8e090839 Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_purge_genco
[ROCm/clr commit: 1563d53c92]
2018-02-22 12:08:52 +00:00
Maneesh Gupta b73c021c8f Merge pull request #303 from phani544/nvccTests3
[nvccTests] Enable hipPeerToPeer_simple on nvcc

[ROCm/clr commit: 60bda80014]
2018-02-14 12:47:23 +05:30
Maneesh Gupta e24c6ff5f9 [dtests] Fix HIT block in hipPeerToPeer_simple.cpp
[ROCm/clr commit: cd71f55fd7]
2018-02-14 09:13:50 +05:30
Alex Voicu eab8624938 Re-sync with upstream.
[ROCm/clr commit: a704bd8b44]
2018-02-12 20:20:24 +00:00
Maneesh Gupta b91b2601f3 Merge pull request #299 from mangupta/hipStreamAddCallback
Implement hipStreamAddCallback

[ROCm/clr commit: 8359c2eb5a]
2018-02-02 08:32:41 +05:30
Evgeny Mankov a17cfac3ff [HIPIFY][tests] Add coalescing.cu test
[ROCm/clr commit: e98ee1d627]
2018-02-01 19:41:36 +03:00
Evgeny Mankov 180cf3f29c [HIPIFY][tests] Add vec_add.cu test
[ROCm/clr commit: f7fb6e2199]
2018-02-01 18:34:16 +03:00
Evgeny Mankov d7d35ed98c [HIPIFY][tests] add new line at the end of file
[ROCm/clr commit: 91ef7b50e5]
2018-02-01 17:36:45 +03:00
Evgeny Mankov 3976fbfe15 [HIPIFY][tests] Add intro.cu test
[ROCm/clr commit: 7d71dfd1f7]
2018-02-01 17:07:48 +03:00
Maneesh Gupta 469ffecc71 hipStreamAddCallback.cpp: Replace unistd sleep with sleep_for
Change-Id: I7a5d40a1acd8be76a0f175bcfa731ad89fb88d81


[ROCm/clr commit: 3aab52d7cc]
2018-01-31 10:48:17 +05:30
Evgeny Mankov 2a1267bd43 [HIPIFY][tests] add poisson-api-example test
+ add missing types
+ doc update


[ROCm/clr commit: eef94a74bc]
2018-01-30 19:50:18 +03:00
Evgeny Mankov ea60d1daec [HIPIFY][tests] fix typo
[ROCm/clr commit: 2ae2693c8a]
2018-01-30 18:55:09 +03:00
Maneesh Gupta b2bb274b7e Fix hipStreamAddCallback testcase for nvcc
Change-Id: Ieec4b8d7933d8d68394d21d27132da206111efc8


[ROCm/clr commit: 6a37c60eaa]
2018-01-30 12:32:46 +05:30
Evgeny Mankov 2583a716a7 [HIPIFY] InclusionDirective refactoring
Due to support of cuRAND headers.

+ compound test on all headers is added;
+ missing entities are added with updating the doc;
+ a couple cuRAND tests are added (https://github.com/ROCmSoftwarePlatform/rocRAND/tree/master/benchmark):
  - the following CUDA entities are still unsupported by hipRAND:
      curandMakeMTGP32Constants
      curandMakeMTGP32KernelState
      curandGetDirectionVectors32
      curandDirectionVectorSet_t
      CURAND_DIRECTION_VECTORS_32_JOEKUO6
      curandStateSobol64_t
      curandStateScrambledSobol64_t
      curandGenerateLongLong
  - and the following - by HIP:
      cudaRuntimeGetVersion
  - those entities are handled by CHECK-NOT directive for now.


[ROCm/clr commit: 58f2d3c93f]
2018-01-29 18:33:47 +03:00
Evgeny Mankov f33c431dd9 [HIPIFY][tests][win] Make cudaRegister.cu building on Windows as well
[ROCm/clr commit: 4df35f4c77]
2018-01-24 20:13:23 +03:00
Evgeny Mankov 2ce3ad2a86 Merge pull request #341 from emankov/hipBLAS
[HIPIFY][fix] CUDA and cuBLAS main headers correct handling

[ROCm/clr commit: 591aeccad3]
2018-01-24 18:09:12 +03:00
Evgeny Mankov cbbf54d122 [HIPIFY][fix] CUDA and cuBLAS main headers correct handling
[ROCm/clr commit: aaa9559768]
2018-01-23 23:43:36 +03:00
Evgeny Mankov f78369ce58 [HIPIFY][tests][win] Uncomment @echo off
[ROCm/clr commit: 35bd23fb07]
2018-01-23 21:46:27 +03:00
Evgeny Mankov 34b797d7f2 [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/clr commit: 8fae5663d2]
2018-01-23 21:43:18 +03:00
Alex Voicu 392dd28899 Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_purge_genco
[ROCm/clr commit: 09c704a2d0]
2018-01-17 14:02:19 +00:00
Evgeny Mankov 9c4549fac4 [HIPIFY][tests] remove concurentKernels.cu as it is one of CUDA SDK samples.
[ROCm/clr commit: 284d1cb4e3]
2018-01-16 20:41:08 +03:00
Evgeny Mankov d299b7c5fb Merge pull request #319 from emankov/issue_211
[HIPIFY][fix][#211] Algorithm for explicit insert of hip include directive

[ROCm/clr commit: 8f84e7a4ee]
2018-01-16 19:47:15 +03:00
Evgeny Mankov 220f545a59 Merge pull request #323 from emankov/cudaBuiltins
[HIPIFY][tests] Remove checks on cudaBuiltins

[ROCm/clr commit: b452cdb678]
2018-01-16 19:46:41 +03:00
Evgeny Mankov adcd58db5c Update headers_test_03.cu
[ROCm/clr commit: 3db7dc5b9e]
2018-01-16 19:21:59 +03:00
Evgeny Mankov f7605413bf Update headers_test_04.cu
[ROCm/clr commit: 44d51e794b]
2018-01-16 19:21:14 +03:00
Evgeny Mankov 0769a80c94 [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/clr commit: 42f0966a9e]
2018-01-16 17:13:29 +03:00
Evgeny Mankov dea3b9ed95 [HIPIFY][tests] Add more suffixes to lit config
[ROCm/clr commit: 5c82a2e7fa]
2018-01-16 16:40:31 +03:00
Maneesh Gupta 90a0d88809 Merge pull request #302 from phani544/nvccWarnings
[nvccWarnings] Fix -Wno-deprecated-declarations in hip_anyall and hip…

[ROCm/clr commit: 03c8eb6d91]
2018-01-16 12:16:51 +05:30
Maneesh Gupta 4e9b4d0e5f Merge pull request #301 from gargrahul/fix_hipPeerToPeer_simple_singlegpu
Return pass on single gpu in hipPeerToPeer_simple

[ROCm/clr commit: 08fbdfcfda]
2018-01-16 12:16:33 +05:30
Maneesh Gupta b40529cdb5 Merge pull request #312 from phani544/nvcctests4
[nvcc] Enable hipGetDeviceAttribute

[ROCm/clr commit: 55b8460a93]
2018-01-16 11:05:15 +05:30
Evgeny Mankov 36b0e4003e [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/clr commit: e90a76a1ef]
2018-01-15 21:05:05 +03:00
emankov ed9caac587 [HIPIFY][#311][fix] Get rid of socat in run_test.sh
[ROCm/clr commit: f83df46b8c]
2018-01-15 14:20:37 +03:00
Evgeny Mankov 674bcc42a3 [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/clr commit: 39a0372077]
2018-01-12 17:15:37 +03:00
Evgeny Mankov cef2317438 Merge pull request #310 from emankov/win_testing
[HIPIFY][tests] Add Windows testing support

[ROCm/clr commit: 1b7c9c6480]
2018-01-12 16:41:56 +03:00
Evgeny Mankov 9a0d16f791 [HIPIFY][tests] Add setlocal to batch script
[ROCm/clr commit: b32639d1a8]
2018-01-10 21:03:02 +03:00
Phaneendr-kumar Lanka 015366e29e [nvcc] Enable hipGetDeviceAttribute
[ROCm/clr commit: dc6094cc60]
2018-01-10 10:51:01 +05:30
Phaneendr-kumar Lanka 215b31eba9 [nvccTests] Enable hipGetDeviceAttribute on nvcc
[ROCm/clr commit: df73989d69]
2018-01-10 10:36:25 +05:30
Evgeny Mankov 3e87dc78e6 [HIPIFY][tests] Add Windows testing support
[ROCm/clr commit: 257bc4748c]
2018-01-09 20:20:28 +03:00
Evgeny Mankov 178554cfef [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/clr commit: 5a45d3ca84]
2017-12-26 20:54:54 +03:00
Phaneendr-kumar Lanka a156207c28 [nvccTests] Enable hipPeerToPeer_simple on nvcc
[ROCm/clr commit: 451c7b37cc]
2017-12-20 14:10:47 +05:30
Phaneendr-kumar Lanka bab8090dfc [nvccWarnings] Fix -Wno-deprecated-declarations in hip_anyall and hip_ballot
[ROCm/clr commit: f69762b300]
2017-12-20 12:05:21 +05:30
Rahul Garg 3c6e6c100f Return pass on single gpu in hipPeerToPeer_simple
[ROCm/clr commit: 037ce74fc9]
2017-12-20 09:36:00 +05:30
Maneesh Gupta 290b5f1738 Implement hipStreamAddCallback
Change-Id: Ib851e4d86ba9c8406ca37b88162ea483ccbc9d36


[ROCm/clr commit: cd9ba0d1e1]
2017-12-19 16:06:14 +05:30
Phaneendr-kumar Lanka 4571ec12ac [nvccTests] Resubmit hipMemcpyDtoD & inline_asm_vadd
[ROCm/clr commit: 89bedb74e7]
2017-12-18 14:46:19 +05:30
Alex Voicu 998b5dc3fa Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_purge_genco
[ROCm/clr commit: 4d0d4dc701]
2017-12-14 13:50:49 +00:00
Phaneendr-kumar Lanka 033e2cde33 [nvccWarnings] Fix warnings seen with dtests on nvcc path
[ROCm/clr commit: 0ac125e3db]
2017-12-14 14:10:37 +05:30
Maneesh Gupta 036ef99c2b Merge pull request #290 from gargrahul/fix_hipPeerToPeer_simple
Fixed hipPeerToPeer_simple test

[ROCm/clr commit: 123d719f0c]
2017-12-12 12:50:14 +05:30
Rahul Garg 56754062fc Fixed hipPeerToPeer_simple test
- Moved test inside p2p dir
- Updated HIPCHECK to ignore hipErrorPeerAccessAlreadyEnabled
- Added check for mGPUs


[ROCm/clr commit: 2de0f1cafd]
2017-12-11 15:23:18 +05:30
Alex Voicu aa48cc7b55 This introduces LipoProteinLipase (lpl), a simple tool for creating fat binaries. It represents a direct replacement of the creaky hccgenco.sh script, which had various issues. The format it uses is that of a code object bundle, generated by the Clang Offload Bundler. The output is always suffixed with the ".adipose" extension. It is shared with HCC. The hipcc script and associated tests are modified to use lpl. Help can be obtained by invoking lpl --help. A more computer-sciency / corporate friendly name is likely to be beneficial, which is a reason for choosing easily searchable/replaceable names such as lpl or adipose.
[ROCm/clr commit: 4e0739c68a]
2017-12-08 04:22:57 +00:00