687fac97dc
Updated context management logic:
...
1) hipSetDevice sets a flag so that next call to hipCtxGetCurrent returns primary context on current device
2) hipCtxGetCurrent returns primary context on current device if TLS context stack is empty
3) hipCtxPopCurrent falls back to primary context on current device as default
4) hipCtxPushCurrent, hipCtxSetCurrent and hipCtxCreate reset the flag set in hipSetDevice
[ROCm/clr commit: c4e9323877
2017-08-08 07:02:22 +05:30
ddf72a1b2c
Merge pull request #136 from mangupta/update_install_markdown
...
[doc] Add details of HIP build time dependencies to INSTALL.md
[ROCm/clr commit: 3061e394bf
2017-07-31 11:05:30 -05:00
10a2a2e3e6
Merge pull request #128 from mangupta/cleanup_amdgpu_target_logic
...
[hipcc] Cleanup amdgpu target logic
[ROCm/clr commit: 3ed8c6c034
2017-07-31 11:05:06 -05:00
e090aef2d2
[doc] Add details of HIP build time dependencies to INSTALL.md
...
Change-Id: Iee87d1345aba716d0ce49f7afb45ba073a16be88
[ROCm/clr commit: 87e71ae681
2017-07-31 14:57:32 +05:30
d3d3cedc1d
Merge pull request #134 from gargrahul/fix_hipMemcpy2DAsync
...
fix hipMemcpy2DAsync
[ROCm/clr commit: 9ded1d02a1
2017-07-31 10:27:18 +05:30
602c3466f9
Merge pull request #135 from bensander/fix_tracing
...
Some fixes to tracing.
[ROCm/clr commit: 06b51109c6
2017-07-31 10:24:41 +05:30
5e2f8804ba
[hipcc] Fix amdgpu target selection logic
...
- Refactoring introduced a bug when user does not specify any target via
--amdgpu-target, but has an invalid target specified in
HCC_AMDGPU_TARGET. In this case the selection logic was defaulting to
gf803.
- Removed defaulting to any specific target if rocm_agent_enumerator
fails. hipcc will report this and die if linking was required.
Change-Id: I76131867049fef92331807dd19a926406dcc1d02
[ROCm/clr commit: 8f6c150134
2017-07-31 10:11:19 +05:30
6079b4b4f6
Some fixes to tracing.
...
[ROCm/clr commit: 9e9f384899
2017-07-28 22:13:43 -05:00
5a1578847e
fix hipMemcpy2DAsync
...
[ROCm/clr commit: 320ae86d44
2017-07-29 06:50:56 +05:30
5a891afc7c
Merge pull request #119 from emankov/master
...
[HIPIFY] CUDA RT Textures support
[ROCm/clr commit: fad59ea8c3
2017-07-28 12:12:41 -05:00
8e35e7a287
[hipcc] Cleanup amdgpu target logic
...
Existing logic has a bug. If user specifies targetA via commandline
options, while enumerator returns targetB, hipcc will create a fatbin
containing targets targetA and targetB. enumerator should only be used
when no target is specified by user (commandline or env var).
Change-Id: I6da857f86860c0e671b5988cd858644a08f723b9
[ROCm/clr commit: 2a2c7575eb
2017-07-28 16:18:15 +05:30
2405c239e1
Merge pull request #127 from bensander/pass_module_kname
...
Pass kernel name to HCC dispatch_hsa_kernel, for debug/profile
[ROCm/clr commit: 791063ad6e
2017-07-28 10:19:15 +05:30
004080bff8
Add workweek check to make sure we have a new enough compiler
...
[ROCm/clr commit: 2781293e89
2017-07-27 23:00:58 -05:00
8b7ce77fc0
Merge pull request #122 from bensander/enable_async_null_stream
...
Set HIP_SYNC_NULL_STREAM=0.
[ROCm/clr commit: 8330fb3fe0
2017-07-28 09:15:56 +05:30
0f78021303
Merge pull request #121 from syifan/master
...
Allow hip cmake to link libraries
[ROCm/clr commit: 6835f5ac59
2017-07-28 09:12:15 +05:30
c8b72cb926
Pass kernel name to HCC dispatch_hsa_kernel, for debug/profile
...
[ROCm/clr commit: a282351763
2017-07-27 22:00:15 -05:00
6e010bec22
Update Cuda2Hip.cpp
...
[ROCm/clr commit: 6c5adf42dd
2017-07-28 01:45:24 +03:00
f9780654b8
Update CUDA_Runtime_API_functions_supported_by_HIP.md
...
[ROCm/clr commit: 4486f91350
2017-07-28 01:41:14 +03:00
4940eea975
Update CUDA_Runtime_API_functions_supported_by_HIP.md
...
[ROCm/clr commit: 681dd9e14d
2017-07-28 01:38:50 +03:00
82a347659c
Merge pull request #110 from sunway513/fix_hipEnvVar_test
...
Fix hipEnvVar test
[ROCm/clr commit: bd563bf761
2017-07-27 13:03:43 -05:00
67afe0ec04
Change to use hipDeviceGetPCIBusId api for hipEnvVarDriver test
...
[ROCm/clr commit: b7c34fb80f
2017-07-27 17:41:49 +00:00
1aa0656d34
Set HIP_SYNC_NULL_STREAM=0.
...
Optimizes null stream synchronization so it uses GPU-side dependency
resolution. Requires HCC __hcc_workweek__ > 17300.
[ROCm/clr commit: cd42711134
2017-07-27 11:11:54 -05:00
1edab9f118
Allow hip cmake to link libraries
...
[ROCm/clr commit: 679075e2f0
2017-07-27 11:46:18 -04:00
e586926eb7
[HIPIFY] CUDA RT Textures support
...
[ROCm/clr commit: fa7719b5b5
2017-07-27 18:39:40 +03:00
97edbda54d
Merge pull request #116 from bensander/enable_coh_host
...
Make host memory allocations coherent by default.
[ROCm/clr commit: 9086c14936
2017-07-27 10:45:32 +05:30
a5b3f825c2
Merge pull request #100 from weixingzhang/texture
...
HIP Texture Support
[ROCm/clr commit: 702651fc85
2017-07-26 19:28:15 -05:00
03e01439aa
Merge pull request #114 from emankov/master
...
[HIPIFY] CUDA Stream Callback support
[ROCm/clr commit: 1be14ad733
2017-07-26 19:27:05 -05:00
70783958f3
Merge pull request #113 from mangupta/avoid_rebuild_cache
...
[cmake] No longer rebuild cmake cache on each build
[ROCm/clr commit: 9e120e3dd3
2017-07-26 19:24:43 -05:00
4f06b4157d
Merge pull request #115 from bensander/README
...
Update release notes.
[ROCm/clr commit: ed9647ad25
2017-07-26 19:23:26 -05:00
235b60165f
Make host memory allocations coherent by default.
...
Associated change is to optimize event recording so it uses
agent-scope releaes (since it was only using system-scope release
to support non-coherent host mem).
Flags and environment variables exist to obtain previous behavior
if desired. Options are documented in new performance guide.
[ROCm/clr commit: 6576201ec2
2017-07-26 19:20:34 -05:00
7eeb6e4d9d
Update release notes.
...
[ROCm/clr commit: e29a53f4a6
2017-07-26 19:03:32 -05:00
7428857399
[HIPIFY] CUDA Stream Callback support
...
[ROCm/clr commit: af9dadf20a
2017-07-26 19:29:50 +03:00
013f6cd0cc
[cmake] No longer rebuild cmake cache on each build
...
Cmake cache was being rebuilt on each build. This was being done
to update HIP_VERSION, HCC_VERSION, .hipInfo and .hipVersion.
However, rebuilding cache also re-runs HIT parser which is slow.
Removing the cache rebuild should speed up the build. But user
needs to explicitly rebuild the cache in case HIP_VERSION or
HCC_VERSION changes by calling "make rebuild_cache"
Change-Id: Ia5476eb7105aa614239c4dc7968c37f5e6cb0b29
[ROCm/clr commit: 1b5d19ff36
2017-07-26 13:51:32 +05:30
7fab0b5ecc
[HIPIFY] Finally finished syncing with CUDA 8.0.61 Driver and Runtime… ( #105 )
...
[hipify-clang] Finally finished syncing with CUDA 8.0.61 Driver and Runtime API (including missing data types, D3D, OpenGL, VDPAU and EGL interop).
+ All the Modules are supported now:
1) 4.1 – 4.31 from CUDA 8.0.61 Driver API
2) CUDA_Driver_API_functions_supported_by_HIP.md updated accordingly
3) 4.1 – 4.31 from CUDA 8.0.61 Runtime API
4) CUDA_Runtime_API_functions_supported_by_HIP.md updated accordingly
+ Typos fixing
+ Annotating
[ROCm/clr commit: 9b10efe419
2017-07-26 09:38:03 +05:30
f2ee8ffd69
Merge pull request #111 from bensander/master
...
Enable HCC_OPT_FLUSH=1 (if HCC compiler new enough)
[ROCm/clr commit: c5790aed94
2017-07-25 12:02:33 +05:30
0e9272cfd7
Enable HCC_OPT_FLUSH=1 (if HCC compiler new enough)
...
[ROCm/clr commit: cdc4291431
2017-07-24 18:57:19 -05:00
3015b8a12d
Update Jenkinsfile to run all the built tests
...
[ROCm/clr commit: af8d028aa4
2017-07-24 19:02:00 +00:00
cf850a4bc7
Re-enable hipEnvVarDriver in Jenkinsfile
...
[ROCm/clr commit: ebd9708dfe
2017-07-24 18:53:46 +00:00
237d1318b2
Fix indentation, binary path and add wait on popen calls to hipEnvVar test
...
[ROCm/clr commit: 046e9c570d
2017-07-24 17:16:13 +00:00
801a927eaf
Merge pull request #109 from mangupta/disable_failing_tests
...
[ci] Exclude sporadically failing test in CI only
[ROCm/clr commit: efdb6608aa
2017-07-24 20:22:45 +05:30
535fe58919
[ci] Exclude sporadically failing test in CI only
...
Change-Id: If76bc89d39aa35f5c246cbcd41a997b580832450
[ROCm/clr commit: db24ee4cfa
2017-07-24 15:16:41 +05:30
8a3304a1b4
Merge pull request #108 from adityaatluri/enum-fix
...
fixed device selection during compilation to use rocm_agent_enumerator
[ROCm/clr commit: 5fdcdf72bd
2017-07-21 16:42:48 -05:00
44c2efd050
fixed device selection during compilation to use rocm_agent_enumerator
...
1. Changed hipcc to use rocm_agent_enumerator
2. Changed square sample test to use device variable
[ROCm/clr commit: b10962a539
2017-07-21 15:50:12 -05:00
af5b83c1ab
Merge pull request #107 from mangupta/enable_frexp
...
Renable frexp(f) device math function
[ROCm/clr commit: 99fbfdf9dc
2017-07-20 14:58:45 +05:30
f29245a846
Renable frexp(f) device math function
...
Change-Id: I53c022b8ddf38cd17ddb42eba457b9020db66395
[ROCm/clr commit: 1bd1c6bea8
2017-07-20 14:41:30 +05:30
ec7b63afcd
[dt] hip_texture.h -> hip_texture_types.h
...
Change-Id: If106efa0a2e52105d4025706fdbc291c27352a74
[ROCm/clr commit: 2448b6ee90
2017-07-19 12:46:18 +05:30
46b5ca8681
Merge pull request #106 from kknox/repo-fix
...
[ci] Remove repo.radeon.com build-args; HiP CI unit tests running
[ROCm/clr commit: 8d038399ea
2017-07-19 10:00:59 +05:30
b1ba8a61aa
Merge pull request #103 from gargrahul/enable_memcpytosymbol_tests
...
Enable memcpytosymbol family functions test
[ROCm/clr commit: 35193c6eac
2017-07-18 14:56:01 +05:30
f3b112716e
Enable memcpytosymbol family functions test
...
[ROCm/clr commit: f2d6da3e34
2017-07-18 12:37:37 +05:30
9ef1519512
Merge pull request #102 from mangupta/disable_broken_tests
...
[dt] temporarily disable broken tests
[ROCm/clr commit: a363fce9b9
2017-07-18 11:34:49 +05:30
Rahul Garg
Ben Sander
Maneesh Gupta
Evgeny Mankov
sunway513
Yifan Sun
Evgeny Mankov
Aditya Atluri