58c6892f4b
Fix ilogb/ilogbf functions to return int
...
This patch will fix hipDoublePrecisionMathDevice test on ThinLTO, which uncovered that hip math_function's ilogb/ilogbf should return type int instead of double. This will match rocdl.
[ROCm/hip commit: 707aaef99d
2017-12-05 23:14:10 +00:00
d0068bfde8
Merge pull request #275 from mangupta/bump_version_1.5
...
Bumped HIP version to 1.5 and updated summary in HIP release notes
[ROCm/hip commit: a0cec19d6e
2017-11-29 15:06:02 -06:00
0ade69d98f
Bumped HIP version to 1.5 and updated summary in HIP release notes
...
Change-Id: I4b612da88236674fac2c585ab6891bdd495511b0
[ROCm/hip commit: f4187b0f16
2017-11-29 13:56:17 +05:30
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
0d2f61daae
Added note in Release notes for texture driver APIs
...
[ROCm/hip commit: a139b533bb
2017-11-27 22:06:50 +05:30
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
9e0e43bfd8
Merge pull request #273 from mangupta/swdev-129574
...
Fix float2int rounding functions
[ROCm/hip commit: 814548407d
2017-11-23 12:04:36 -06:00
2e043b7c0e
Fix float2int rounding functions
...
Change-Id: I67943859a6344c5eec0eaa23418c9b802ef72468
[ROCm/hip commit: 4c96882366
2017-11-23 09:57:24 +05:30
52b93658a9
Merge pull request #263 from ChrisKitching/headers
...
[HIPIFY] Add hipify mappings for all CUDA headers that have HIP equivalents
[ROCm/hip commit: 4e92a034d0
2017-11-22 21:24:21 +03:00
13879387e5
Fixed review comments
...
[ROCm/hip commit: 56862b1c35
2017-11-21 21:19:06 +05:30
03552f2e94
Changed function hipMemcpy_2D to hipMemcpyParam2D
...
[ROCm/hip commit: 9866fa250d
2017-11-21 12:36:24 +05:30
6e332812fc
Merge pull request #264 from pzins/missing_end_marker
...
Fix missing MARKER_END
[ROCm/hip commit: e8ede28ec4
2017-11-20 06:08:01 -06:00
97ee22c3f5
-Moved coGlobals in hipModule class (takes care of multi module case)
...
-Used mutex scope for updating coGlobals
[ROCm/hip commit: f97c5f9a64
2017-11-20 16:23:18 +05:30
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
62f20c6dc8
Update hipModuleGetTexRef API
...
[ROCm/hip commit: c7d60a7a75
2017-11-19 22:10:46 +05:30
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
e5aae56998
Removed redundant desc variable
...
[ROCm/hip commit: ae1eb7a03a
2017-11-15 18:28:27 +05:30
58b37dce5f
-Fixed texture driver API sample
...
-Added hipTexRefSetAddress and hipTexRefSetAddress2D APIs
[ROCm/hip commit: 4b19c2aa0c
2017-11-15 18:23:28 +05:30
65a8021933
[nvccTests]Enabled inline_asm_vadd on nvcc
...
[ROCm/hip commit: 18f6e31d1d
2017-11-14 16:37:59 +05:30
0263292087
Texture code reorganized
...
[ROCm/hip commit: 63680edd30
2017-11-14 11:09:35 +05:30
d917c6b546
Fix missing MARKER_END
...
Logging status of hipCtxSynchronize was missing
Test if hip profiling is active for MARKER_END in ihipPostLaunchKernel
Add MARKER_END after the completion of a kernel launched through
the "grid launch"
[ROCm/hip commit: 6baaed8e48
2017-11-13 16:13:19 -05:00
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
096136750c
Use proper clang diagnostics for printing warnings
...
Much pretty. Very wow
This gives users all the usual power when it comes to manipulating
clang diagnostics. People can pass -Werror can have hipify fail if
it doesn't completely translate a file, for example. Much nicer
than reinventing the wheel.
[ROCm/hip commit: 6b767a59ba
2017-11-13 20:58:55 +00:00
78cf713140
Use a custom FrontendAction to simplify identifier translation
...
Most of what hipify does is really just replacing CUDA idenitifers
with HIP ones. CUDA function calls, preprocessor macro calls,
enum references, types, etc.
This is problematic: calls/types/enum-refs require name resolution
for the AST matcher to work. This fails in the presence of code
deleted by the preprocessor, and in two-pass template compilation.
Instead, we can simply hook the lexer and have it rewrite the
identifiers for us.
This approach means identifier transformations will work correctly
regardless of where they appear (and we get to delete lots of code)
- Fixes #260
- Helps a bit with #207 - it will still fail to translate kernel
calls in preprocessor-ignored code, but everything except kerel
launches should translate correctly now, even in
preprocessor-deleted code.
[ROCm/hip commit: 24cdc5e1d3
2017-11-13 20:58:54 +00:00
c2d54f0154
Add hipify mappings for all CUDA headers that have HIP equivalents
...
I'm particularly running into issues with `device_types.h` in real
CUDA code...
[ROCm/hip commit: 23b5d26582
2017-11-13 17:20:07 +00:00
1451d8fc89
Add a test that exposes #260
...
[ROCm/hip commit: 9165df3848
2017-11-13 16:18:15 +00:00
b13465cfdd
Add a couple of missing CHECK directives to concurrentKernels.cu
...
[ROCm/hip commit: 4ab091ce1e
2017-11-13 16:17:19 +00:00
0fd5239b14
Merge pull request #261 from gargrahul/fix_module_api_sample
...
Fix module_api sample
[ROCm/hip commit: 85975e719d
2017-11-13 11:55:54 +05:30
93a390b9c2
Fix module_api sample
...
[ROCm/hip commit: 83adf6525e
2017-11-13 08:56:39 +05:30
2315ba55d6
Added texture 2D driver API usage example
...
[ROCm/hip commit: 68cc7766c6
2017-11-09 22:35:29 +05:30
49a2c6468e
Texture driver APIs support
...
[ROCm/hip commit: ef09c4918d
2017-11-09 22:10:55 +05:30
56d3677499
Merge pull request #250 from AlexVlx/feature_add_agent_global_support
...
Support for agent globals
[ROCm/hip commit: 31bcb59f62
2017-11-09 07:52:09 +05:30
6368c2abc7
Merge pull request #255 from AlexVlx/remove_some_trailing_whitespace
...
Clean up trailing whitespace so as to reduce noise in #246 .
[ROCm/hip commit: ebd58d43fa
2017-11-08 10:29:19 +05:30
f71d0a049f
Merge pull request #253 from mangupta/hit_add_cmakecmd
...
[hit] Add support for cmake commands as part of test infra
[ROCm/hip commit: caa7174652
2017-11-08 09:50:29 +05:30
35d8af2001
Clean up trailing whitespace so as to reduce noise in #246 .
...
[ROCm/hip commit: d8e323d4b5
2017-11-08 00:08:55 +00:00
d6764bc6ba
Merge pull request #254 from bensander/event_thread_safe
...
Event thread safe
[ROCm/hip commit: 9fd6c18ef8
2017-11-07 17:59:51 +01:00
34943a2c40
Merge pull request #252 from phani544/newTests2
...
More tests for memory,stream & error APIs
[ROCm/hip commit: 247d563114
2017-11-07 10:38:18 +05:30
6fd3d9fda5
identation change in hipPeekAtLastError
...
[ROCm/hip commit: e06c546283
2017-11-07 09:51:32 +05:30
d9db9dabeb
Check for null event in hipEventElapsedTime
...
[ROCm/hip commit: f278f67d2d
2017-11-06 23:49:31 +00:00
465b24123b
hipStreamWaitEvent returns success if event created but not recorded
...
[ROCm/hip commit: 16708dd2e0
2017-11-06 23:49:31 +00:00
f80896d58b
Make hipEvent_t thread safe.
...
Support re-recording of same event by different threads.
- Add criticalData structure to hipEvent_t, similar to mechanism used
for streams, contexts, device. Events are always locked
after streams to avoid deadlock.
- ihipEvent_t::locked_copyCrit can be used to copy critical state
including marker. The critical state in the event can then
be re-recorded.
- refactor hipEventElapsedTime. Remmove stale debug code, native signal
refs.
[ROCm/hip commit: 4a2e6f8955
2017-11-06 23:49:25 +00:00
879699fe0b
[hit] Add support for cmake commands as part of test infra
...
Cmake supports several builtin command-line tools. These tools can
now be specified as part of the HIT block. These commands will be
run during cmake configure step.
Change-Id: I32466c94b2fe1ecdc30249755fc027102295617d
[ROCm/hip commit: 197a7e2600
2017-11-06 16:53:57 +05:30
Aaron En Ye Shi
Ben Sander
Maneesh Gupta
Rahul Garg
Evgeny Mankov
Alex Voicu
Phaneendr-kumar Lanka
Pierre
Chris Kitching
Phaneendr-kumar Lanka