6bddac1cfa
Merge pull request #263 from ChrisKitching/headers
...
[HIPIFY] Add hipify mappings for all CUDA headers that have HIP equivalents
2017-11-22 21:24:21 +03:00
4e0baa79b3
P4 to Git Change 1485337 by todli@todli-win-opencl-kv1 on 2017/11/21 18:53:38
...
SWDEV-126904 - Fix conformance Pipe read/write tests failures for ROCm/LC path and PAL/LC path
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#32 edit
2017-11-21 18:58:23 -05:00
0e496d9c9f
P4 to Git Change 1485325 by gandryey@gera-lnx-rcf on 2017/11/21 18:10:36
...
SWDEV-136068 - PAL support for Linux Pro: SSG support on OpenCL 1.2
- Enable LiquidFlash extension when DGMA available only.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#37 edit
2017-11-21 18:17:45 -05:00
0755f1fc26
Modify the set component of the memcpy test (unclear why there is a memset component to begin with).
2017-11-21 17:52:01 +00:00
38029f2849
Fixed review comments
2017-11-21 21:19:06 +05:30
fb1021cc0a
This corrects how addresses are formed for symbols which reside in shared objects. For this case, the .value component of an ELF symbol holds the offset from the base VA where the shared object was loaded. Thus, to correctly obtain the VA of the object refered by the symbol, we must add the offset to the VA where the shared object is loaded. We were already doing this correctly for symbols denoting functions, but we were incorrect for those denoting objects.
2017-11-21 13:15:13 +00:00
c0f413a07a
Merge 'master' into 'amd-master'
...
Change-Id: Ie37ee84b9c4f2808bd0dc2986e20feeb4449cea3
2017-11-21 04:10:37 -06:00
e7579ebca0
P4 to Git Change 1484863 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/21 03:00:05
...
SWDEV-2 - Change OpenCL version number from 2540 to 2541.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2288 edit
2017-11-21 03:11:16 -05:00
24307fe5c4
Changed function hipMemcpy_2D to hipMemcpyParam2D
2017-11-21 12:36:24 +05:30
f8c1c1b38e
Refactor the __device__ versions of memset and memcpy to be less awkward i.e. not return nullptr as opposed to the destination pointer (it can only be assumed it was done for maximum confusion) and actually unroll as they claim to. Change all of the {to, from}Symbol functions to use hipModuleGetGlobal, as opposed to hc::accelerator::get_symbol_address which is no longer valid with module based dispatch.
2017-11-21 02:40:34 +00:00
d3a8bbdeb5
P4 to Git Change 1484669 by wchau@wchau_WIN_OCL_HSA on 2017/11/20 17:33:26
...
SWDEV-138242 - [QR] Screen corruption when opening DVR or Radeon Settings overlay in several apps (PUBG, Dirt3, GoW4, etc)
- Fix the mapping entries for 10-bits channel format between the OGL surface formats (hData.format) returned by wglResourceAttachAMD function and the OCL image format. No alpha channel is supported.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevicegl.cpp#8 edit
2017-11-20 17:44:21 -05:00
24f8a93ff7
Clean-up some remaining noise in program_state.cpp.
2017-11-20 22:41:46 +00:00
27bc487635
Correct ill-formed merge in earlier commit and adjust for differences with the new CUDA natural indexing mechanism.
2017-11-20 16:33:52 +00:00
30d90dab38
Re-sync with upstream.
2017-11-20 15:34:50 +00:00
a1e0c96689
Merge pull request #264 from pzins/missing_end_marker
...
Fix missing MARKER_END
2017-11-20 06:08:01 -06:00
eff09fcd86
-Moved coGlobals in hipModule class (takes care of multi module case)
...
-Used mutex scope for updating coGlobals
2017-11-20 16:23:18 +05:30
b2c9b7af01
Merge 'master' into 'amd-master'
...
Change-Id: I4cbe49d40a046c80e4968aac8fa7fd760e2d9709
2017-11-20 04:10:56 -06:00
4477d3d314
Merge pull request #266 from gargrahul/fix_half2_gfx900
...
Fixed half2 issue on gfx900
2017-11-20 07:28:41 +05:30
29c0ab8401
Merge pull request #265 from phani544/nvccTests
...
[nvccTests]Enabled inline_asm_vadd on nvcc
2017-11-20 07:28:29 +05:30
aeadc3f18f
Fix test on cuda
2017-11-19 15:31:02 -06:00
a43262e699
Merge branch 'feature_natural_indexing' of https://github.com/AlexVlx/HIP
2017-11-19 15:25:17 -06:00
fc34fd6f03
Temporarily disable P2P on nvidia (fails on dual GPU)
2017-11-19 15:21:37 -06:00
76f174b536
Update hipModuleGetTexRef API
2017-11-19 22:10:46 +05:30
0cc921f103
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.
2017-11-19 01:54:12 +00:00
07c9337f57
This actually (tries) to do the right thing all the way, by using memcpy for bitcasting, and not rely on undefined behaviour of a different flavour as a substitute for the original undefined behaviour. Note that the compiler will (should) optimise down to the same emitted code, since this is a pattern it understands.
2017-11-18 01:16:31 +00:00
d7d77cfbe1
This fixes some outright quaint choices made when implementing HIP's bitwise conversion functions, by using simple reinterpret_casts, as is idiomatic. These functions are supposed to be re-entrant, correct and efficient. Sadly, they were neither: they hid a massive race condition against a value stored in global memory, which means that they were also unreasonably slow if they ever managed to be correct, and relied on union based type punning which is in a grey area of the standard. It is difficult to ascertain what may have been the reason for coming up with this quirky solution.
2017-11-17 16:00:28 +00:00
d0a0f6575e
P4 to Git Change 1483566 by gandryey@gera-lnx-rcf on 2017/11/16 18:12:27
...
SWDEV-79445 - Remove unused fields
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl_amd.hpp#19 edit
2017-11-16 18:22:09 -05:00
45ac5b70df
Merge remote-tracking branch 'origin/master' into feature_use_module_based_dispatch_instead_of_pfe
2017-11-16 23:20:15 +00:00
d0c3f25bf9
P4 to Git Change 1483131 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/16 03:00:04
...
SWDEV-2 - Change OpenCL version number from 2539 to 2540.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2287 edit
2017-11-16 03:07:49 -05:00
cfc9f87465
Fixed test case for GFX900
2017-11-16 09:34:52 +05:30
5ec0d059a3
P4 to Git Change 1483021 by lmoriche@lmoriche_opencl_dev2 on 2017/11/15 21:49:30
...
SWDEV-118564 - [OCL-LC-ROCm] Disable HSAILProgram and HSAILKernel if the compiler library is not available.
Affected files ...
... //depot/stg/opencl/drivers/opencl/opencldefs#222 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#214 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#39 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#76 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#76 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.cpp#89 edit
2017-11-15 21:58:49 -05:00
88783fe59b
P4 to Git Change 1482981 by skeely@skeely_HSA_linux on 2017/11/15 18:17:38
...
SWDEV-136633 - Remove correlation handle.
Not used by debugger or profiler, dead code.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#47 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#15 edit
2017-11-15 18:24:51 -05:00
0e9cee7205
P4 to Git Change 1482914 by wchau@wchau_OCL_boltzmann on 2017/11/15 16:12:45
...
SWDEV-137374 - Collecting counters from some TCC, TCP and TA block instances causes kernel to hang
- fixed by using the new AQLProfile feature to obtain precise size for command/data buffers
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccounters.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#46 edit
2017-11-15 16:22:18 -05:00
20947f80fb
Fixed half2 issue on gfx900
2017-11-15 18:52:59 +05:30
e2e499461a
Removed redundant desc variable
2017-11-15 18:28:27 +05:30
edbfeeb141
-Fixed texture driver API sample
...
-Added hipTexRefSetAddress and hipTexRefSetAddress2D APIs
2017-11-15 18:23:28 +05:30
9fa3ed4f6f
[nvccTests]Enabled inline_asm_vadd on nvcc
2017-11-14 16:37:59 +05:30
0e891db6e4
P4 to Git Change 1482174 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/14 03:00:05
...
SWDEV-2 - Change OpenCL version number from 2538 to 2539.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2286 edit
2017-11-14 03:13:39 -05:00
e536eb038d
Texture code reorganized
2017-11-14 11:09:35 +05:30
e60a95d7dd
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"
2017-11-13 16:13:19 -05:00
642af94492
Add an explicit check for proper rewriting of CUDA includes
2017-11-13 21:02:42 +00:00
e8c1e7bb11
Add a preprocessor conditional to one of the tests
...
Hurrah, we can cope with ifdefs now (except for kernel launches)
2017-11-13 20:58:55 +00:00
506deca07f
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.
2017-11-13 20:58:55 +00:00
7a441aef10
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.
2017-11-13 20:58:54 +00:00
9014c89f04
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...
2017-11-13 17:20:07 +00:00
0afc6b2e95
Add a test that exposes #260
2017-11-13 16:18:15 +00:00
4353fc06d7
Add a couple of missing CHECK directives to concurrentKernels.cu
2017-11-13 16:17:19 +00:00
5d03b99851
Merge 'master' into 'amd-master'
...
Change-Id: I2d2b621a937a8a645072fe76c371ccb36f059a6e
2017-11-13 04:11:00 -06:00
7f3653af7a
Merge pull request #261 from gargrahul/fix_module_api_sample
...
Fix module_api sample
2017-11-13 11:55:54 +05:30
e434a23be5
Fix module_api sample
2017-11-13 08:56:39 +05:30
Evgeny Mankov
foreman
Alex Voicu
Rahul Garg
Jenkins
Ben Sander
Maneesh Gupta
Phaneendr-kumar Lanka
Pierre
Chris Kitching