bb35299560
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.
2017-11-28 17:23:06 +00:00
4b7cb0624e
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.
2017-11-28 17:23:06 +00:00
7761f63bbc
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...
2017-11-28 17:23:06 +00:00
ea28466b7b
P4 to Git Change 1487653 by wchau@wchau_OCL_boltzmann on 2017/11/28 11:28:09
...
SWDEV-119491 - Add support for cl_amd_assembly_program extension
This is a sub-task of SWDEV-134396. Part 1/4 of the required changes:
(1) OpenCL API / Runtime, (2) ROCm Runtime - compiler invocation, (3) ROCm Driver, (4) Enabling Extension
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_common.hpp#19 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#57 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#45 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl1.2/CL/cl_ext.h#19 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.0/CL/cl_ext.h#35 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.1/CL/cl_ext.h#12 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.2/CL/cl_ext.h#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#215 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#293 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.hpp#42 edit
2017-11-28 11:41:42 -05:00
1f86279494
P4 to Git Change 1487653 by wchau@wchau_OCL_boltzmann on 2017/11/28 11:28:09
...
SWDEV-119491 - Add support for cl_amd_assembly_program extension
This is a sub-task of SWDEV-134396. Part 1/4 of the required changes:
(1) OpenCL API / Runtime, (2) ROCm Runtime - compiler invocation, (3) ROCm Driver, (4) Enabling Extension
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_common.hpp#19 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#57 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#45 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl1.2/CL/cl_ext.h#19 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.0/CL/cl_ext.h#35 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.1/CL/cl_ext.h#12 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.2/CL/cl_ext.h#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#215 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#293 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.cpp#90 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.hpp#42 edit
2017-11-28 11:41:42 -05:00
e304c22316
P4 to Git Change 1487650 by wchau@wchau_OCL_boltzmann on 2017/11/28 11:21:33
...
SWDEV-139422 - Lexa Linux Support - OCL
- fixed the OpenCL/LC sanity failures on Windows by adding support of Polaris12 in Settings::create()
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#38 edit
2017-11-28 11:37:01 -05:00
9e953711e4
Merge 'master' into 'amd-master'
...
Change-Id: I0dccd195692aea64254d91bb899c093459b376b9
2017-11-28 04:11:35 -06:00
57eac2965e
P4 to Git Change 1487469 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/28 03:00:04
...
SWDEV-2 - Change OpenCL version number from 2544 to 2545.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2292 edit
2017-11-28 03:07:17 -05:00
e93a24bdbe
Merge pull request #256 from gargrahul/texture_driver_api_support
...
Texture driver APIs support
2017-11-27 13:52:39 -06:00
6c18df987d
Added note in Release notes for texture driver APIs
2017-11-27 22:06:50 +05:30
f55bfb60f3
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP
2017-11-27 17:33:48 +03:00
b25d199111
Merge pull request #262 from ChrisKitching/frontendaction
...
[HIPIFY] Mostly fix preprocessor-or-template induced issues
2017-11-27 17:30:11 +03:00
713bf036bb
P4 to Git Change 1486756 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/25 03:00:05
...
SWDEV-2 - Change OpenCL version number from 2543 to 2544.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2291 edit
2017-11-25 03:11:18 -05:00
88936eb203
P4 to Git Change 1486724 by wchau@wchau_OCL_boltzmann on 2017/11/24 17:48:34
...
SWDEV-139422 - Lexa Linux Support - OCL
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings.h#21 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_amdil.h#22 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_amdil64.h#21 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_hsail.h#25 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_hsail64.h#25 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings.h#53 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_amdil.h#48 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_amdil64.h#44 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_hsail.h#50 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_hsail64.h#45 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudefs.hpp#150 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#579 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#66 edit
2017-11-24 17:58:22 -05:00
fd406fce20
Re-sync with upstream.
2017-11-24 13:04:12 +00:00
d5aac47d05
Merge 'master' into 'amd-master'
...
Change-Id: I9b15fd04a369c32b6c9bef1c0d67a90b28dfe69b
2017-11-24 04:10:50 -06:00
ab0e2fb2fe
P4 to Git Change 1486480 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/24 03:00:04
...
SWDEV-2 - Change OpenCL version number from 2542 to 2543.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2290 edit
2017-11-24 03:10:32 -05:00
3e9a4cfdd1
Porting guides update for texture APIs usage
2017-11-24 12:00:55 +05:30
460f5d125e
P4 to Git Change 1486043 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/23 03:00:05
...
SWDEV-2 - Change OpenCL version number from 2541 to 2542.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2289 edit
2017-11-23 13:15:43 -05:00
77de4b96cf
Merge pull request #273 from mangupta/swdev-129574
...
Fix float2int rounding functions
2017-11-23 12:04:36 -06:00
c1dc716d76
Merge 'master' into 'amd-master'
...
Change-Id: I74751b8fe8b223a9bdcb18c6e340c5ff8c771a64
2017-11-23 04:10:36 -06:00
822743845c
Fix float2int rounding functions
...
Change-Id: I67943859a6344c5eec0eaa23418c9b802ef72468
2017-11-23 09:57:24 +05:30
dfa532db98
Remove leftover comment.
2017-11-22 19:37:03 +00:00
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
Alex Voicu
Chris Kitching
foreman
Jenkins
Ben Sander
Rahul Garg
Evgeny Mankov
Evgeny Mankov
Maneesh Gupta