Commit Graph

13197 Commits

Author SHA1 Message Date
foreman d53d7be489 P4 to Git Change 1471997 by lmoriche@lmoriche_opencl_dev2 on 2017/10/18 11:30:15
SWDEV-132888 - OCL kernel execution time is long at the first run on Linux, Vega, HSAIL (ProRender unit test)
	Don't finalize ISA binaries if recompilation is not requested.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#74 edit
2017-10-18 11:39:33 -04:00
Jenkins 3bcd5d3fe3 Merge 'master' into 'amd-master'
Change-Id: I11589b3fff3bb58717f4f6d7045245815bbdf0cc
2017-10-18 04:11:00 -05:00
foreman ce8ed40695 P4 to Git Change 1471770 by johtaylo@johtaylo-jtincrementor2-increment on 2017/10/18 03:00:57
SWDEV-2 - Change OpenCL version number from 2521 to 2522.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2269 edit
2017-10-18 03:10:53 -04:00
Evgeny Mankov 69b1b91311 Merge pull request #195 from emankov/master
[HIPIFY] CUDA RT Textures and Arrays support update
[HIPIFY] cmake changes
[HIPIFY][#199][Partial fix] Fix for cudaLaunchKernel transformation
2017-10-17 18:21:28 +03:00
foreman 0702d1b040 P4 to Git Change 1471146 by johtaylo@johtaylo-jtincrementor2-increment on 2017/10/17 03:00:04
SWDEV-2 - Change OpenCL version number from 2520 to 2521.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2268 edit
2017-10-17 03:08:26 -04:00
Chris Kitching 14061bf0e6 If an output path is given _use it_
Don't append .hip to a user-provided output file...
2017-10-16 17:32:57 +01:00
Chris Kitching bd8a90a05b Operate on a temp file in-place
This copies to the output after operation, instead of working
_on_ the output. This allows includes to work correctly, while
supporting output paths anywhere on the filesystem.

Fixes #208
Fixes #206
2017-10-16 17:32:56 +01:00
foreman a423364ee7 P4 to Git Change 1470466 by johtaylo@johtaylo-jtincrementor2-increment on 2017/10/16 03:00:05
SWDEV-2 - Change OpenCL version number from 2519 to 2520.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2267 edit
2017-10-16 03:06:39 -04:00
foreman ff21b677d8 P4 to Git Change 1470428 by kzhuravl@kzhuravl-fiji-ocllc on 2017/10/16 01:46:27
SWDEV-125823 - Fix perforce opencl/rocm build

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#28 edit
2017-10-16 01:52:40 -04:00
foreman c48579eda1 P4 to Git Change 1470070 by johtaylo@johtaylo-jtincrementor2-increment on 2017/10/14 03:00:22
SWDEV-2 - Change OpenCL version number from 2518 to 2519.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2266 edit
2017-10-14 03:16:12 -04:00
foreman d4911729e6 P4 to Git Change 1469983 by lmoriche@lmoriche_opencl_dev2 on 2017/10/13 17:30:16
SWDEV-133886 - [Linux-Pro][VEGA ][Nuke]OpenCL kernel compilation failed" error is observed with Nuke on Vega10
	- Port CL#1116855 to OCL/ROCm.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#73 edit
2017-10-13 17:36:33 -04:00
foreman 59ed7d2445 P4 to Git Change 1469850 by gandryey@gera-w8 on 2017/10/13 13:56:50
SWDEV-79445 - OCL generic changes and code clean-up
	- Remove obsolete/unused code

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldebugmanager.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#62 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#34 edit
2017-10-13 14:10:40 -04:00
foreman c6ab68be17 P4 to Git Change 1469594 by johtaylo@johtaylo-jtincrementor2-increment on 2017/10/13 03:00:04
SWDEV-2 - Change OpenCL version number from 2517 to 2518.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2265 edit
2017-10-13 03:17:38 -04:00
foreman e0b141b516 P4 to Git Change 1469436 by kzhuravl@kzhuravl-fiji-ocllc on 2017/10/12 18:56:04
SWDEV-125823 - Fix perforce opencl build for upcoming merge

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#72 edit
2017-10-12 19:07:29 -04:00
foreman 05216e1f54 P4 to Git Change 1469411 by wchau@wchau_OCL_boltzmann on 2017/10/12 17:51:56
SWDEV-120036 - Supporting the cl_amd_device_attribute_query on the ROC device
	- divided the query of HSA_AMD_AGENT_INFO_MEMORY_WIDTH by 32 to obtained the globale memory channels as done in ORCA and PAL

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#69 edit
2017-10-12 17:59:29 -04:00
foreman 23d806c514 P4 to Git Change 1469232 by kzhuravl@kzhuravl-fiji-ocllc on 2017/10/12 13:32:01
SWDEV-125823 - Fix perforce opencl build

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#38 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#47 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#20 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#29 edit
2017-10-12 13:38:43 -04:00
Evgeny Mankov f3ef942407 [HIPIFY][#199][Partial fix] Fix for cudaLaunchKernel transformation
[Synopsis]
If any of kernel arguments is a MACRO its location calculation is wrong (location of its definition is actually calculated).
Thus garbage code is being produced on the place of such a MACRO starting from the end of its actual definition.

[Solution]
Add isMacroBodyExpansion and isMacroArgExpansion checks on kernel arguments.
2017-10-12 20:05:42 +03:00
foreman 3c7f4d6c49 P4 to Git Change 1469140 by emankov@em-hsa-lightning on 2017/10/12 10:53:13
SWDEV-86035 - Fix OCL build on Linux after LLVM merge (CL 1469082)

	TODO: PAL build should be fixed accordingly

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#27 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#71 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#28 edit
2017-10-12 10:57:57 -04:00
foreman 469491fd51 P4 to Git Change 1469018 by johtaylo@johtaylo-jtincrementor2-increment on 2017/10/12 03:00:04
SWDEV-2 - Change OpenCL version number from 2516 to 2517.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2264 edit
2017-10-12 03:09:03 -04:00
foreman d9a5ce031c P4 to Git Change 1468787 by wchau@wchau_OCL_boltzmann on 2017/10/11 15:37:08
SWDEV-116372 - Implement OpenCL profile extension for ROCr using AQL-PM4 library

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccounters.cpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccounters.hpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#44 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/perfctr.hpp#6 edit
2017-10-11 15:44:54 -04:00
foreman bf1ff9f160 P4 to Git Change 1468408 by johtaylo@johtaylo-jtincrementor2-increment on 2017/10/11 03:00:05
SWDEV-2 - Change OpenCL version number from 2515 to 2516.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2263 edit
2017-10-11 03:09:36 -04:00
foreman 7b524705c1 P4 to Git Change 1468181 by gandryey@gera-w8 on 2017/10/10 17:42:02
SWDEV-133815 - PAL support for Linux Pro w/OpenCL 2.0 support
	- Fix the clear size in FillBuffer. It's in bytes.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#61 edit
2017-10-10 17:54:02 -04:00
foreman 3bd2d13b40 P4 to Git Change 1467821 by johtaylo@johtaylo-jtincrementor-increment on 2017/10/10 03:00:05
SWDEV-2 - Change OpenCL version number from 2514 to 2515.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2262 edit
2017-10-10 03:06:59 -04:00
Evgeny Mankov ff38a484af [HIPIFY] cmake changes
+ standalone build support
+ WIN MSVC support
+ disable lit testing by default
+ to enable lit testing -DHIPIFY_CLANG_TESTS=1 should be specified

Tested builds:
+ hipify-clang standalone           {Ubuntu 16.04|Windows 10} {Debug|Release} {x86|x64a} {g++|clang++|MSVC 2017} {llvm 3.8.0|llvm 3.9.0} {-DHIPIFY_CLANG_TESTS=1| }
+ HIP {-DHIPIFY_CLANG_LLVM_DIR=..|} {Ubuntu 16.04}            {Debug|Release} {x86|x64a} {hcc}                   {llvm 3.8.0|llvm 3.9.0} {-DHIPIFY_CLANG_TESTS=1| }
2017-10-09 20:28:20 +03:00
Evgeny Mankov 86e0aa63d0 Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP 2017-10-09 20:17:43 +03:00
Alex Voicu b222448efd This fixes incorrect usage of the reader object, which created arcane
mismatches when one reader accessed another's section.
2017-10-09 15:46:38 +01:00
Alex Voicu 2de3ab422f Merge remote-tracking branch 'origin/master' into feature_support_globals_for_module_api 2017-10-09 13:28:13 +01:00
Alex Voicu 582779c6c6 This adds cursory support for globals to the HIP module loading API. The
style is purposefully alien so as to signal that HIP experts should turn
it into HIP worthy code as soon as possible.
2017-10-09 13:27:11 +01:00
Ben Sander c4612f3dc9 Test cleanup. 2017-10-07 07:54:10 -07:00
Ben Sander cb613bb6a8 Add copy_coherency test
Test cache managemenent and synchronization between kernel and copy commands
in separate queues.
2017-10-07 07:54:10 -07:00
Jenkins 1a9e92e412 Merge 'master' into 'amd-master'
Change-Id: I473b92d17f663938831469c09f9cc65340ee30f6
2017-10-06 04:10:55 -05:00
foreman efcf004ed5 P4 to Git Change 1467094 by johtaylo@johtaylo-jtincrementor-increment on 2017/10/06 03:00:04
SWDEV-2 - Change OpenCL version number from 2513 to 2514.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2261 edit
2017-10-06 03:06:50 -04:00
Maneesh Gupta 89ad18584d Merge pull request #196 from mangupta/bump_hip_version
Bump HIP version to 1.4 and update release notes
2017-10-06 10:59:39 +05:30
Maneesh Gupta 253c1bf890 Bump HIP version to 1.4 and update release notes
Change-Id: I3570dedb32fe5fec6f60565c587a3282a4c6c709
2017-10-06 10:26:11 +05:30
Evgeny Mankov 858315b4cd [HIPIFY] CUDA RT Textures and Arrays support update 2017-10-05 16:38:36 +03:00
foreman 3f6483c03c P4 to Git Change 1466632 by johtaylo@johtaylo-jtincrementor-increment on 2017/10/05 03:00:05
SWDEV-2 - Change OpenCL version number from 2512 to 2513.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2260 edit
2017-10-05 03:12:01 -04:00
Maneesh Gupta 7bc98ced9d Merge pull request #188 from gargrahul/texture2D_tests
Added Texture 2D object and reference APIs tests
2017-10-05 12:01:10 +05:30
foreman 051ffe4780 P4 to Git Change 1466505 by wchau@wchau_OCL_boltzmann on 2017/10/04 16:34:02
SWDEV-134554 - OCLPerfConcurrency is failed on Vega10 Lnx Pro after CL#1465654
	- fixed the issue by limit the number of asyn queues to 8, which matches the number of pipes.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdefs.hpp#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#68 edit
2017-10-04 16:45:05 -04:00
Jenkins c282718ccb Merge 'master' into 'amd-master'
Change-Id: I5af5b86d5786354ed8c9ddb9155f6a8b4f23e41b
2017-10-04 04:11:16 -05:00
foreman eb35e4050b P4 to Git Change 1466185 by johtaylo@johtaylo-jtincrementor-increment on 2017/10/04 03:00:04
SWDEV-2 - Change OpenCL version number from 2511 to 2512.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2259 edit
2017-10-04 03:10:50 -04:00
foreman 55a4b40473 P4 to Git Change 1466145 by todli@todli-ubuntu on 2017/10/03 21:32:44
SWDEV-126904 - rocm Pipe: fill device info for Pipe, and initialize Pipe memory object according to clk_pipe_t structure

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#67 edit
2017-10-03 21:40:52 -04:00
foreman 4833d179d9 P4 to Git Change 1466121 by lmoriche@lmoriche_opencl_dev on 2017/10/03 18:21:02
SWDEV-86035 - Fix OCL/PAL build on Linux
	- Remove BUILD_HSA_TARGET (Was HSA's OpenCL/HSA/HSAIL build)
	- Make it possible to build OCL/PAL without OCL/ORCA (BUILD_PAL_DEVICE=yes BUILD_GPU_DEVICE=no)

Affected files ...

... //depot/stg/opencl/drivers/opencl/Makefile#58 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/Makefile#12 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/build/Makefile.api#162 edit
... //depot/stg/opencl/drivers/opencl/compiler/Makefile#68 edit
... //depot/stg/opencl/drivers/opencl/compiler/clc/build/Makefile.clc#19 edit
... //depot/stg/opencl/drivers/opencl/compiler/clc/src/build/Makefile.clc#17 edit
... //depot/stg/opencl/drivers/opencl/compiler/edg/build/Makefile.edg#11 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/Makefile#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/common/build/Makefile.common#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/gpu/scwrapper/build/Makefile.scwrapper#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/build/Makefile.complib#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/complibdefs#11 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/Makefile#17 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/build/Makefile.common#38 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/gpu/build/Makefile.gpu#40 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/build/Makefile.complib#96 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/complibdefs#55 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/llvmdefs#46 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/tools/Makefile#38 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm32/llvmdefs#4 edit
... //depot/stg/opencl/drivers/opencl/compiler/tools/aoc2/build/Makefile.aoc2#33 edit
... //depot/stg/opencl/drivers/opencl/library/Makefile#28 edit
... //depot/stg/opencl/drivers/opencl/library/build/Makefile#8 edit
... //depot/stg/opencl/drivers/opencl/library/build/Makefile.library#60 edit
... //depot/stg/opencl/drivers/opencl/library/gpu/common/build/Makefile.common#28 edit
... //depot/stg/opencl/drivers/opencl/library/hsa/hsail/build/Makefile.hsail#46 edit
... //depot/stg/opencl/drivers/opencl/opencldefs#212 edit
... //depot/stg/opencl/drivers/opencl/openclrules#97 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/binary/build/Makefile.binary#25 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/complib/build/Makefile.complib#43 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/spir/build/Makefile.spir#21 edit
2017-10-03 18:34:48 -04:00
foreman acd5580045 P4 to Git Change 1465968 by asalmanp@asalmanp-ocl-stg on 2017/10/03 13:51:45
SWDEV-79278 - [OCL][VG12] enabling Vega12 in mainline for OCL for Bring-up

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/13550/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#23 edit
2017-10-03 14:03:21 -04:00
Maneesh Gupta 132316fecf Merge pull request #194 from bensander/fix_genco_math_path
Fix math ordering for --genco mode.
2017-10-03 16:17:34 +05:30
Maneesh Gupta cdb5ed9a9c Merge pull request #186 from gargrahul/fix_texture_nvcc
Fix texture support on HIP/NVCC path
2017-10-03 15:10:44 +05:30
foreman 7eca6c1d96 P4 to Git Change 1465784 by johtaylo@johtaylo-jtincrementor-increment on 2017/10/03 03:00:04
SWDEV-2 - Change OpenCL version number from 2510 to 2511.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2258 edit
2017-10-03 03:11:13 -04:00
Ben Sander 2e9b78c274 Fix math ordering for --genco mode. 2017-10-02 21:52:16 +00:00
foreman 676a9d5003 P4 to Git Change 1465654 by wchau@wchau_OCL_boltzmann on 2017/10/02 16:13:43
SWDEV-120036 - Supporting the cl_amd_device_attribute_query on the ROC device
	- resubmit the codes with the addition of global free memory query support

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#66 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#27 edit
2017-10-02 16:31:08 -04:00
Rahul Garg 71a5a0cb42 Fixed review comment 2017-10-02 17:29:08 +05:30
Jenkins 8f10017332 Merge 'master' into 'amd-master'
Change-Id: I15bbc627aa36c8886d0f03f4a2bfad8df2c5a0da
2017-10-02 04:11:34 -05:00