Граф коммитов

13197 Коммитов

Автор SHA1 Сообщение Дата
foreman 1d7462b716 P4 to Git Change 1446482 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/12 03:00:04
SWDEV-2 - Change OpenCL version number from 2474 to 2475.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2222 edit
2017-08-12 03:16:29 -04:00
foreman b076dfd8ea P4 to Git Change 1446389 by lmoriche@lmoriche_opencl_dev2 on 2017/08/11 16:56:26
SWDEV-127386 - Revert to HSAIL instead of LC
	- Fixes the asic_reg include files paths.

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/api/v0_8/aclKstatsr800.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/gpu/scwrapper/7XX/devState7XX.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/gpu/scwrapper/7XX/scState7XX.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/gpu/scwrapper/EGNI/devStateEGNI.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/gpu/scwrapper/EGNI/scCompile89.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/gpu/scwrapper/EGNI/scStateEGNI.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/gpu/scwrapper/SI/devStateSI.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/gpu/scwrapper/SI/scStateSI.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/backends/gpu/scwrapper/devState.cpp#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/complibdefs#8 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_amdil.h#18 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_amdil64.h#17 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_hsail.h#18 edit
... //depot/stg/opencl/drivers/opencl/compiler/legacy-lib/utils/v0_8/target_mappings_hsail64.h#18 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/api/v0_8/aclKstatsr800.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/complibdefs#51 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_amdil.h#44 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_amdil64.h#40 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_hsail.h#43 edit
... //depot/stg/opencl/drivers/opencl/compiler/lib/utils/v0_8/target_mappings_hsail64.h#38 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/binary/build/Makefile.binary#22 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/complib/build/Makefile.complib#40 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/spir/build/Makefile.spir#16 edit
2017-08-11 17:09:47 -04:00
Maneesh Gupta c48b1dc8ff [ci] Continue building remaining dtests on failure
Change-Id: Iab7fd53517e0b66dd5f71efb9e65bd2e9c91355b
2017-08-11 15:57:20 +05:30
Maneesh Gupta 88ff8d9da4 [dtests] Fix hip_threadfence_system test's BUILD command
Change-Id: I037c523369e4bddd7a386ffe117fe97a178900fd
2017-08-11 14:49:17 +05:30
Jenkins d9bffbe09a Merge 'master' into 'amd-master'
Change-Id: I91979b423c77711019ab0e2aec11f03e4ad252c9
2017-08-11 04:11:32 -05:00
foreman 77376bcf0b P4 to Git Change 1446008 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/11 03:00:03
SWDEV-2 - Change OpenCL version number from 2473 to 2474.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2221 edit
2017-08-11 03:12:56 -04:00
Siu Chi Chan 8c2cda8f9e add C++11 compilation flags and minor bug fixes 2017-08-10 17:58:36 +00:00
Jenkins 105f08c197 Merge 'master' into 'amd-master'
Change-Id: I958da2155a9578cc0e136651b1d71e1de1b0c0c7
2017-08-10 04:10:42 -05:00
foreman 18cb009335 P4 to Git Change 1445436 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/10 03:00:04
SWDEV-2 - Change OpenCL version number from 2472 to 2473.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2220 edit
2017-08-10 03:21:34 -04:00
Maneesh Gupta 2bd79ab9f5 Merge pull request #138 from scchan/threadfence_system
implement __threadfence_system
2017-08-10 12:51:05 +05:30
Maneesh Gupta 0d537f9966 [dtests] Disable hip_threadfence_system.tst on nvcc
The test needs some more modifications before it is ready for building
on nvcc path. Disabling it for now so that the pull request can be
merged.

Change-Id: I19a894fcda7b2159f86a4e4e95a409c5655d3760
2017-08-10 12:05:58 +05:30
Ben Sander e810da61f3 Merge pull request #146 from gargrahul/docs_update_memcpysymbol
docs update for memcpytosymbol support
2017-08-09 17:48:48 -05:00
Ben Sander dfc87a85bd Merge pull request #145 from gargrahul/context_mgmt_changes
Updated context management logic:
2017-08-09 17:47:45 -05:00
Ben Sander 2a3ba24776 Merge pull request #139 from gargrahul/disable_p2pcoherency_test
Disable failing test p2p_copy_coherency
2017-08-09 16:54:33 -05:00
foreman 2211f5f559 P4 to Git Change 1445200 by skeely@skeely_HSA_linux on 2017/08/09 15:59:56
SWDEV-124331 - Follow HSA loader spec.

	Extend lifetime of loaded ELF and code reader to the lifetime of the loaded executable.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#69 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.hpp#27 edit
2017-08-09 16:24:27 -04:00
foreman ee24635439 P4 to Git Change 1445015 by jatang@jatang-opencl-hsa-stg1 on 2017/08/09 09:53:58
SWDEV-121625 - Fix a memory leak.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#16 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#34 edit
2017-08-09 10:07:10 -04:00
Maneesh Gupta 077c5a75af Merge pull request #147 from mangupta/bump_workweek
Bump min hcc_workweek required for named kernel dispatch to 17312
2017-08-09 14:10:07 +05:30
foreman f0156efc5b P4 to Git Change 1444919 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/09 03:00:05
SWDEV-2 - Change OpenCL version number from 2471 to 2472.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2219 edit
2017-08-09 03:13:00 -04:00
Weixing Zhang e4de2d1138 [HIP Texture] The GPU virtual address for texture memory needs to be
aligned.

In hcc_am, a bigger buffer will be allocated for alignment purpose
and _unalignedDevicePointer is added in struct AmPointerInfo for
original allocated address.
2017-08-08 11:18:00 -04:00
foreman fefb3cdd96 P4 to Git Change 1444368 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/08 03:00:05
SWDEV-2 - Change OpenCL version number from 2470 to 2471.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2218 edit
2017-08-08 03:13:29 -04:00
Maneesh Gupta dabd6d2bc6 Bump min hcc_workweek required for named kernel dispatch to 17312
Change-Id: I8c7b58306b279ed113d03260e4bc6086bb8b4e68
2017-08-08 11:08:55 +05:30
foreman b6c867ed8b P4 to Git Change 1444314 by lmoriche@lmoriche_palamida on 2017/08/08 00:46:38
SWDEV-102733 - [OCL-LC-ROCm] Cmake build Write CMakeLists.txt to enable building with and without the DK environment
	- Restore the change in CL#1444178, was - Use the internal libelf instead of the system's when building with cmake.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#10 edit
2017-08-08 00:59:55 -04:00
foreman f27162ba57 P4 to Git Change 1444296 by lmoriche@lmoriche_palamida on 2017/08/08 00:10:29
SWDEV-102733 - [OCL-LC-ROCm] Cmake build Write CMakeLists.txt to enable building with and without the DK environment
	- Disable LLVM object compression. Allows closed source LLVM binaries to run with the open source runtime
	- Define the DEBUG macro for Debug build types
	- Use the prepared amdgcn lib instead of the static lib when generating the .bc includes for the runtime.

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#14 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/CMakeLists.txt#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/CMakeLists.txt#8 edit
2017-08-08 00:31:20 -04:00
foreman c0cdecf544 P4 to Git Change 1444296 by lmoriche@lmoriche_palamida on 2017/08/08 00:10:29
SWDEV-102733 - [OCL-LC-ROCm] Cmake build Write CMakeLists.txt to enable building with and without the DK environment
	- Disable LLVM object compression. Allows closed source LLVM binaries to run with the open source runtime
	- Define the DEBUG macro for Debug build types
	- Use the prepared amdgcn lib instead of the static lib when generating the .bc includes for the runtime.

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#14 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/CMakeLists.txt#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/CMakeLists.txt#8 edit
2017-08-08 00:31:20 -04:00
Rahul Garg a8512b7597 docs update for memcpytosymbol support 2017-08-08 09:13:12 +05:30
Rahul Garg c4e9323877 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
2017-08-08 07:02:22 +05:30
foreman bc473f8a3c P4 to Git Change 1444178 by lmoriche@lmoriche_opencl_dev2 on 2017/08/07 14:50:37
SWDEV-102733 - [OCL-LC-ROCm] Cmake build Write CMakeLists.txt to enable building with and without the DK environment
	- Use the internal libelf instead of the system's when building with cmake.
	- Don't include codecvt if WITH_LIQUID_FLASH is not defined
	- Don't memset the device::Kernel::workGroupInfo_, there's a std::string in it. The constructor already zeroes all the fields.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#8 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_lqdflash_amd.cpp#21 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#25 edit
2017-08-07 15:00:33 -04:00
foreman fdba30e5cc P4 to Git Change 1444178 by lmoriche@lmoriche_opencl_dev2 on 2017/08/07 14:50:37
SWDEV-102733 - [OCL-LC-ROCm] Cmake build Write CMakeLists.txt to enable building with and without the DK environment
	- Use the internal libelf instead of the system's when building with cmake.
	- Don't include codecvt if WITH_LIQUID_FLASH is not defined
	- Don't memset the device::Kernel::workGroupInfo_, there's a std::string in it. The constructor already zeroes all the fields.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#8 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_lqdflash_amd.cpp#21 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#25 edit
2017-08-07 15:00:33 -04:00
foreman 11d000a8c4 P4 to Git Change 1443936 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/05 03:00:05
SWDEV-2 - Change OpenCL version number from 2469 to 2470.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2217 edit
2017-08-05 03:18:14 -04:00
foreman 543cc3223a P4 to Git Change 1443821 by asalmanp@asalmanp-ocl-stg on 2017/08/04 16:24:19
SWDEV-79278 - [OCL][PAL] use HwPipeBottom to query the start time of an event.
	The reason is that if there are many dispatches run in a loop with profiling enabled, then it is possible that the HwPipeStart of an event can occur before the HwPipeBottom of the previous dispatch and this will affect the timing reported by profiling.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/13242/diff/1/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paltimestamp.cpp#3 edit
2017-08-04 16:48:42 -04:00
foreman bc2edb53b1 P4 to Git Change 1443478 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/04 03:00:04
SWDEV-2 - Change OpenCL version number from 2468 to 2469.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2216 edit
2017-08-04 03:17:42 -04:00
foreman 5c3633dd1f P4 to Git Change 1442964 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/03 03:00:04
SWDEV-2 - Change OpenCL version number from 2467 to 2468.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2215 edit
2017-08-03 03:41:56 -04:00
foreman 734b880d80 P4 to Git Change 1442704 by lmoriche@lmoriche_opencl_dev2 on 2017/08/02 14:33:33
SWDEV-1 - Add the required license files.

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/LICENSE.TXT#1 add
... //depot/stg/opencl/drivers/opencl/compiler/lib/linker/tools/opencl-link/LICENSE.TXT#1 add
2017-08-02 14:55:45 -04:00
foreman 994c4018f6 P4 to Git Change 1442652 by bsumner@bsumner-lin-opencl on 2017/08/02 13:00:18
SWDEV-129003 - fix incorrect code for pal device

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#43 edit
2017-08-02 13:13:59 -04:00
foreman 786006f223 P4 to Git Change 1442616 by bsumner@bsumner-lin-opencl on 2017/08/02 11:33:24
SWDEV-129003 - correct logic for library control to fix regression

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#42 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#68 edit
2017-08-02 11:50:30 -04:00
foreman 47b228ee67 P4 to Git Change 1442588 by jatang@jatang-opencl-hsa-stg2 on 2017/08/02 10:51:02
SWDEV-95919 - Expose all counters PAL supports.

	At the request from CodeXL, and with the counter block index list provided by CodeXL.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.cpp#13 edit
2017-08-02 11:39:21 -04:00
Rahul Garg f916a7654e Disable failing test p2p_copy_coherency 2017-08-02 14:47:13 +05:30
Siu Chi Chan b6e22b5c93 implement __threadfence_system 2017-08-02 08:50:18 +00:00
foreman e758c4da35 P4 to Git Change 1442443 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/02 03:00:05
SWDEV-2 - Change OpenCL version number from 2466 to 2467.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2214 edit
2017-08-02 03:12:14 -04:00
foreman c3b49d2ce1 P4 to Git Change 1442310 by gandryey@gera-w8 on 2017/08/01 18:13:31
SWDEV-128975 - Enable khr FP16 extension from runtime

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#20 edit
2017-08-01 18:25:45 -04:00
foreman a8f8ab14f0 P4 to Git Change 1442246 by bsumner@bsumner-lin-opencl on 2017/08/01 16:04:23
SWDEV-128916 - use AMD_GPU_FORCE_SINGLE_FP_DENORM in determining daz_opt library control

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#41 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#67 edit
2017-08-01 16:19:37 -04:00
Jenkins ec23826498 Merge 'master' into 'amd-master'
Change-Id: Id400e2e3c0fa393ca934634dee46496aca8ade21
2017-08-01 04:11:20 -05:00
foreman 5cf9593233 P4 to Git Change 1441906 by johtaylo@johtaylo-jtincrementor-increment on 2017/08/01 03:00:04
SWDEV-2 - Change OpenCL version number from 2465 to 2466.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2213 edit
2017-08-01 03:11:39 -04:00
Ben Sander 3061e394bf Merge pull request #136 from mangupta/update_install_markdown
[doc] Add details of HIP build time dependencies to INSTALL.md
2017-07-31 11:05:30 -05:00
Ben Sander 3ed8c6c034 Merge pull request #128 from mangupta/cleanup_amdgpu_target_logic
[hipcc] Cleanup amdgpu target logic
2017-07-31 11:05:06 -05:00
Maneesh Gupta 87e71ae681 [doc] Add details of HIP build time dependencies to INSTALL.md
Change-Id: Iee87d1345aba716d0ce49f7afb45ba073a16be88
2017-07-31 14:57:32 +05:30
Jenkins b7ec447657 Merge 'master' into 'amd-master'
Change-Id: I510b01084b5aad8382044fe828a099896fa12aff
2017-07-31 04:11:17 -05:00
Maneesh Gupta 9ded1d02a1 Merge pull request #134 from gargrahul/fix_hipMemcpy2DAsync
fix hipMemcpy2DAsync
2017-07-31 10:27:18 +05:30
Maneesh Gupta 06b51109c6 Merge pull request #135 from bensander/fix_tracing
Some fixes to tracing.
2017-07-31 10:24:41 +05:30
Maneesh Gupta 8f6c150134 [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
2017-07-31 10:11:19 +05:30