Commit Graph

11608 Commits

Author SHA1 Message Date
foreman f089bd78bb 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


[ROCm/clr commit: ee24635439]
2017-08-09 10:07:10 -04:00
foreman eb72ffa150 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


[ROCm/clr commit: f0156efc5b]
2017-08-09 03:13:00 -04:00
Weixing Zhang a7f95bb8ee [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.


[ROCm/clr commit: e4de2d1138]
2017-08-08 11:18:00 -04:00
foreman 1cf1afd0b1 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


[ROCm/clr commit: fefb3cdd96]
2017-08-08 03:13:29 -04:00
Maneesh Gupta 51c48e4cef Bump min hcc_workweek required for named kernel dispatch to 17312
Change-Id: I8c7b58306b279ed113d03260e4bc6086bb8b4e68


[ROCm/clr commit: dabd6d2bc6]
2017-08-08 11:08:55 +05:30
foreman 114902e52e 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


[ROCm/clr commit: b6c867ed8b]
2017-08-08 00:59:55 -04:00
foreman 6bbfea6065 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


[ROCm/clr commit: f27162ba57]
2017-08-08 00:31:20 -04:00
foreman 27fd9ccb0d 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


[ROCm/clr commit: c0cdecf544]
2017-08-08 00:31:20 -04:00
Rahul Garg 93d30119d0 docs update for memcpytosymbol support
[ROCm/clr commit: a8512b7597]
2017-08-08 09:13:12 +05:30
Rahul Garg 687fac97dc 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


[ROCm/clr commit: c4e9323877]
2017-08-08 07:02:22 +05:30
foreman adac402caa 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


[ROCm/clr commit: bc473f8a3c]
2017-08-07 15:00:33 -04:00
foreman d780734803 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


[ROCm/clr commit: fdba30e5cc]
2017-08-07 15:00:33 -04:00
foreman ca3a1ca083 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


[ROCm/clr commit: 11d000a8c4]
2017-08-05 03:18:14 -04:00
foreman beb6c4ee1c 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


[ROCm/clr commit: 543cc3223a]
2017-08-04 16:48:42 -04:00
foreman 5a1b2dfb08 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


[ROCm/clr commit: bc2edb53b1]
2017-08-04 03:17:42 -04:00
foreman cad1d58dfb 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


[ROCm/clr commit: 5c3633dd1f]
2017-08-03 03:41:56 -04:00
foreman 1931724e2f 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


[ROCm/clr commit: 734b880d80]
2017-08-02 14:55:45 -04:00
foreman 573b84613e 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


[ROCm/clr commit: 994c4018f6]
2017-08-02 13:13:59 -04:00
foreman 68bcaa70f6 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


[ROCm/clr commit: 786006f223]
2017-08-02 11:50:30 -04:00
foreman 4a84fdf3e3 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


[ROCm/clr commit: 47b228ee67]
2017-08-02 11:39:21 -04:00
Rahul Garg b32cf1b3e8 Disable failing test p2p_copy_coherency
[ROCm/clr commit: f916a7654e]
2017-08-02 14:47:13 +05:30
Siu Chi Chan 6598eabd24 implement __threadfence_system
[ROCm/clr commit: b6e22b5c93]
2017-08-02 08:50:18 +00:00
foreman 4fe36f5eef 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


[ROCm/clr commit: e758c4da35]
2017-08-02 03:12:14 -04:00
foreman 2d574a8191 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


[ROCm/clr commit: c3b49d2ce1]
2017-08-01 18:25:45 -04:00
foreman 13b1d666cf 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


[ROCm/clr commit: a8f8ab14f0]
2017-08-01 16:19:37 -04:00
foreman 9fd466e4fc 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


[ROCm/clr commit: 5cf9593233]
2017-08-01 03:11:39 -04:00
Ben Sander ddf72a1b2c Merge pull request #136 from mangupta/update_install_markdown
[doc] Add details of HIP build time dependencies to INSTALL.md

[ROCm/clr commit: 3061e394bf]
2017-07-31 11:05:30 -05:00
Ben Sander 10a2a2e3e6 Merge pull request #128 from mangupta/cleanup_amdgpu_target_logic
[hipcc] Cleanup amdgpu target logic

[ROCm/clr commit: 3ed8c6c034]
2017-07-31 11:05:06 -05:00
Maneesh Gupta e090aef2d2 [doc] Add details of HIP build time dependencies to INSTALL.md
Change-Id: Iee87d1345aba716d0ce49f7afb45ba073a16be88


[ROCm/clr commit: 87e71ae681]
2017-07-31 14:57:32 +05:30
Maneesh Gupta d3d3cedc1d Merge pull request #134 from gargrahul/fix_hipMemcpy2DAsync
fix hipMemcpy2DAsync

[ROCm/clr commit: 9ded1d02a1]
2017-07-31 10:27:18 +05:30
Maneesh Gupta 602c3466f9 Merge pull request #135 from bensander/fix_tracing
Some fixes to tracing.

[ROCm/clr commit: 06b51109c6]
2017-07-31 10:24:41 +05:30
Maneesh Gupta 5e2f8804ba [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


[ROCm/clr commit: 8f6c150134]
2017-07-31 10:11:19 +05:30
foreman a3d0c8e992 P4 to Git Change 1441225 by johtaylo@johtaylo-jtincrementor-increment on 2017/07/29 03:00:04
SWDEV-2 - Change OpenCL version number from 2464 to 2465.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2212 edit


[ROCm/clr commit: 55a79e227a]
2017-07-29 03:13:41 -04:00
Ben Sander 6079b4b4f6 Some fixes to tracing.
[ROCm/clr commit: 9e9f384899]
2017-07-28 22:13:43 -05:00
Rahul Garg 5a1578847e fix hipMemcpy2DAsync
[ROCm/clr commit: 320ae86d44]
2017-07-29 06:50:56 +05:30
Ben Sander 5a891afc7c Merge pull request #119 from emankov/master
[HIPIFY] CUDA RT Textures support

[ROCm/clr commit: fad59ea8c3]
2017-07-28 12:12:41 -05:00
foreman c1846c32fa P4 to Git Change 1440849 by jatang@jatang-opencl-hsa-stg1 on 2017/07/28 10:17:34
SWDEV-95919 - Avoid flushing when PerfCounter is enabled.

	To make sure PerfStart/dispatch/PerfEnd are in the same cmdBuffer

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#27 edit


[ROCm/clr commit: 6b27cc35a1]
2017-07-28 10:35:46 -04:00
Maneesh Gupta 8e35e7a287 [hipcc] Cleanup amdgpu target logic
Existing logic has a bug. If user specifies targetA via commandline
options, while enumerator returns targetB, hipcc will create a fatbin
containing targets targetA and targetB. enumerator should only be used
when no target is specified by user (commandline or env var).

Change-Id: I6da857f86860c0e671b5988cd858644a08f723b9


[ROCm/clr commit: 2a2c7575eb]
2017-07-28 16:18:15 +05:30
foreman e4157876e9 P4 to Git Change 1440715 by johtaylo@johtaylo-jtincrementor-increment on 2017/07/28 03:00:04
SWDEV-2 - Change OpenCL version number from 2463 to 2464.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2211 edit


[ROCm/clr commit: e69572cd38]
2017-07-28 03:14:42 -04:00
Maneesh Gupta 2405c239e1 Merge pull request #127 from bensander/pass_module_kname
Pass kernel name to HCC dispatch_hsa_kernel, for debug/profile

[ROCm/clr commit: 791063ad6e]
2017-07-28 10:19:15 +05:30
Ben Sander 004080bff8 Add workweek check to make sure we have a new enough compiler
[ROCm/clr commit: 2781293e89]
2017-07-27 23:00:58 -05:00
Maneesh Gupta 8b7ce77fc0 Merge pull request #122 from bensander/enable_async_null_stream
Set HIP_SYNC_NULL_STREAM=0.

[ROCm/clr commit: 8330fb3fe0]
2017-07-28 09:15:56 +05:30
Maneesh Gupta 0f78021303 Merge pull request #121 from syifan/master
Allow hip cmake to link libraries

[ROCm/clr commit: 6835f5ac59]
2017-07-28 09:12:15 +05:30
Ben Sander c8b72cb926 Pass kernel name to HCC dispatch_hsa_kernel, for debug/profile
[ROCm/clr commit: a282351763]
2017-07-27 22:00:15 -05:00
Evgeny Mankov 6e010bec22 Update Cuda2Hip.cpp
[ROCm/clr commit: 6c5adf42dd]
2017-07-28 01:45:24 +03:00
Evgeny Mankov f9780654b8 Update CUDA_Runtime_API_functions_supported_by_HIP.md
[ROCm/clr commit: 4486f91350]
2017-07-28 01:41:14 +03:00
Evgeny Mankov 4940eea975 Update CUDA_Runtime_API_functions_supported_by_HIP.md
[ROCm/clr commit: 681dd9e14d]
2017-07-28 01:38:50 +03:00
Ben Sander 82a347659c Merge pull request #110 from sunway513/fix_hipEnvVar_test
Fix hipEnvVar test

[ROCm/clr commit: bd563bf761]
2017-07-27 13:03:43 -05:00
sunway513 67afe0ec04 Change to use hipDeviceGetPCIBusId api for hipEnvVarDriver test
[ROCm/clr commit: b7c34fb80f]
2017-07-27 17:41:49 +00:00
Ben Sander 1aa0656d34 Set HIP_SYNC_NULL_STREAM=0.
Optimizes null stream synchronization so it uses GPU-side dependency
resolution. Requires HCC __hcc_workweek__ > 17300.


[ROCm/clr commit: cd42711134]
2017-07-27 11:11:54 -05:00