2
0
Gráfico de cometimentos

4345 Cometimentos

Autor(a) SHA1 Mensagem Data
Alex Voicu 1df423165b Remove leftover noise. 2019-11-06 02:46:21 +02:00
Alex Voicu 55fd1363e2 __half2 should walk like CUDA and talk like CUDA 2019-11-06 02:43:04 +02:00
Rahul Garg 6833886449 Merge pull request #1626 from mhbliao/hliao/master/fix.windows.build
Use portable macro for deprecation message.
2019-11-05 10:08:43 -08:00
Evgeny Mankov 7b1ca3dd91 Merge pull request #1595 from emankov/cmake
[HIP][cmake] Simplify `UNIX` related code (the beginning)
2019-11-05 20:30:55 +03:00
Michael LIAO 7ca43b98d1 Use portable macro for deprecation message. 2019-11-05 11:51:00 -05:00
Evgeny Mankov cf5d1caab3 Merge pull request #1624 from emankov/hipify
[HIPIFY][#1409] Fix for kernel launch macro expansion
2019-11-05 14:04:51 +03:00
Evgeny Mankov a1c380f38d [HIPIFY][#1409] Fix for kernel launch macro expansion
+ Add a corresponding test kernel_launch_01.cu
+ Add isBefore() check to avoid crash on Replacement with negative length

TODO:
+ Compatibility with former LLVM versions
+ More complicated kernel launch tests
2019-11-05 14:00:13 +03:00
Rahul Garg 8b3fce8069 Deprecate HIP Markers (#1622)
* Deprecate HIP markers

* Deprecate profiler start/stop
2019-11-05 12:32:59 +05:30
Aryan Salmanpour 7a3d592ed0 [hip][tests] Add two more workgroup sizes for testing hipLaunchCooperativeKernel (#1613) 2019-11-05 12:32:46 +05:30
foreman cbbe0e78cf P4 to Git Change 2024544 by cpaquot@cpaquot-ocl-lc-lnx on 2019/11/04 16:35:14
SWDEV-145570 - [HIP] Fetched properties from current device and not default 0 one.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_device_runtime.cpp#21 edit
2019-11-04 16:42:31 -05:00
foreman bd34138596 P4 to Git Change 2024543 by cpaquot@cpaquot-ocl-lc-lnx on 2019/11/04 16:32:23
SWDEV-206239 - [HIP] Return hipErrorMemoryAllocation for fine grained VRAM for now

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#83 edit
2019-11-04 16:39:35 -05:00
foreman 759a2c2ce5 P4 to Git Change 2024454 by axie@axie-hip-rocm on 2019/11/04 14:38:31
SWDEV-198863 - Options for hip-clang-vdi path to provide the chicken bits, or functional equivalents to HCC_DB (phase 1)

	1. The log macros is turned off for release build.  So log functions has zero impact to release build.
	2. The log macros have level, mask, condition control. So we can have more control to avoid log flooding.

	I also adjusted some existing log to use new log functions.
	1. To excercise and test the new log functions.
	2. To improve performance slightly.
	3. The change is mainly for HIP-ROCM, we can move more in next phases for PAL or ORCA.
	4. I make these log feature unavailable for release build. We can revert to old log functions for release build in a case by case method.

	Tests:
	1. http://ocltc.amd.com:8111/viewModification.html?modId=128289&personal=true&tab=vcsModificationBuilds
	http://ocltc.amd.com:8111/viewModification.html?modId=128358&personal=true&tab=vcsModificationBuilds

	2. release build, run hip program, there is no log
	3. fastdebug build, run hip program,
	export LOG_LEVEL=3
	export GPU_LOG_MASK=4294967295
	There was a lot of logs.

	4. fastdebug build, run hip program,
	export LOG_LEVEL=2
	export GPU_LOG_MASK=4294967295
	There was no logs.

	5. fastdebug build, run hip program,
	export LOG_LEVEL=3
	export GPU_LOG_MASK=4294967294
	There was much less logs.

	6. fastdebug build, run hip program,
	export LOG_LEVEL=3
	export GPU_LOG_MASK=47102
	There was even much less logs. The logs was expected according to the mask.

	7. Tested step 2 to 6 similarily in Windows and Linux

	ReviewBoard: http://ocltc.amd.com/reviews/r/18215

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_internal.hpp#46 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#82 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_stream.cpp#26 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hiprtc_internal.hpp#2 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#29 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/comgrctx.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.cpp#29 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#68 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#137 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#91 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#100 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/commandqueue.cpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/runtime.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/debug.hpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#323 edit
2019-11-04 14:44:59 -05:00
Jeff Daily 6c3479a155 fix race condition in hipEventRecord 2019-11-04 17:45:11 +00:00
foreman 1405654d70 P4 to Git Change 2024314 by kjayapra@0_HIPWS_LNX1_ROCM on 2019/11/04 11:44:45
SWDEV-206759 - Fixing Compilation error.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#47 edit
2019-11-04 11:53:27 -05:00
foreman f55f2b8cee P4 to Git Change 2024251 by kjayapra@0_HIPWS_LNX1_ROCM on 2019/11/04 10:07:42
SWDEV-206759 - Adding support for duplicate global vars

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_internal.hpp#45 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#81 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#46 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#48 edit
... //depot/stg/opencl/drivers/opencl/make/hip.git/tests/build/Makefile.hip_tests#30 edit
2019-11-04 10:13:20 -05:00
Alex Voicu ed0d6ec51e Separate volatile for clarity. Handle assignment. 2019-11-02 22:02:08 +02:00
Evgeny Mankov 7142b884ab [HIPIFY] Introduce --cuda-gpu-arch as hipify-clang's option
+ Pass it to clang if specified
2019-11-02 14:19:31 +03:00
Alex Voicu 2d76dde05b Accessors should work even when oddly volatile. 2019-11-01 22:18:01 +02:00
Evgeny Mankov 48bb6df7e2 Merge pull request #1615 from emankov/hipify
[HIPIFY][CUB][#1460][perl] Add "cub::" namespace prefix support in hipify-perl as well
2019-11-01 14:35:55 +03:00
Evgeny Mankov c5a2a2daf2 [HIPIFY][CUB][#1460][perl] Add "cub::" namespace prefix support in hipify-perl as well 2019-11-01 14:34:18 +03:00
Rahul Garg 1bec1445bb Merge pull request #1582 from amd-lthakur/hipExtMLK
Adding a directed test case for hipExtModuleLaunchKernel() api.
2019-10-31 17:13:26 -07:00
Rahul Garg 2199f8a6c6 Merge pull request #1598 from lmoriche/master
Fix a code object memory corruption
2019-10-31 17:12:24 -07:00
Rahul Garg f556e15361 Add stream 2019-10-31 12:15:56 -04:00
Rahul Garg 0718ba0f00 Fix HIP init calls in hipMemcpy2DFromArray 2019-10-31 12:15:56 -04:00
Evgeny Mankov e79fd55d01 [HIPIFY][cmake][#1572] Fix: Do not override CMAKE_INSTALL_PREFIX
Affects building with HIP, standalone building is not changed
2019-10-31 16:55:06 +03:00
Rahul Garg 07f4431de8 Formatting changes 2019-10-30 18:12:51 -07:00
Rahul Garg cd1435cbc7 Formatting changes ,variable name and check update 2019-10-30 18:09:21 -07:00
Rahul Garg aeb7cebbad Merge pull request #1515 from ansurya/tex_unbind_issue_fix
Fix undefined ref to hipUnbindTexture for texture types
2019-10-30 17:54:15 -07:00
foreman e0107c5792 P4 to Git Change 2022168 by jujiang@JJ-OCL-hip on 2019/10/30 18:06:41
SWDEV-208594 - [HIP][Windows] Output mismatch with texture ref test functions with float4 type

	-Fix TexRef1D float/float4, and TexRef2D tests.
	http://ocltc.amd.com/reviews/r/18203/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_texture.cpp#26 edit
2019-10-30 18:11:27 -04:00
Laurent Morichetti 3243f06eef Addressed review comments
Change comment "must exceed" to "must be no shorter than"
move the std::string instead of creating a copy
2019-10-30 13:14:41 -07:00
Evgeny Mankov 961bc5737e Merge pull request #1593 from emankov/doc
[HIP][cmake] Move all *_INSTALL_DIR variables up before first add_subdirectory()
2019-10-30 22:10:05 +03:00
foreman 234e21e08c P4 to Git Change 2021977 by kjayapra@1_HIPWS_LNX1_PAL on 2019/10/30 13:27:19
SWDEV-209747 - Improve HIP Error codes and debug messages.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_context.cpp#24 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_device.cpp#25 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_device_runtime.cpp#20 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_event.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#80 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#45 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_peer.cpp#8 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#47 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_profile.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_surface.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_texture.cpp#25 edit
2019-10-30 13:37:03 -04:00
foreman 988882bb4f P4 to Git Change 2021608 by michliao@hliao-dev-00-hip.rocm-workspace on 2019/10/30 01:13:58
SWDEV-145570 - [HIP] Fix occupancy API prototype.

	- They need to be C API, i.e. extern "C".
	- Follow the current API and use `uint32_t` instead of `int`.
	  + TODO: We need to revert them back once that APIs are changed to be
	    compatible with CUDA.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#46 edit
2019-10-30 01:19:24 -04:00
Michael LIAO 61bc68a5f4 [HIP] Correct headers and add missing function templates for hip-clang.
- Fix 2 runtime API prototypes
  `hipOccupancyMaxActiveBlocksPerMultiprocessor` and
  `hipOccupancyMaxActiveBlocksPerMultiprocessorWithFlags`
- Add missing function templates of them in hip-clang.
2019-10-29 22:00:11 -04:00
Rahul Garg 9840cdac99 Merge pull request #1602 from ROCm-Developer-Tools/revert-1560-satyanveshd/hipoccupy
Revert "Cooperative groups match with cuda SWDEV-205006"
2019-10-29 16:54:36 -07:00
Evgeny Mankov 050fdad7b7 [HIPIFY][#1603] Fix 2019-10-29 22:10:36 +03:00
Rahul Garg 27221bc823 Revert "Fix occupany APIs (#1560)"
This reverts commit 6c5fbf9b4a.
2019-10-29 11:41:08 -07:00
Evgeny Mankov dd2243f2fa [HIPIFY][Linux] Rollback --cuda-compile-host-device on Linux
[Reason] It doesn't work with LLVM 9 and higher; Windows is fine
2019-10-29 20:53:54 +03:00
Evgeny Mankov 411b18a124 [HIPIFY] Introduce --cuda-compile-host-device for LLVM >= 9
* LLVM < 9 continues using --cuda-host-only
2019-10-29 19:42:53 +03:00
Evgeny Mankov 5dd00bdf52 [HIPIFY] cudaMemcpy2DFromArray(Async) support 2019-10-29 19:12:42 +03:00
Laurent Morichetti 66c91b42e6 Fix a code object memory corruption
The lifetime of the buffer given to
hsa_code_object_reader_create_from_memory must exceed that of the
code object reader. We need to create a copy of the code object
binary memory (file) that is kept allocated until the code object
reader is destroyed.
2019-10-29 08:23:57 -07:00
Evgeny Mankov 4c5c6b4910 [HIP][cmake] Simplify UNIX related code (the beginning)
[REASONS]
1. Make OS-dependent code more clear and readable
2. To ease Windows support
2019-10-28 23:22:27 +03:00
Evgeny Mankov 3df22b2fde [HIP][doc] NVIDIA-nvcc -> HIP-nvcc 2019-10-28 22:46:33 +03:00
Evgeny Mankov d312bce79d [HIP][doc] AMD-hcc -> HIP-hcc 2019-10-28 21:41:12 +03:00
Evgeny Mankov 6284b041e5 [HIP][doc] Fix typo: AMD-clang -> HIP-clang
HIP-clang is already used below instead of AMD-clang
2019-10-28 21:19:21 +03:00
Evgeny Mankov 8100e084b8 [HIP][cmake] Move all *_INSTALL_DIR variables up before first add_subdirectory()
[REASON]
Those vars (may) used by cmake in subdirectories (#1571)
2019-10-28 21:07:00 +03:00
Evgeny Mankov f68bee02f5 [HIPIFY][tests] Rename the ambiguous call as well 2019-10-25 16:07:31 +03:00
Evgeny Mankov 9529e1d91d [HIPIFY][tests] Fix ambiguous call to cusparseGetErrorString declared in cusparse.h 2019-10-25 16:04:20 +03:00
Anusha Godavarthy Surya 9332a39838 Merge branch 'master' into tex_unbind_issue_fix 2019-10-25 15:54:25 +05:30
amd-lthakur 626cd5d07a Excluded the test case for nvcc platform 2019-10-25 15:52:11 +05:30