AI/rocm-systems
2
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
76,333 Commits 3 Branches 0 Tags
develop
Commit Graph
76333 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Maneesh Gupta 6337247921 Merge pull request #615 from aaronenyeshi/enable-hip-compiler 
Enable HIP_COMPILER to choose HIP-Clang lib links

[ROCm/clr commit: 0123fb816d]
 2018-08-10 09:34:51 +05:30
Maneesh Gupta 0123fb816d Merge pull request #615 from aaronenyeshi/enable-hip-compiler 
Enable HIP_COMPILER to choose HIP-Clang lib links
 2018-08-10 09:34:51 +05:30
Maneesh Gupta be85f53160 Merge pull request #615 from aaronenyeshi/enable-hip-compiler 
Enable HIP_COMPILER to choose HIP-Clang lib links

[ROCm/hip commit: 04a34aa46a]
 2018-08-10 09:34:51 +05:30
Maneesh Gupta 04a34aa46a Merge pull request #615 from aaronenyeshi/enable-hip-compiler 
Enable HIP_COMPILER to choose HIP-Clang lib links
 2018-08-10 09:34:51 +05:30
Maneesh Gupta a3e7b7c18e Merge pull request #613 from ROCm-Developer-Tools/hcc-compat 
Add HCC compatibility mode for hip-clang

[ROCm/clr commit: a5f9ae90d2]
 2018-08-10 09:32:31 +05:30
Maneesh Gupta a5f9ae90d2 Merge pull request #613 from ROCm-Developer-Tools/hcc-compat 
Add HCC compatibility mode for hip-clang
 2018-08-10 09:32:31 +05:30
Maneesh Gupta 28739aa597 Merge pull request #613 from ROCm-Developer-Tools/hcc-compat 
Add HCC compatibility mode for hip-clang

[ROCm/hip commit: 11cccaa5d0]
 2018-08-10 09:32:31 +05:30
Maneesh Gupta 11cccaa5d0 Merge pull request #613 from ROCm-Developer-Tools/hcc-compat 
Add HCC compatibility mode for hip-clang
 2018-08-10 09:32:31 +05:30
Maneesh Gupta 4e2e234a56 Merge pull request #617 from gargrahul/genco_remove_adipose_extn 
Remove adipose extension from genco output

[ROCm/clr commit: 497610f96c]
 2018-08-10 09:31:44 +05:30
Maneesh Gupta 497610f96c Merge pull request #617 from gargrahul/genco_remove_adipose_extn 
Remove adipose extension from genco output
 2018-08-10 09:31:44 +05:30
Maneesh Gupta 1027f112b9 Merge pull request #617 from gargrahul/genco_remove_adipose_extn 
Remove adipose extension from genco output

[ROCm/hip commit: b5f2ad0715]
 2018-08-10 09:31:44 +05:30
Maneesh Gupta b5f2ad0715 Merge pull request #617 from gargrahul/genco_remove_adipose_extn 
Remove adipose extension from genco output
 2018-08-10 09:31:44 +05:30
Maneesh Gupta f74ececf41 Merge pull request #619 from ROCm-Developer-Tools/revert-pr457 
Revert pr457

[ROCm/clr commit: 79e9a2dfa4]
 2018-08-10 09:25:57 +05:30
Maneesh Gupta 79e9a2dfa4 Merge pull request #619 from ROCm-Developer-Tools/revert-pr457 
Revert pr457
 2018-08-10 09:25:57 +05:30
Maneesh Gupta 5b8e25b541 Merge pull request #619 from ROCm-Developer-Tools/revert-pr457 
Revert pr457

[ROCm/hip commit: d358ce75db]
 2018-08-10 09:25:57 +05:30
Maneesh Gupta d358ce75db Merge pull request #619 from ROCm-Developer-Tools/revert-pr457 
Revert pr457
 2018-08-10 09:25:57 +05:30
Yong Zhao 110e754f64 Differentiate gfx700 and improve the logic by introducing is_gfx700() 
Because gfx700 has local memory but other APUs don't, we should reflect
that in the code. Meanwhile, fix a bug that on gfx902 svm aperture is not
added when calling hsaKmtGetNodeMemoryProperties().

Change-Id: Id840f2db0b14fda9ee713b219a9474c15f8a9771
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
 2018-08-09 21:39:37 -04:00
Yong Zhao 6086ae78bb Differentiate gfx700 and improve the logic by introducing is_gfx700() 
Because gfx700 has local memory but other APUs don't, we should reflect
that in the code. Meanwhile, fix a bug that on gfx902 svm aperture is not
added when calling hsaKmtGetNodeMemoryProperties().

Change-Id: Id840f2db0b14fda9ee713b219a9474c15f8a9771
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>


[ROCm/ROCR-Runtime commit: 110e754f64]
 2018-08-09 21:39:37 -04:00
Evgeny Mankov def4c5fbbf Merge pull request #624 from emankov/cuComplex 
[HIPIFY][Complex] Add cuComplex support

[ROCm/clr commit: d1540de3b8]
 2018-08-09 20:01:51 +03:00
Evgeny Mankov d1540de3b8 Merge pull request #624 from emankov/cuComplex 
[HIPIFY][Complex] Add cuComplex support
 2018-08-09 20:01:51 +03:00
Evgeny Mankov dea3ca882b Merge pull request #624 from emankov/cuComplex 
[HIPIFY][Complex] Add cuComplex support

[ROCm/hip commit: 3ddfbfa94a]
 2018-08-09 20:01:51 +03:00
Evgeny Mankov 3ddfbfa94a Merge pull request #624 from emankov/cuComplex 
[HIPIFY][Complex] Add cuComplex support
 2018-08-09 20:01:51 +03:00
sunway513 3621ec1971 resolve a segfault bug when env var not set; remove startup_kernel_loader class 
[ROCm/clr commit: 7c467220a8]
 2018-08-09 16:40:26 +00:00
sunway513 7c467220a8 resolve a segfault bug when env var not set; remove startup_kernel_loader class 2018-08-09 16:40:26 +00:00
sunway513 cfe96a2db0 resolve a segfault bug when env var not set; remove startup_kernel_loader class 
[ROCm/hip commit: 17f38937e0]
 2018-08-09 16:40:26 +00:00
sunway513 17f38937e0 resolve a segfault bug when env var not set; remove startup_kernel_loader class 2018-08-09 16:40:26 +00:00
Sean Keely 6c47780620 Experimental flag to swap copy agent for async copy APIs. 
Adds env flag HSA_REV_COPY_DIR.  If set to 1 async copy will
copy from dst device to src device rather than from src to dst.

Change-Id: I3095642066fa026dc112c2eac06db9393341cd7e
 2018-08-09 10:58:14 -04:00
Sean Keely 896a035951 Experimental flag to swap copy agent for async copy APIs. 
Adds env flag HSA_REV_COPY_DIR.  If set to 1 async copy will
copy from dst device to src device rather than from src to dst.

Change-Id: I3095642066fa026dc112c2eac06db9393341cd7e


[ROCm/ROCR-Runtime commit: 6c47780620]
 2018-08-09 10:58:14 -04:00
xinhui pan 8fbf4a26ec thunk: fix a vm area release issue 
On some asics, like tonga, the memory alignment size is as big as 0x8000.

fmm_allocate* alloc vm area with size passed in which is not aligned mostly.
But __fmm_release free vm area with vm_object_t->size which is aligned.

That might cause aperture_release_area fail to free the vm area as the
size might be bigger than zone itself or it just free another vm area
nearby unexpected.

This patch somehow will alloc more space than it needed on tonga.
gfx900+ is not affected.

Change-Id: I5a88c92b08c4e6f6bc05881798f769b55d6debe9
Signed-off-by: xinhui pan <xinhui.pan@amd.com>
 2018-08-09 06:08:15 -04:00
xinhui pan ed7fc6883d thunk: fix a vm area release issue 
On some asics, like tonga, the memory alignment size is as big as 0x8000.

fmm_allocate* alloc vm area with size passed in which is not aligned mostly.
But __fmm_release free vm area with vm_object_t->size which is aligned.

That might cause aperture_release_area fail to free the vm area as the
size might be bigger than zone itself or it just free another vm area
nearby unexpected.

This patch somehow will alloc more space than it needed on tonga.
gfx900+ is not affected.

Change-Id: I5a88c92b08c4e6f6bc05881798f769b55d6debe9
Signed-off-by: xinhui pan <xinhui.pan@amd.com>


[ROCm/ROCR-Runtime commit: 8fbf4a26ec]
 2018-08-09 06:08:15 -04:00
Jenkins ef784cfbda Merge 'master' into 'amd-master' 
Change-Id: I02f86242eebb6f3035681ed074eb024b8556420e


[ROCm/clr commit: 7096be425a]
 2018-08-09 04:09:46 -05:00
Jenkins 7096be425a Merge 'master' into 'amd-master' 
Change-Id: I02f86242eebb6f3035681ed074eb024b8556420e
 2018-08-09 04:09:46 -05:00
Jenkins e73b409b55 Merge 'master' into 'amd-master' 
Change-Id: I02f86242eebb6f3035681ed074eb024b8556420e


[ROCm/hip commit: b4c7ec1f94]
 2018-08-09 04:09:46 -05:00
Jenkins b4c7ec1f94 Merge 'master' into 'amd-master' 
Change-Id: I02f86242eebb6f3035681ed074eb024b8556420e
 2018-08-09 04:09:46 -05:00
foreman 7aeeb26dc9 P4 to Git Change 1591182 by chui@ocl-promo-incrementor on 2018/08/09 02:56:37 
SWDEV-2 - Change OpenCL version number from 2712 to 2713.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2460 edit


[ROCm/clr commit: 53e1b3b74f]
 2018-08-09 03:16:04 -04:00
foreman 53e1b3b74f P4 to Git Change 1591182 by chui@ocl-promo-incrementor on 2018/08/09 02:56:37 
SWDEV-2 - Change OpenCL version number from 2712 to 2713.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2460 edit
 2018-08-09 03:16:04 -04:00
foreman 7ad3f2f33a P4 to Git Change 1591041 by vsytchen@vsytchen-win10 on 2018/08/08 18:46:17 
SWDEV-159881 - [OCL][ROCm] Add SVM coarse-grain buffer support with device memory (Part 1)

	1. Implement submitSvmFree/Copy/FillMemory.
	2. Add macro IS_HIP that determines if the client is HIP.
	3. Add setting enableCoarseGrainSVM that allows the use of device memory for coarse grain SVM allocations.
	4. Set enableCoarseGrainSVM to be true only for HIP.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15597/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#93 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.cpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#35 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.hpp#15 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#61 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#294 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/macros.hpp#10 edit


[ROCm/clr commit: b33c52ed6f]
 2018-08-08 18:58:03 -04:00
foreman b33c52ed6f P4 to Git Change 1591041 by vsytchen@vsytchen-win10 on 2018/08/08 18:46:17 
SWDEV-159881 - [OCL][ROCm] Add SVM coarse-grain buffer support with device memory (Part 1)

	1. Implement submitSvmFree/Copy/FillMemory.
	2. Add macro IS_HIP that determines if the client is HIP.
	3. Add setting enableCoarseGrainSVM that allows the use of device memory for coarse grain SVM allocations.
	4. Set enableCoarseGrainSVM to be true only for HIP.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15597/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#93 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.cpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#35 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.hpp#15 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#61 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#294 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/macros.hpp#10 edit
 2018-08-08 18:58:03 -04:00
Evgeny b8d4223665 licensing annotation 
[ROCm/roctracer commit: a27f63b110]
 2018-08-08 15:47:30 -05:00
Evgeny a27f63b110 licensing annotation 2018-08-08 15:47:30 -05:00
foreman b641645bbf P4 to Git Change 1590896 by vsytchen@vsytchen-win10 on 2018/08/08 14:49:41 
SWDEV-79445 - OCL generic changes and code clean-up

	1. std::auto_ptr is deprecated in c++11 and removed in c++17. Use unique_ptr instead.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15576/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#65 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#21 edit


[ROCm/clr commit: ac9ebe294b]
 2018-08-08 15:05:57 -04:00
foreman ac9ebe294b P4 to Git Change 1590896 by vsytchen@vsytchen-win10 on 2018/08/08 14:49:41 
SWDEV-79445 - OCL generic changes and code clean-up

	1. std::auto_ptr is deprecated in c++11 and removed in c++17. Use unique_ptr instead.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/15576/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#65 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#21 edit
 2018-08-08 15:05:57 -04:00
Evgeny 0b7a1a9d71 update 
[ROCm/roctracer commit: db0c1959b1]
 2018-08-08 13:43:01 -05:00
Evgeny db0c1959b1 update 2018-08-08 13:43:01 -05:00
Yong Zhao fe04dd6890 Calculate and store the first gpu mem during initializaiton 
Previously we used the first dgpu mem, but after careful examination, we
found it only needs to be a GPU, so we modify the code to reflect that as
well.

Change-Id: I069d9b8e247aed55c1f885b79f743ea8e03ddf93
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
 2018-08-08 13:54:09 -04:00
Yong Zhao 569a2dc80f Calculate and store the first gpu mem during initializaiton 
Previously we used the first dgpu mem, but after careful examination, we
found it only needs to be a GPU, so we modify the code to reflect that as
well.

Change-Id: I069d9b8e247aed55c1f885b79f743ea8e03ddf93
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>


[ROCm/ROCR-Runtime commit: fe04dd6890]
 2018-08-08 13:54:09 -04:00
foreman 39397d988f P4 to Git Change 1590860 by lmoriche@lmoriche_opencl_dev2 on 2018/08/08 12:49:56 
SWDEV-161464 - OpenCL github project rpm and deb package issue
	- Add CPack packaging to the CMake build.

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#20 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#14 edit


[ROCm/clr commit: d600b28bd0]
 2018-08-08 13:05:50 -04:00
foreman d600b28bd0 P4 to Git Change 1590860 by lmoriche@lmoriche_opencl_dev2 on 2018/08/08 12:49:56 
SWDEV-161464 - OpenCL github project rpm and deb package issue
	- Add CPack packaging to the CMake build.

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#20 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#14 edit
 2018-08-08 13:05:50 -04:00
foreman bc3d4a0298 P4 to Git Change 1590860 by lmoriche@lmoriche_opencl_dev2 on 2018/08/08 12:49:56 
SWDEV-161464 - OpenCL github project rpm and deb package issue
	- Add CPack packaging to the CMake build.

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#20 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#14 edit


[ROCm/clr commit: a326b96d41]
 2018-08-08 13:05:50 -04:00
foreman a326b96d41 P4 to Git Change 1590860 by lmoriche@lmoriche_opencl_dev2 on 2018/08/08 12:49:56 
SWDEV-161464 - OpenCL github project rpm and deb package issue
	- Add CPack packaging to the CMake build.

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#20 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#14 edit
 2018-08-08 13:05:50 -04:00