AI/rocm-systems
2
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
64,512 Commits 3 Branches 0 Tags
bb1295bcdfd72123700cd66e631326ab38e82db8
Commit Graph
64512 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Jenkins d2019c7208 Merge 'master' into 'amd-master' 
Change-Id: Id908670145a36a8198ddda03893d72e65d303767


[ROCm/clr commit: 28fe0ce82f]
 2017-11-02 04:11:06 -05:00
Jenkins 28fe0ce82f Merge 'master' into 'amd-master' 
Change-Id: Id908670145a36a8198ddda03893d72e65d303767
 2017-11-02 04:11:06 -05:00
Jenkins e090fe155b Merge 'master' into 'amd-master' 
Change-Id: Id908670145a36a8198ddda03893d72e65d303767


[ROCm/hip commit: dcc153109b]
 2017-11-02 04:11:06 -05:00
Jenkins dcc153109b Merge 'master' into 'amd-master' 
Change-Id: Id908670145a36a8198ddda03893d72e65d303767
 2017-11-02 04:11:06 -05:00
foreman 2124e9430c P4 to Git Change 1477762 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/02 03:00:04 
SWDEV-2 - Change OpenCL version number from 2532 to 2533.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2280 edit


[ROCm/clr commit: 0c391434f5]
 2017-11-02 03:09:14 -04:00
foreman 0c391434f5 P4 to Git Change 1477762 by johtaylo@johtaylo-jtincrementor2-increment on 2017/11/02 03:00:04 
SWDEV-2 - Change OpenCL version number from 2532 to 2533.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2280 edit
 2017-11-02 03:09:14 -04:00
Maneesh Gupta f579dd3c7d Remove libsupc++ dependency from HIP 
Change-Id: Ib843f99dfb3057b7c28029250c2449732ea7f17f


[ROCm/clr commit: 473208368e]
 2017-11-02 12:29:09 +05:30
Maneesh Gupta 473208368e Remove libsupc++ dependency from HIP 
Change-Id: Ib843f99dfb3057b7c28029250c2449732ea7f17f
 2017-11-02 12:29:09 +05:30
Maneesh Gupta 94a22fe015 Remove libsupc++ dependency from HIP 
Change-Id: Ib843f99dfb3057b7c28029250c2449732ea7f17f


[ROCm/hip commit: f34f5c8684]
 2017-11-02 12:29:09 +05:30
Maneesh Gupta f34f5c8684 Remove libsupc++ dependency from HIP 
Change-Id: Ib843f99dfb3057b7c28029250c2449732ea7f17f
 2017-11-02 12:29:09 +05:30
foreman 2cde3eaeb0 P4 to Git Change 1477714 by kzhuravl@kzhuravl-fiji-ocllc on 2017/11/02 00:03:53 
SWDEV-102733 - More cmake and other updates to fix open source build

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/amdocl.map#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/CMakeLists.txt#10 edit


[ROCm/clr commit: 10bed67bd8]
 2017-11-02 00:09:45 -04:00
foreman 10bed67bd8 P4 to Git Change 1477714 by kzhuravl@kzhuravl-fiji-ocllc on 2017/11/02 00:03:53 
SWDEV-102733 - More cmake and other updates to fix open source build

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/amdocl.map#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/CMakeLists.txt#10 edit
 2017-11-02 00:09:45 -04:00
foreman 2f78f7fa00 P4 to Git Change 1477714 by kzhuravl@kzhuravl-fiji-ocllc on 2017/11/02 00:03:53 
SWDEV-102733 - More cmake and other updates to fix open source build

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/amdocl.map#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/CMakeLists.txt#10 edit


[ROCm/clr commit: 06f3d6cad5]
 2017-11-02 00:09:45 -04:00
foreman 06f3d6cad5 P4 to Git Change 1477714 by kzhuravl@kzhuravl-fiji-ocllc on 2017/11/02 00:03:53 
SWDEV-102733 - More cmake and other updates to fix open source build

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/amdocl.map#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/CMakeLists.txt#10 edit
 2017-11-02 00:09:45 -04:00
Alex Voicu 41045dd24d This corrects some interesting choices that were present in the HIP 
unit tests such as e.g. de-allocating memory allocated with new[] using
free. All of these were identified via cppcheck.


[ROCm/clr commit: 58a18eaf0c]
 2017-11-01 22:51:22 +00:00
Alex Voicu 58a18eaf0c This corrects some interesting choices that were present in the HIP 
unit tests such as e.g. de-allocating memory allocated with new[] using
free. All of these were identified via cppcheck.
 2017-11-01 22:51:22 +00:00
Alex Voicu b8a81d2b75 This corrects some interesting choices that were present in the HIP 
unit tests such as e.g. de-allocating memory allocated with new[] using
free. All of these were identified via cppcheck.


[ROCm/hip commit: a619ac6f92]
 2017-11-01 22:51:22 +00:00
Alex Voicu a619ac6f92 This corrects some interesting choices that were present in the HIP 
unit tests such as e.g. de-allocating memory allocated with new[] using
free. All of these were identified via cppcheck.
 2017-11-01 22:51:22 +00:00
Alex Voicu 840895525a Correctly deal with functions from shared objects, wherein the program visible VA == so_base_va + st_value(function_symbol). Remove quaint usage of pfe for hipMemset (which is actually fill_n). 
[ROCm/clr commit: 4693c5e56c]
 2017-11-01 22:33:13 +00:00
Alex Voicu 4693c5e56c Correctly deal with functions from shared objects, wherein the program visible VA == so_base_va + st_value(function_symbol). Remove quaint usage of pfe for hipMemset (which is actually fill_n). 2017-11-01 22:33:13 +00:00
Alex Voicu dab971370e Correctly deal with functions from shared objects, wherein the program visible VA == so_base_va + st_value(function_symbol). Remove quaint usage of pfe for hipMemset (which is actually fill_n). 
[ROCm/hip commit: 2cacda91bb]
 2017-11-01 22:33:13 +00:00
Alex Voicu 2cacda91bb Correctly deal with functions from shared objects, wherein the program visible VA == so_base_va + st_value(function_symbol). Remove quaint usage of pfe for hipMemset (which is actually fill_n). 2017-11-01 22:33:13 +00:00
foreman 80e0bed02b P4 to Git Change 1477581 by wchau@wchau_WIN_OCL_HSA on 2017/11/01 16:33:34 
SWDEV-136305 - [OCL 2.1 Plat] API calls for all drivers

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_command.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#87 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#27 edit


[ROCm/clr commit: ab934181fa]
 2017-11-01 16:53:27 -04:00
foreman ab934181fa P4 to Git Change 1477581 by wchau@wchau_WIN_OCL_HSA on 2017/11/01 16:33:34 
SWDEV-136305 - [OCL 2.1 Plat] API calls for all drivers

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_command.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#87 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#27 edit
 2017-11-01 16:53:27 -04:00
foreman d1584c846c P4 to Git Change 1477581 by wchau@wchau_WIN_OCL_HSA on 2017/11/01 16:33:34 
SWDEV-136305 - [OCL 2.1 Plat] API calls for all drivers

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_command.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#87 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#27 edit


[ROCm/clr commit: bafc102e17]
 2017-11-01 16:53:27 -04:00
foreman bafc102e17 P4 to Git Change 1477581 by wchau@wchau_WIN_OCL_HSA on 2017/11/01 16:33:34 
SWDEV-136305 - [OCL 2.1 Plat] API calls for all drivers

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_command.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_svm.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#87 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#27 edit
 2017-11-01 16:53:27 -04:00
Ben Sander 725f46aa94 Merge pull request #237 from bensander/use_ctxptr_for_p2p 
Use ctxptr for p2p

[ROCm/clr commit: fe32685fbc]
 2017-11-01 18:55:25 +01:00
Ben Sander fe32685fbc Merge pull request #237 from bensander/use_ctxptr_for_p2p 
Use ctxptr for p2p
 2017-11-01 18:55:25 +01:00
Ben Sander 2979a99888 Merge pull request #237 from bensander/use_ctxptr_for_p2p 
Use ctxptr for p2p

[ROCm/hip commit: 09d866a639]
 2017-11-01 18:55:25 +01:00
Ben Sander 09d866a639 Merge pull request #237 from bensander/use_ctxptr_for_p2p 
Use ctxptr for p2p
 2017-11-01 18:55:25 +01:00
Ben Sander 6e82cc25df Add HIP_DB=warn + message if sync on dangerous event. 
[ROCm/clr commit: 172b9f96e6]
 2017-11-01 10:44:34 -07:00
Ben Sander 172b9f96e6 Add HIP_DB=warn + message if sync on dangerous event. 2017-11-01 10:44:34 -07:00
Ben Sander 6c60773e82 Add HIP_DB=warn + message if sync on dangerous event. 
[ROCm/hip commit: 70c25bdf8e]
 2017-11-01 10:44:34 -07:00
Ben Sander 70c25bdf8e Add HIP_DB=warn + message if sync on dangerous event. 2017-11-01 10:44:34 -07:00
Ben Sander 19935275ea Merge pull request #245 from scchan/centos_fixes 
various fixes for centos/rhel

[ROCm/clr commit: 5a80c4108e]
 2017-11-01 18:10:29 +01:00
Ben Sander 5a80c4108e Merge pull request #245 from scchan/centos_fixes 
various fixes for centos/rhel
 2017-11-01 18:10:29 +01:00
Ben Sander 6f3b28d27c Merge pull request #245 from scchan/centos_fixes 
various fixes for centos/rhel

[ROCm/hip commit: 86f62accfd]
 2017-11-01 18:10:29 +01:00
Ben Sander 86f62accfd Merge pull request #245 from scchan/centos_fixes 
various fixes for centos/rhel
 2017-11-01 18:10:29 +01:00
foreman 7fa1b2c5b1 P4 to Git Change 1477431 by kzhuravl@kzhuravl-fiji-ocllc on 2017/11/01 12:56:46 
SWDEV-102733 - Update cmake for CL 1455364

	Testing: open source build, also here http://git.amd.com:8080/#/c/113674/

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#18 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/CMakeLists.txt#7 edit


[ROCm/clr commit: 6293fd1825]
 2017-11-01 13:01:29 -04:00
foreman 6293fd1825 P4 to Git Change 1477431 by kzhuravl@kzhuravl-fiji-ocllc on 2017/11/01 12:56:46 
SWDEV-102733 - Update cmake for CL 1455364

	Testing: open source build, also here http://git.amd.com:8080/#/c/113674/

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#18 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/CMakeLists.txt#7 edit
 2017-11-01 13:01:29 -04:00
foreman fa72a9a820 P4 to Git Change 1477431 by kzhuravl@kzhuravl-fiji-ocllc on 2017/11/01 12:56:46 
SWDEV-102733 - Update cmake for CL 1455364

	Testing: open source build, also here http://git.amd.com:8080/#/c/113674/

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#18 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/CMakeLists.txt#7 edit


[ROCm/clr commit: 6afeb11d56]
 2017-11-01 13:01:29 -04:00
foreman 6afeb11d56 P4 to Git Change 1477431 by kzhuravl@kzhuravl-fiji-ocllc on 2017/11/01 12:56:46 
SWDEV-102733 - Update cmake for CL 1455364

	Testing: open source build, also here http://git.amd.com:8080/#/c/113674/

Affected files ...

... //depot/stg/opencl/drivers/opencl/CMakeLists.txt#18 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/CMakeLists.txt#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/CMakeLists.txt#7 edit
 2017-11-01 13:01:29 -04:00
Alex Voicu b738633bcb This switches HIP from its currently convoluted macro + pfe based dispatch mechanism to a more natural one partially based on the existing module API. The basic idea is that HCC will always correctly emit __global__ functions: as empty-bodied stubs, on host, and as kernels, on device. It then becomes trivial to obtain the mangled name on host, at dispatch, from the function's address, and then to use the mangled name to retrieve the kernel. This should address all problems stemming from serialisation, dubious mismatches due to the manufactured functor, macro-isms et al. It also immediately enables support for generalised globals as a consequence of that being available in the module API. Finally, it will make debug much easier, since the actual names of the __global__ functions will automatically be used in traces etc. One detail is that due to how dispatch works now (hipLaunchKernel and hipLaunchKernelGGL are themselves variadic function templates which deduce the function type of the callee), in certain cases it may be necesssary to insert explicit casts to ensure that the variadic argument list selects a viable overload - this can be observed in some unit tests. Eventually we may be able to remove this limitation, but for now it does not appear terribly onerous. The code is not extremely HIPpie, nor is it fully optimised, but rather is intended as a starting point for the HIP team to make its own. 
[ROCm/clr commit: 28f87f7d2e]
 2017-11-01 15:09:59 +00:00
Alex Voicu 28f87f7d2e This switches HIP from its currently convoluted macro + pfe based dispatch mechanism to a more natural one partially based on the existing module API. The basic idea is that HCC will always correctly emit __global__ functions: as empty-bodied stubs, on host, and as kernels, on device. It then becomes trivial to obtain the mangled name on host, at dispatch, from the function's address, and then to use the mangled name to retrieve the kernel. This should address all problems stemming from serialisation, dubious mismatches due to the manufactured functor, macro-isms et al. It also immediately enables support for generalised globals as a consequence of that being available in the module API. Finally, it will make debug much easier, since the actual names of the __global__ functions will automatically be used in traces etc. One detail is that due to how dispatch works now (hipLaunchKernel and hipLaunchKernelGGL are themselves variadic function templates which deduce the function type of the callee), in certain cases it may be necesssary to insert explicit casts to ensure that the variadic argument list selects a viable overload - this can be observed in some unit tests. Eventually we may be able to remove this limitation, but for now it does not appear terribly onerous. The code is not extremely HIPpie, nor is it fully optimised, but rather is intended as a starting point for the HIP team to make its own. 2017-11-01 15:09:59 +00:00
Alex Voicu 70a41e7dac This switches HIP from its currently convoluted macro + pfe based dispatch mechanism to a more natural one partially based on the existing module API. The basic idea is that HCC will always correctly emit __global__ functions: as empty-bodied stubs, on host, and as kernels, on device. It then becomes trivial to obtain the mangled name on host, at dispatch, from the function's address, and then to use the mangled name to retrieve the kernel. This should address all problems stemming from serialisation, dubious mismatches due to the manufactured functor, macro-isms et al. It also immediately enables support for generalised globals as a consequence of that being available in the module API. Finally, it will make debug much easier, since the actual names of the __global__ functions will automatically be used in traces etc. One detail is that due to how dispatch works now (hipLaunchKernel and hipLaunchKernelGGL are themselves variadic function templates which deduce the function type of the callee), in certain cases it may be necesssary to insert explicit casts to ensure that the variadic argument list selects a viable overload - this can be observed in some unit tests. Eventually we may be able to remove this limitation, but for now it does not appear terribly onerous. The code is not extremely HIPpie, nor is it fully optimised, but rather is intended as a starting point for the HIP team to make its own. 
[ROCm/hip commit: c2482d1255]
 2017-11-01 15:09:59 +00:00
Alex Voicu c2482d1255 This switches HIP from its currently convoluted macro + pfe based dispatch mechanism to a more natural one partially based on the existing module API. The basic idea is that HCC will always correctly emit __global__ functions: as empty-bodied stubs, on host, and as kernels, on device. It then becomes trivial to obtain the mangled name on host, at dispatch, from the function's address, and then to use the mangled name to retrieve the kernel. This should address all problems stemming from serialisation, dubious mismatches due to the manufactured functor, macro-isms et al. It also immediately enables support for generalised globals as a consequence of that being available in the module API. Finally, it will make debug much easier, since the actual names of the __global__ functions will automatically be used in traces etc. One detail is that due to how dispatch works now (hipLaunchKernel and hipLaunchKernelGGL are themselves variadic function templates which deduce the function type of the callee), in certain cases it may be necesssary to insert explicit casts to ensure that the variadic argument list selects a viable overload - this can be observed in some unit tests. Eventually we may be able to remove this limitation, but for now it does not appear terribly onerous. The code is not extremely HIPpie, nor is it fully optimised, but rather is intended as a starting point for the HIP team to make its own. 2017-11-01 15:09:59 +00:00
Jenkins 6f25720c66 Merge 'master' into 'amd-master' 
Change-Id: Ic61bd45a4904ddb1645e90b9e8fb42ffeab4825a


[ROCm/clr commit: 4401c8c390]
 2017-11-01 04:42:40 -05:00
Jenkins 4401c8c390 Merge 'master' into 'amd-master' 
Change-Id: Ic61bd45a4904ddb1645e90b9e8fb42ffeab4825a
 2017-11-01 04:42:40 -05:00
Jenkins 267f2040f4 Merge 'master' into 'amd-master' 
Change-Id: Ic61bd45a4904ddb1645e90b9e8fb42ffeab4825a


[ROCm/hip commit: 7d55fc385b]
 2017-11-01 04:42:40 -05:00
Jenkins 7d55fc385b Merge 'master' into 'amd-master' 
Change-Id: Ic61bd45a4904ddb1645e90b9e8fb42ffeab4825a
 2017-11-01 04:42:40 -05:00