AI/rocm-systems
2
0 Tükrözés 0
Kód Hibajegyek Egyesítési kérések Actions Packages Projektek Kiadások Wiki Tevékenység
64 512 Commit-ok 3 Ágak 0 Címkék
bb1295bcdfd72123700cd66e631326ab38e82db8
Commit gráf
64512 Commit-ok
This Branch
This Branch
Minden ág
Szerző SHA1 Üzenet Dátum
Aditya Atluri 6c272debb9 fixed threadfence ir 
Change-Id: Ia3afb54bdb50864e678d849608d72a3c321edba1


[ROCm/clr commit: 537dc7597b]
 2017-01-27 08:42:26 -06:00
Aditya Atluri 537dc7597b fixed threadfence ir 
Change-Id: Ia3afb54bdb50864e678d849608d72a3c321edba1
 2017-01-27 08:42:26 -06:00
Aditya Atluri ad08bdcfb0 fixed threadfence ir 
Change-Id: Ia3afb54bdb50864e678d849608d72a3c321edba1


[ROCm/hip commit: f7ff199daa]
 2017-01-27 08:42:26 -06:00
Aditya Atluri f7ff199daa fixed threadfence ir 
Change-Id: Ia3afb54bdb50864e678d849608d72a3c321edba1
 2017-01-27 08:42:26 -06:00
Aditya Atluri 4b732551bb fixed kernel only compilation for module api 
Change-Id: I567992fa9b87125318edba41fd82d2f7bc5504a1


[ROCm/clr commit: 33d89d06aa]
 2017-01-27 08:41:42 -06:00
Aditya Atluri 33d89d06aa fixed kernel only compilation for module api 
Change-Id: I567992fa9b87125318edba41fd82d2f7bc5504a1
 2017-01-27 08:41:42 -06:00
Aditya Atluri a13cb5af4f fixed kernel only compilation for module api 
Change-Id: I567992fa9b87125318edba41fd82d2f7bc5504a1


[ROCm/hip commit: 6ba848a40f]
 2017-01-27 08:41:42 -06:00
Aditya Atluri 6ba848a40f fixed kernel only compilation for module api 
Change-Id: I567992fa9b87125318edba41fd82d2f7bc5504a1
 2017-01-27 08:41:42 -06:00
Rahul Garg 24a50f7606 hipMallocArray fixes for NV path 
Change-Id: I1ca43e6bc0cd405998888005c20dfb1ea57003d5


[ROCm/clr commit: 125983eed9]
 2017-01-27 14:32:08 +05:30
Rahul Garg 125983eed9 hipMallocArray fixes for NV path 
Change-Id: I1ca43e6bc0cd405998888005c20dfb1ea57003d5
 2017-01-27 14:32:08 +05:30
Rahul Garg 1d4c0862f1 hipMallocArray fixes for NV path 
Change-Id: I1ca43e6bc0cd405998888005c20dfb1ea57003d5


[ROCm/hip commit: 3e21d55c98]
 2017-01-27 14:32:08 +05:30
Rahul Garg 3e21d55c98 hipMallocArray fixes for NV path 
Change-Id: I1ca43e6bc0cd405998888005c20dfb1ea57003d5
 2017-01-27 14:32:08 +05:30
foreman aa850366f2 P4 to Git Change 1366677 by johtaylo@johtaylo-jtincrementor-increment on 2017/01/27 03:00:05 
SWDEV-2 - Change OpenCL version number from 2347 to 2348.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2094 edit


[ROCm/clr commit: 40561d2c67]
 2017-01-27 03:12:31 -05:00
foreman 40561d2c67 P4 to Git Change 1366677 by johtaylo@johtaylo-jtincrementor-increment on 2017/01/27 03:00:05 
SWDEV-2 - Change OpenCL version number from 2347 to 2348.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2094 edit
 2017-01-27 03:12:31 -05:00
foreman ca4a2ca2a0 P4 to Git Change 1366502 by gandryey@gera-lnx-rcf-lc on 2017/01/26 14:44:13 
SWDEV-112016 - [ROCm CQE][OCLonLC][QR][G] Seg fault observed with "sub_buffers_read_write" of Buffers, due to CL#1364923
	- Take the host pointer for CPU access in bufferfill.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#8 edit


[ROCm/clr commit: 027f8d9108]
 2017-01-26 14:52:51 -05:00
foreman 027f8d9108 P4 to Git Change 1366502 by gandryey@gera-lnx-rcf-lc on 2017/01/26 14:44:13 
SWDEV-112016 - [ROCm CQE][OCLonLC][QR][G] Seg fault observed with "sub_buffers_read_write" of Buffers, due to CL#1364923
	- Take the host pointer for CPU access in bufferfill.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#8 edit
 2017-01-26 14:52:51 -05:00
foreman ece92c4e21 P4 to Git Change 1366459 by gandryey@gera-w8 on 2017/01/26 13:37:23 
SWDEV-112016 - [ROCm CQE][OCLonLC][QR][G] Seg fault observed with "sub_buffers_read_write" of Buffers, due to CL#1364923
	- Fix subbuffers logic with AHP allocations
	- Make AHP allocations to use UHP path

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#7 edit


[ROCm/clr commit: 5fd072d9b3]
 2017-01-26 13:45:49 -05:00
foreman 5fd072d9b3 P4 to Git Change 1366459 by gandryey@gera-w8 on 2017/01/26 13:37:23 
SWDEV-112016 - [ROCm CQE][OCLonLC][QR][G] Seg fault observed with "sub_buffers_read_write" of Buffers, due to CL#1364923
	- Fix subbuffers logic with AHP allocations
	- Make AHP allocations to use UHP path

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocmemory.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#7 edit
 2017-01-26 13:45:49 -05:00
pensun 41bb48dd49 more fix on hipmallocarray on NV path 
Change-Id: I890a36cab10c101f4a112bc4567f765b318d486c


[ROCm/clr commit: f18efd5d15]
 2017-01-26 12:30:52 -06:00
pensun f18efd5d15 more fix on hipmallocarray on NV path 
Change-Id: I890a36cab10c101f4a112bc4567f765b318d486c
 2017-01-26 12:30:52 -06:00
pensun 58721e8b7d more fix on hipmallocarray on NV path 
Change-Id: I890a36cab10c101f4a112bc4567f765b318d486c


[ROCm/hip commit: 2e1a66103a]
 2017-01-26 12:30:52 -06:00
pensun 2e1a66103a more fix on hipmallocarray on NV path 
Change-Id: I890a36cab10c101f4a112bc4567f765b318d486c
 2017-01-26 12:30:52 -06:00
Jay Cornwall 1cd46afe6d Implement SDMA path for Gfx9 
Gfx9 requires monotonic write pointer and doorbell.
Cound fields are 1-based compared with 0-based pre-Gfx9.

- Restructure implementation to use monotonic ring indices
- Remove redundant submission size checks (handled by AcquireWriteAddress)
- Unify copy/fill per-command limit (documentation is unclear)

Change-Id: I57c1675221d2e63aa319fee700d9951671e1bd65
 2017-01-26 13:11:21 -05:00
Jay Cornwall 22ffe11f5c Implement SDMA path for Gfx9 
Gfx9 requires monotonic write pointer and doorbell.
Cound fields are 1-based compared with 0-based pre-Gfx9.

- Restructure implementation to use monotonic ring indices
- Remove redundant submission size checks (handled by AcquireWriteAddress)
- Unify copy/fill per-command limit (documentation is unclear)

Change-Id: I57c1675221d2e63aa319fee700d9951671e1bd65


[ROCm/ROCR-Runtime commit: 1cd46afe6d]
 2017-01-26 13:11:21 -05:00
pensun 0ecc88bebd fix missing semicolon on NV path 
Change-Id: I3cfecb7bd534578a1f5a07ca9397092dcf01db07


[ROCm/clr commit: 42f22162e0]
 2017-01-26 11:28:15 -06:00
pensun 42f22162e0 fix missing semicolon on NV path 
Change-Id: I3cfecb7bd534578a1f5a07ca9397092dcf01db07
 2017-01-26 11:28:15 -06:00
pensun 5eb33462b7 fix missing semicolon on NV path 
Change-Id: I3cfecb7bd534578a1f5a07ca9397092dcf01db07


[ROCm/hip commit: 8404215658]
 2017-01-26 11:28:15 -06:00
pensun 8404215658 fix missing semicolon on NV path 
Change-Id: I3cfecb7bd534578a1f5a07ca9397092dcf01db07
 2017-01-26 11:28:15 -06:00
foreman 3bf60565c8 P4 to Git Change 1366316 by johtaylo@johtaylo-jtincrementor-increment on 2017/01/26 03:00:04 
SWDEV-2 - Change OpenCL version number from 2346 to 2347.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2093 edit


[ROCm/clr commit: 356b1574bf]
 2017-01-26 03:14:16 -05:00
foreman 356b1574bf P4 to Git Change 1366316 by johtaylo@johtaylo-jtincrementor-increment on 2017/01/26 03:00:04 
SWDEV-2 - Change OpenCL version number from 2346 to 2347.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2093 edit
 2017-01-26 03:14:16 -05:00
Ben Sander b46ee1d193 Add HIP_FAIL_SOC. 
Fail sub-optimal-copies rather than perform them slowly.
SOC occur on async copy of unpinned memory, or P2P copy between GPUs
that are not peers.


[ROCm/clr commit: 1a24178c78]
 2017-01-25 21:53:17 -06:00
Ben Sander 1a24178c78 Add HIP_FAIL_SOC. 
Fail sub-optimal-copies rather than perform them slowly.
SOC occur on async copy of unpinned memory, or P2P copy between GPUs
that are not peers.
 2017-01-25 21:53:17 -06:00
Ben Sander bf3b6354ae Add HIP_FAIL_SOC. 
Fail sub-optimal-copies rather than perform them slowly.
SOC occur on async copy of unpinned memory, or P2P copy between GPUs
that are not peers.


[ROCm/hip commit: 0409bf639c]
 2017-01-25 21:53:17 -06:00
Ben Sander 0409bf639c Add HIP_FAIL_SOC. 
Fail sub-optimal-copies rather than perform them slowly.
SOC occur on async copy of unpinned memory, or P2P copy between GPUs
that are not peers.
 2017-01-25 21:53:17 -06:00
Ben Sander ad2ba66ce6 Read HCC_OPT_FLUSH and optimize dispatch accordingly. 
If HCC is in this mode, we can use less aggressive flushes in some
cases.


[ROCm/clr commit: 2f7a8ec39c]
 2017-01-25 21:50:52 -06:00
Ben Sander 2f7a8ec39c Read HCC_OPT_FLUSH and optimize dispatch accordingly. 
If HCC is in this mode, we can use less aggressive flushes in some
cases.
 2017-01-25 21:50:52 -06:00
Ben Sander e129b09a6f Read HCC_OPT_FLUSH and optimize dispatch accordingly. 
If HCC is in this mode, we can use less aggressive flushes in some
cases.


[ROCm/hip commit: 1635b8f43f]
 2017-01-25 21:50:52 -06:00
Ben Sander 1635b8f43f Read HCC_OPT_FLUSH and optimize dispatch accordingly. 
If HCC is in this mode, we can use less aggressive flushes in some
cases.
 2017-01-25 21:50:52 -06:00
foreman 3523379860 P4 to Git Change 1366280 by kzhuravl@kzhuravl-kaveri-cl-on-lc on 2017/01/25 21:14:50 
SWDEV-94644 - Switch back to bare numbers in pal when processing note entries. In order to use constants and enums from the llvm's header, we need to clean up similar loader's header (they conflict). Ideally we should move torwards not having headers with similar definitions.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#32 edit


[ROCm/clr commit: 32413bdc80]
 2017-01-25 21:21:04 -05:00
foreman 32413bdc80 P4 to Git Change 1366280 by kzhuravl@kzhuravl-kaveri-cl-on-lc on 2017/01/25 21:14:50 
SWDEV-94644 - Switch back to bare numbers in pal when processing note entries. In order to use constants and enums from the llvm's header, we need to clean up similar loader's header (they conflict). Ideally we should move torwards not having headers with similar definitions.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#32 edit
 2017-01-25 21:21:04 -05:00
foreman e9d11c526f P4 to Git Change 1366205 by kzhuravl@kzhuravl-fiji-cl-on-lc on 2017/01/25 18:04:35 
SWDEV-94644 - Make sure we are processing metadata note entry with supported n_type. Update build log and fail for not supported metadata n_type. Use constants defined in AMDGPUPTNote.h

	This change is needed for https://reviews.llvm.org/D29115

	This change is required for CL 1366203

	ReviewBoardURL: http://ocltc.amd.com/reviews/r/12223/
	Testing: lightning conformance tests locally

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#54 edit


[ROCm/clr commit: 4ad12d089c]
 2017-01-25 18:12:20 -05:00
foreman 4ad12d089c P4 to Git Change 1366205 by kzhuravl@kzhuravl-fiji-cl-on-lc on 2017/01/25 18:04:35 
SWDEV-94644 - Make sure we are processing metadata note entry with supported n_type. Update build log and fail for not supported metadata n_type. Use constants defined in AMDGPUPTNote.h

	This change is needed for https://reviews.llvm.org/D29115

	This change is required for CL 1366203

	ReviewBoardURL: http://ocltc.amd.com/reviews/r/12223/
	Testing: lightning conformance tests locally

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#54 edit
 2017-01-25 18:12:20 -05:00
foreman c671c916f9 P4 to Git Change 1365943 by lmoriche@lmoriche_opencl_dev on 2017/01/25 11:37:20 
SWDEV-102726 - [OCL-LC-ROCm] Open source OpenCL Runtime
	- Cleanups: Remove CL_HSA_ENABLED/DISABLED_AMD.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_device.cpp#60 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl1.2/CL/cl_ext.h#13 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.0/CL/cl_ext.h#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.1/CL/cl_ext.h#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.hpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#208 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#283 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocappprofile.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#36 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#53 edit


[ROCm/clr commit: ff3c30e9ce]
 2017-01-25 11:44:06 -05:00
foreman ff3c30e9ce P4 to Git Change 1365943 by lmoriche@lmoriche_opencl_dev on 2017/01/25 11:37:20 
SWDEV-102726 - [OCL-LC-ROCm] Open source OpenCL Runtime
	- Cleanups: Remove CL_HSA_ENABLED/DISABLED_AMD.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_device.cpp#60 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl1.2/CL/cl_ext.h#13 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.0/CL/cl_ext.h#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.1/CL/cl_ext.h#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.hpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#208 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#283 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocappprofile.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#36 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#53 edit
 2017-01-25 11:44:06 -05:00
foreman 4dba732b4a P4 to Git Change 1365943 by lmoriche@lmoriche_opencl_dev on 2017/01/25 11:37:20 
SWDEV-102726 - [OCL-LC-ROCm] Open source OpenCL Runtime
	- Cleanups: Remove CL_HSA_ENABLED/DISABLED_AMD.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_device.cpp#60 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl1.2/CL/cl_ext.h#13 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.0/CL/cl_ext.h#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.1/CL/cl_ext.h#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.hpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#208 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#283 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocappprofile.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#36 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#53 edit


[ROCm/clr commit: aae258198d]
 2017-01-25 11:44:06 -05:00
foreman aae258198d P4 to Git Change 1365943 by lmoriche@lmoriche_opencl_dev on 2017/01/25 11:37:20 
SWDEV-102726 - [OCL-LC-ROCm] Open source OpenCL Runtime
	- Cleanups: Remove CL_HSA_ENABLED/DISABLED_AMD.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#52 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_device.cpp#60 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl1.2/CL/cl_ext.h#13 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.0/CL/cl_ext.h#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/khronos/headers/opencl2.1/CL/cl_ext.h#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.cpp#15 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/appprofile.hpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#208 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#283 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocappprofile.cpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#36 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#53 edit
 2017-01-25 11:44:06 -05:00
Aditya Atluri 38a90f6119 added device functions header to hip_runtime.h 
Change-Id: I635931e1fbe4b7f0f64f3a126c0f1badcd6d234b


[ROCm/clr commit: 33a3ebad27]
 2017-01-25 08:14:30 -06:00
Aditya Atluri 33a3ebad27 added device functions header to hip_runtime.h 
Change-Id: I635931e1fbe4b7f0f64f3a126c0f1badcd6d234b
 2017-01-25 08:14:30 -06:00
Aditya Atluri 4395881206 added device functions header to hip_runtime.h 
Change-Id: I635931e1fbe4b7f0f64f3a126c0f1badcd6d234b


[ROCm/hip commit: d75d0596bf]
 2017-01-25 08:14:30 -06:00
Aditya Atluri d75d0596bf added device functions header to hip_runtime.h 
Change-Id: I635931e1fbe4b7f0f64f3a126c0f1badcd6d234b
 2017-01-25 08:14:30 -06:00