Chauncey Hui
ca0a327df2
SWDEV-2 - Change OpenCL version number from 3104 to 3105
2020-03-07 03:00:03 -05:00
Vladislav Sytchenko
e76d867740
SWDEV-224023
...
Each WGP consists of 2 CU, so the number of available SIMD units is doubled.
Change-Id: I43978a8a9139c33f5f776b344a36bee927cc187d
2020-03-06 13:43:36 -05:00
Chauncey Hui
ee5eb0107d
SWDEV-2 - Change OpenCL version number from 3103 to 3104
2020-03-05 03:00:02 -05:00
German Andryeyev
0fc433e076
SWDEV-193956 - [hipclang-vdi-rocm][perf]
...
~45% to 50% of Performance drop on rocBLAS_int8 test
Add support for active waits without blocking the host thread.
Change-Id: Ie7bb48dcafcb4c93d448bf74749b829b626c3578
2020-03-04 17:02:15 -05:00
Payam
9106a7dff4
clean up
...
Change-Id: I1a5bbd12bba35af5d52f9ddc0df71dd0d004d122
2020-03-04 13:35:49 -05:00
Chauncey Hui
cc9f32ed27
SWDEV-2 - Change OpenCL version number from 3102 to 3103
2020-03-04 03:00:02 -05:00
Jason Tang
f51ff32113
Seperate PAL and ROCm
...
Change-Id: I7d0fbbab88c0541f17274da6e8850f2c6783dcd1
2020-03-03 16:06:51 -05:00
Vladislav Sytchenko
243a3c2aa4
SWDEV-224335
...
cl_bool needed to be replaced with uint32_t instead of bool. This is due to cl_bool being a typedef of cl_uint32.
Currently clGetDeviceInfo() reports incorrect size for the return value, due to cl_bool being 4 bytes and c++ bool being 1 byte.
Change-Id: I647a4b8873627059865c84c8ca27694dbc0916de
2020-03-03 11:50:37 -05:00
Chauncey Hui
8038b8262c
SWDEV-2 - Change OpenCL version number from 3101 to 3102
2020-03-03 03:00:03 -05:00
German Andryeyev
622c714165
SWDEV-79445
...
Add MS HWS support. PAL reports just one compute engine
in that mode and runtime needs extra logic to detect RT queues.
Change-Id: I011f1f1b18dec6a7195a4f1fe939f8029bc269ae
2020-02-28 19:05:17 -05:00
Chauncey Hui
3bfaa242c8
SWDEV-2 - Change OpenCL version number from 3100 to 3101
2020-02-26 03:00:03 -05:00
Vladislav Sytchenko
019d1feea5
Remove OpenCL Single Buffer Allocation Restriction
...
Change-Id: I5c37a7f08b02ed74ec6984c6da9ffa5dc9bf0f52
2020-02-25 11:41:18 -05:00
Payam
0eea98b755
removed AMD referenced internal url
...
http://172.24.5.22:8888/palamida/InventoryDetails.htm?inventoryId=80447&projectId=1704
Change-Id: I917942cfddd165018904afda7a1ab76cdbc91595
2020-02-25 11:08:19 -05:00
Chauncey Hui
beda512630
SWDEV-2 - Change OpenCL version number from 3099 to 3100
2020-02-25 03:00:02 -05:00
Payam
19791a242b
clean up
...
Change-Id: Ic0201ffd1231f05d265165c62b475f768756991c
2020-02-25 02:13:12 -05:00
jujiang
518a75ca66
SWDEV-196333-hipCopyhammer_H2D&hipCopyHammer_D2H tests fix return false case
...
Change-Id: I919e098f8b1b8c41b200bd32dcf108977c472b43
2020-02-24 15:08:21 -05:00
German Andryeyev
0fb8e378b1
SWDEV-221395 - [OpenCL] Failure to Create RTQ2
...
Don't add real time queues into the pool of generic queues.
Change-Id: I7f6865df740b8a2fbbec5e897a988a2151ef5a9e
2020-02-21 16:50:10 -05:00
German Andryeyev
77ff161324
SWDEV-193956 - [hipclang-vdi-rocm][perf]
...
Retain command before a wait.
Change-Id: I0ab8f1352af32c96567dad9e31b3687bdf407bf6
2020-02-21 16:43:21 -05:00
Chauncey Hui
ec84e8d6e2
SWDEV-2 - Change OpenCL version number from 3087 to 3099
2020-02-21 15:31:26 -05:00
German Andryeyev
a66d09f5a3
SWDEV-193956 - [hipclang-vdi-rocm][perf]
...
~45% to 50% of Performance drop on rocBLAS_int8 test
Use the last command in the queue for a wait.
Add extra print information about processed commands.
Add an option to disable file location printing.
Change-Id: I4187883e1a90e571fde3128af98368108fda8785
2020-02-21 15:21:15 -05:00
Chauncey Hui
fea14a7201
SWDEV-2 - Change OpenCL version number from 3086 to 3087
...
Change-Id: Iee9ff16e0e41e2468c32a6af82dc65a63714a679
2020-02-21 14:11:33 -05:00
Vladislav Sytchenko
696d00e71b
Correct pitch alignment calculation
...
When we're aligning rowPitch to imagePitchAlignment, rowPitch is in pixels,
but imagePitchAlignment_ is bytes, so we end up overaligning the pitch.
Convert imagePitchAlignment_ to pixels before doing any logic.
Change-Id: Ia5ab9d54bed150fe974e86b060dbadc196165b29
2020-02-20 18:00:27 -05:00
Vladislav Sytchenko
5de65ba4a0
Enable SVM atomics for HIP/Win
...
hip_threadfence_system passes locally with this change. This also fixes
hipHostMalloc() failures when hipHostMallocMapped flag is used.
Change-Id: Id412efe502accc7c6e7676b52c05ccb9d8fbbe67
2020-02-19 23:22:37 -05:00
Jason Tang
290b42625a
SWDEV-207312 - Comment out incorrect cl-gl inter-op code to facilitate Linux-Pro testing
...
Change-Id: I273476465332ffcda50a6095f839e1bc07863c8e
2020-02-19 17:56:45 -05:00
Payam
e019d12f81
updated install to include header files from include dir and elf dir
...
Change-Id: Ie7a8de6e5788de082703d806d0e5248bee9d1394
2020-02-19 16:42:12 -05:00
German Andryeyev
1d25343af8
SWDEV-79445 OCL generic changes and code clean-up
...
Remove a workaround to CS_PARTIAL_FLUSH added in CL#1495187,
since PAL is no longer uses CS_PARTIAL_FLUSH.
Change-Id: I03edc7595459e19aad33b2b0901f0ebe4754d310
2020-02-18 18:00:12 -05:00
German Andryeyev
374f612b7c
SWDEV-193956
...
[hipclang-vdi-rocm][perf]~45% to 50% of Performance drop on
rocBLAS_int8 test
- Enable AMD_OPT_FLUSH optimization by default to match HCC
- Disable CPU writes to GPU memory on boards with large bar,
because it requires HDP flush tracking.
- Enable L2 cache on kernel arguments, because L2 will be
invalidated on memory reuse .
Change-Id: I124cf250bdd4d19c523ce542c163813828f8fbdc
2020-02-18 14:26:00 -05:00
Vladislav Sytchenko
afa685234c
Add .gitignore file.
...
Change-Id: Ia072769a04a6c2ed11eb245efc00dd9d555c4d93
2020-02-18 11:09:50 -05:00
German Andryeyev
1be1e69f2a
SWDEV-222307 - Add CMake support for PAL
...
Remove dependency on COMGR headers from backends.
Remove GFX103 PAL defines.
Change-Id: I6ff76dca2a0c84bc191e8fc8b639f2f5872d2085
2020-02-18 10:56:31 -05:00
Saleel Kudchadker
a788f0bc15
Increase the amount of free mem withheld
...
Change-Id: I37ec2250885758f122db6eac0e897dc16d02558d
2020-02-15 16:14:16 -08:00
Saleel Kudchadker
0730b39adb
Implement HIP_HIDDEN_FREE_MEM env var
...
Set value to 256Mb to reflect what HIP/HCC reserves
Change-Id: Icaadf79f60d3916965ac168da237d15b975b1fe4
2020-02-14 12:57:11 -05:00
Christophe Paquot
566144edb2
Append before setting last command to avoid corner case
...
Change-Id: Iafe5f899427f0119e7f43e96af38e6e3a1dbfc93
2020-02-13 22:23:20 -05:00
Karthik Jayaprakash
7fb53890b8
SWDEV-210443 - For Numa nodes pick up the CPU that has Memory pool.
...
Change-Id: If52852b6f12053e4dfe8a83b8aa5743137c3d6dc
2020-02-13 20:48:37 -05:00
Scott Linder
da2e4d449c
Stop using deprecated Comgr option API
...
Update a use of the deprecated amd_comgr_action_info_set_options to
instead use amd_comgr_action_info_set_option_list.
Completely remove all references to amd_comgr_action_info_set_options
and amd_comgr_action_info_get_options from the runtime.
Change-Id: I12a0803c87430722364ec22818e249caf3798c88
2020-02-13 18:53:48 -05:00
Laurent Morichetti
b81816f482
Fix build errors for PAL and GSL
...
The last commit to replace the cl_* types with standard types
failed to correct issues introduced in the PAL and GPU backend.
Change-Id: I926997234dfbe346fc165a7bc4e1b8aabab7bac5
2020-02-13 16:52:32 -05:00
Saleel Kudchadker
a965c1eb0e
HIP version can be set in HIPRTC top layer
...
Indicate that its HIP_VDI to the compiler.
Change-Id: I691ddaa764b3ad62398003856c2480b2eece1f46
2020-02-12 23:19:44 -08:00
Laurent Morichetti
d9d9c69399
Replace cl_* integral types with standard types.
...
cl_bool -> bool
cl_int -> int32_t
cl_uint -> uint32_t
cl_long -> int64_t
cl_ulong -> uint64_t
cl_float -> float
cl_double -> double
cl_bitfield -> uint64_t
Change-Id: I840c8993b55f98f5b745d21e27f5f28233647a58
2020-02-12 13:16:06 -08:00
German Andryeyev
da5f4c554e
Add CMake support for PAL backend
...
Change-Id: Id0673d43217be305aa4ca7a612c416baee3fb23c
2020-02-10 11:18:24 -05:00
Payam
853b2e38a4
updated find_path for opencl so it doesn't break cmake if opencl dir is passed
...
and opencl path is not found
Change-Id: I288dccef8d871bdf4e3e146de9337c1938c231ac
2020-02-07 02:45:46 -05:00
Laurent Morichetti
b4c6143a2f
Update copyright info
...
Change-Id: Ia4f9ff0f5f873b4223a8cca154188bb0d2f1abba
2020-02-04 09:26:14 -08:00
Laurent Morichetti
20c7173849
Merge branch 'origin/pghafari/vdi-prototype' into lmoriche/amd-master
...
Change-Id: Id3b833d405596735becb3346f3b08c6da57033fe
2020-01-30 20:12:13 -08:00
foreman
914c2eb8b6
P4 to Git Change 2062441 by chui@ocl-promo-incrementor on 2020/01/24 03:00:22
...
SWDEV-2 - Change OpenCL version number from 3085 to 3086.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2833 edit
2020-01-24 03:09:41 -05:00
foreman
6ace9abcd6
P4 to Git Change 2062152 by gandryey@gera-win10 on 2020/01/23 13:48:08
...
SWDEV-197836 - Drop the use of llvm header files in opencl runtime
- COv2 doesn't report HostCall argument properly. Make a workaround for it.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.cpp#34 edit
2020-01-23 13:55:16 -05:00
foreman
0edb23bf71
P4 to Git Change 2061934 by chui@ocl-promo-incrementor on 2020/01/23 03:00:21
...
SWDEV-2 - Change OpenCL version number from 3084 to 3085.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2832 edit
2020-01-23 03:10:00 -05:00
foreman
836301fd4a
P4 to Git Change 2061572 by kjayapra@2_HIPWS_P2P_ROCM2 on 2020/01/22 12:08:52
...
SWDEV-145570 - MI200 Support changes
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdefs.hpp#29 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#151 edit
2020-01-22 12:13:41 -05:00
foreman
7bbcdc4186
P4 to Git Change 2061411 by chui@ocl-promo-incrementor on 2020/01/22 03:00:20
...
SWDEV-2 - Change OpenCL version number from 3083 to 3084.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2831 edit
2020-01-22 03:08:48 -05:00
foreman
7cb078bf63
P4 to Git Change 2061164 by gandryey@gera-win10 on 2020/01/21 18:19:35
...
SWDEV-197836 - Drop the use of llvm header files in opencl runtime
- Remove llvm::AMDGPU::HSAMD::Kernel::Metadata usage
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.cpp#33 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.hpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#78 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.hpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#86 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.hpp#31 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#55 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.hpp#28 edit
2020-01-21 18:24:20 -05:00
foreman
29dd0eb7a2
P4 to Git Change 2061101 by skudchad@skudchad_test2_win_opencl on 2020/01/21 16:47:25
...
SWDEV-219917 - [VDI Cleanup] Remove some direct OpenCL references, introduce a common functionality.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/18488/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/build/Makefile.hip#30 edit
... //depot/stg/opencl/drivers/opencl/api/hip/fixme.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_internal.hpp#51 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hiprtc_internal.hpp#3 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/build/Makefile.api#190 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_common.hpp#25 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#61 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_device.cpp#75 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#31 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_icd.cpp#36 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_platform_amd.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#54 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#610 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#180 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#150 edit
... //depot/stg/opencl/drivers/opencl/runtime/include/vdi_agent_amd.h#1 add
... //depot/stg/opencl/drivers/opencl/runtime/include/vdi_common.hpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/os/os.hpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/os/os_posix.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/os/os_win32.cpp#50 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/agent.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/agent.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#54 edit
... //depot/stg/opencl/drivers/opencl/runtime/runtimedefs#54 edit
2020-01-21 16:52:40 -05:00
foreman
69884318ac
P4 to Git Change 2060936 by gandryey@gera-win10 on 2020/01/21 13:28:16
...
SWDEV-197836 - Drop the use of llvm header files in opencl runtime
- Remove usage of llvm::AMDGPU::HSAMD::Kernel::Arg::Metadata
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.cpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.hpp#21 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devprogram.cpp#77 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#102 edit
2020-01-21 12:36:01 -06:00
foreman
2e299c52b0
P4 to Git Change 2060601 by chui@ocl-promo-incrementor on 2020/01/21 03:00:20
...
SWDEV-2 - Change OpenCL version number from 3082 to 3083.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2830 edit
2020-01-21 03:06:13 -05:00