76333 Commits
Author SHA1 Message Date
Evgeny cc7268a832 support for python apps profiling
Change-Id: I2dd6d9d760abb1dab59f0d3464b9a50008694187


[ROCm/rocprofiler commit: c0703c063c]
2019-05-16 12:07:07 -05:00
Gilbert Lee 60f91f645d Updating RCCL based on NCCL 2.3.7
- Contains modifications to support AMD hardware
- Adds unit tests


[ROCm/rccl commit: 55a4b22ad7]
2019-05-16 16:16:18 +00:00
Gilbert Lee 55a4b22ad7 Updating RCCL based on NCCL 2.3.7
- Contains modifications to support AMD hardware
- Adds unit tests
2019-05-16 16:16:18 +00:00
Evgeny Mankov 824d5d8792 Update README.md
[ROCm/clr commit: 633323c981]
2019-05-16 18:16:17 +03:00
Evgeny Mankov 633323c981 Update README.md 2019-05-16 18:16:17 +03:00
Evgeny Mankov ca5d1e1ce6 Update README.md
[ROCm/hip commit: b29b8bb690]
2019-05-16 18:16:17 +03:00
Evgeny Mankov b29b8bb690 Update README.md 2019-05-16 18:16:17 +03:00
Evgeny Mankov df5dbdd6a6 Merge pull request #1116 from emankov/master
[HIPIFY][doc] Update README.md

[ROCm/clr commit: ab865dbf0e]
2019-05-16 18:10:09 +03:00
Evgeny Mankov ab865dbf0e Merge pull request #1116 from emankov/master
[HIPIFY][doc] Update README.md
2019-05-16 18:10:09 +03:00
Evgeny Mankov 0662c1e98d Merge pull request #1116 from emankov/master
[HIPIFY][doc] Update README.md

[ROCm/hip commit: 482c6aebb7]
2019-05-16 18:10:09 +03:00
Evgeny Mankov 482c6aebb7 Merge pull request #1116 from emankov/master
[HIPIFY][doc] Update README.md
2019-05-16 18:10:09 +03:00
Evgeny Mankov 71647e33bf [HIPIFY][doc] Update README.md
+ Update logs
+ Formatting


[ROCm/clr commit: df2a64cf0d]
2019-05-16 18:07:11 +03:00
Evgeny Mankov df2a64cf0d [HIPIFY][doc] Update README.md
+ Update logs
+ Formatting
2019-05-16 18:07:11 +03:00
Evgeny Mankov 50253b37be [HIPIFY][doc] Update README.md
+ Update logs
+ Formatting


[ROCm/hip commit: 6508ca8e76]
2019-05-16 18:07:11 +03:00
Evgeny Mankov 6508ca8e76 [HIPIFY][doc] Update README.md
+ Update logs
+ Formatting
2019-05-16 18:07:11 +03:00
Evgeny Mankov 9d0ac6be5e Merge pull request #1115 from emankov/master
[HIPIFY][cuDNN] Add cudnnGetFilter4dDescriptor support

[ROCm/clr commit: 21518887bc]
2019-05-16 16:39:34 +03:00
Evgeny Mankov 21518887bc Merge pull request #1115 from emankov/master
[HIPIFY][cuDNN] Add cudnnGetFilter4dDescriptor support
2019-05-16 16:39:34 +03:00
Evgeny Mankov fa872ef65d Merge pull request #1115 from emankov/master
[HIPIFY][cuDNN] Add cudnnGetFilter4dDescriptor support

[ROCm/hip commit: 390db35dfb]
2019-05-16 16:39:34 +03:00
Evgeny Mankov 390db35dfb Merge pull request #1115 from emankov/master
[HIPIFY][cuDNN] Add cudnnGetFilter4dDescriptor support
2019-05-16 16:39:34 +03:00
Evgeny Mankov 76c52aa429 [HIPIFY][cuDNN] Add cudnnGetFilter4dDescriptor support
+ Update cudnn_convolution_forward test accordingly


[ROCm/clr commit: 02f8dfe7d8]
2019-05-16 16:36:23 +03:00
Evgeny Mankov 02f8dfe7d8 [HIPIFY][cuDNN] Add cudnnGetFilter4dDescriptor support
+ Update cudnn_convolution_forward test accordingly
2019-05-16 16:36:23 +03:00
Evgeny Mankov ce28dc83e4 [HIPIFY][cuDNN] Add cudnnGetFilter4dDescriptor support
+ Update cudnn_convolution_forward test accordingly


[ROCm/hip commit: aed2affda2]
2019-05-16 16:36:23 +03:00
Evgeny Mankov aed2affda2 [HIPIFY][cuDNN] Add cudnnGetFilter4dDescriptor support
+ Update cudnn_convolution_forward test accordingly
2019-05-16 16:36:23 +03:00
Alex Voicu a4a3132c64 Add HIPRTC, glorious ersatz for NVRTC (#1097)
* Add ersatz for NVRTC.

* Fix extraneous paren and use correct namespace.

* Use lowerCamelCase (yuck, yuck) consistently.

* Link against FS when building hiprtc lib.

* Correctly mark Manipulators. Fix dual compile.

* Add unit tests. Extend HIT to accept linker options.

* Make sure the HIPRTC library is installed.

* Better logging. Try to auto-detect the target.

* Stop specifying the target explicitly.

* Add missing flavour of `hipModuleLaunchKernel`.

* Program was already destroyed.

* Don't use `--genco`. Fix mangled name trimming.

* Fix HIPRTC breakage due to upstream noise.

* [dtests] Replace RUN -> TEST in hiprtc tests

Change-Id: Ie499e92dfe4e5c94634b1c2b76cf52d241bcfea3

* [hit] Set HIP_PATH to HIP_ROOT_DIR for all tests

Change-Id: Ib0ad1f99bc71c03e363e055dd508a7a4a210680a


[ROCm/clr commit: a538eb705a]
2019-05-16 18:28:54 +05:30
Alex Voicu a538eb705a Add HIPRTC, glorious ersatz for NVRTC (#1097)
* Add ersatz for NVRTC.

* Fix extraneous paren and use correct namespace.

* Use lowerCamelCase (yuck, yuck) consistently.

* Link against FS when building hiprtc lib.

* Correctly mark Manipulators. Fix dual compile.

* Add unit tests. Extend HIT to accept linker options.

* Make sure the HIPRTC library is installed.

* Better logging. Try to auto-detect the target.

* Stop specifying the target explicitly.

* Add missing flavour of `hipModuleLaunchKernel`.

* Program was already destroyed.

* Don't use `--genco`. Fix mangled name trimming.

* Fix HIPRTC breakage due to upstream noise.

* [dtests] Replace RUN -> TEST in hiprtc tests

Change-Id: Ie499e92dfe4e5c94634b1c2b76cf52d241bcfea3

* [hit] Set HIP_PATH to HIP_ROOT_DIR for all tests

Change-Id: Ib0ad1f99bc71c03e363e055dd508a7a4a210680a
2019-05-16 18:28:54 +05:30
Alex Voicu d5a3acfd69 Add HIPRTC, glorious ersatz for NVRTC (#1097)
* Add ersatz for NVRTC.

* Fix extraneous paren and use correct namespace.

* Use lowerCamelCase (yuck, yuck) consistently.

* Link against FS when building hiprtc lib.

* Correctly mark Manipulators. Fix dual compile.

* Add unit tests. Extend HIT to accept linker options.

* Make sure the HIPRTC library is installed.

* Better logging. Try to auto-detect the target.

* Stop specifying the target explicitly.

* Add missing flavour of `hipModuleLaunchKernel`.

* Program was already destroyed.

* Don't use `--genco`. Fix mangled name trimming.

* Fix HIPRTC breakage due to upstream noise.

* [dtests] Replace RUN -> TEST in hiprtc tests

Change-Id: Ie499e92dfe4e5c94634b1c2b76cf52d241bcfea3

* [hit] Set HIP_PATH to HIP_ROOT_DIR for all tests

Change-Id: Ib0ad1f99bc71c03e363e055dd508a7a4a210680a


[ROCm/hip commit: ccfb764a59]
2019-05-16 18:28:54 +05:30
Alex Voicu ccfb764a59 Add HIPRTC, glorious ersatz for NVRTC (#1097)
* Add ersatz for NVRTC.

* Fix extraneous paren and use correct namespace.

* Use lowerCamelCase (yuck, yuck) consistently.

* Link against FS when building hiprtc lib.

* Correctly mark Manipulators. Fix dual compile.

* Add unit tests. Extend HIT to accept linker options.

* Make sure the HIPRTC library is installed.

* Better logging. Try to auto-detect the target.

* Stop specifying the target explicitly.

* Add missing flavour of `hipModuleLaunchKernel`.

* Program was already destroyed.

* Don't use `--genco`. Fix mangled name trimming.

* Fix HIPRTC breakage due to upstream noise.

* [dtests] Replace RUN -> TEST in hiprtc tests

Change-Id: Ie499e92dfe4e5c94634b1c2b76cf52d241bcfea3

* [hit] Set HIP_PATH to HIP_ROOT_DIR for all tests

Change-Id: Ib0ad1f99bc71c03e363e055dd508a7a4a210680a
2019-05-16 18:28:54 +05:30
Maneesh Gupta ef71f962f9 Merge pull request #1113 from wenkaidu/hop_count
Use NUMA distance for hop count calculation

[ROCm/clr commit: 3178ae2f92]
2019-05-16 14:16:29 +05:30
Maneesh Gupta 3178ae2f92 Merge pull request #1113 from wenkaidu/hop_count
Use NUMA distance for hop count calculation
2019-05-16 14:16:29 +05:30
Maneesh Gupta 37226415d8 Merge pull request #1113 from wenkaidu/hop_count
Use NUMA distance for hop count calculation

[ROCm/hip commit: de7ec55bea]
2019-05-16 14:16:29 +05:30
Maneesh Gupta de7ec55bea Merge pull request #1113 from wenkaidu/hop_count
Use NUMA distance for hop count calculation
2019-05-16 14:16:29 +05:30
Maneesh Gupta 13f8cc0139 Merge pull request #1112 from kpyzhov/hipModule-test
Upload pre-built kernel binary for hipModule test.

[ROCm/clr commit: 8e9bc62f6e]
2019-05-16 14:16:18 +05:30
Maneesh Gupta 8e9bc62f6e Merge pull request #1112 from kpyzhov/hipModule-test
Upload pre-built kernel binary for hipModule test.
2019-05-16 14:16:18 +05:30
Maneesh Gupta 0d973555ee Merge pull request #1112 from kpyzhov/hipModule-test
Upload pre-built kernel binary for hipModule test.

[ROCm/hip commit: 6e4646bb80]
2019-05-16 14:16:18 +05:30
Maneesh Gupta 6e4646bb80 Merge pull request #1112 from kpyzhov/hipModule-test
Upload pre-built kernel binary for hipModule test.
2019-05-16 14:16:18 +05:30
foreman 9596c6ea6b P4 to Git Change 1783724 by chui@ocl-promo-incrementor on 2019/05/16 03:00:05
SWDEV-2 - Change OpenCL version number from 2900 to 2901.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2648 edit


[ROCm/clr commit: 544a731139]
2019-05-16 03:12:36 -04:00
foreman 544a731139 P4 to Git Change 1783724 by chui@ocl-promo-incrementor on 2019/05/16 03:00:05
SWDEV-2 - Change OpenCL version number from 2900 to 2901.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2648 edit
2019-05-16 03:12:36 -04:00
foreman 775ae4f1f5 P4 to Git Change 1783658 by cpaquot@cpaquot-ocl-lc-lnx on 2019/05/15 22:55:22
SWDEV-189541 - [HIP] Make sure maxSvmSize is power of two.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#136 edit


[ROCm/clr commit: 0ac6dcbd24]
2019-05-15 23:14:28 -04:00
foreman 0ac6dcbd24 P4 to Git Change 1783658 by cpaquot@cpaquot-ocl-lc-lnx on 2019/05/15 22:55:22
SWDEV-189541 - [HIP] Make sure maxSvmSize is power of two.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#136 edit
2019-05-15 23:14:28 -04:00
Chris Freehill 52ae3fc6d5 Merge pull request #40 from cfreehill/master
Check for root access early for functions that require it

[ROCm/rocm_smi_lib commit: acc508de60]
2019-05-15 16:55:43 -05:00
Chris Freehill acc508de60 Merge pull request #40 from cfreehill/master
Check for root access early for functions that require it
2019-05-15 16:55:43 -05:00
Chris Freehill 29a2617c19 Merge pull request #40 from cfreehill/master
Check for root access early for functions that require it

[ROCm/amdsmi commit: acc508de60]
2019-05-15 16:55:43 -05:00
Chris Freehill c57a91d856 Check for root access early for functions that require it
[ROCm/rocm_smi_lib commit: 7b9ff01a37]
2019-05-15 16:54:20 -05:00
Chris Freehill 7b9ff01a37 Check for root access early for functions that require it 2019-05-15 16:54:20 -05:00
Chris Freehill 1429d987f5 Check for root access early for functions that require it
[ROCm/amdsmi commit: 7b9ff01a37]
2019-05-15 16:54:20 -05:00
Wenkai Du 3d75b10e0b Use NUMA distance for hop count calculation
[ROCm/clr commit: 56d2dc0022]
2019-05-15 21:50:35 +00:00
Wenkai Du 56d2dc0022 Use NUMA distance for hop count calculation 2019-05-15 21:50:35 +00:00
Wenkai Du bea3232428 Use NUMA distance for hop count calculation
[ROCm/hip commit: e8e58e9ce5]
2019-05-15 21:50:35 +00:00
Wenkai Du e8e58e9ce5 Use NUMA distance for hop count calculation 2019-05-15 21:50:35 +00:00
Stanley Tsang 1ced548da6 Update README.md
[ROCm/rccl-tests commit: 3aa32972f4]
2019-05-15 11:22:34 -06:00