AI/rocm-systems
2
0 Forkuj 0
Kod Zgłoszenia Oczekujące zmiany Akcje Pakiety Projekty Wydania Wiki Aktywność
76 333 Commity 3 Gałęzie 0 Tagi
develop
Wykres commitów
76333 Commity
Ta gałąź
Ta gałąź
Wszystkie gałęzie
Autor SHA1 Wiadomość Data
Anusha Godavarthy Surya c5fc879606 Fix undefine ref to hipUbindTexture for texture types 
[ROCm/clr commit: a5d9f56bef]
 2019-10-09 16:26:06 +05:30
Anusha Godavarthy Surya a5d9f56bef Fix undefine ref to hipUbindTexture for texture types 2019-10-09 16:26:06 +05:30
Anusha Godavarthy Surya 04080d4bb1 Fix undefine ref to hipUbindTexture for texture types 
[ROCm/hip commit: af5f195e46]
 2019-10-09 16:26:06 +05:30
Anusha Godavarthy Surya af5f195e46 Fix undefine ref to hipUbindTexture for texture types 2019-10-09 16:26:06 +05:30
foreman 7174fcd31c P4 to Git Change 2010466 by chui@ocl-promo-incrementor on 2019/10/09 03:00:46 
SWDEV-2 - Change OpenCL version number from 3015 to 3016.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2763 edit


[ROCm/clr commit: dcaa953e8d]
 2019-10-09 03:04:07 -04:00
foreman dcaa953e8d P4 to Git Change 2010466 by chui@ocl-promo-incrementor on 2019/10/09 03:00:46 
SWDEV-2 - Change OpenCL version number from 3015 to 3016.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2763 edit
 2019-10-09 03:04:07 -04:00
Evgeny 3f73d90d61 start/stop API 
[ROCm/roctracer commit: 72b5494f0b]
 2019-10-09 01:00:05 -05:00
Evgeny 72b5494f0b start/stop API 2019-10-09 01:00:05 -05:00
Evgeny 266d2fd9c8 tracing layer unifying with hcc: removing API_ID_ANY 
[ROCm/clr commit: ed29c10394]
 2019-10-08 19:09:43 -05:00
Evgeny ed29c10394 tracing layer unifying with hcc: removing API_ID_ANY 2019-10-08 19:09:43 -05:00
Evgeny 8c0b43156e tracing layer unifying with hcc: removing API_ID_ANY 
[ROCm/hip commit: 4e93833035]
 2019-10-08 19:09:43 -05:00
Evgeny 4e93833035 tracing layer unifying with hcc: removing API_ID_ANY 2019-10-08 19:09:43 -05:00
Wenkai Du f86ee41415 Enable tree kernels in build 
Need to tune and specify NCCL_TREE_THRESHOLD to allow usage


[ROCm/rccl commit: 76976c9e2e]
 2019-10-08 23:20:11 +00:00
Wenkai Du 76976c9e2e Enable tree kernels in build 
Need to tune and specify NCCL_TREE_THRESHOLD to allow usage
 2019-10-08 23:20:11 +00:00
foreman 4ca6ca35b6 P4 to Git Change 2010251 by vsytchen@vsytchen-remote-ocl-win10 on 2019/10/08 18:30:23 
SWDEV-193973 - Update perfcounter info to accomodate PAL interface changes

	Gfx103 added perf counters for three new blocks - GeDist, GeSe and Df

	1. Update the blockIdToIndexSelect array to reflect these changes.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/18063/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.cpp#25 edit


[ROCm/clr commit: 5fc5006853]
 2019-10-08 18:38:10 -04:00
foreman 5fc5006853 P4 to Git Change 2010251 by vsytchen@vsytchen-remote-ocl-win10 on 2019/10/08 18:30:23 
SWDEV-193973 - Update perfcounter info to accomodate PAL interface changes

	Gfx103 added perf counters for three new blocks - GeDist, GeSe and Df

	1. Update the blockIdToIndexSelect array to reflect these changes.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/18063/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.cpp#25 edit
 2019-10-08 18:38:10 -04:00
Oak Zeng da789a2584 Fix memory map issue in KFDMemoryTest.CacheInvalidationOnRemoteWrite 
The memory need to be mapped for both local and remote GPU access

Change-Id: I4aeaffc0851b6107fc91e9eaa6150764b06f5ca9
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
 2019-10-08 16:33:51 -05:00
Oak Zeng 3a93aff9f3 Fix memory map issue in KFDMemoryTest.CacheInvalidationOnRemoteWrite 
The memory need to be mapped for both local and remote GPU access

Change-Id: I4aeaffc0851b6107fc91e9eaa6150764b06f5ca9
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>


[ROCm/ROCR-Runtime commit: da789a2584]
 2019-10-08 16:33:51 -05:00
Changpeng Fang d8a06589c9 Tuning the inline and unroll to reduce the scratch usage 
Summary:
 1. remove the noinline attribute for AllReduceThreeKernel;
 2. change AUTPUNROLL for tree functions to 1 or 2;
 Combining 1 and 2 will reduce the scratch usage from 1256 to 952


[ROCm/rccl commit: eec319038e]
 2019-10-08 14:02:25 -07:00
Changpeng Fang eec319038e Tuning the inline and unroll to reduce the scratch usage 
Summary:
 1. remove the noinline attribute for AllReduceThreeKernel;
 2. change AUTPUNROLL for tree functions to 1 or 2;
 Combining 1 and 2 will reduce the scratch usage from 1256 to 952
 2019-10-08 14:02:25 -07:00
rkebichi 70abcbb7d7 Update roctracer_kfd.h 
[ROCm/roctracer commit: af41d4ae2e]
 2019-10-08 16:38:03 -04:00
rkebichi af41d4ae2e Update roctracer_kfd.h 2019-10-08 16:38:03 -04:00
Evgeny Mankov 06243bbe2e Merge pull request #1513 from emankov/hipify-clang 
[HIPIFY][doc] Add a few words about hipify-perl

[ROCm/clr commit: 7c3f5a387d]
 2019-10-08 22:30:25 +03:00
Evgeny Mankov 7c3f5a387d Merge pull request #1513 from emankov/hipify-clang 
[HIPIFY][doc] Add a few words about hipify-perl
 2019-10-08 22:30:25 +03:00
Evgeny Mankov a8b7ebefb0 Merge pull request #1513 from emankov/hipify-clang 
[HIPIFY][doc] Add a few words about hipify-perl

[ROCm/hip commit: 4a4a620389]
 2019-10-08 22:30:25 +03:00
Evgeny Mankov 4a4a620389 Merge pull request #1513 from emankov/hipify-clang 
[HIPIFY][doc] Add a few words about hipify-perl
 2019-10-08 22:30:25 +03:00
Evgeny Mankov 19870d6e3d [HIPIFY][doc] Add a few words about hipify-perl 
+ Update testing and versions


[ROCm/clr commit: eaffbb10b8]
 2019-10-08 22:27:48 +03:00
Evgeny Mankov eaffbb10b8 [HIPIFY][doc] Add a few words about hipify-perl 
+ Update testing and versions
 2019-10-08 22:27:48 +03:00
Evgeny Mankov 7aa4b75259 [HIPIFY][doc] Add a few words about hipify-perl 
+ Update testing and versions


[ROCm/hip commit: de1b81b78a]
 2019-10-08 22:27:48 +03:00
Evgeny Mankov de1b81b78a [HIPIFY][doc] Add a few words about hipify-perl 
+ Update testing and versions
 2019-10-08 22:27:48 +03:00
foreman 7f796aa557 P4 to Git Change 2010058 by kjayapra@0_HIPWS_LNX1_ROCM on 2019/10/08 14:44:53 
SWDEV-144570 - Implementation of APIs hipMemsetD8Async, hipMemAllocPitch, hipMemAllocHost and template for hipMemsetD16, hipMemsetD16Async.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#30 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#29 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#75 edit


[ROCm/clr commit: 250ecb0bdb]
 2019-10-08 14:55:27 -04:00
foreman 250ecb0bdb P4 to Git Change 2010058 by kjayapra@0_HIPWS_LNX1_ROCM on 2019/10/08 14:44:53 
SWDEV-144570 - Implementation of APIs hipMemsetD8Async, hipMemAllocPitch, hipMemAllocHost and template for hipMemsetD16, hipMemsetD16Async.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#30 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#29 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#75 edit
 2019-10-08 14:55:27 -04:00
foreman 6285c64be1 P4 to Git Change 2010058 by kjayapra@0_HIPWS_LNX1_ROCM on 2019/10/08 14:44:53 
SWDEV-144570 - Implementation of APIs hipMemsetD8Async, hipMemAllocPitch, hipMemAllocHost and template for hipMemsetD16, hipMemsetD16Async.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#30 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#29 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#75 edit


[ROCm/hip commit: e455ddb5b3]
 2019-10-08 14:55:27 -04:00
foreman e455ddb5b3 P4 to Git Change 2010058 by kjayapra@0_HIPWS_LNX1_ROCM on 2019/10/08 14:44:53 
SWDEV-144570 - Implementation of APIs hipMemsetD8Async, hipMemAllocPitch, hipMemAllocHost and template for hipMemsetD16, hipMemsetD16Async.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#30 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#29 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#75 edit
 2019-10-08 14:55:27 -04:00
foreman 5ad6c23d09 P4 to Git Change 2009953 by eshcherb@evgeny-hip on 2019/10/08 12:36:36 
SWDEV-197287 - HIP tracing layer instrumentation - Windows link issues.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_intercept.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_prof_api.h#2 edit


[ROCm/clr commit: 88f0064461]
 2019-10-08 12:46:05 -04:00
foreman 88f0064461 P4 to Git Change 2009953 by eshcherb@evgeny-hip on 2019/10/08 12:36:36 
SWDEV-197287 - HIP tracing layer instrumentation - Windows link issues.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_intercept.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_prof_api.h#2 edit
 2019-10-08 12:46:05 -04:00
foreman 2005705374 P4 to Git Change 2009953 by eshcherb@evgeny-hip on 2019/10/08 12:36:36 
SWDEV-197287 - HIP tracing layer instrumentation - Windows link issues.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_intercept.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_prof_api.h#2 edit


[ROCm/hip commit: 3990498a1e]
 2019-10-08 12:46:05 -04:00
foreman 3990498a1e P4 to Git Change 2009953 by eshcherb@evgeny-hip on 2019/10/08 12:36:36 
SWDEV-197287 - HIP tracing layer instrumentation - Windows link issues.

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_intercept.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_prof_api.h#2 edit
 2019-10-08 12:46:05 -04:00
foreman 6f4f575ac7 P4 to Git Change 2009907 by ssahasra@ssahasra-hip-vdi on 2019/10/08 11:19:25 
SWDEV-204782 - store extra information per HSA queue

	The new struct QueueInfo is used to store metadata about each HSA
	queue. For hostcall, this structure will eventually contain a pointer to
	the hostcall buffer allocated to each HSA queue.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#135 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#41 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#88 edit


[ROCm/clr commit: 1820fe21cf]
 2019-10-08 10:27:38 -05:00
foreman 1820fe21cf P4 to Git Change 2009907 by ssahasra@ssahasra-hip-vdi on 2019/10/08 11:19:25 
SWDEV-204782 - store extra information per HSA queue

	The new struct QueueInfo is used to store metadata about each HSA
	queue. For hostcall, this structure will eventually contain a pointer to
	the hostcall buffer allocated to each HSA queue.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#135 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#41 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#88 edit
 2019-10-08 10:27:38 -05:00
Evgeny Mankov 9f1e0cc4c1 Merge pull request #1512 from emankov/perl 
[HIPIFY][#1487][fix] Translate correctly kernel names prefixed with namespace

[ROCm/clr commit: 6ab6fc99a0]
 2019-10-08 16:01:32 +03:00
Evgeny Mankov 6ab6fc99a0 Merge pull request #1512 from emankov/perl 
[HIPIFY][#1487][fix] Translate correctly kernel names prefixed with namespace
 2019-10-08 16:01:32 +03:00
Evgeny Mankov bd979868b6 Merge pull request #1512 from emankov/perl 
[HIPIFY][#1487][fix] Translate correctly kernel names prefixed with namespace

[ROCm/hip commit: 763bd7002a]
 2019-10-08 16:01:32 +03:00
Evgeny Mankov 763bd7002a Merge pull request #1512 from emankov/perl 
[HIPIFY][#1487][fix] Translate correctly kernel names prefixed with namespace
 2019-10-08 16:01:32 +03:00
Evgeny Mankov 808f59cd1c [HIPIFY][#1487][fix] Translate correctly kernel names prefixed with namespace 
+ Modify CUDA2HIP_perl for the fix
+ Add ns_kernel_launch.cu test
+ Update hipify-perl by hipify-clang -perl


[ROCm/clr commit: 4a2d87b70c]
 2019-10-08 15:58:48 +03:00
Evgeny Mankov 4a2d87b70c [HIPIFY][#1487][fix] Translate correctly kernel names prefixed with namespace 
+ Modify CUDA2HIP_perl for the fix
+ Add ns_kernel_launch.cu test
+ Update hipify-perl by hipify-clang -perl
 2019-10-08 15:58:48 +03:00
Evgeny Mankov 69ea727e92 [HIPIFY][#1487][fix] Translate correctly kernel names prefixed with namespace 
+ Modify CUDA2HIP_perl for the fix
+ Add ns_kernel_launch.cu test
+ Update hipify-perl by hipify-clang -perl


[ROCm/hip commit: 3286ffdfc0]
 2019-10-08 15:58:48 +03:00
Evgeny Mankov 3286ffdfc0 [HIPIFY][#1487][fix] Translate correctly kernel names prefixed with namespace 
+ Modify CUDA2HIP_perl for the fix
+ Add ns_kernel_launch.cu test
+ Update hipify-perl by hipify-clang -perl
 2019-10-08 15:58:48 +03:00
foreman 2fb7d0e5cc P4 to Git Change 2009716 by chui@ocl-promo-incrementor on 2019/10/08 03:00:45 
SWDEV-2 - Change OpenCL version number from 3014 to 3015.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2762 edit


[ROCm/clr commit: 35a4ac7c6b]
 2019-10-08 03:06:14 -04:00
foreman 35a4ac7c6b P4 to Git Change 2009716 by chui@ocl-promo-incrementor on 2019/10/08 03:00:45 
SWDEV-2 - Change OpenCL version number from 3014 to 3015.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2762 edit
 2019-10-08 03:06:14 -04:00