AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
54,851 Commits 3 Branches 0 Tags
a2cedb7fe5ccb4c0bbd911a661672e7d581e95e4
Commit Graph

54851 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
foreman 655732efab P4 to Git Change 1539091 by vsytchen@vsytchen-ocl-win10 on 2018/04/10 14:57:40 
SWDEV-150166 - [OCL][LC][Ellesmere][Windows] oclcompiler.OCLStructOperations[30] causing crash

	1. Set the default amount of command buffer allocated per queue to 4 for pre-gfx9 and 12 for gfx9+ pal devices.
	2. Limit the amount of command buffers allocated for device queue to 2.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14594/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#50 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#89 edit
 2018-04-10 15:53:40 -04:00
Hari Thangirala 3e0cd85d69 Allow HSA_ENABLE_SDMA to override runtime defaults. 
Change-Id: I2305304228010157bfb589c365f4a998577231cd
 2018-04-10 12:56:48 -04:00
Hari Thangirala 28e79a42c2 Allow HSA_ENABLE_SDMA to override runtime defaults. 
Change-Id: I2305304228010157bfb589c365f4a998577231cd


[ROCm/ROCR-Runtime commit: 3e0cd85d69]
 2018-04-10 12:56:48 -04:00
foreman dc5e6fb1e2 P4 to Git Change 1538923 by vsytchen@vsytchen-ocl-win10 on 2018/04/10 12:18:20 
SWDEV-150166 - [OCL][LC][Ellesmere][Windows] oclcompiler.OCLStructOperations[30] causing crash

	1. Add runtime flag GPU_MAX_COMMAND_BUFFERS to set the amount of command buffers allocated per queue for pal devices.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14572/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#47 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#288 edit


[ROCm/clr commit: 19332a7d5e]
 2018-04-10 12:34:33 -04:00
foreman 19332a7d5e P4 to Git Change 1538923 by vsytchen@vsytchen-ocl-win10 on 2018/04/10 12:18:20 
SWDEV-150166 - [OCL][LC][Ellesmere][Windows] oclcompiler.OCLStructOperations[30] causing crash

	1. Add runtime flag GPU_MAX_COMMAND_BUFFERS to set the amount of command buffers allocated per queue for pal devices.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14572/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#47 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#288 edit
 2018-04-10 12:34:33 -04:00
foreman a9c0878566 P4 to Git Change 1538910 by vsytchen@vsytchen-ocl-win10 on 2018/04/10 11:54:42 
SWDEV-150453 - [CQE OCL][DTB][Perf][QR][Vega][DTB-BLOCKER] Performance drop observed on multiple subtests while running Nuke

	1. Clean up suballocation chunk creation logic.
	2. Try to cache a resource if it wasn't a suballocation.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14591/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#62 edit


[ROCm/clr commit: 3e14baceee]
 2018-04-10 12:00:04 -04:00
foreman 3e14baceee P4 to Git Change 1538910 by vsytchen@vsytchen-ocl-win10 on 2018/04/10 11:54:42 
SWDEV-150453 - [CQE OCL][DTB][Perf][QR][Vega][DTB-BLOCKER] Performance drop observed on multiple subtests while running Nuke

	1. Clean up suballocation chunk creation logic.
	2. Try to cache a resource if it wasn't a suballocation.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/14591/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#62 edit
 2018-04-10 12:00:04 -04:00
Laurent Morichetti 51a692ce2e Create one hipModule_t per device 
[ROCm/clr commit: f4cde23be3]
 2018-04-10 08:57:34 -07:00
Laurent Morichetti f4cde23be3 Create one hipModule_t per device 2018-04-10 08:57:34 -07:00
Laurent Morichetti 91f996035c Create one hipModule_t per device 2018-04-10 08:57:34 -07:00
Konstantin Zhuravlyov 7ef70f7eaa Bring naming on par with the spec (hsa-runtime) 
Change-Id: Ie1903c90a195cf95b186eb5552131a20af408adf
 2018-04-10 09:15:02 -04:00
Konstantin Zhuravlyov 683c95a3b7 Bring naming on par with the spec (hsa-runtime) 
Change-Id: Ie1903c90a195cf95b186eb5552131a20af408adf


[ROCm/ROCR-Runtime commit: 7ef70f7eaa]
 2018-04-10 09:15:02 -04:00
foreman c9199e3bed P4 to Git Change 1538669 by johtaylo@johtaylo-jtincrementor2-increment on 2018/04/10 03:00:05 
SWDEV-2 - Change OpenCL version number from 2627 to 2628.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2375 edit


[ROCm/clr commit: caa618b3e4]
 2018-04-10 03:08:48 -04:00
foreman caa618b3e4 P4 to Git Change 1538669 by johtaylo@johtaylo-jtincrementor2-increment on 2018/04/10 03:00:05 
SWDEV-2 - Change OpenCL version number from 2627 to 2628.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2375 edit
 2018-04-10 03:08:48 -04:00
Evgeny cf11e49e2a rocprofiler-dev package 
Change-Id: I80c4f6fd0619f4985516be66dedd2945abcdf9af
 2018-04-09 09:05:56 -05:00
Evgeny a9869caa8b rocprofiler-dev package 
Change-Id: I80c4f6fd0619f4985516be66dedd2945abcdf9af


[ROCm/rocprofiler commit: cf11e49e2a]
 2018-04-09 09:05:56 -05:00
Jenkins 5cc1610281 Merge 'master' into 'amd-master' 
Change-Id: I2bb8d2d98bb90185d663d0dc3bad1803acd857cc


[ROCm/clr commit: f61ca7be5c]
 2018-04-09 04:10:14 -05:00
Jenkins f61ca7be5c Merge 'master' into 'amd-master' 
Change-Id: I2bb8d2d98bb90185d663d0dc3bad1803acd857cc
 2018-04-09 04:10:14 -05:00
Jenkins 61c2b91ebe Merge 'master' into 'amd-master' 
Change-Id: I2bb8d2d98bb90185d663d0dc3bad1803acd857cc
 2018-04-09 04:10:14 -05:00
Maneesh Gupta dffc1d1534 Merge pull request #390 from mangupta/hipmemcpy_fix 
hipMemcpyAsync returns success when trying to copy 0 bytes

[ROCm/clr commit: 2d1d79cb22]
 2018-04-09 14:02:36 +05:30
Maneesh Gupta 2d1d79cb22 Merge pull request #390 from mangupta/hipmemcpy_fix 
hipMemcpyAsync returns success when trying to copy 0 bytes
 2018-04-09 14:02:36 +05:30
Maneesh Gupta 399a17d755 Merge pull request #390 from mangupta/hipmemcpy_fix 
hipMemcpyAsync returns success when trying to copy 0 bytes
 2018-04-09 14:02:36 +05:30
Maneesh Gupta 07e41f3ca0 Merge pull request #388 from lmoriche/master 
Add support for clang offload bundles and <<<>>> kernel launch.

[ROCm/clr commit: d945c85fa7]
 2018-04-09 12:40:28 +05:30
Maneesh Gupta d945c85fa7 Merge pull request #388 from lmoriche/master 
Add support for clang offload bundles and <<<>>> kernel launch.
 2018-04-09 12:40:28 +05:30
Maneesh Gupta ac7c5dfd0b Merge pull request #388 from lmoriche/master 
Add support for clang offload bundles and <<<>>> kernel launch.
 2018-04-09 12:40:28 +05:30
Maneesh Gupta cdb7f8f354 hipMemcpyAsync returns success when trying to copy 0 bytes 
Change-Id: I4c0ee7ccc7563e2df657b50356cdd7fec9a1ef15


[ROCm/clr commit: 445de66560]
 2018-04-09 12:39:44 +05:30
Maneesh Gupta 445de66560 hipMemcpyAsync returns success when trying to copy 0 bytes 
Change-Id: I4c0ee7ccc7563e2df657b50356cdd7fec9a1ef15
 2018-04-09 12:39:44 +05:30
Maneesh Gupta 03eca1c57e hipMemcpyAsync returns success when trying to copy 0 bytes 
Change-Id: I4c0ee7ccc7563e2df657b50356cdd7fec9a1ef15
 2018-04-09 12:39:44 +05:30
Maneesh Gupta e2d8f322ec [ci] Disable nvcc CI builds 
[ROCm/clr commit: 04f116a9e8]
 2018-04-09 12:23:56 +05:30
Maneesh Gupta 04f116a9e8 [ci] Disable nvcc CI builds 2018-04-09 12:23:56 +05:30
Maneesh Gupta 4ac59148a9 [ci] Disable nvcc CI builds 2018-04-09 12:23:56 +05:30
Maneesh Gupta 90a69472f3 Merge pull request #389 from scchan/adjust_texture_hcc_workweek 
adjust the hcc work week for the texture fix

[ROCm/clr commit: e5b14cd918]
 2018-04-09 10:54:16 +05:30
Maneesh Gupta e5b14cd918 Merge pull request #389 from scchan/adjust_texture_hcc_workweek 
adjust the hcc work week for the texture fix
 2018-04-09 10:54:16 +05:30
Maneesh Gupta d98eaf5923 Merge pull request #389 from scchan/adjust_texture_hcc_workweek 
adjust the hcc work week for the texture fix
 2018-04-09 10:54:16 +05:30
Chris Freehill 0d9e71a63a Revert "Re-enable rocm-smi with new c api" 
This reverts commit 2e81d33395.

Change-Id: I9866610597a6de97a3c06ef9646f0afc85f149f4
 2018-04-07 19:59:13 -04:00
Chris Freehill 51ac0cfd8c Revert "Re-enable rocm-smi with new c api" 
This reverts commit 075f246147.

Change-Id: I9866610597a6de97a3c06ef9646f0afc85f149f4


[ROCm/ROCR-Runtime commit: 0d9e71a63a]
 2018-04-07 19:59:13 -04:00
Chris Freehill 2e81d33395 Re-enable rocm-smi with new c api 
Change-Id: Idf393f31522bac8ac0c3c03a930ef66d97ce5fa2
 2018-04-07 18:55:30 -04:00
Chris Freehill 075f246147 Re-enable rocm-smi with new c api 
Change-Id: Idf393f31522bac8ac0c3c03a930ef66d97ce5fa2


[ROCm/ROCR-Runtime commit: 2e81d33395]
 2018-04-07 18:55:30 -04:00
Ramesh Errabolu f25d59cab2 Compute size of command buffer based on support for HDP Flush 
Change-Id: I4987a262c191a91cd845fe18002c314a95a9ed8c
 2018-04-07 13:36:09 -04:00
Ramesh Errabolu f081e81976 Compute size of command buffer based on support for HDP Flush 
Change-Id: I4987a262c191a91cd845fe18002c314a95a9ed8c


[ROCm/ROCR-Runtime commit: f25d59cab2]
 2018-04-07 13:36:09 -04:00
foreman 01310b171d P4 to Git Change 1537782 by johtaylo@johtaylo-jtincrementor2-increment on 2018/04/07 03:00:05 
SWDEV-2 - Change OpenCL version number from 2626 to 2627.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2374 edit


[ROCm/clr commit: 16ece70d4a]
 2018-04-07 03:08:48 -04:00
foreman 16ece70d4a P4 to Git Change 1537782 by johtaylo@johtaylo-jtincrementor2-increment on 2018/04/07 03:00:05 
SWDEV-2 - Change OpenCL version number from 2626 to 2627.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2374 edit
 2018-04-07 03:08:48 -04:00
foreman d393bbbd62 P4 to Git Change 1537729 by cpaquot@cpaquot-ocl-lc-lnx on 2018/04/06 17:59:29 
SWDEV-145570 - [HIP] Use Svm path for both hipMalloc and hipHostMalloc
	Make sure hipMemCpy uses SvmBuffer to fetch the cl_mem

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#8 edit


[ROCm/clr commit: 03a6601214]
 2018-04-06 18:08:18 -04:00
foreman 03a6601214 P4 to Git Change 1537729 by cpaquot@cpaquot-ocl-lc-lnx on 2018/04/06 17:59:29 
SWDEV-145570 - [HIP] Use Svm path for both hipMalloc and hipHostMalloc
	Make sure hipMemCpy uses SvmBuffer to fetch the cl_mem

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#8 edit
 2018-04-06 18:08:18 -04:00
foreman e7f206d249 P4 to Git Change 1537729 by cpaquot@cpaquot-ocl-lc-lnx on 2018/04/06 17:59:29 
SWDEV-145570 - [HIP] Use Svm path for both hipMalloc and hipHostMalloc
	Make sure hipMemCpy uses SvmBuffer to fetch the cl_mem

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#8 edit
 2018-04-06 18:08:18 -04:00
Siu Chi Chan b24d6e7296 adjust the hcc work week for the texture fix 
[ROCm/clr commit: 5df923cdfa]
 2018-04-06 15:46:55 -04:00
Siu Chi Chan 5df923cdfa adjust the hcc work week for the texture fix 2018-04-06 15:46:55 -04:00
Siu Chi Chan f48e471dd4 adjust the hcc work week for the texture fix 2018-04-06 15:46:55 -04:00
foreman c507deb37f P4 to Git Change 1537540 by gandryey@gera-w8 on 2018/04/06 12:30:49 
SWDEV-79445 - OCL generic changes and code clean-up
	- Reduce the managed buffer alignment to 128 bytes
	- Add direct upload function to the constant buffer
	- Add heap preference print into the active allocations

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palconstbuf.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palconstbuf.hpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#87 edit


[ROCm/clr commit: c006b7b262]
 2018-04-06 12:39:00 -04:00
foreman c006b7b262 P4 to Git Change 1537540 by gandryey@gera-w8 on 2018/04/06 12:30:49 
SWDEV-79445 - OCL generic changes and code clean-up
	- Reduce the managed buffer alignment to 128 bytes
	- Add direct upload function to the constant buffer
	- Add heap preference print into the active allocations

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palconstbuf.cpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palconstbuf.hpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#87 edit
 2018-04-06 12:39:00 -04:00