AI/rocm-systems
2
0
Garpu 0
Kode Masalah Tarik Permintaan Actions Packages Projects Rilis Wiki Kegiatan
6.604 Melakukan 3 Cabang 0 Tag
537b3dd67faed63a2e6ba494cf440fffcea2b09b
Grafik Komit

6604 Melakukan

This Branch
This Branch
All Branches
Penulis SHA1 Pesan Tanggal
Alex Voicu 50388a3bd1 Re-sync with upstream. 
[ROCm/clr commit: 9ec697c620]
 2018-10-10 11:43:49 +01:00
Maneesh Gupta c4ed6b18fb Implementation for stream priority 
- Requires ROCm 1.9.x or higher
- Requires HCC with PR#886 merged

Change-Id: Id7c95ea091ee610e80c9ad815f1cb989cba570ca


[ROCm/clr commit: 07ee1f07d8]
 2018-10-05 16:27:46 +05:30
Aaron Enye Shi 1835636df3 Replace IRIF fences with atomic_work_item_fence 
[ROCm/clr commit: 03822afaa9]
 2018-10-04 21:47:28 +00:00
Jenkins ef7a6f3af5 Merge 'master' into 'amd-master' 
Change-Id: I1884a7f1ee85ee14592fd6c2f28beb4872d0fd13


[ROCm/clr commit: 3cb93c2ed2]
 2018-10-04 04:09:36 -05:00
Maneesh Gupta 09ff91c564 Merge pull request #697 from yxsamliu/dev-lib-path 
Let hipcc add --hip-device-lib-path by default for hip-clang

[ROCm/clr commit: e7d3f3860e]
 2018-10-04 07:40:37 +05:30
Maneesh Gupta 023f8071d0 Merge pull request #700 from ROCm-Developer-Tools/fix-long-long-decl 
Fix hip_vector_types.h for long long vectors

[ROCm/clr commit: ed51044502]
 2018-10-04 07:39:30 +05:30
Aaron Enye Shi 766ce1b4ff Fix hip_vector_types.h for long long vectors 
There was a missing long in the declaration for [u]longlongN types.

[ROCm/clr commit: 6a71cf17a1]
 2018-10-03 13:57:52 -04:00
Evgeny Mankov f34f37f539 Merge pull request #699 from emankov/master 
[HIPIFY] CUDA 10.0 Driver API initial support

[ROCm/clr commit: bde7c600c4]
 2018-10-03 20:33:37 +03:00
Evgeny Mankov a89c112545 [HIPIFY] CUDA 10.0 Driver API initial support 
[ROCm/clr commit: cb4eb94174]
 2018-10-03 20:29:22 +03:00
Rahul Garg ed5c4bca1d Corrected the width calculation logic to accomodate multi channels 
[ROCm/clr commit: a78d68d639]
 2018-10-03 12:07:38 +05:30
Yaxun Sam Liu fbc0c4bb66 Let hipcc add --hip-device-lib-path by default for hip-clang 
hip-clang by default assumes -fno-gpu-rdc, therefore requires
--hip-device-lib-path by default.


[ROCm/clr commit: 88768895bc]
 2018-10-01 15:14:54 -04:00
Yaxun Sam Liu cb971f0a48 Add HIPCC_COMPILE_FLAGS_APPEND 
[ROCm/clr commit: 2c361906fa]
 2018-10-01 14:51:29 -04:00
Rahul Garg 8981438983 Fixed image width for linear resource type texture 
[ROCm/clr commit: 167265c279]
 2018-10-01 15:28:34 +05:30
Jenkins 611c52b0ce Merge 'master' into 'amd-master' 
Change-Id: I1cfb603a45cb6ffb834491ddd6f3ade667ab016c


[ROCm/clr commit: a0199ea596]
 2018-09-28 04:09:54 -05:00
Evgeny Mankov ec3a6c3f91 Merge pull request #695 from emankov/master 
[HIPIFY][cmake] CUDA 10.0 is not supported.

[ROCm/clr commit: 28e5a5ced7]
 2018-09-27 19:08:58 +03:00
Evgeny Mankov 821b36d636 [HIPIFY][cmake] CUDA 10.0 is not supported. 
[ROCm/clr commit: 4e7b330037]
 2018-09-27 19:05:22 +03:00
Jenkins d94a57e4fd Merge 'master' into 'amd-master' 
Change-Id: Ieb0558a488ebf992a77c84ff4d81fba764a70401


[ROCm/clr commit: 02f5bb95aa]
 2018-09-27 04:40:39 -05:00
Wen-Heng (Jack) Chung 73fc21f717 Keep the map which tracks GPU kernel symbols to grow monotonically 
[ROCm/clr commit: e257de95f3]
 2018-09-26 19:49:02 +00:00
Wen-Heng (Jack) Chung 1e956fcd70 Improve performance of re-initialization logic 
Keep track of shared libaries already discovered. Do not build HSA executables
for them.


[ROCm/clr commit: 060b3c0bf8]
 2018-09-26 19:48:56 +00:00
Wen-Heng (Jack) Chung 4e0f0b3e89 HIP program state re-initialization logic 
This commit is to support kernels dynamically loaded thru means such as
dlopen() after HIP runtime initializes.


[ROCm/clr commit: 319f007bf1]
 2018-09-26 19:48:47 +00:00
Evgeny Mankov 4746b1872b Merge pull request #691 from emankov/docs 
[HIPIFY][docs] Fix typos in Readme.md

[ROCm/clr commit: c778463625]
 2018-09-26 17:27:18 +03:00
Evgeny Mankov e9acd2671d [HIPIFY][docs] Fix typos in Readme.md 
[ROCm/clr commit: 6056686796]
 2018-09-26 17:26:25 +03:00
Evgeny Mankov a4c3741ec7 Merge pull request #690 from emankov/hipBLAS 
[HIPIFY][doc] Update README.md due to new LLVM 7.0.0 and CUDA 10.0 re…

[ROCm/clr commit: e879118d87]
 2018-09-26 17:05:47 +03:00
Evgeny Mankov 298ca9b3cd [HIPIFY][doc] Update README.md due to new LLVM 7.0.0 and CUDA 10.0 releases. 
[ROCm/clr commit: a7e75c72ee]
 2018-09-26 17:01:59 +03:00
Maneesh Gupta 1a59703cdb Merge pull request #689 from gargrahul/hipmemset_ret_success_sizezero 
Return hipSuccess when sizeBytes=0 in hipMemset

[ROCm/clr commit: 5bd2219f9d]
 2018-09-26 13:57:44 +05:30
Rahul Garg e0efc8a09e Return hipSuccess when sizeBytes=0 in hipMemset 
[ROCm/clr commit: bd27310127]
 2018-09-26 12:47:36 +05:30
Maneesh Gupta 27986e6788 Merge pull request #685 from ROCm-Developer-Tools/hip-trig-return 
Improve hip_trig test case

[ROCm/clr commit: 802520f5f1]
 2018-09-26 09:50:48 +05:30
Aaron Enye Shi 4d59fbbcbe Use sinf and cosf from ocml device libs 
Using llvm_amdgcn builtin fails to produce accurate values, we should move to using the ocml device library versions.


[ROCm/clr commit: eeb6c11050]
 2018-09-25 19:31:39 +00:00
foreman 909f353400 P4 to Git Change 1610499 by skudchad@skudchad-lnx on 2018/09/25 14:43:35 
SWDEV-145570 - [HIP] - Map hipinfo sample from HIP mirror so that we have the same hipinfo

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/hip/hip_peer.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/tools/hipinfo/CMakeLists.txt#2 edit
... //depot/stg/opencl/drivers/opencl/tools/hipinfo/build/Makefile.hipinfo#2 edit
... //depot/stg/opencl/drivers/opencl/tools/hipinfo/hipinfo.cpp#2 delete


[ROCm/clr commit: 8d912e037a]
 2018-09-25 15:01:11 -04:00
Aaron Enye Shi 20e9391cfb Use trig functions from ocml instead 
[ROCm/clr commit: 04ed44f074]
 2018-09-25 15:58:36 +00:00
Evgeny Mankov 2a6861aa64 Merge pull request #687 from emankov/hipBLAS 
[HIPIFY][BLAS] Add support of hipblasGemmEx and corresponding types

[ROCm/clr commit: d12c1f7eff]
 2018-09-25 18:48:06 +03:00
Evgeny Mankov 11dde91716 [HIPIFY][BLAS] Add support of hipblasGemmEx and corresponding types 
TODO (hipBLAS/HIP): rename hipblasDatatype_t to hipDataType_t and move it from hipBLAS to HIP, as Data types are used not only in BLAS library.


[ROCm/clr commit: 65035fa485]
 2018-09-25 18:46:23 +03:00
Evgeny Mankov 8359f85a51 Merge pull request #686 from emankov/docs 
[HIPIFY][docs] Update CUDNN_API_supported_by_HIP.md

[ROCm/clr commit: fae1de41e2]
 2018-09-25 16:52:19 +03:00
Evgeny Mankov 37b1248da2 [HIPIFY][docs] Update CUDNN_API_supported_by_HIP.md 
[ROCm/clr commit: f627d9a9a2]
 2018-09-25 16:50:40 +03:00
Jenkins e1050a6596 Merge 'master' into 'amd-master' 
Change-Id: Ida77d16d15313c8e52cdcb36b8e68e9d5c406256


[ROCm/clr commit: 9e5e2f454f]
 2018-09-25 04:09:56 -05:00
Aaron Enye Shi 4bbfaf06b5 Fix missing HIP_ASSERT in hip_trig 
[ROCm/clr commit: bc5de031a5]
 2018-09-24 15:01:24 +00:00
Maneesh Gupta 0d75b78a5a Merge pull request #683 from ROCm-Developer-Tools/hip-float-rounded 
Disable non-default-rounded functions

[ROCm/clr commit: ad008c5e3f]
 2018-09-24 09:32:52 +05:30
Jenkins ec1859900c Merge 'master' into 'amd-master' 
Change-Id: I3de7b9ac03c05e50e7fbdb855e120b2dff8d23b4


[ROCm/clr commit: d7d15b126b]
 2018-09-23 20:41:55 -05:00
Aaron Enye Shi f4fc30ccc7 Improve hip_trig test case 
Hip_trig is failing but returning a passing value on HIP-Clang.  Also update with debug output and free arrays used.

[ROCm/clr commit: afef6a3ece]
 2018-09-21 15:28:10 -04:00
Maneesh Gupta 4219d3d796 Merge pull request #684 from ROCm-Developer-Tools/mangupta-patch-2 
[ci] Renable nvcc testing

[ROCm/clr commit: 5468e01d04]
 2018-09-21 11:05:45 +05:30
Maneesh Gupta 203e3dd5d5 Update hipTestFMA.cpp 
[ROCm/clr commit: a4bdbe0aaf]
 2018-09-21 11:00:08 +05:30
Maneesh Gupta e300bdf211 [ci] Renable nvcc testing 
Change-Id: I7d720b41a3ddc99453fee8b9be30494bfec3a808


[ROCm/clr commit: cc4e8c7e8b]
 2018-09-21 10:11:31 +05:30
Aaron Enye Shi 646de2e876 Disable non-default-rounded functions 
Device library has removed the non-default-rounded functions, so hipFloatMath will fail to build. These include the removal of __ocml_sqrt_rte, __ocml_sqrt_rtn, __ocml_sqrt_rtp, and __ocml_sqrt_rtz. As seen here: https://github.com/RadeonOpenCompute/ROCm-Device-Libs/commit/2fc04e10e1354edee331ce700f98a60f8255effb . Disable these function tests for now, until they are re-enabled, or deleted completely.

[ROCm/clr commit: a3dea28c9d]
 2018-09-20 16:33:32 -04:00
Maneesh Gupta f648d28bcb Merge pull request #614 from ROCm-Developer-Tools/fma 
Add overloading resolution functions for fma

[ROCm/clr commit: 7cec85e1ae]
 2018-09-20 13:38:03 +05:30
Maneesh Gupta f742125288 Update hipTestFMA.cpp 
Fix the test so that it works on nvcc path as well.

[ROCm/clr commit: e614aac0da]
 2018-09-20 11:23:51 +05:30
Maneesh Gupta 1e11b0352b Merge pull request #682 from aaronenyeshi/hip-config-files 
Create separate config files for hcc and clang

[ROCm/clr commit: ff8bdd0375]
 2018-09-20 11:21:31 +05:30
Maneesh Gupta 59bf30190b Merge pull request #681 from yxsamliu/fix-warning-static 
Silent warnings about duplicate static keyword

[ROCm/clr commit: d333dc10cd]
 2018-09-20 07:59:10 +05:30
Aaron Enye Shi ee366fad74 Create separate config files for hcc and clang 
The state of HIP_COMPILER is not passing into config files, therefore config files cannot use if statements to determine dependency. For HIP-Clang, we should remove find_dependency(hcc), so we create separate config files depending on compiler path. This fixes issue in apps that uses hip-config.cmake.


[ROCm/clr commit: 73a5ea0f9f]
 2018-09-19 18:29:56 +00:00
Yaxun Sam Liu 2f6bee46f9 Silent warnings about duplicate static keyword 
static is already in __DEVICE__, so should be removed.


[ROCm/clr commit: cfa71293ce]
 2018-09-19 10:39:45 -04:00
Yaxun Sam Liu a7b03bee08 Add fma function with float and _Float16 arguments 
[ROCm/clr commit: a8bed200b7]
 2018-09-19 09:59:33 -04:00