a58a408e71
Merge pull request #702 from aaronenyeshi/fix-missing-irif-lib
...
Replace IRIF fences with atomic_work_item_fence
[ROCm/hip commit: dbe4431d98
2018-10-17 10:53:27 +05:30
de8b3d2e7d
Merge pull request #698 from yxsamliu/compile-flags
...
Add HIPCC_COMPILE_FLAGS_APPEND
[ROCm/hip commit: 4b754e1d77
2018-10-17 10:53:17 +05:30
cc642e9066
Merge pull request #696 from gargrahul/fix_texrestypelin_size
...
Fixed image width for linear resource type texture
[ROCm/hip commit: 7ea27d05bc
2018-10-17 06:11:23 +05:30
240bf09a95
Merge pull request #708 from mangupta/swdev-125523
...
Add missing hipHostRegister flags on nvcc path
[ROCm/hip commit: 797d151444
2018-10-17 06:10:25 +05:30
5b192ed119
[HIPIFY] Code cleanup and formatting
...
[ROCm/hip commit: ee3a5cc722
2018-10-15 15:27:37 +03:00
83e56b2ed4
Add missing hipHostRegister flags on nvcc path
...
Change-Id: I69f09204d9c544935104d4168ab8d3626666a623
[ROCm/hip commit: 64d1cf86b7
2018-10-15 15:30:24 +05:30
1690cba3d7
Update samples.
...
[ROCm/hip commit: 7839045d30
2018-10-13 23:28:22 +01:00
69b0baf37f
Minimal should mean minimal.
...
[ROCm/hip commit: 5312336ce2
2018-10-11 00:21:41 +01:00
62d7a132c8
Trailing whitespace is still not the final frontier.
...
[ROCm/hip commit: 50265028fc
2018-10-11 00:08:09 +01:00
d68ed45708
Address Aaron's comments
...
[ROCm/hip commit: 3e4dbd32a1
2018-10-11 00:03:01 +01:00
684f8133dd
Use HIP math functions, stop using hipLaunchParm.
...
[ROCm/hip commit: 069bbbd7ed
2018-10-10 11:56:54 +01:00
0d30e15646
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_minimal_changes_for_hc_next
...
[ROCm/hip commit: 4bc40551b5
2018-10-10 11:44:09 +01:00
6d0b50e9b9
Re-sync with upstream.
...
[ROCm/hip commit: ca375cb8c5
2018-10-10 11:43:49 +01:00
b35590db18
Implementation for stream priority
...
- Requires ROCm 1.9.x or higher
- Requires HCC with PR#886 merged
Change-Id: Id7c95ea091ee610e80c9ad815f1cb989cba570ca
[ROCm/hip commit: da64156fb2
2018-10-05 16:27:46 +05:30
188df279a9
Replace IRIF fences with atomic_work_item_fence
...
[ROCm/hip commit: 0787f74ac2
2018-10-04 21:47:28 +00:00
ce454b49d6
Merge pull request #697 from yxsamliu/dev-lib-path
...
Let hipcc add --hip-device-lib-path by default for hip-clang
[ROCm/hip commit: 4ab45ef878
2018-10-04 07:40:37 +05:30
ff1c7e9d27
Fix hip_vector_types.h for long long vectors
...
There was a missing long in the declaration for [u]longlongN types.
[ROCm/hip commit: 5dd35576f6
2018-10-03 13:57:52 -04:00
a7a959093b
[HIPIFY] CUDA 10.0 Driver API initial support
...
[ROCm/hip commit: e3d7cc2885
2018-10-03 20:29:22 +03:00
8401146cd6
Corrected the width calculation logic to accomodate multi channels
...
[ROCm/hip commit: 5a3d89e99c
2018-10-03 12:07:38 +05:30
a71be7ff2d
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/hip commit: 43402d5602
2018-10-01 15:14:54 -04:00
f201230ad3
Add HIPCC_COMPILE_FLAGS_APPEND
...
[ROCm/hip commit: dcc85be374
2018-10-01 14:51:29 -04:00
5a48bc2168
Fixed image width for linear resource type texture
...
[ROCm/hip commit: 0b8fc1d66a
2018-10-01 15:28:34 +05:30
bdd0d785fd
[HIPIFY][cmake] CUDA 10.0 is not supported.
...
[ROCm/hip commit: d0c683fcde
2018-09-27 19:05:22 +03:00
63a075fc96
Keep the map which tracks GPU kernel symbols to grow monotonically
...
[ROCm/hip commit: dd56942335
2018-09-26 19:49:02 +00:00
70dd826abf
Improve performance of re-initialization logic
...
Keep track of shared libaries already discovered. Do not build HSA executables
for them.
[ROCm/hip commit: 35c542b70f
2018-09-26 19:48:56 +00:00
4e04cf3d2a
HIP program state re-initialization logic
...
This commit is to support kernels dynamically loaded thru means such as
dlopen() after HIP runtime initializes.
[ROCm/hip commit: dab1a0f9db
2018-09-26 19:48:47 +00:00
7a6684d9e1
[HIPIFY][docs] Fix typos in Readme.md
...
[ROCm/hip commit: c943885a65
2018-09-26 17:26:25 +03:00
ed68d1c931
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/hip commit: 23448bbf9b
2018-09-26 17:05:47 +03:00
b1d9cff60a
[HIPIFY][doc] Update README.md due to new LLVM 7.0.0 and CUDA 10.0 releases.
...
[ROCm/hip commit: 221ef1db1f
2018-09-26 17:01:59 +03:00
6d53af5a60
Return hipSuccess when sizeBytes=0 in hipMemset
...
[ROCm/hip commit: 90f57d452a
2018-09-26 12:47:36 +05:30
502fda5308
Merge pull request #685 from ROCm-Developer-Tools/hip-trig-return
...
Improve hip_trig test case
[ROCm/hip commit: 5c665acf74
2018-09-26 09:50:48 +05:30
19d76382d6
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/hip commit: 77c07d4118
2018-09-25 19:31:39 +00:00
e38b163ba8
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/hip commit: 0a8d4ee78d
2018-09-25 15:01:11 -04:00
93a84365ab
Use trig functions from ocml instead
...
[ROCm/hip commit: 5179a72cda
2018-09-25 15:58:36 +00:00
9ff79bfeb7
Merge pull request #687 from emankov/hipBLAS
...
[HIPIFY][BLAS] Add support of hipblasGemmEx and corresponding types
[ROCm/hip commit: 3a1157653f
2018-09-25 18:48:06 +03:00
e47c0c0a9e
[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/hip commit: d279c7a1dd
2018-09-25 18:46:23 +03:00
9ed4fbc85a
[HIPIFY][docs] Update CUDNN_API_supported_by_HIP.md
...
[ROCm/hip commit: 4e06ab07e2
2018-09-25 16:50:40 +03:00
9762215e54
Fix missing HIP_ASSERT in hip_trig
...
[ROCm/hip commit: 3d3820272a
2018-09-24 15:01:24 +00:00
a7c2d2ab08
Merge pull request #683 from ROCm-Developer-Tools/hip-float-rounded
...
Disable non-default-rounded functions
[ROCm/hip commit: ca6b916d15
2018-09-24 09:32:52 +05:30
8408bc5536
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/hip commit: 357b6844fa
2018-09-21 15:28:10 -04:00
780b0f38b8
Merge pull request #684 from ROCm-Developer-Tools/mangupta-patch-2
...
[ci] Renable nvcc testing
[ROCm/hip commit: 0e3ba5a47d
2018-09-21 11:05:45 +05:30
d98ef3cc48
Update hipTestFMA.cpp
...
[ROCm/hip commit: 255589ae15
2018-09-21 11:00:08 +05:30
71e60d0574
[ci] Renable nvcc testing
...
Change-Id: I7d720b41a3ddc99453fee8b9be30494bfec3a808
[ROCm/hip commit: 6d794cd505
2018-09-21 10:11:31 +05:30
6efd97931c
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/hip commit: c11220f224
2018-09-20 16:33:32 -04:00
70f9bd87c6
Merge pull request #614 from ROCm-Developer-Tools/fma
...
Add overloading resolution functions for fma
[ROCm/hip commit: 3d67c9f952
2018-09-20 13:38:03 +05:30
8431e3620a
Update hipTestFMA.cpp
...
Fix the test so that it works on nvcc path as well.
[ROCm/hip commit: ecd6a212c7
2018-09-20 11:23:51 +05:30
c51a4d28f7
Merge pull request #682 from aaronenyeshi/hip-config-files
...
Create separate config files for hcc and clang
[ROCm/hip commit: 70b0b1d600
2018-09-20 11:21:31 +05:30
80a9f02f42
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/hip commit: e01c53b185
2018-09-19 18:29:56 +00:00
f6318119a9
Silent warnings about duplicate static keyword
...
static is already in __DEVICE__, so should be removed.
[ROCm/hip commit: a5c961e26c
2018-09-19 10:39:45 -04:00
2d4040f75d
Add fma function with float and _Float16 arguments
...
[ROCm/hip commit: bd622a4b4a
2018-09-19 09:59:33 -04:00
Maneesh Gupta
Evgeny Mankov
Alex Voicu
Aaron Enye Shi
Rahul Garg
Yaxun Sam Liu
Wen-Heng (Jack) Chung
Evgeny Mankov
foreman