Grafik Komit

3015 Melakukan

Penulis SHA1 Pesan Tanggal
Maneesh Gupta 9199fe21dd Merge pull request #733 from ex-rzr/fix_array_alloc_size
Fix allocation size of arrays with multiple and/or non-32-bit channels
2018-10-31 14:08:58 +05:30
Maneesh Gupta 0b86b421c1 Merge pull request #714 from aaronenyeshi/remove-static-hip-device
Remove libhip_device.a static library
2018-10-31 14:08:29 +05:30
Maneesh Gupta 7f3e7b5334 Merge pull request #713 from scchan/master-hcc_early_finalize_support
Support more than one device code blobs in a single .kernel section
2018-10-31 14:04:06 +05:30
Evgeny Mankov e17d24b46f Merge pull request #741 from emankov/master
[HIPIFY][fix][#739] Fix garbage after replacements
2018-10-30 19:37:19 +03:00
Evgeny Mankov a8e6033aa3 [HIPIFY][fix][#739] Fix garbage after replacements
[Issue] https://github.com/ROCm-Developer-Tools/HIP/issues/739
[Resolution] Always use an std::string not a clang::StringRef for replacement

P.S. Occurred only on Linux, on Windows works fine.
2018-10-30 19:35:59 +03:00
Evgeny Mankov ce2a7b849f Merge pull request #740 from emankov/master
[HIPIFY][fix] Return back cudaDeviceProp's struct field warpSize to hipWarpSize mapping
2018-10-30 15:55:17 +03:00
Evgeny Mankov 104be4b677 [HIPIFY][fix] Return back cudaDeviceProp's struct field warpSize to hipWarpSize mapping. 2018-10-30 15:53:00 +03:00
Maneesh Gupta 2c99ef9aee Merge pull request #726 from ROCm-Developer-Tools/feature_minimal_changes_for_hc_next
hipLaunchKernel, hipLaunchParm are deprecated, and shall be removed.
2018-10-30 09:20:39 +05:30
Evgeny Mankov 9d3de1e552 Merge pull request #736 from emankov/master
[HIPIFY] Modify HIP types to conform to CUDA's ones
2018-10-29 20:57:22 +03:00
Evgeny Mankov f83eabfa9e [HIPIFY] Modify HIP types to conform to CUDA's ones 2018-10-29 20:51:25 +03:00
Evgeny Mankov 25aae88fd5 Merge pull request #734 from emankov/master
[HIPIFY] CUDA Runtime API data types total revise
2018-10-29 17:16:07 +03:00
Evgeny Mankov c5bfa09b04 [HIPIFY] CUDA Runtime API data types total revise
+ for all CUDA versions up to 10.0
+ add missing types
+ fix typos
+ sync with HIP
+ sync with CUDA Driver API
+ update CUDA_Runtime_API_functions_supported_by_HIP.md
+ update CUDA Driver API map accordingly
+ update CUDA_Driver_API_functions_supported_by_HIP.md
+ formatting, annotating
2018-10-29 17:13:00 +03:00
Anton Gorenko 21f044eac8 Fix allocation size of arrays with multiple and/or non-32-bit channels
hipMallocArray and hipMalloc3DArray must use sum of bits
of all components.
2018-10-29 18:12:00 +06:00
Evgeny Mankov 4b18752641 Merge pull request #729 from emankov/master
[HIPIFY][doc] Readme update
2018-10-26 15:04:00 +03:00
Evgeny Mankov 368e9d5100 [HIPIFY][doc] Readme update
Clang 7.0.0 release has a known bug https://bugs.llvm.org/show_bug.cgi?id=36384, thus 7.0.0 is unstable release for Linux and Windows.
Last stable and tested LLVM+Clang release is 6.0.1.
2018-10-26 15:01:58 +03:00
Aaron Enye Shi 817b27d530 Remove libhip_device.a static library
Move remaining function definitions from device_util.cpp to hip_runtime.h header. We can now remove the static library completely as device_util.cpp was the last file part of target hip::hip_device .
2018-10-25 19:52:35 +00:00
Evgeny Mankov 7c3cea210b Merge pull request #727 from emankov/master
[HIPIFY][cmake][fix] Mark all target_link_libraries with PRIVATE keyword
2018-10-25 17:11:30 +03:00
Evgeny Mankov 2c367bc8af [HIPIFY][cmake][fix] Mark all target_link_libraries with PRIVATE keyword
[Reason]
Avoid cmake error occurred when mixing signatures with AddLLVM.cmake

[Error]
CMake Error at CMakeLists.txt:26 (target_link_libraries): The keyword signature for target_link_libraries has already been used with the target "hipify-clang".
All uses of target_link_libraries with a target must be either all-keyword or all-plain.

Error occurred only on Linux and LLVM 7.0.0
2018-10-25 17:09:18 +03:00
Alex Voicu e4181b85be hipLaunchKernel, hipLaunchParm are deprecated, and shall be removed. 2018-10-25 13:32:17 +01:00
Maneesh Gupta f6f160fa6b Merge pull request #723 from mangupta/fix_double_shfl
Fix logic for double variants of __shfl*
2018-10-25 06:01:38 +05:30
Maneesh Gupta 7e5b2dc91b Merge pull request #720 from mangupta/make_rocm19_usable_again
Make HIP functional again with HCC from ROCm 1.9.x
2018-10-25 06:01:27 +05:30
Maneesh Gupta c47c54cab9 Merge pull request #716 from yxsamliu/gfx906
Let hipcc handle gfx906 for hip-clang
2018-10-25 06:01:16 +05:30
Maneesh Gupta 19404e603d Fix logic for double variants of __shfl*
Change-Id: I604f00b54cf4bd9c5f26ca6fa680fca5e9629417
2018-10-24 12:39:09 +05:30
Maneesh Gupta 0703a2d0f0 Make HIP functional again with HCC from ROCm 1.9.x
Change-Id: I214acdfd0b79dcf783993e44fe31baee64fd4dc3
2018-10-24 10:41:56 +05:30
Evgeny Mankov d4358295f5 Merge pull request #719 from emankov/master
[HIPIFY] Split CUDA2HIP map into a number of maps based on API type
2018-10-23 00:03:02 +03:00
Evgeny Mankov 5d1255272b [HIPIFY] Split CUDA2HIP map into a number of maps based on API type
[Reasons]
+ Simplify the support
+ Optimize compilation and code generation time

[Additionally]
+ Update minimum required version of cmake
+ Fix MSVC compile options force update
2018-10-23 00:00:10 +03:00
Yaxun Sam Liu 283fb42604 Let hipcc handle gfx906 for hip-clang 2018-10-21 10:04:30 -04:00
Maneesh Gupta 4a00b244a3 Merge pull request #705 from ROCm-Developer-Tools/feature_minimal_changes_for_hc_next
Feature minimal changes for hc next
2018-10-19 06:58:31 +05:30
Siu Chi Chan 30ce25e627 Support more than one bundles in a single .kernel section
When compiling with Early Finalization enabled in HCC,
the resulting .kernel section of the host object now may
contain more than one device code bundles.  This is to
teach the HIP runtime to correctly extract all the
bundles from the .kernel section.
2018-10-18 17:00:27 -04:00
Evgeny Mankov 7e8046cfe3 Merge pull request #712 from emankov/master
[HIPIFY] CUDA Driver API data types total revise
2018-10-18 18:52:41 +03:00
Evgeny Mankov 520e795a8d [HIPIFY] CUDA Driver API data types total revise
+ for all CUDA versions
+ add missing types
+ fix typos
+ sync with HIP
+ update CUDA_Driver_API_functions_supported_by_HIP.md
+ formatting, annotating
2018-10-18 18:50:24 +03:00
Alex Voicu 5ccaf2fa7d Dumb workaround is still needed, so add it back. 2018-10-18 15:33:46 +01:00
Alex Voicu e66a75ea55 Guard new includes. 2018-10-18 12:29:27 +01:00
Alex Voicu fe959f7bd7 Re-sync with upstream. 2018-10-18 12:27:03 +01:00
Maneesh Gupta 1a5025c57e Merge pull request #688 from aaronenyeshi/fix-sinf-cosf-ocml
Use sinf and cosf from ocml device libs
2018-10-18 16:39:20 +05:30
Maneesh Gupta d133493669 Merge pull request #692 from whchung/hip-reinit-take2
HIP program state re-initialization logic (take 2)
2018-10-18 12:06:41 +05:30
Maneesh Gupta 0b1333255f Merge pull request #711 from nicholasmalaya/patch-1
Updates to HIP porting guide
2018-10-18 12:06:31 +05:30
Maneesh Gupta e889c04747 Merge pull request #710 from mangupta/use_hipLaunchKernelGGL
Replace hipLaunchKernel -> hipLaunchKernelGGL
2018-10-18 08:36:59 +05:30
Nicholas Malaya 26e9489287 Update hip_porting_guide.md 2018-10-17 14:27:11 -05:00
Nicholas Malaya 62c57a65bd Fixing link 2018-10-17 14:26:49 -05:00
Nicholas Malaya 29db8e9678 Fixing a link 2018-10-17 14:25:54 -05:00
Nicholas Malaya 32c122eae5 Adding library equivalent section 2018-10-17 14:25:07 -05:00
Nicholas Malaya b1b9366656 Small editing changes to clean up document 2018-10-17 14:11:25 -05:00
Nicholas Malaya 2ef15fd5b6 Fixing a broken indentation
Minor (cosmetic) edit to make items appear in ordered bulleted list
2018-10-17 13:56:51 -05:00
Nicholas Malaya d9e03872ab Update hip_porting_guide.md
Adding hyperlink to bin/hipconvertinplace.sh
2018-10-17 13:49:47 -05:00
Maneesh Gupta 52e320f396 Replace hipLaunchKernel -> hipLaunchKernelGGL
Change-Id: I4d99009e1199811d417becf1e1b934ec4d4e30be
2018-10-17 14:32:25 +05:30
Maneesh Gupta c9e4ed1149 Fix typos in Jenkinsfile 2018-10-17 11:13:37 +05:30
Maneesh Gupta f5356fa9ec Update Jenkinsfile
Disable rocm-1.9x testing in CI due to incompatible changes with HCC from ROCm 1.9.x
2018-10-17 11:03:43 +05:30
Maneesh Gupta c24b06fa0a Merge pull request #703 from mangupta/stream_create_with_priority
Implementation for stream priority
2018-10-17 10:53:43 +05:30
Maneesh Gupta dbe4431d98 Merge pull request #702 from aaronenyeshi/fix-missing-irif-lib
Replace IRIF fences with atomic_work_item_fence
2018-10-17 10:53:27 +05:30