Gráfico de commits

3163 Commits

Autor SHA1 Mensaje Fecha
Maneesh Gupta c2011c2a2d Merge pull request #1028 from gargrahul/fix_d2d_async_test
[dtest] Fix D2DAsync test

[ROCm/clr commit: 3ba7afcfc1]
2019-04-24 16:49:13 +05:30
Aaron Enye Shi 9cd137f2e4 Add COMGR relative path for build machines
[ROCm/clr commit: 6b3095f7cb]
2019-04-23 17:16:26 -04:00
Evgeny Mankov bc3583c9bd [HIPIFY][doc] Provide patches for clang's bug 38811
+ Update Readme.md accordingly


[ROCm/clr commit: 87fa81f7be]
2019-04-23 21:13:00 +03:00
Evgeny Mankov 176db946b2 [HIPIFY][hipify-perl] Formatting
[ROCm/clr commit: 65dd1d4c7d]
2019-04-23 17:55:47 +03:00
David Salinas 5624c3837d Revert "append the ELF flags for sram-ecc and xnack to the target triple per code object"
This reverts commit d1f4e7ea54.


[ROCm/clr commit: 1237a0b691]
2019-04-18 11:49:40 -04:00
Rahul Garg c6dd7c9678 Fix D2DAsync test
[ROCm/clr commit: f1dc017167]
2019-04-18 07:35:06 +05:30
Evgeny Mankov 3586f0be35 [HIPIFY][SPARSE] cuSPARSE 10.1 support
[ROCm/clr commit: 95aca4f9a9]
2019-04-16 14:59:44 +03:00
Evgeny Mankov e08460eb09 [HIPIFY][BLAS] cuBLAS 10.1 support
[ROCm/clr commit: bbcacd0146]
2019-04-16 12:52:58 +03:00
Evgeny Mankov 999640effd Merge pull request #1023 from emankov/master
[HIPIFY][cuDNN] Add partial cudnnRNNBiasMode_t support

[ROCm/clr commit: f5f1636181]
2019-04-16 11:03:22 +03:00
Evgeny Mankov 26129109df [HIPIFY][cuDNN] Add partial cudnnRNNBiasMode_t support
[ROCm/clr commit: 5fa84735a6]
2019-04-16 11:01:01 +03:00
Maneesh Gupta 7c43b9ee4b Merge pull request #995 from david-salinas/add_sram-ecc_and_xnack_flags_to_triple
Append the ELF flags for sram-ecc and xnack to the target triple per code object

[ROCm/clr commit: 715a500b97]
2019-04-16 09:10:04 +05:30
Maneesh Gupta dac817873f Merge pull request #1019 from scchan/lazy_binding
minor workaround for lazy binding

[ROCm/clr commit: 22660bed74]
2019-04-16 08:36:10 +05:30
Jeff Daily cf4e198a91 In hipFree, synchronize owner of memory (#1018)
* In hipFree, if memory is associated with a device, synchronize that device's streams.

This changes the behavior from synchronizing the currently set TLS device.

* All devices sync in hipFree for _appId=-1 case.

* Revert "All devices sync in hipFree for _appId=-1 case."

This reverts commit 1efb34d6a8426661e45bc5f763422a1147aeac10.

* add HIP_SYNC_FREE env var


[ROCm/clr commit: cf8fb43e6b]
2019-04-16 08:35:55 +05:30
Mr-LiuSw e909811963 add little changes in hip_runtime_api.h to work with c language (#1017)
* Update hip_runtime_api.h

when i try to use mpicc or gcc to compile a c language code which call some hip runtime api , error occured as
> /path/to/hcc_detail/hip_runtime_api.h:2268:33: error: unknown type name ‘hipFuncAttributes’; 
> hipFuncGetAttributes(hipFuncAttributes* attr, const void* func);
 
add ' struct ' for the first parameter of hipFuncGetAttributes will get ride of this problem.


[ROCm/clr commit: 64bdf82265]
2019-04-16 08:35:36 +05:30
Aaron Enye Shi 10048a5631 Use COMgr to read Kernel Args Metadata (#1006)
* Add CMAKE dep to amd_comgr

* Use COMGR for read_kernarg_metadata in COV2

* Do not assume kernargs exist

* Add proper metadata destroy cleanup

* Use a process function for easier destroy

* Remove old read_kernarg_metadata

* Clean up HCC, prints, names

* Use COMGR in CMAKE by default

* Move metadata lookup for keyword values into helper

* Remove C string usage for lookup_keyword_value

* Guard COMGR for non-NVCC path

* Add hip_hcc dependency on comgr package

* Add lifetime to metadata nodes

* Find COMGR config file for amd_comgr target

* Move set_active data earlier


[ROCm/clr commit: 2c80975e9c]
2019-04-16 08:34:39 +05:30
Evgeny Mankov 27275c9e8e [HIPIFY] cuDNN 7.5.0.56 support
[ROCm/clr commit: 64f0f29111]
2019-04-15 15:46:46 +03:00
Maneesh Gupta c82695a311 [ci] Enable tests on ROCm 2.3
Change-Id: Id344ef600b0868f36f2e7ac08d5664234d88835b


[ROCm/clr commit: 72e17e3c92]
2019-04-15 12:38:01 +05:30
Yaxun (Sam) Liu 7d58d7b02a hip-clang: Add __align__
CUDA has __align__. Define eqivalent for hip-clang.


[ROCm/clr commit: e200ece4da]
2019-04-10 14:17:18 -04:00
Evgeny Mankov ca6021640b [HIPIFY] CUDA 10.1 Runtime API support
[ROCm/clr commit: b11bf48270]
2019-04-10 18:41:36 +03:00
Evgeny Mankov 61a6949cf0 [HIPIFY] CUDA 10.1 Driver API support
[ROCm/clr commit: 9a660c0d48]
2019-04-10 15:03:34 +03:00
Maneesh Gupta f8194fd6f1 Merge pull request #1013 from yxsamliu/config
Fix hip-config.cmake for hip-clang

[ROCm/clr commit: 75691ff3e4]
2019-04-10 07:53:22 +00:00
Yaxun (Sam) Liu f6151a55fd hip-clang: fix hipcc options
Use -O3 for default optimization level.
Fix --hip-device-lib-path for warnings about unused option.


[ROCm/clr commit: 419eeb4fe0]
2019-04-09 22:31:13 -04:00
Yaxun (Sam) Liu 65aa1eb59c Fix hip-config.cmake for hip-clang
Define HIP_COMPILER and HIP_RUNTIME in hip-config.cmake to
facilitate other packages identify hip-clang and HIP/VDI
runtime.


[ROCm/clr commit: a781d2e017]
2019-04-09 16:41:01 -04:00
Yaxun (Sam) Liu 40cf556b82 hip-clang: add include path for hsa headers
[ROCm/clr commit: 98642129cc]
2019-04-09 15:01:50 -04:00
Maneesh Gupta 6f8a83bd11 Merge pull request #1010 from ROCm-Developer-Tools/mangupta-patch-1
[ci] Disable hipLaunchParm.tst for now

[ROCm/clr commit: aa8f17193e]
2019-04-09 03:19:56 +00:00
Evgeny Mankov 0947324f18 [HIPIFY][cmake][doc] Update CMakeLists and Readme cause CUDA 10.1 and clang 8.0.0 are released
+ Fix the error in cmake: clang 8.0.0 supports CUDA 10.0, not 10.1; only trunk clang 9.0.0 supports CUDA 10.1.
+ Update Readme:
  1. clang's bug 36384 is gone, so latest stable release for Linux is clang 8.0.0, which supports CUDA up to 10.0;
  2. update dependencies, testing and building notes.


[ROCm/clr commit: 79e6bd8426]
2019-04-08 20:05:21 +03:00
Maneesh Gupta 47fab26a20 [ci] Disable hipLaunchParm.tst for now
Due to a HCC bug in rocm-head, the test fails to compile. Disabling the test until the issue is resolved.

Change-Id: Ib4e7baf0b9c2cb5f5dbe38e6dd2bab894d28886a


[ROCm/clr commit: 27013c9af6]
2019-04-08 16:14:25 +05:30
Yaxun (Sam) Liu d8acabf24c Fix regression on multi-gpu due to PR#997
[ROCm/clr commit: 5c67ee11f4]
2019-04-05 22:54:41 -04:00
Evgeny Mankov 8d78207849 Merge pull request #1003 from acowley/patch-1
hipify: translate cudaErrorInvalidSymbol

[ROCm/clr commit: 3352d7b174]
2019-04-05 20:21:27 +03:00
David Salinas d1f4e7ea54 append the ELF flags for sram-ecc and xnack to the target triple per code object
[ROCm/clr commit: 4d0dc45078]
2019-04-05 13:17:11 -04:00
Evgeny Mankov 9eb10c5b4d [HIPIFY][doc] Fix typos and minor text inaccuracies in HIP FAQ
[ROCm/clr commit: 4990a1003b]
2019-04-05 19:19:38 +03:00
Siu Chi Chan f6837a4e7f minor workaround for lazy binding
[ROCm/clr commit: b5045af7e9]
2019-04-02 17:28:06 -04:00
Anthony Cowley 191dfc8dff hipify: translate cudaErrorInvalidSymbol
[ROCm/clr commit: f15dd58a91]
2019-04-02 08:54:37 -04:00
Maneesh Gupta bedff2406a Merge pull request #998 from yxsamliu/doc
hip-clang: update installation guide.

[ROCm/clr commit: 2d9e5615b7]
2019-04-02 05:08:18 +00:00
Maneesh Gupta 9d2c0c8e5d Merge pull request #997 from yxsamliu/mgpu
hip-clang: fix kernel not found on multi-gpu

[ROCm/clr commit: a6e7dfefe3]
2019-04-02 05:07:31 +00:00
Evgeny Mankov 17ac0d3e19 [HIPIFY][tests] Fix typo in test for CUDA 10.x
[ROCm/clr commit: 5b59f87305]
2019-04-01 19:52:08 +03:00
Evgeny Mankov 236624a229 [HIPIFY][cmake] Update CMakeLists and Readme cause CUDA 10.1 and clang 8.0.0 are released
[ROCm/clr commit: 799a6f5512]
2019-04-01 19:44:52 +03:00
Yaxun Sam Liu 12ac74bad1 hip-clang: fix kernel not found on multi-gpu
__hipRegisterFunction is called during by .init functions during program initialization.
It calls hipModuleGetFunction to locate kernel symbol in code objects. hipModuleGetFunction
assumes current device when locating kernel symbols. This works for HCC but not for hip-clang,
since hip-clang needs to locate kernel symbols for different devices without switching
between devices.

This patch introduces a new hsa agent parameter to ihipModuleGetFunction, which allows
__hipRegisterFunction to choose the correct hsa agent when locating kernel symbols. By
default it uses this_agent(), therefore this patch has no impact on HCC.


[ROCm/clr commit: 8f5c812a68]
2019-03-31 10:08:20 -04:00
Yaxun (Sam) Liu 54c2b79351 Update INSTALL.md
[ROCm/clr commit: 76a9fdd924]
2019-03-30 08:29:08 -04:00
Yaxun Sam Liu 79ac0097dc hip-clang: update installation guide.
[ROCm/clr commit: 598604aa7f]
2019-03-30 08:24:49 -04:00
Wen-Heng (Jack) Chung cfe930f9d6 Make hipModuleGetGlobal be in HIP runtime so it can be discovered at runtime (#981)
* Make hipModuleGetGlobal be in HIP runtime so it can be discovered at runtime

In HIP PR #929, quite a few HIP public APIs were made as inline functions with
hidden visibility. It was necessary to support applications with shared
libraries with GPU kernels launched via hipLaunchKernelGGL(), after HIP runtime
is initialized.

In empirical tests, the implementation has been proved to be a bit too
excessive, especially for hipModuleGetGlobal(). The function is used by another
type of client applications which relies on the existence of this function
within HIP runtime so global symbols from HSA code objects loaded dynamically
at runtime can be retrieved programmtically.

This commit moves hipModuleGetGlobal() back to src/hip_module.cpp, and makes it
visible and not inline, to fulfill requirements for applications
aforementioned. It does not change the behavior of applications depending on
hipLaunchKernelGGL().

* Add HIP_INIT_API into the implementation of hipModuleGetGlobal

Address review comments.

* Fix failing HIP unit tests


[ROCm/clr commit: 04915cea2f]
2019-03-29 03:45:04 +00:00
Maneesh Gupta d99bc4c540 Merge pull request #992 from gargrahul/handle_d2d_memcpy2d
Handle D2D in memcpy2D

[ROCm/clr commit: f9f4cee347]
2019-03-28 04:41:36 +00:00
Jeff Daily 5233d41c6c improve program state commentary
Disambiguate calling many varibles "agent".
More detail in exception message.
Create and discard map placeholders; no need to call std::vector::clear() on map value.


[ROCm/clr commit: f5e4fff6cc]
2019-03-27 21:40:27 +00:00
Rahul Garg 73bb9a74bb Handle D2D in memcpy2D
[ROCm/clr commit: 50d623981e]
2019-03-28 02:21:45 +05:30
Jeff Daily 9cee2c5311 load program state once per agent
[ROCm/clr commit: 2845b4c4b8]
2019-03-27 18:19:10 +00:00
Maneesh Gupta a0b29c8ed0 Merge pull request #987 from gargrahul/fix_hostmalloc_double_device_map
Avoid double mapping of devices to hostMalloc buffer

[ROCm/clr commit: 93906a072c]
2019-03-27 05:23:47 +00:00
Maneesh Gupta 6fb7f626ba Merge pull request #990 from mhbliao/hliao/master/sw
SWDEV-184380 Fix hcc compilation

[ROCm/clr commit: 178e3ecdca]
2019-03-27 05:23:26 +00:00
Michael LIAO c5717a37d7 SWDEV-184380 Fix hcc compilation
- `hcc` has no builtin. Need to invoke LLVM intrinsic directly.


[ROCm/clr commit: d355122bf9]
2019-03-26 15:20:17 -04:00
Rahul Garg 0d47ae4203 Let hipHostMalloc always share/map pinned host ptr
[ROCm/clr commit: 9b38380c03]
2019-03-26 10:19:13 +05:30
Rahul Garg 21d7bbab11 Avoid double mapping of devices to hostMalloc buffer
[ROCm/clr commit: ad11972f47]
2019-03-25 23:07:05 +05:30