3f5e937afc
Merge pull request #949 from gargrahul/single_stream_concurrent_kernels
...
Add extension for kernel concurrency on same stream
[ROCm/hip commit: 352b17346c
2019-03-06 17:34:54 +05:30
df7d8c46ed
Merge pull request #932 from ROCm-Developer-Tools/feature_maybe_dlopen_test
...
Add one test case for complex dynamic loading behavior
[ROCm/hip commit: 0c4a40efcc
2019-03-06 17:32:23 +05:30
0c16497abd
dlopen() fixes ( #929 )
...
* Initial attempt to switch over to internally linked state.
* Add missing CMake update.
* hipLaunchKernelGGLImpl must be inline as well. Ensure internal linkage.
* Ensure global retrieval uses internally linked state.
* Hide HC in the implementation. Minimise ADL woes.
* Strange software exists, and must be catered to.
* Use a less spammy mechanism for ensuring internal linkage / non-export.
* Remove leftover internal detail.
[ROCm/hip commit: ea0fcf3e61
2019-03-06 17:31:44 +05:30
5d6fd17fbe
Add extension for kernel concurrency on same stream
...
[ROCm/hip commit: 59081c69fc
2019-03-06 12:55:39 +05:30
2264e69da3
Merge pull request #936 from mangupta/swdev-174923
...
[hipconfig] Update HIP_PLATFORM detection logic
[ROCm/hip commit: 2d67bc5e9c
2019-03-06 06:08:11 +05:30
effdffc006
[HIPIFY] Change CUDA Driver's functions' cuMemsetD32(Async) mapping
...
cuMemsetD32(Async) -> hipMemsetD32(Async) (was hipMemset(Async))
based on:
[#933 ] https://github.com/ROCm-Developer-Tools/HIP/pull/933
[ROCm/hip commit: a87d798d90
2019-03-05 18:13:18 +03:00
54c72c1079
Update hipMemset.cpp
...
Address build issues on nvcc path.
[ROCm/hip commit: 51f29b9cee
2019-03-05 12:11:11 +05:30
19b6b2b570
Update hip_runtime_api.h
...
Use hipCUResultTohipError instead of hipCUDAErrorTohipError in hipMemsetD32 & hipMemsetD32Async.
[ROCm/hip commit: 8db717c769
2019-03-05 12:10:01 +05:30
da589e38ed
Address code review comments to use hipDeviceptr_t
...
[ROCm/hip commit: 5cbd28f29b
2019-03-05 05:51:05 +00:00
ea689f63ca
Add implementation for NVCC path
...
[ROCm/hip commit: 0337b686ef
2019-03-04 20:11:12 -08:00
085c6c15b2
Add direct test for hipMemsetD32 and hipMemsetD32Async
...
[ROCm/hip commit: bfde8a7fab
2019-03-04 17:20:32 +00:00
0b7f38d100
Add hipMemsetD32 and hipMemsetD32Async
...
Add 2 extra memset functions which fills memory with integer-typed data
Also change the parameters of ihipMemset to better explain the semantic
[ROCm/hip commit: 7ebbbd3525
2019-03-04 17:00:33 +00:00
a60c0222f0
Merge pull request #939 from gargrahul/update_hipmemset_test
...
[dtest] Update hipMemset test
[ROCm/hip commit: de4a9b8446
2019-03-03 20:29:55 +05:30
7a9ebee08a
Fix review comments
...
[ROCm/hip commit: 131c0ea326
2019-03-02 23:38:37 +05:30
91f6e6b1e8
Merge pull request #945 from wkwchau/hipMemset3D_fix
...
Fix hipMemset3D test
[ROCm/hip commit: d28c13ed69
2019-03-01 21:18:12 +05:30
4a0d68ba3f
Fix hipMemset3D test
...
Calculate the allocated size based on the width, height and depth.
[ROCm/hip commit: 8d92d1ebd7
2019-02-28 22:42:46 +00:00
4093c03dd7
Fix hipMemset test for HIP/NVCC
...
[ROCm/hip commit: 77c6d5451f
2019-03-01 03:46:57 +05:30
d9f59b18f8
Revert "hipcc should consume -mcode-object-v3 flag"
...
This reverts commit 1a8b50e63ce8556388f9
2019-02-28 11:21:47 -05:00
e748fd2ae0
Revert "Change code-object flag to only HIP-Clang"
...
This reverts commit 17a853c2771bd8d24278
2019-02-28 11:20:04 -05:00
f46d2a3010
Revert "Consume the code obj args to prevent duplicates"
...
This reverts commit b19e4b5b63737972d31c
2019-02-28 11:19:35 -05:00
f3def1c107
Merge pull request #938 from gargrahul/fix_hipBusBW_p2p_bidir
...
Fix hipBusBW sample for P2P bidirectional test
[ROCm/hip commit: b93666bdde
2019-02-28 07:14:38 +05:30
f0bb5690f1
Merge pull request #937 from yxsamliu/nan2
...
Fix nan for windows
[ROCm/hip commit: 07b0e9574c
2019-02-28 07:14:27 +05:30
2e700104de
Merge pull request #935 from gargrahul/fix_hipbusbw_beatsoverflow
...
Fix hipBusBW overflow with setting beats/iterations
[ROCm/hip commit: 2da14e97f2
2019-02-28 07:14:16 +05:30
fa0c9d8a73
Update hipMemset test
...
[ROCm/hip commit: 026dc9457e
2019-02-28 06:54:49 +05:30
c7620fc4e9
Fix hipBusBW sample for P2P bidirectional test
...
[ROCm/hip commit: 70278f1777
2019-02-28 00:56:07 +05:30
48ab0aa588
Fix nan for windows
...
[ROCm/hip commit: 278007218a
2019-02-27 12:33:26 -05:00
55da014b79
[hipcofig] Update HIP_PLATFORM detection logic
...
HIP_PLATFORM detection logic relied on finding a working KFD. If it was
found, the platform was set as hcc else as nvcc.
However this logic is flawed since it is possible for the development
system to only have the user mode bits to build HIP application code.
Hence the better logic is to rely on finding a suitable compiler.
The new logic is as follows:
- look for a working HCC. If found, platform is set as hcc.
- else look for a working NVCC. If found, platform is set as nvcc.
- else the platform defaults to hcc for now.
Change-Id: Ifcc42c29a19f722153d5c23c55f1a8765dceaf6b
[ROCm/hip commit: 8b25f7b4cf
2019-02-27 14:10:21 +05:30
6391066444
Fix hipBusBW overflow with setting beats/iterations
...
[ROCm/hip commit: 673ecd02fe
2019-02-27 00:18:52 +05:30
67723bd3e7
Fix forceinline for non HCC compilation
...
[ROCm/hip commit: 55145feae6
2019-02-26 07:50:09 +05:30
c79a5a798e
Add one test case for complex dynamic loading behavior
...
Existing HIT syntax doesn't seem to support the expected build and run steps
for this test.
[ROCm/hip commit: 8e5bb3c57a
2019-02-25 17:03:31 +00:00
55d9cd6a65
[HIPIFY][doc] Update README.md
...
+ Populate Dependencies section with upcoming LLVM versions
+ Add clang bugs for not working configs LLVM+CUDA
+ Update Testing section
[ROCm/hip commit: 391aa7221b
2019-02-25 18:26:25 +03:00
5f4b9a8f8f
[HIPIFY][tests] caffe2 test fix
...
[ROCm/hip commit: 3a8ef9c8a2
2019-02-25 17:12:32 +03:00
3a57fc0a4b
[HIPIFY][Caffe2] Initial Caffe2 support
...
[ROCm/hip commit: 2619f22e5c
2019-02-23 20:46:22 +03:00
992f431c99
Merge pull request #925 from yxsamliu/h2f
...
Add __gnu_h2f_ieee and __gnu_f2h_ieee
[ROCm/hip commit: 31c4cc78b1
2019-02-22 13:38:15 +05:30
7ef8b1138f
Add __gnu_h2f_ieee and __gnu_f2h_ieee
...
The implementation is copied from HCC runtime.
For hcc it has no effect since apps can find them in either hcc runtime or HIP
runtime.
hip-clang needs it in HIP/HCC runtime so that HIP/HCC and HIP/VDI runtime are
swappable.
[ROCm/hip commit: c5e813f64c
2019-02-21 12:48:28 -05:00
b19e4b5b63
Consume the code obj args to prevent duplicates
...
[ROCm/hip commit: 2cd34f3c01
2019-02-19 17:02:27 +00:00
0d99882b85
Merge pull request #919 from emankov/master
...
[HIPIFY][DNN] Revise and sync with CUDNN 10 and hipDNN
[ROCm/hip commit: 6eb8256883
2019-02-15 15:06:28 +03:00
b46dd95907
Merge pull request #916 from mangupta/swdev-179677
...
Fix signature for unsigned long long variant of atomicExch
[ROCm/hip commit: 438cf792b7
2019-02-14 12:46:32 +05:30
d91590a98b
[HIPIFY][DNN] Revise and sync with CUDNN 10 and hipDNN
...
+ CUDNN_API_supported_by_HIP.md update
+ CUDA_Runtime_API_functions_supported_by_HIP.md update
+ libraryPropertyType_t is moved to Runtime
+ test update
[ROCm/hip commit: d26dc3cea7
2019-02-13 19:40:59 +03:00
3052464cb8
Merge pull request #918 from ROCm-Developer-Tools/ci_updates
...
[ci] Switch tests in CI infrastructure to cuda-10.x
[ROCm/hip commit: 22b55a9b83
2019-02-13 14:05:23 +05:30
dd980e7e72
[ci] Switch CI tests to cuda-10.x
...
Change-Id: I99e99bcf528d0c38924bd3a86a3067628f2bb3ea
[ROCm/hip commit: 336a781a2d
2019-02-13 13:22:08 +05:30
7094c2d28d
Initialize HIP_LIB_PATH on hcc path
...
Change-Id: I8f392fffcd6a3714c20cb17e876dbaad999c33a0
[ROCm/hip commit: c8579ead67
2019-02-13 09:57:21 +05:30
8f1b3d34f7
Fix signature for unsigned long long variant of atomicExch
...
This fixes #888
Change-Id: I2b2dc5ed1ff2a26083ad9d102eccac90f67801ae
[ROCm/hip commit: f0618df8f4
2019-02-13 09:45:07 +05:30
f18ddd57da
Merge pull request #913 from aaronenyeshi/fix-texture-constant-addrspace
...
Fix texture using constant addrspace 4
[ROCm/hip commit: ca7a53b13d
2019-02-13 08:59:01 +05:30
6d16a4b679
Merge pull request #912 from ROCm-Developer-Tools/remove-cpp-function-templates-for-malloc
...
Remove C++ function templates for hipMalloc and hipHostMalloc
[ROCm/hip commit: f9daeb1c51
2019-02-13 08:58:26 +05:30
4441aff847
Merge pull request #910 from aaronenyeshi/hip-code-obj-v3-passing
...
hipcc should consume -mcode-object-v3 flag
[ROCm/hip commit: d91bbf881c
2019-02-13 08:58:19 +05:30
1dad8c4329
Fix texture using constant addrspace 4
...
[ROCm/hip commit: 63b400beea
2019-02-12 16:56:22 +00:00
17a853c277
Change code-object flag to only HIP-Clang
...
[ROCm/hip commit: 1c6365fbe7
2019-02-11 17:18:12 +00:00
abd8e75c47
Introduce __HIP_DISABLE_CPP_FUNCTIONS__ macro to disable C++ wrappers
...
hipMalloc and hipHostMalloc are C++ function templates by default. In some
applications they need to discover the decltype of underlying C functions. In
this commit, a new macro __HIP_DISABLE_CPP_FUNCTIONS__ is introduced to
suppress the C++ function templates.
Existing HIP applications don't need to be changed. hipMalloc and hipHostMalloc
will behave just the same.
For new applications which depends on identifying decltypes of underlying C
functions, __HIP_DISABLE_CPP_FUNCTIONS__ shall be defined prior to including
HIP headers.
[ROCm/hip commit: eba3bd3082
2019-02-11 09:33:15 -06:00
9ab6e7b7f6
Merge pull request #911 from lmoriche/hip_clang
...
Allow HIP_LIB_PATH to be overriden at the command line. Use HIP_LIB_P…
[ROCm/hip commit: 31c4a0dff1
2019-02-11 11:26:39 +05:30
Maneesh Gupta
Alex Voicu
Rahul Garg
Evgeny Mankov
Wen-Heng (Jack) Chung
Wilkin Chau
Yaxun Sam Liu
Aaron Enye Shi