Graf commitů

4136 Commity

Autor SHA1 Zpráva Datum
Srinivasuluch 844928348f Update hipLaunchParm.cpp
Added a macro to disable the alignment test as it's broken

[ROCm/hip commit: a76d8f5580]
2018-06-27 19:57:44 +05:30
Srinivasuluch c2a44fa2e9 Update hipLaunchParm.cpp
pass by value for struct

[ROCm/hip commit: 6bd047fc47]
2018-06-27 16:45:51 +05:30
Aaron Enye Shi 6e2ee0f857 Implement __shfl_* funcs into HIP headers
[ROCm/hip commit: 9ac31e0bb6]
2018-06-26 18:32:11 +00:00
Alex Voicu 158e2ed16d Existence is a complex affair.
[ROCm/hip commit: 3c83e047df]
2018-06-26 00:41:35 +01:00
Yaxun (Sam) Liu af0e9b54de Add workaround to hipcc for build failure in tensorflow due to missing symbol __cpu_model
https://github.com/tensorflow/tensorflow/issues/9593


[ROCm/hip commit: 021728cd86]
2018-06-25 18:14:51 -04:00
Alex Voicu e2fef7283b Be nice to GCC, it is old and worthy of respect.
[ROCm/hip commit: 99c61ce7e4]
2018-06-25 22:59:07 +01:00
Yaxun (Sam) Liu c205c090f4 Include host_defines.h in hip_fp16.h since it uses __host__ __device__ attributes
[ROCm/hip commit: 02b160491d]
2018-06-25 15:34:34 -04:00
Alex Voicu 9fed6fed2b Removes use of unimplemented OCML functionality.
[ROCm/hip commit: 6c7a64efa2]
2018-06-25 19:16:27 +01:00
Alex Voicu 51c5249b40 Let's try this again...
[ROCm/hip commit: 9d91b802a5]
2018-06-25 17:49:50 +01:00
Srinivasuluch 76e307618d Update hipLaunchParm.cpp
Added validation part for struct, added two struct padding tests

[ROCm/hip commit: d8290f5a7b]
2018-06-25 16:53:12 +05:30
Aaron Enye Shi 260e50769b Add HIP Compute Mode
[ROCm/hip commit: ff924ecb3d]
2018-06-22 14:37:19 +00:00
Alex Voicu 5da1ca5db7 Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_native_vector_types
[ROCm/hip commit: 859133a045]
2018-06-22 12:19:32 +01:00
Aaron Enye Shi a7baff62e7 HIPCC - Use clang if clang++ is not compiled
[ROCm/hip commit: 73023e0a54]
2018-06-21 18:12:55 +00:00
Aaron Enye Shi 20674cfcb2 Replace __hip_hc_ir_ inline asm with __ockl_* functions
[ROCm/hip commit: 8ac864c2e3]
2018-06-20 20:40:14 +00:00
Aaron Enye Shi e2f8af2f3d Implement __ballot, __any, __all into HIP headers
[ROCm/hip commit: 6dc16bbf04]
2018-06-20 17:39:39 +00:00
Aaron Enye Shi 2a2f34b42d Implement hip_hc.ll into HIP headers
Move all __hip_hc_ir_* functions from hip_hc.ll into HIP header as inline asm. Remove hip_hc.ll and build dependencies from HIP.


[ROCm/hip commit: 2142eb4d12]
2018-06-20 17:39:31 +00:00
Aaron Enye Shi 0fca41a7ce Implement device_functions.cpp into HIP headers
Move all Integer Intrinsics, device_functions.cpp definitions and HIP specific device functions into HIP headers. Implement the device functions using llvm_intrinsics and device-libs functions instead of calling hc::__* functions. Remove device_functions.cpp since everything is now defined in header.


[ROCm/hip commit: e02fc7e680]
2018-06-20 17:39:23 +00:00
Aaron Enye Shi 14f721702a Move hipclang funcs into corresponding headers
[ROCm/hip commit: fe4e6c53fc]
2018-06-20 17:39:15 +00:00
Aaron Enye Shi 8d65776127 Split __llvm and device lib funcs into new headers
[ROCm/hip commit: cfe37484c9]
2018-06-20 17:39:06 +00:00
Aaron Enye Shi cb46df1654 Add get_dynamicgroupbaseptr def and remove hc_
[ROCm/hip commit: 27f600b425]
2018-06-20 17:38:59 +00:00
Aaron Enye Shi 9b03a036c3 Add prefix __ to memory scope and order
[ROCm/hip commit: 871cfc6fd2]
2018-06-20 17:38:52 +00:00
Aaron Enye Shi cdd7931ac1 Add __llvm_fence funcs and __ prefixes
[ROCm/hip commit: cfa8fc1ca5]
2018-06-20 17:38:45 +00:00
Aaron Enye Shi b34868005a Add hipclang amdgcn functions
These are moving from hipclang in device library to hip headers. These are required for the functionality of HIPclang project.


[ROCm/hip commit: c453b42bff]
2018-06-20 17:38:37 +00:00
Maneesh Gupta a4b9e5305f Merge pull request #507 from ROCm-Developer-Tools/fix-forward
Add __device__ to device functions in hip_fp16_math_fwd.h

[ROCm/hip commit: fc80fb4ab3]
2018-06-20 14:21:46 +05:30
Maneesh Gupta 6932d45c14 Merge pull request #504 from ROCm-Developer-Tools/fix-vector3
Fix channel_descriptor.h about vector 3 for gcc

[ROCm/hip commit: cffc5ad273]
2018-06-20 14:20:29 +05:30
Maneesh Gupta 27e2af1773 Merge pull request #490 from ROCm-Developer-Tools/feature_decouple_atomics_from_hc
Switch the atomic implementation to use Clang  builtins.

[ROCm/hip commit: 946c8da88a]
2018-06-20 14:16:43 +05:30
Maneesh Gupta 4cdc20a6ce Merge pull request #457 from whchung/hip-reinit
HIP program state re-initialization logic

[ROCm/hip commit: 836627279f]
2018-06-20 09:37:27 +05:30
Yaxun (Sam) Liu 8696038043 Let hipcc handle library with extension lo for hip-clang
[ROCm/hip commit: 46d3c1d51e]
2018-06-19 10:51:08 -04:00
Yaxun (Sam) Liu b8ae2784e9 Add conj, operator-,==,!= for hipFloatComplex/hipDoubleComplex
[ROCm/hip commit: 84da72dae8]
2018-06-19 10:49:59 -04:00
pradeepisro 4c9fad371f added option HIP_BUILD_VERBOSE to enable verbosity in HIP build
[ROCm/hip commit: f6938961b9]
2018-06-19 13:50:24 +05:30
pradeepisro 1eb91f1bab added changes to FindHIP.cmake which would allow us to build using ninja #467
[ROCm/hip commit: 4f0aefbd63]
2018-06-19 12:26:18 +05:30
Maneesh Gupta 163e55fe10 Merge pull request #516 from bddppq/empty-generator-expression
Properly handle (empty) cmake generator expression

[ROCm/hip commit: 1b88a2ce2f]
2018-06-19 09:38:21 +05:30
Maneesh Gupta 3475fe6efa Merge pull request #520 from ntrost57/master
added missing hipCmul() to nvcc_detail/hip_complex.h

[ROCm/hip commit: 523e7fd9b2]
2018-06-19 09:37:50 +05:30
Wen-Heng (Jack) Chung d214b045c3 Keep the map which tracks GPU kernel symbols to grow monotonically
[ROCm/hip commit: 32789a8b7d]
2018-06-18 16:54:18 -05:00
Yaxun (Sam) Liu a46f62a5c0 Add abs/real/imag functions for hipFloatComplex/hipDoubleComplex
[ROCm/hip commit: 9181fbb0b7]
2018-06-18 11:57:57 -04:00
Maneesh Gupta 411414acc5 Merge pull request #521 from gargrahul/temp_fixmemcpy2dasync_trsmissue
Use memcpy kernel for all pinned memory cases in hipMemcpy2DAsync

[ROCm/hip commit: 3d8317a50d]
2018-06-18 09:34:02 +05:30
Yaxun (Sam) Liu fa9e73ccdc Add missing __device__ __host__ to complex constructor
Also add missing typedef value_type


[ROCm/hip commit: 7a5605d006]
2018-06-17 20:20:32 -04:00
Yaxun (Sam) Liu 0e29f327e2 Includes <cmath> or <math.h> by __cplusplus in hip_complex.h
[ROCm/hip commit: 2523c39a37]
2018-06-17 20:20:32 -04:00
Yaxun (Sam) Liu cf6cdab029 Include cmath instead of math.h in hip_complex.h
[ROCm/hip commit: 325cf3ccf0]
2018-06-17 20:20:32 -04:00
Yaxun (Sam) Liu 0b10ab2b7e Add missing macro MAKE_COMPONENT_CONSTRUCTOR_TWO_COMPONENT to hip_complex.h
[ROCm/hip commit: 5eeb57b0a6]
2018-06-17 20:20:32 -04:00
Yaxun (Sam) Liu acaf783f52 Fix handling of static library in hipcc for hip-clang
[ROCm/hip commit: 2b32dbd414]
2018-06-17 20:11:10 -04:00
Yaxun (Sam) Liu 0573ee79de Let hipcc handle static library for hip-clang only if it contains bundles
[ROCm/hip commit: f0935e6d4f]
2018-06-17 20:11:10 -04:00
Alex Voicu 8d9917f199 Revert "Revert "Switch over to using native vector types, for better codegen. Remove noise.""
This reverts commit 3792417463.


[ROCm/hip commit: 28a1aef8a1]
2018-06-16 22:59:36 +01:00
Wen-Heng (Jack) Chung c6b975bf13 Improve performance of re-initialization logic
Keep track of shared libaries already discovered. Do not build HSA executables
for them.


[ROCm/hip commit: ece4539c1d]
2018-06-15 18:07:33 -05:00
Rahul Garg 388679efc8 TEMP- fix memcpy2dAsync for trsm issue
[ROCm/hip commit: cd23905897]
2018-06-15 16:08:29 +05:30
Lakhan Singh 093eedea5e Made changes as suggested.
[ROCm/hip commit: 90c8230cfa]
2018-06-15 11:30:02 +05:30
Nico Trost 494d34f4ee added missing hipCmul() to nvcc_detail/hip_complex.h
[ROCm/hip commit: 0b1e698e74]
2018-06-14 21:49:54 +02:00
Wen-Heng (Jack) Chung e5ca9eb081 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: 379b7a2241]
2018-06-14 15:46:49 +00:00
Maneesh Gupta 94b64ea44b Merge pull request #519 from gargrahul/fix_memcpy2dasync_streamres
Fix stream resolution in memcpy2dasync

[ROCm/hip commit: bae22822f2]
2018-06-14 12:34:32 +05:30
Rahul Garg 312999de41 Fix stream resolution in memcpy2dasync
[ROCm/hip commit: 069e2c34c9]
2018-06-14 11:58:56 +05:30