cdad3de88d
Update hipLaunchParm.cpp
...
Changing macro name
[ROCm/clr commit: ef33a0ad4d
2018-06-27 22:06:53 +05:30
cf720fbe95
Update hipLaunchParm.cpp
...
wrap up to 80 characters per line
[ROCm/clr commit: 52e808da4d
2018-06-27 22:04:12 +05:30
9865b4d6e6
Update hipLaunchParm.cpp
...
changing the condition, a = b, as Sam suggested
[ROCm/clr commit: f69d89e79f
2018-06-27 21:48:37 +05:30
8597d19217
Update hipLaunchParm.cpp
...
[ROCm/clr commit: 22fd883df8
2018-06-27 20:49:07 +05:30
f266afbec8
Update hipLaunchParm.cpp
...
Added a macro to disable the alignment test as it's broken
[ROCm/clr commit: 681ce0182e
2018-06-27 19:57:44 +05:30
714efd908b
Update hipLaunchParm.cpp
...
pass by value for struct
[ROCm/clr commit: 52f3ec8f26
2018-06-27 16:45:51 +05:30
c60682797a
Implement __shfl_* funcs into HIP headers
...
[ROCm/clr commit: e44eaa1a1e
2018-06-26 18:32:11 +00:00
18ce8e6251
Existence is a complex affair.
...
[ROCm/clr commit: 2acf7f033c
2018-06-26 00:41:35 +01:00
bba741a913
Add workaround to hipcc for build failure in tensorflow due to missing symbol __cpu_model
...
https://github.com/tensorflow/tensorflow/issues/9593
[ROCm/clr commit: 632baba353
2018-06-25 18:14:51 -04:00
e0c1000e9c
Be nice to GCC, it is old and worthy of respect.
...
[ROCm/clr commit: b9ead38478
2018-06-25 22:59:07 +01:00
9d35209f8f
Include host_defines.h in hip_fp16.h since it uses __host__ __device__ attributes
...
[ROCm/clr commit: c74682ef1b
2018-06-25 15:34:34 -04:00
4fcfb64a88
Removes use of unimplemented OCML functionality.
...
[ROCm/clr commit: 9452298fbe
2018-06-25 19:16:27 +01:00
89d6db12fe
Let's try this again...
...
[ROCm/clr commit: 3ff1d4081e
2018-06-25 17:49:50 +01:00
57eb2560f0
Update hipLaunchParm.cpp
...
Added validation part for struct, added two struct padding tests
[ROCm/clr commit: c5b643999c
2018-06-25 16:53:12 +05:30
4ad4f6a489
Add HIP Compute Mode
...
[ROCm/clr commit: c73cd64f5b
2018-06-22 14:37:19 +00:00
8b9ac66103
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_native_vector_types
...
[ROCm/clr commit: 0e0d43bfe1
2018-06-22 12:19:32 +01:00
a764b09a14
HIPCC - Use clang if clang++ is not compiled
...
[ROCm/clr commit: dc850cc3e7
2018-06-21 18:12:55 +00:00
3f19f0979b
Replace __hip_hc_ir_ inline asm with __ockl_* functions
...
[ROCm/clr commit: 5d4986d470
2018-06-20 20:40:14 +00:00
7cb3cec513
Implement __ballot, __any, __all into HIP headers
...
[ROCm/clr commit: 9a295a732d
2018-06-20 17:39:39 +00:00
d09a2f9237
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/clr commit: 175c87f2bf
2018-06-20 17:39:31 +00:00
7f2693010b
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/clr commit: ad5f1dcbf2
2018-06-20 17:39:23 +00:00
8f558387fc
Move hipclang funcs into corresponding headers
...
[ROCm/clr commit: e8a18a5473
2018-06-20 17:39:15 +00:00
133a800e94
Split __llvm and device lib funcs into new headers
...
[ROCm/clr commit: 366207f8af
2018-06-20 17:39:06 +00:00
a769701c15
Add get_dynamicgroupbaseptr def and remove hc_
...
[ROCm/clr commit: 0694d0300a
2018-06-20 17:38:59 +00:00
69bdb11cf1
Add prefix __ to memory scope and order
...
[ROCm/clr commit: 7cade79d98
2018-06-20 17:38:52 +00:00
9020ef1b53
Add __llvm_fence funcs and __ prefixes
...
[ROCm/clr commit: 4298ed308e
2018-06-20 17:38:45 +00:00
1e6f00bf67
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/clr commit: f4399d57a3
2018-06-20 17:38:37 +00:00
8e2a1e0acd
Merge pull request #507 from ROCm-Developer-Tools/fix-forward
...
Add __device__ to device functions in hip_fp16_math_fwd.h
[ROCm/clr commit: 272c16d34e
2018-06-20 14:21:46 +05:30
f1571c9750
Merge pull request #504 from ROCm-Developer-Tools/fix-vector3
...
Fix channel_descriptor.h about vector 3 for gcc
[ROCm/clr commit: 29aa297899
2018-06-20 14:20:29 +05:30
bdc67ac1b4
Merge pull request #490 from ROCm-Developer-Tools/feature_decouple_atomics_from_hc
...
Switch the atomic implementation to use Clang builtins.
[ROCm/clr commit: d27991e1c8
2018-06-20 14:16:43 +05:30
721a3f60be
Merge pull request #457 from whchung/hip-reinit
...
HIP program state re-initialization logic
[ROCm/clr commit: 8ff33a83b1
2018-06-20 09:37:27 +05:30
4831cd44fc
Let hipcc handle library with extension lo for hip-clang
...
[ROCm/clr commit: 454d45e5bb
2018-06-19 10:51:08 -04:00
b93308449e
Add conj, operator-,==,!= for hipFloatComplex/hipDoubleComplex
...
[ROCm/clr commit: 2b5242b2c3
2018-06-19 10:49:59 -04:00
64b4f4101f
added option HIP_BUILD_VERBOSE to enable verbosity in HIP build
...
[ROCm/clr commit: bdfd6957aa
2018-06-19 13:50:24 +05:30
cd9a2cbe42
added changes to FindHIP.cmake which would allow us to build using ninja #467
...
[ROCm/clr commit: 6bdb5f3541
2018-06-19 12:26:18 +05:30
b43f3bdd30
Merge pull request #516 from bddppq/empty-generator-expression
...
Properly handle (empty) cmake generator expression
[ROCm/clr commit: cae3aeb923
2018-06-19 09:38:21 +05:30
5b20f2ee29
Merge pull request #520 from ntrost57/master
...
added missing hipCmul() to nvcc_detail/hip_complex.h
[ROCm/clr commit: a24f1d7353
2018-06-19 09:37:50 +05:30
ca62af218c
Keep the map which tracks GPU kernel symbols to grow monotonically
...
[ROCm/clr commit: 8f521edff1
2018-06-18 16:54:18 -05:00
1709777f1b
Add abs/real/imag functions for hipFloatComplex/hipDoubleComplex
...
[ROCm/clr commit: 0de3ef7b32
2018-06-18 11:57:57 -04:00
c1f37d4fb5
Merge pull request #521 from gargrahul/temp_fixmemcpy2dasync_trsmissue
...
Use memcpy kernel for all pinned memory cases in hipMemcpy2DAsync
[ROCm/clr commit: d30f3f0c88
2018-06-18 09:34:02 +05:30
37fe9e0346
Add missing __device__ __host__ to complex constructor
...
Also add missing typedef value_type
[ROCm/clr commit: 40d2d8a0bd
2018-06-17 20:20:32 -04:00
2dfbd89f5c
Includes <cmath> or <math.h> by __cplusplus in hip_complex.h
...
[ROCm/clr commit: 5d0d2ea455
2018-06-17 20:20:32 -04:00
92959fa686
Include cmath instead of math.h in hip_complex.h
...
[ROCm/clr commit: cc44a3d234
2018-06-17 20:20:32 -04:00
0163a94106
Add missing macro MAKE_COMPONENT_CONSTRUCTOR_TWO_COMPONENT to hip_complex.h
...
[ROCm/clr commit: 8ddadf835d
2018-06-17 20:20:32 -04:00
5efe15283b
Fix handling of static library in hipcc for hip-clang
...
[ROCm/clr commit: fd03c8fc18
2018-06-17 20:11:10 -04:00
0b5fe1601c
Let hipcc handle static library for hip-clang only if it contains bundles
...
[ROCm/clr commit: d442a57002
2018-06-17 20:11:10 -04:00
58edb652ca
Revert "Revert "Switch over to using native vector types, for better codegen. Remove noise.""
...
This reverts commit c1cd1513aafa370fcf19
2018-06-16 22:59:36 +01:00
1d1b402e5b
Improve performance of re-initialization logic
...
Keep track of shared libaries already discovered. Do not build HSA executables
for them.
[ROCm/clr commit: b883ea759d
2018-06-15 18:07:33 -05:00
1c2acf1467
TEMP- fix memcpy2dAsync for trsm issue
...
[ROCm/clr commit: 007e2a4b5f
2018-06-15 16:08:29 +05:30
0f582a7893
Made changes as suggested.
...
[ROCm/clr commit: 936b878d72
2018-06-15 11:30:02 +05:30
Srinivasuluch
Aaron Enye Shi
Alex Voicu
Yaxun (Sam) Liu
Maneesh Gupta
pradeepisro
Wen-Heng (Jack) Chung
Rahul Garg
Lakhan Singh