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
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
3eb353ec44
added missing hipCmul() to nvcc_detail/hip_complex.h
...
[ROCm/clr commit: 6815c7bdd7
2018-06-14 21:49:54 +02:00
865fe01b37
HIP program state re-initialization logic
...
This commit is to support kernels dynamically loaded thru means such as
dlopen() after HIP runtime initializes.
[ROCm/clr commit: 04640992dc
2018-06-14 15:46:49 +00:00
a41cb78337
Fix stream resolution in memcpy2dasync
...
[ROCm/clr commit: 2ae3be9773
2018-06-14 11:58:56 +05:30
dfe8629088
Fix retrieved locked ptr offset
...
[ROCm/clr commit: 68554e155b
2018-06-13 23:10:05 +05:30
3a79e00741
Properly handle (empty) cmake generator expression
...
[ROCm/clr commit: 704f8c7b8f
2018-06-12 23:53:18 -07:00
8983f78d21
[GETandALGN]: Get channel and alignment details
...
[ROCm/clr commit: 7d6f1b8e38
2018-06-12 15:22:05 +05:30
ab65bd63a8
Update hipLaunchParm.cpp
...
cleanup
[ROCm/clr commit: db67638c5a
2018-06-11 15:21:20 +05:30
bceb5d6766
Adding struct test for hipLaunchKernel()
...
[ROCm/clr commit: 47835efac5
2018-06-11 12:37:38 +05:30
cbfa36c0ea
Merge pull request #505 from ROCm-Developer-Tools/fix-hipcc-linker
...
Let hipcc handle library in linker response file for hip-clang
[ROCm/clr commit: 359e6609bc
2018-06-11 12:01:45 +05:30
ad3c3314bc
Merge pull request #506 from ROCm-Developer-Tools/fix-extern-shared
...
Add support of extern __shared__ for hip-clang
[ROCm/clr commit: 181cde1899
2018-06-11 11:59:58 +05:30
3a77334a98
Update hip_porting_guide.md
...
use ".hip.cpp" for *source* files
[ROCm/clr commit: 683894c698
2018-06-09 17:16:08 -07:00
c1cd1513aa
Revert "Switch over to using native vector types, for better codegen. Remove noise."
...
[ROCm/clr commit: d137271083
2018-06-08 16:48:22 -04:00
7f5b121990
Add __device__ to device functions in hip_fp16_math_fwd.h
...
[ROCm/clr commit: 9566616dd2
2018-06-08 11:23:52 -04:00
3536fbeb2b
Add more function declarations for hip-clang
...
[ROCm/clr commit: 93fbbfc8ad
2018-06-08 11:20:42 -04:00
e25084dd6d
Fix channel_descriptor.h about vector 3 for gcc
...
[ROCm/clr commit: 6215587197
2018-06-08 11:18:41 -04:00
ef8c4b51ae
Add support of extern __shared__ for hip-clang
...
[ROCm/clr commit: 9398c9c927
2018-06-08 11:17:25 -04:00
581de8660a
Let hipcc handle library in linker response file for hip-clang
...
[ROCm/clr commit: 8d3e4b4475
2018-06-08 11:14:26 -04:00
236413158d
Merge pull request #482 from ROCm-Developer-Tools/feature_clean_up_hip_math
...
Switch to using ROCDL directly, as opposed to via HC. Add missing bits.
[ROCm/clr commit: cb642f14ab
2018-06-06 16:07:22 +05:30
95907c967d
Merge pull request #496 from gargrahul/add_gettexresdesc_nvcc
...
Add getTextureResourceDescriptor on NVCC
[ROCm/clr commit: a1ad2b9c65
2018-06-06 15:12:11 +05:30
c4b344dab4
Merge pull request #487 from gargrahul/fix_hiparray_alloc_flag_nvcc
...
Map hipArray alloc flags on NVCC
[ROCm/clr commit: a432847b1b
2018-06-06 15:11:40 +05:30
e34247ca19
Merge pull request #497 from gargrahul/fix_memcpy3d_fastpath
...
Fix hipMemcpy3D for fast path
[ROCm/clr commit: 53037472ff
2018-06-06 14:44:02 +05:30
Aaron Enye Shi
Maneesh Gupta
Yaxun (Sam) Liu
pradeepisro
Wen-Heng (Jack) Chung
Alex Voicu
Rahul Garg
Lakhan Singh
Nico Trost
Junjie Bai
Srinivasuluch
Tomas Wood
Siu Chi Chan