121993cae8
Merge pull request #447 from ROCm-Developer-Tools/feature_native_vector_types
...
Switch over to using native vector types, for better codegen. Remove noise.
[ROCm/hip commit: 68c36f9125
2018-06-01 13:58:07 +05:30
7f9b00ba19
Merge pull request #466 from ROCm-Developer-Tools/feature_use_Float16
...
Feature use _Float16 and match CUDA __half behaviour.
[ROCm/hip commit: bdf2645713
2018-06-01 13:50:12 +05:30
54024c3dc1
Merge branch 'feature_use_Float16' of https://github.com/ROCm-Developer-Tools/HIP into feature_use_Float16
...
[ROCm/hip commit: b9b1e0b703
2018-05-31 15:27:31 +01:00
90e7799bf4
Add missing interop with volatile. Fix unit tests.
...
[ROCm/hip commit: 0108819e2a
2018-05-31 15:27:12 +01:00
2bd034a0d9
Fix __syncthreads for hip-clang
...
[ROCm/hip commit: b7641cf835
2018-05-30 16:33:18 -04:00
de13fa6e8b
Add more function declarations for hip-clang
...
[ROCm/hip commit: 6b8218e5a0
2018-05-30 06:51:03 -04:00
b92ace4cdb
Merge pull request #469 from yxsamliu/fun
...
Add math function declaration for hip-clang
[ROCm/hip commit: a1fea02c6e
2018-05-30 15:01:27 +05:30
475591057b
Add signature for hipFuncGetAttributes to nvcc_details
...
Change-Id: I06d5b50028fcfe3ea9d81f749b02be6b094c0977
[ROCm/hip commit: 7fd92d471b
2018-05-30 11:24:48 +05:30
6dc1a919ac
Fix hipBindTexture on NVCC path
...
[ROCm/hip commit: d67b614b22
2018-05-30 10:59:07 +05:30
4751d72fdf
Merge pull request #471 from Jorghi12/patch-4
...
Adding double/long int signatures for abs
[ROCm/hip commit: c8aca45856
2018-05-30 08:31:32 +05:30
798fb51e11
GCC only supports power-of-2 component counts, so round up to next square.
...
[ROCm/hip commit: 75390c7083
2018-05-29 01:22:26 +01:00
24b35fc052
Add 1d texture types for NVCC path
...
[ROCm/hip commit: 024f77ce61
2018-05-28 15:02:06 +05:30
50ccc9fc63
Update math_functions.h
...
CUDA also has a function named labs.
[ROCm/hip commit: 6e2b9d0547
2018-05-26 16:22:10 -04:00
3eeb326c96
Add missing alias half / half2 aliases
...
[ROCm/hip commit: 98395ad38c
2018-05-26 12:10:50 +01:00
a82eb2dfa2
Adding double/long int signatures for abs
...
Adding overloads for abs that are found in cuda's math_functions.
[ROCm/hip commit: 4f6904b5c7
2018-05-26 00:41:24 -04:00
960fe360f5
Add more function declarations to hip-clang
...
[ROCm/hip commit: b7801f1fe3
2018-05-25 16:18:46 -04:00
ff34ae3562
Missing bits.
...
[ROCm/hip commit: 32388cbf28
2018-05-25 20:12:21 +01:00
c7b7301d48
Add math function declaration for hip-clang
...
[ROCm/hip commit: f9693a9210
2018-05-25 12:22:16 -04:00
4ceb9cbc09
Missing commit.
...
[ROCm/hip commit: 6f819f226b
2018-05-23 17:57:47 +01:00
51e2e27488
Merge pull request #445 from ROCm-Developer-Tools/feature_func_attributes
...
Add support for the hipFuncGetAttributes interface.
[ROCm/hip commit: df3bb9fc32
2018-05-22 09:37:41 +05:30
9cb5c4efd8
Add hipMalloc3D to nvcc detail
...
Change-Id: I8a5654066ed1504e3b05eddbbdebf05fd52aa149
[ROCm/hip commit: 661561eead
2018-05-21 11:33:09 +05:30
22c2164216
defined hipPitchedPtr
...
Added a define for hipPitchedPtr to resolve a compiler error
[ROCm/hip commit: 1a108ef7f3
2018-05-18 09:11:50 -04:00
3d1d7ccf30
Merge pull request #433 from gargrahul/add_hipmemset3d
...
Added hipMemset3D
[ROCm/hip commit: 03ac8e6a92
2018-05-18 14:54:15 +05:30
b53c717615
Merge pull request #440 from yxsamliu/assert2
...
Add __assert_fail, __device_trap and hipErrorAssert for clang
[ROCm/hip commit: dcb4477f9f
2018-05-18 14:13:27 +05:30
8712744ba0
Switch over to using native vector types, for better codegen. Remove noise.
...
[ROCm/hip commit: b8c98d2357
2018-05-12 00:14:17 +01:00
d5f965c44a
Add support for the hipFuncGetAttributes interface.
...
[ROCm/hip commit: 13274ce559
2018-05-11 03:35:10 +01:00
bec6249f99
Fix warning about inlined function is not defined
...
[ROCm/hip commit: 19f3ed6f62
2018-05-08 16:38:50 -04:00
cbbe58dcd5
Add __assert_fail, __device_trap and hipErrorAssert for clang
...
[ROCm/hip commit: 7672b44c79
2018-05-08 15:42:27 -04:00
923d831d5e
add intrinsics mbcnt_lo, mbcnt_hi, lane_id
...
[ROCm/hip commit: b285145966
2018-05-08 13:43:53 -04:00
e2a2b5bdcf
Added hipMemset3D
...
[ROCm/hip commit: da302c3e93
2018-05-07 10:24:30 +05:30
e687245eb0
Cleaned up
...
[ROCm/hip commit: b4585a2a90
2018-05-02 12:54:17 +05:30
ab1dabe61b
Fix texture 3D for HIP/NVCC
...
[ROCm/hip commit: 9de5f23d54
2018-05-02 11:56:37 +05:30
d3d11ff829
Merge pull request #419 from gargrahul/fix_hip_gcc_host_build
...
Fix gcc build issues for host code
[ROCm/hip commit: adcd8553c3
2018-05-01 12:42:50 +05:30
ef13aa3a0b
Merge pull request #415 from deven-amd/master
...
Checkin to fix bugs in math functions.
[ROCm/hip commit: e17ade3afb
2018-05-01 12:29:03 +05:30
b272e57c33
Merge pull request #410 from gargrahul/hipCtx_deprecation_warning
...
Mark hipCtx APIs as deprecated
[ROCm/hip commit: caa13f98ed
2018-05-01 12:23:22 +05:30
93fc0a8312
Merge pull request #406 from gargrahul/fix_tex1D_coordinate_type
...
Resolve tex1D float to int conversion issue
[ROCm/hip commit: 365d155774
2018-05-01 09:18:11 +05:30
c1b94eb29f
Fix gcc build issues for host code
...
[ROCm/hip commit: 639001933c
2018-04-25 12:30:11 +05:30
16d2b986aa
Checkin to fix bugs in math functions.
...
This change fixes the following bugs that were discovered while debuggnig TF unit test failures (cwise_ops_test)
1. __hisinf and __hisnan routines
Both had incorrect implementations.
2. abs
A "long long" (64bit int) version was missing, resulting in the 32bit version being used for 64bit ints (which resulted in incorrect results, when the value passed in was outside the 32bit int range)
3. lgamma
We seemed to have a custom version for the 'double' datatype (which was giving incorrect results). Replaced it with a call to the 'double' version of the underlying 'hc::precision_math::lgamma'
[ROCm/hip commit: af586bbbf2
2018-04-24 18:10:07 +00:00
c4df5688c4
Moved deprecated macro to the end
...
[ROCm/hip commit: 19cb6c61ab
2018-04-20 21:57:23 +05:30
3b4875ba77
Mark hipCtx APIs as deprecated
...
[ROCm/hip commit: a039dbf2dd
2018-04-20 17:34:48 +05:30
80d7e34418
Resolve tex1D float to int conversion issue
...
[ROCm/hip commit: ffe18d1505
2018-04-18 14:15:18 +05:30
e1e88f3bff
Added hipMemset2DAsync support
...
[ROCm/hip commit: 3cfb9c0d40
2018-04-17 18:27:27 +05:30
29c54aa96a
Merge pull request #395 from lmoriche/master
...
Add missing __device__ function attributes.
[ROCm/hip commit: bda18af06d
2018-04-12 14:51:32 +05:30
3d9e3019d0
Add missing __device__ function attributes.
...
[ROCm/hip commit: 211c18e674
2018-04-11 09:29:37 -07:00
9d80544e28
Merge pull request #388 from lmoriche/master
...
Add support for clang offload bundles and <<<>>> kernel launch.
[ROCm/hip commit: ac7c5dfd0b
2018-04-09 12:40:28 +05:30
83343a2bba
adjust the hcc work week for the texture fix
...
[ROCm/hip commit: f48e471dd4
2018-04-06 15:46:55 -04:00
de2f2a87ff
Don't include __clang_cuda_builtin_vars.h
...
[ROCm/hip commit: bc6fa2bc62
2018-04-05 16:27:05 -07:00
9e1d2064c9
Add support for clang offload bundles and <<<>>> kernel launch.
...
[ROCm/hip commit: 0c1893ea62
2018-04-04 13:32:33 -07:00
e5e0efe002
Fix texture driver api TRFS flags
...
[ROCm/hip commit: 62fc6c85e0
2018-04-02 21:47:20 +05:30
3f0fa73342
Change constant address space to 4
...
when compiling with a newer hcc. This is
due to a recent change to address space
mapping in the amdgpu compiler backend.
[ROCm/hip commit: 0d8b97274a
2018-03-26 18:13:59 -04:00
Maneesh Gupta
Alex Voicu
Yaxun (Sam) Liu
Rahul Garg
Jorghi12
founta
Siu Chi Chan
Deven Desai
Laurent Morichetti