17453a6278
Implement hip_ldg Functions into HIP header
...
Move all the function definitions for hip_ldg.cpp into hip_ldg.h header and enable for HIP clang path.
[ROCm/hip commit: 76f86ef097
2018-07-05 20:38:46 +00:00
8e1a7fdd09
Implement min/max functions in HIP header
...
Remove using hc::precise_math min and max. Instead we can use ocml directly for device and std:: for host.
[ROCm/hip commit: 47d78e372e
2018-07-05 20:15:41 +00:00
0ea959ba9d
Implement Memory Fence Functions in header
...
Enabled __llvm_fence_* functions for seq_cst.
[ROCm/hip commit: 930a16bccd
2018-07-04 23:35:24 +00:00
6bcb3cca86
Workaround cast warning of smaller integer type for __to_local
...
For now, guard the __to_local function for device compile only since a local pointer should be same size as unsigned int on GPU compile. Also change to void* instead of char*.
[ROCm/hip commit: 07de5cb334
2018-07-04 20:52:55 +00:00
e8fac0449e
Merge branch 'master' into hipclang-add-amdgcn-funcs
...
[ROCm/hip commit: 2975f2a10a
2018-07-04 17:36:08 +00:00
a4eb081242
Merge pull request #530 from ROCm-Developer-Tools/hipclang-compute-mode
...
Add HIP Compute Mode
[ROCm/hip commit: 4b4d78fdb1
2018-07-04 10:55:48 +05:30
a31dc511f9
Merge pull request #503 from ROCm-Developer-Tools/fix-complex
...
Fix hip_complex.h
[ROCm/hip commit: 2ce48fbc05
2018-06-28 12:15:22 +05:30
e3996a5e16
Merge pull request #495 from ROCm-Developer-Tools/hip-clang-upstream
...
add more device functions for hip-clang
[ROCm/hip commit: 76b2d0f82d
2018-06-28 11:42:01 +05:30
fe5afd44f4
Fix typo
...
[ROCm/hip commit: dde875f23b
2018-06-28 11:19:22 +05:30
bf2a6352b7
Merge pull request #536 from ROCm-Developer-Tools/hotfix_remove_unimplemented_math
...
Removes use of unimplemented OCML functionality.
[ROCm/hip commit: 525716bf91
2018-06-28 11:15:57 +05:30
6e2ee0f857
Implement __shfl_* funcs into HIP headers
...
[ROCm/hip commit: 9ac31e0bb6
2018-06-26 18:32:11 +00:00
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
9fed6fed2b
Removes use of unimplemented OCML functionality.
...
[ROCm/hip commit: 6c7a64efa2
2018-06-25 19:16:27 +01:00
260e50769b
Add HIP Compute Mode
...
[ROCm/hip commit: ff924ecb3d
2018-06-22 14:37:19 +00:00
20674cfcb2
Replace __hip_hc_ir_ inline asm with __ockl_* functions
...
[ROCm/hip commit: 8ac864c2e3
2018-06-20 20:40:14 +00:00
e2f8af2f3d
Implement __ballot, __any, __all into HIP headers
...
[ROCm/hip commit: 6dc16bbf04
2018-06-20 17:39:39 +00:00
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
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
14f721702a
Move hipclang funcs into corresponding headers
...
[ROCm/hip commit: fe4e6c53fc
2018-06-20 17:39:15 +00:00
8d65776127
Split __llvm and device lib funcs into new headers
...
[ROCm/hip commit: cfe37484c9
2018-06-20 17:39:06 +00:00
cb46df1654
Add get_dynamicgroupbaseptr def and remove hc_
...
[ROCm/hip commit: 27f600b425
2018-06-20 17:38:59 +00:00
9b03a036c3
Add prefix __ to memory scope and order
...
[ROCm/hip commit: 871cfc6fd2
2018-06-20 17:38:52 +00:00
cdd7931ac1
Add __llvm_fence funcs and __ prefixes
...
[ROCm/hip commit: cfa8fc1ca5
2018-06-20 17:38:45 +00:00
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
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
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
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
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
b8ae2784e9
Add conj, operator-,==,!= for hipFloatComplex/hipDoubleComplex
...
[ROCm/hip commit: 84da72dae8
2018-06-19 10:49:59 -04:00
a46f62a5c0
Add abs/real/imag functions for hipFloatComplex/hipDoubleComplex
...
[ROCm/hip commit: 9181fbb0b7
2018-06-18 11:57:57 -04:00
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
0e29f327e2
Includes <cmath> or <math.h> by __cplusplus in hip_complex.h
...
[ROCm/hip commit: 2523c39a37
2018-06-17 20:20:32 -04:00
cf6cdab029
Include cmath instead of math.h in hip_complex.h
...
[ROCm/hip commit: 325cf3ccf0
2018-06-17 20:20:32 -04:00
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
494d34f4ee
added missing hipCmul() to nvcc_detail/hip_complex.h
...
[ROCm/hip commit: 0b1e698e74
2018-06-14 21:49:54 +02:00
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
a6fb892e43
Merge pull request #506 from ROCm-Developer-Tools/fix-extern-shared
...
Add support of extern __shared__ for hip-clang
[ROCm/hip commit: e0400674fd
2018-06-11 11:59:58 +05:30
3792417463
Revert "Switch over to using native vector types, for better codegen. Remove noise."
...
[ROCm/hip commit: 7a4aace13d
2018-06-08 16:48:22 -04:00
8e6b72b04d
Add __device__ to device functions in hip_fp16_math_fwd.h
...
[ROCm/hip commit: 17e3093f0e
2018-06-08 11:23:52 -04:00
11ad6077ae
Add more function declarations for hip-clang
...
[ROCm/hip commit: d726ba1d9a
2018-06-08 11:20:42 -04:00
a96a56a986
Fix channel_descriptor.h about vector 3 for gcc
...
[ROCm/hip commit: 9141037105
2018-06-08 11:18:41 -04:00
2f017c1200
Add support of extern __shared__ for hip-clang
...
[ROCm/hip commit: cc14ed0981
2018-06-08 11:17:25 -04:00
b54be20b05
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/hip commit: 203dd6cb70
2018-06-06 16:07:22 +05:30
52eee341cc
Merge pull request #496 from gargrahul/add_gettexresdesc_nvcc
...
Add getTextureResourceDescriptor on NVCC
[ROCm/hip commit: 02ea7f13b3
2018-06-06 15:12:11 +05:30
ddbf7f1028
Merge pull request #487 from gargrahul/fix_hiparray_alloc_flag_nvcc
...
Map hipArray alloc flags on NVCC
[ROCm/hip commit: de5043c47c
2018-06-06 15:11:40 +05:30
522677e2dd
Add getTextureResourceDescriptor on NVCC
...
[ROCm/hip commit: 17bb8dbe86
2018-06-05 18:46:25 +05:30
6b3d95c2f6
Fix hideous typos.
...
[ROCm/hip commit: 23f5feaf13
2018-06-03 03:03:55 +01:00
192839c71b
Add missing __device__ for forward declares.
...
[ROCm/hip commit: 59adb5e52a
2018-06-02 17:46:37 +01:00
f7fd20ec17
Switch the atomic implementation to use Clang builtins.
...
[ROCm/hip commit: 089ab3b947
2018-06-02 12:27:17 +01:00
07115e0c02
Add integrated device property
...
[ROCm/hip commit: 1a02bc364f
2018-06-02 13:11:16 +05:30
Aaron Enye Shi
Maneesh Gupta
Yaxun (Sam) Liu
Alex Voicu
Nico Trost
Wen-Heng (Jack) Chung
Siu Chi Chan
Rahul Garg