2d50392c17
Add *_rn functions back into HIP intrinsics
...
Add back the round-to-nearest-even intrinsics back to HIP math
intrinsics as it caused regression.
2018-12-18 19:31:54 +00:00
4251a70bc0
Revert "Rely on code object metadat for kernarg arguments alignof and sizeof."
...
This reverts commit 299b9d1382
2018-11-29 11:38:37 -05:00
30a9be5643
Revert "Handle (odd) corner case of argumentless __global__ function."
...
This reverts commit 927b06f8d4
2018-11-29 11:38:34 -05:00
99bb89b756
Merge pull request #760 from eshcherb/roctracer-hip-frontend-181113
...
Roctracer hip frontend 181113
2018-11-23 11:08:25 +05:30
e9b88711e2
Merge branch 'master' into getsymboladdress
2018-11-20 12:03:22 +01:00
f71b8cbc7d
Fix hipGetSymbolAddress/hipGetSymbolSize on nvcc
2018-11-15 09:48:00 +01:00
0c72d32b44
Merge pull request #756 from yxsamliu/fix-heap
...
Define __hip_device_heap in header for hip-clang only
2018-11-14 13:22:31 +05:30
0774b275c8
rebase to master, tracer related changes
2018-11-13 15:50:34 +00:00
1e49cff87a
specialized spawner object
2018-11-13 15:33:26 +00:00
e362688adf
renaming HIP_INIT_CB_API to HIP_INIT_API
2018-11-13 15:33:26 +00:00
8c88932f30
hip_prof_(api/str).h moving under hcc_detail dir
2018-11-13 15:33:26 +00:00
d35567f40a
compilation fix - struct name fix
2018-11-13 15:33:26 +00:00
2f2c955ae0
fix
2018-11-13 15:33:26 +00:00
084a68be63
adding activity prof layer
2018-11-13 15:33:26 +00:00
c44f2795d5
Define __hip_device_heap in header for hip-clang only
2018-11-12 16:39:41 -05:00
927b06f8d4
Handle (odd) corner case of argumentless __global__ function.
2018-11-12 00:32:35 +00:00
392e2ba1ba
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_get_alignment_and_size_from_metadata
2018-11-08 06:53:06 -08:00
7b3bbc85c5
Guard rcp rounded implementation as well
...
Since rcp implementations of non-default rounded versions are not correct or supported in OCML, guard them using the same macro OCML_BASIC_ROUNDED_OPERATIONS. Also update the docs and tests.
2018-11-06 19:53:28 +00:00
9aa92238ab
Guard the OCML rounded operations instead
...
Instead of commenting all these functions out, guard the functions with a macro OCML_BASIC_ROUNDED_OPERATIONS.
2018-11-06 16:32:14 +00:00
4da2d92281
Introduce ihipModuleGetGlobal
2018-11-06 09:54:34 +01:00
cef6e8ef1f
Remove non-working non-default-rounded math apis
...
In ROCm-Device-Libs, they have dropped the non-default-rounded versions of add, sub, mul, div, sqrt and fma. Therefore, ocml has removed the rte, rtp, rtn, and rtz counterparts. This will remove the same math APIs in HIP for _ru, _rd, _rn, and _rz.
2018-11-05 22:34:16 +00:00
8049cdafab
Document return values of hipMemcpyToSymbol, hipGetSymbolAddress
2018-11-04 11:47:17 +01:00
0b6f5791f8
Implement hipGetSymbolAddress and hipGetSymbolSize
2018-11-04 10:39:34 +01:00
1c525d7222
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_get_alignment_and_size_from_metadata
2018-11-01 23:17:27 +00:00
cdd0109e70
Move the global arrays for hip malloc/free
...
from a header into a source file such that
there's only an unique copy in an executable
and prevent wasting static memory on the host
Change-Id: Id5b62766f77809c8d7b47892cb7149c490dcbdb9
2018-11-01 16:20:35 -04:00
6eac038694
typedef struct hipFuncAttributes now C compatible.
...
Fixes #591 .
Fixes #694 .
2018-10-31 14:12:45 +05:30
c7f2198c6e
Merge pull request #714 from aaronenyeshi/remove-static-hip-device
...
Remove libhip_device.a static library
2018-10-31 14:08:29 +05:30
8f667984af
Merge pull request #713 from scchan/master-hcc_early_finalize_support
...
Support more than one device code blobs in a single .kernel section
2018-10-31 14:04:06 +05:30
000766850d
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_get_alignment_and_size_from_metadata
2018-10-30 23:34:46 +00:00
b68caf7653
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_get_alignment_and_size_from_metadata
2018-10-28 17:02:10 +00:00
299b9d1382
Rely on code object metadat for kernarg arguments alignof and sizeof.
2018-10-28 17:01:00 +00:00
ba43d1ce1b
Remove libhip_device.a static library
...
Move remaining function definitions from device_util.cpp to hip_runtime.h header. We can now remove the static library completely as device_util.cpp was the last file part of target hip::hip_device .
2018-10-25 19:52:35 +00:00
a743939900
hipLaunchKernel, hipLaunchParm are deprecated, and shall be removed.
2018-10-25 13:32:17 +01:00
05beeec84d
Merge pull request #723 from mangupta/fix_double_shfl
...
Fix logic for double variants of __shfl*
2018-10-25 06:01:38 +05:30
7b6d232672
Fix logic for double variants of __shfl*
...
Change-Id: I604f00b54cf4bd9c5f26ca6fa680fca5e9629417
2018-10-24 12:39:09 +05:30
b01ac26948
Make HIP functional again with HCC from ROCm 1.9.x
...
Change-Id: I214acdfd0b79dcf783993e44fe31baee64fd4dc3
2018-10-24 10:41:56 +05:30
407e092a13
Merge pull request #705 from ROCm-Developer-Tools/feature_minimal_changes_for_hc_next
...
Feature minimal changes for hc next
2018-10-19 06:58:31 +05:30
f39873c584
Support more than one bundles in a single .kernel section
...
When compiling with Early Finalization enabled in HCC,
the resulting .kernel section of the host object now may
contain more than one device code bundles. This is to
teach the HIP runtime to correctly extract all the
bundles from the .kernel section.
2018-10-18 17:00:27 -04:00
3678063598
Dumb workaround is still needed, so add it back.
2018-10-18 15:33:46 +01:00
602280eb8b
Re-sync with upstream.
2018-10-18 12:27:03 +01:00
30523b72a2
Merge pull request #688 from aaronenyeshi/fix-sinf-cosf-ocml
...
Use sinf and cosf from ocml device libs
2018-10-18 16:39:20 +05:30
9143ae6bdb
Merge pull request #692 from whchung/hip-reinit-take2
...
HIP program state re-initialization logic (take 2)
2018-10-18 12:06:41 +05:30
95be669f4a
Merge pull request #703 from mangupta/stream_create_with_priority
...
Implementation for stream priority
2018-10-17 10:53:43 +05:30
3485d86746
Merge pull request #702 from aaronenyeshi/fix-missing-irif-lib
...
Replace IRIF fences with atomic_work_item_fence
2018-10-17 10:53:27 +05:30
d71006eb99
Add missing hipHostRegister flags on nvcc path
...
Change-Id: I69f09204d9c544935104d4168ab8d3626666a623
2018-10-15 15:30:24 +05:30
217fe345ca
Minimal should mean minimal.
2018-10-11 00:21:41 +01:00
b2b482c78e
Address Aaron's comments
2018-10-11 00:03:01 +01:00
c564ccbffc
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into feature_minimal_changes_for_hc_next
2018-10-10 11:44:09 +01:00
9ec697c620
Re-sync with upstream.
2018-10-10 11:43:49 +01:00
07ee1f07d8
Implementation for stream priority
...
- Requires ROCm 1.9.x or higher
- Requires HCC with PR#886 merged
Change-Id: Id7c95ea091ee610e80c9ad815f1cb989cba570ca
2018-10-05 16:27:46 +05:30
Aaron Enye Shi
Siu Chi Chan
Maneesh Gupta
Michael Kuron
root
Evgeny
Yaxun Sam Liu
Alex Voicu
Michael Kuron
Jeff Daily