Commit Graph

164 Commits

Author SHA1 Message Date
Michael LIAO eb43303d0b [Device Function] Fix implementation of __bitinsert_u64
- It's a common mistake by assuming 1 << shamt would be promoted to
  64-bit, if shamt is a 64-bit integer. That's not the case. Replace
  that left shift to a 64-bit one to ensure it won't fall into undefined
  behavior.
- Fix the host-side implementation as well for device function testing.


[ROCm/clr commit: 2380eb8ecc]
2019-04-30 08:59:13 -04:00
Aaron Enye Shi 859c3bc699 Fix mixed dot for Jenkins rocm_2_0
[ROCm/clr commit: 2ab6fd374c]
2019-01-24 22:48:35 +00:00
Aaron Enye Shi d54135c38d Exclude mixed dot functions from nvcc path
[ROCm/clr commit: 77de87d0cd]
2019-01-24 21:00:45 +00:00
Aaron Enye Shi 5024e71039 Fix mixed dot for Jenkins rocm_head
[ROCm/clr commit: a014668d3a]
2019-01-23 16:39:25 +00:00
Aaron Enye Shi 0e1860dd53 Add tests for dot functions
[ROCm/clr commit: bbe5a0381f]
2019-01-22 22:32:28 +00:00
Maneesh Gupta e7195f7dc2 Update hipAsynchronousStreams.cpp
This test needs to be excluded from nvcc platform

[ROCm/clr commit: 79251fc4e2]
2019-01-07 09:26:21 +05:30
Sameer Sahasrabuddhe 0a99432a01 introduce test for asynchronous streams
This test is identical to the HCC tests under
tests/Unit/OCKL/AsyncStreams, but only for synchronous operation.


[ROCm/clr commit: 39574dba4c]
2019-01-04 05:51:50 -05:00
Aaron Enye Shi 56262f0970 Add *_rn functions back into HIP intrinsics
Add back the round-to-nearest-even intrinsics back to HIP math
intrinsics as it caused regression.


[ROCm/clr commit: 2d50392c17]
2018-12-18 19:31:54 +00:00
Michael Kuron 4b77b5c1ba Merge branch 'master' into getsymboladdress
[ROCm/clr commit: e9b88711e2]
2018-11-20 12:03:22 +01:00
Aaron Enye Shi 890beb81d6 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.


[ROCm/clr commit: 7b3bbc85c5]
2018-11-06 19:53:28 +00:00
Aaron Enye Shi 4480bb6d06 Guard the OCML rounded operations instead
Instead of commenting all these functions out, guard the functions with a macro OCML_BASIC_ROUNDED_OPERATIONS.


[ROCm/clr commit: 9aa92238ab]
2018-11-06 16:32:14 +00:00
Michael Kuron 35227acd6d Test for hipGetSymbolSize and hipGetSymbolAddress
[ROCm/clr commit: fe2281f101]
2018-11-06 11:39:34 +01:00
Aaron Enye Shi 5c1dc7a071 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.


[ROCm/clr commit: cef6e8ef1f]
2018-11-05 22:34:16 +00:00
Alex Voicu c505c2be38 Re-sync with upstream.
[ROCm/clr commit: 602280eb8b]
2018-10-18 12:27:03 +01:00
Maneesh Gupta 50e89b0a30 Replace hipLaunchKernel -> hipLaunchKernelGGL
Change-Id: I4d99009e1199811d417becf1e1b934ec4d4e30be


[ROCm/clr commit: e1fe095471]
2018-10-17 14:32:25 +05:30
Alex Voicu f3495964ea Minimal should mean minimal.
[ROCm/clr commit: 217fe345ca]
2018-10-11 00:21:41 +01:00
Alex Voicu 0e5f21c96b Trailing whitespace is still not the final frontier.
[ROCm/clr commit: 7874ec8aaf]
2018-10-11 00:08:09 +01:00
Alex Voicu 50388a3bd1 Re-sync with upstream.
[ROCm/clr commit: 9ec697c620]
2018-10-10 11:43:49 +01:00
Maneesh Gupta 27986e6788 Merge pull request #685 from ROCm-Developer-Tools/hip-trig-return
Improve hip_trig test case

[ROCm/clr commit: 802520f5f1]
2018-09-26 09:50:48 +05:30
Aaron Enye Shi 20e9391cfb Use trig functions from ocml instead
[ROCm/clr commit: 04ed44f074]
2018-09-25 15:58:36 +00:00
Aaron Enye Shi 4bbfaf06b5 Fix missing HIP_ASSERT in hip_trig
[ROCm/clr commit: bc5de031a5]
2018-09-24 15:01:24 +00:00
Maneesh Gupta 0d75b78a5a Merge pull request #683 from ROCm-Developer-Tools/hip-float-rounded
Disable non-default-rounded functions

[ROCm/clr commit: ad008c5e3f]
2018-09-24 09:32:52 +05:30
Aaron Enye Shi f4fc30ccc7 Improve hip_trig test case
Hip_trig is failing but returning a passing value on HIP-Clang.  Also update with debug output and free arrays used.

[ROCm/clr commit: afef6a3ece]
2018-09-21 15:28:10 -04:00
Maneesh Gupta 203e3dd5d5 Update hipTestFMA.cpp
[ROCm/clr commit: a4bdbe0aaf]
2018-09-21 11:00:08 +05:30
Aaron Enye Shi 646de2e876 Disable non-default-rounded functions
Device library has removed the non-default-rounded functions, so hipFloatMath will fail to build. These include the removal of __ocml_sqrt_rte, __ocml_sqrt_rtn, __ocml_sqrt_rtp, and __ocml_sqrt_rtz. As seen here: https://github.com/RadeonOpenCompute/ROCm-Device-Libs/commit/2fc04e10e1354edee331ce700f98a60f8255effb . Disable these function tests for now, until they are re-enabled, or deleted completely.

[ROCm/clr commit: a3dea28c9d]
2018-09-20 16:33:32 -04:00
Maneesh Gupta f742125288 Update hipTestFMA.cpp
Fix the test so that it works on nvcc path as well.

[ROCm/clr commit: e614aac0da]
2018-09-20 11:23:51 +05:30
Yaxun Sam Liu a7b03bee08 Add fma function with float and _Float16 arguments
[ROCm/clr commit: a8bed200b7]
2018-09-19 09:59:33 -04:00
Maneesh Gupta 0bae7eaad3 [dests] Fix hipTestClock, hipTestNew & hipTestGlobalVariable tests for nvcc
nvcc does not support global kernels in struct/class

Change-Id: I2d7297e0c3725564215e20dbdd31c0bb8d7a07de


[ROCm/clr commit: f63ffaf6e5]
2018-09-17 15:32:05 +05:30
Maneesh Gupta 6e7f871105 [dtests] Fix deviceLib/hipSimpleAtomicsTest for nvcc
Change-Id: I23cbea2820d41da6f6a1bcab4bc3b59ac21799dd


[ROCm/clr commit: 7066147760]
2018-09-17 15:26:45 +05:30
Maneesh Gupta 51f5e9ea04 [dtests] Fix deviceLib/hipTestIncludeMath on nvcc path
Change-Id: Ifb121886bec6c1134e98bd194ff1713f28454d33


[ROCm/clr commit: 644fc85a37]
2018-09-17 15:15:49 +05:30
Alex Voicu f5d204450c Align with HC Next.
[ROCm/clr commit: 26c26f63cb]
2018-09-17 11:50:29 +03:00
Maneesh Gupta 20abaa15c4 Merge branch 'master' into support-malloc
[ROCm/clr commit: b23609ad42]
2018-09-17 10:17:25 +05:30
Yaxun (Sam) Liu dabbf3771b Support placement new in hip-clang
[ROCm/clr commit: cc0fbc0e2e]
2018-09-04 16:53:46 -04:00
Maneesh Gupta 7891e7423d Merge pull request #657 from yxsamliu/fix-clz
Fix ambiguity of __clz and __clzll

[ROCm/clr commit: 6dfb6fac8b]
2018-09-03 16:34:42 +05:30
Maneesh Gupta 7b45626603 Merge pull request #651 from yxsamliu/hip-clang-clock
Add clock() and clock64()

[ROCm/clr commit: d515998ac4]
2018-09-03 16:32:30 +05:30
Yaxun Sam Liu 1da85d8537 Fix ambiguity of __clz and __clzll
[ROCm/clr commit: 701519d27d]
2018-08-31 18:07:57 -04:00
Aaron Enye Shi 31864c4973 Remove testing bitinsert/extract on nvcc path
[ROCm/clr commit: ecfb2bdeba]
2018-08-29 15:29:53 +00:00
Yaxun Sam Liu 137880f369 Add clock() and clock64()
[ROCm/clr commit: 0f4546deca]
2018-08-29 10:51:00 -04:00
Aaron Enye Shi 7801c309b3 Add tests for bitextract and bitinsert
[ROCm/clr commit: 622342f01d]
2018-08-28 20:01:54 +00:00
Yaxun Sam Liu d3295e61e2 Fix __HIP_ARCH_* not defined after including math_functions.h
hcc_detail/math_functions.h used to include hcc_detail/hip_runtime.h.

Removing it has caused regression in TensorFlow 1.8.

Put it back for backward compatibiliity.


[ROCm/clr commit: 87de95975a]
2018-08-08 08:55:28 -04:00
Yaxun Sam Liu 6e153a743f Fix __HIP_DEVICE_COMPILE__ not defined when hip/math_functions.h is included
This fixes build failure in TensorFlow 1.8 for HCC


[ROCm/clr commit: 058eb7535b]
2018-08-07 17:14:39 -04:00
Yaxun Sam Liu 6df5aef807 Fix declaration conflict when hip/math_functions.h is included first
This fixes build failure in TensorFlow 1.8 for HCC


[ROCm/clr commit: 69bbf45b44]
2018-08-07 15:44:59 -04:00
Yaxun Sam Liu d539617d9b Do not use std::complex in test hipDeviceMalloc
[ROCm/clr commit: fc1ed91ddb]
2018-07-27 17:07:00 -04:00
Yaxun Sam Liu ea77788a5f Fix thread index calculation in __hip_malloc
[ROCm/clr commit: f08f26942c]
2018-07-27 16:24:51 -04:00
Yaxun Sam Liu 9a4744566f Support malloc/free for hip-clang
[ROCm/clr commit: d17dc21c9c]
2018-07-27 16:24:51 -04:00
Brian Sumner beb7f13068 Drop use of NVCC_COMPAT since it is always set
[ROCm/clr commit: 8d80abb30f]
2018-07-27 09:29:29 -07:00
Maneesh Gupta 951d920990 Merge pull request #595 from mangupta/patch4-fixhipStdComplex
[tests] Fixed build & disabled run of hipStdComplex on nvcc path

[ROCm/clr commit: 86188f04c8]
2018-07-26 06:17:04 +05:30
Maneesh Gupta 7033561423 [tests] Fixed build & disabled run of hipStdComplex on nvcc path
Change-Id: I885e96902faa065f6559183f33b6a7aa1f37e393


[ROCm/clr commit: 843020bfe6]
2018-07-25 15:39:45 +05:30
Aaron Enye Shi 6353687511 Fix return EXIT_FAILURE if ballot or anyall fails
[ROCm/clr commit: 8ab8a37812]
2018-07-24 20:39:48 +00:00
Maneesh Gupta 746e56a61b Merge pull request #543 from ROCm-Developer-Tools/add-std-complex
Support std::complex for hip-clang

[ROCm/clr commit: 5632faf928]
2018-07-19 07:14:45 +05:30