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
6f0cc9efa0
Merge 'master' into 'amd-master'
...
Change-Id: Ia897c694ffbbce2ab01493d3ea60e42701ce021e
[ROCm/clr commit: 8b4feff6e2
2018-06-20 04:09:40 -05:00
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
8852a00b64
P4 to Git Change 1570469 by johtaylo@johtaylo-jtincrementor2-increment on 2018/06/20 03:00:04
...
SWDEV-2 - Change OpenCL version number from 2677 to 2678.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2425 edit
[ROCm/clr commit: e7b38959a2
2018-06-20 03:11:11 -04:00
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
3a13de082e
P4 to Git Change 1570202 by gandryey@gera-w8 on 2018/06/19 13:58:38
...
SWDEV-155436 - Write dispatch dimensions to COMPUTE registers for OpenCL support for RGP
- Add the dispatch dimensions to the RGP trace
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palgpuopen.hpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#111 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#290 edit
[ROCm/clr commit: 64fd3e50a0
2018-06-19 14:06:00 -04:00
2d187d848a
P4 to Git Change 1570186 by gandryey@gera-w8 on 2018/06/19 13:20:24
...
SWDEV-150518 - [IQE][DG2018][I+eA][SSG] System hangs when trying to preview cache video to AMD SSG
- Disable optimization for "disabled deferred allocations" in SSG path. There is an extra logic to support double copy transfers with allocations in the invisible heap. It's not an official requirement for the SSG extension and hasn't been tested, but Adobe utilizes that path.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#89 edit
[ROCm/clr commit: f67ed6630e
2018-06-19 13:28:44 -04:00
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
c51a2daa95
P4 to Git Change 1570053 by jatang@jatang-opencl-hsa-stg5 on 2018/06/19 09:47:32
...
SWDEV-155306 - Restore ClockMode when the last queue is destroyed.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#110 edit
[ROCm/clr commit: 8d82c5e97b
2018-06-19 09:53:09 -04:00
eb6fb65f26
Merge 'master' into 'amd-master'
...
Change-Id: I539a79195161876b0a6eae952f64af85d4c47b28
[ROCm/clr commit: 2ee0f5310b
2018-06-19 04:09:57 -05:00
64b4f4101f
added option HIP_BUILD_VERBOSE to enable verbosity in HIP build
...
[ROCm/clr commit: bdfd6957aa
2018-06-19 13:50:24 +05:30
fc1737739c
P4 to Git Change 1569929 by johtaylo@johtaylo-jtincrementor2-increment on 2018/06/19 03:00:05
...
SWDEV-2 - Change OpenCL version number from 2676 to 2677.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2424 edit
[ROCm/clr commit: 956ec86f42
2018-06-19 03:15:24 -04:00
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
fc5992d539
P4 to Git Change 1569647 by gandryey@gera-lnx-rcf-lc on 2018/06/18 14:04:00
...
SWDEV-79445 - OCL generic changes and code clean-up
-Following CL#1568521. Correct LDS size look-up.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#57 edit
[ROCm/clr commit: 1e1aa59aed
2018-06-18 14:15:59 -04:00
1709777f1b
Add abs/real/imag functions for hipFloatComplex/hipDoubleComplex
...
[ROCm/clr commit: 0de3ef7b32
2018-06-18 11:57:57 -04:00
c1f37d4fb5
Merge pull request #521 from gargrahul/temp_fixmemcpy2dasync_trsmissue
...
Use memcpy kernel for all pinned memory cases in hipMemcpy2DAsync
[ROCm/clr commit: d30f3f0c88
2018-06-18 09:34:02 +05:30
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
237990a06a
P4 to Git Change 1569377 by johtaylo@johtaylo-jtincrementor2-increment on 2018/06/17 03:00:05
...
SWDEV-2 - Change OpenCL version number from 2675 to 2676.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2423 edit
[ROCm/clr commit: e9aafc3e93
2018-06-17 03:10:08 -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
1829ba2e3f
P4 to Git Change 1568675 by johtaylo@johtaylo-jtincrementor2-increment on 2018/06/15 03:00:05
...
SWDEV-2 - Change OpenCL version number from 2674 to 2675.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2422 edit
[ROCm/clr commit: ccd4fe1653
2018-06-15 03:11:00 -04:00
0f582a7893
Made changes as suggested.
...
[ROCm/clr commit: 936b878d72
2018-06-15 11:30:02 +05:30
b1d3182703
P4 to Git Change 1568521 by gandryey@gera-w8 on 2018/06/14 17:43:52
...
SWDEV-79445 - OCL generic changes and code clean-up
- Change LDS setup to account the size, since LC forces 4 bytes for LDS offsets always
http://ocltc.amd.com/reviews/r/15197/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#130 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#327 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#109 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.hpp#11 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#38 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#34 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#25 edit
[ROCm/clr commit: d2b85cc118
2018-06-14 17:51:35 -04:00
7e6f2cf63b
P4 to Git Change 1568521 by gandryey@gera-w8 on 2018/06/14 17:43:52
...
SWDEV-79445 - OCL generic changes and code clean-up
- Change LDS setup to account the size, since LC forces 4 bytes for LDS offsets always
http://ocltc.amd.com/reviews/r/15197/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpublit.cpp#130 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpukernel.cpp#327 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palblit.cpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#109 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocblit.hpp#11 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#38 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.cpp#88 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.cpp#34 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/kernel.hpp#25 edit
[ROCm/clr commit: f6d8feabeb
2018-06-14 17:51:35 -04:00
cf0a8d99de
P4 to Git Change 1568474 by asalmanp@asalmanp-ocl-stg on 2018/06/14 16:29:06
...
SWDEV-132899 - [OCL][GFX10] OCLGLDepthTex[0] and OCLGLDepthTex[4] subtests of OCLTST/OCLGL are failing on gfx10 Emulator
extending the Depth24_Stencil8 workaround for gfx10 based on gfx10 Image SRDs
ReviewBoardURL = http://ocltc.amd.com/reviews/r/15194/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#67 edit
[ROCm/clr commit: c149902a4d
2018-06-14 16:39:10 -04:00
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
f523f6a066
Merge 'master' into 'amd-master'
...
Change-Id: Ife0db35b29ac732ba661499de009ada0456df724
[ROCm/clr commit: 379214d251
2018-06-14 04:09:37 -05:00
912c090d93
P4 to Git Change 1568143 by johtaylo@johtaylo-jtincrementor2-increment on 2018/06/14 03:00:06
...
SWDEV-2 - Change OpenCL version number from 2673 to 2674.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2421 edit
[ROCm/clr commit: 32add1a1c0
2018-06-14 03:13:46 -04:00
15a1689939
Merge pull request #519 from gargrahul/fix_memcpy2dasync_streamres
...
Fix stream resolution in memcpy2dasync
[ROCm/clr commit: edab13da7d
2018-06-14 12:34:32 +05:30
a41cb78337
Fix stream resolution in memcpy2dasync
...
[ROCm/clr commit: 2ae3be9773
2018-06-14 11:58:56 +05:30
ea9fae9ca2
Merge pull request #518 from gargrahul/fix_pr_484_devptroffset
...
Fix retrieved locked ptr offset
[ROCm/clr commit: f5fccba009
2018-06-14 07:37:34 +05:30
Aaron Enye Shi
Jenkins
Maneesh Gupta
foreman
Yaxun (Sam) Liu
pradeepisro
Wen-Heng (Jack) Chung
Alex Voicu
Rahul Garg
Lakhan Singh
Nico Trost