54aca29012
update the hipify-perl
...
[ROCm/clr commit: d805e98fcb
2020-01-31 14:36:37 -05:00
cbefd62db9
code clean up
...
[ROCm/clr commit: 75572a4175
2020-01-31 13:08:25 -05:00
540a8d6337
Merge branch 'origin/pghafari/hip-vdi' into lmoriche/amd-master-next
...
Change-Id: I22c145d39f430ca571a981687bcb034ea6e3b8a2
[ROCm/clr commit: 2f1305b9a4
2020-01-31 07:33:12 -08:00
a6012c4bfb
[dtest] Avoid resViewDesc for non-array resource in texture creation ( #1823 )
...
[ROCm/clr commit: cb632005bc
2020-01-30 14:04:41 -08:00
2733df36b5
[HIP][HIPIFY] Add some missing flags for cooperative launch and occupancy APIs
...
[ROCm/clr commit: 6db9b782be
2020-01-30 15:05:53 -05:00
7f98f77350
Merge pull request #1700 from scchan/object_load_error_check
...
add error checking for code object loading
[ROCm/clr commit: f1c70ea6ba
2020-01-30 21:31:03 +03:00
bb38362f74
Merge HIP/VDI branch 'amd-staging' into lmoriche/amd-master-next
...
Change-Id: Iabaab4e72815ba483a1330ec6a1130f2b86676f0
[ROCm/clr commit: 6f3e18a764
2020-01-29 15:02:13 -08:00
2c6e880e05
Match Occupancy APIs syntax with CUDA ( #1625 )
...
* Match Occupancy APIs syntax with CUDA and fix tests using these APIs
[ROCm/clr commit: 262ad13dd5
2020-01-29 13:05:53 -08:00
4162b55dbe
Add missing texturePitchAlignment member to the hipDeviceProp_t struct. ( #1802 )
...
* Add missing texturePitchAlignment member to the hipDeviceProp_t struct.
* Add missing hipDeviceAttributeTexturePitchAlignment enumerator to the hipDeviceAttribute_t enum.
* Initialize texturePitchAlignment to 256. This works for gfx9+, but is technically overaligned in most cases for pre-gfx9.
* Add the texturePitchAlignment property to the NVCC path.
[ROCm/clr commit: 6da0c82b78
2020-01-27 16:37:00 -08:00
5f26aba8d4
Merge pull request #1820 from emankov/HIP
...
[HIPIFY] Update Readme.md
[ROCm/clr commit: e419d738e7
2020-01-27 17:23:06 +03:00
2011431f49
[HIPIFY] Update Readme.md
...
Restructure contents in order to have separated same-level information about hipify-clang and hipify-perl.
[ROCm/clr commit: 5a788eb048
2020-01-27 17:21:32 +03:00
ea7ee2b8ba
Merge pull request #1813 from emankov/HIP
...
[HIP][HIPIFY] Readmes actualization
[ROCm/clr commit: 37da8171bc
2020-01-27 12:50:48 +03:00
43ee24a0cf
[HIPIFY][ #1819 ] Fix for not found clang's system header files
...
Use absolute paths instead of relative ones.
[ROCm/clr commit: 5fae88f84b
2020-01-27 12:37:26 +03:00
cf5027de69
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into HIP
...
[ROCm/clr commit: e57c2b3147
2020-01-27 12:08:22 +03:00
f1747af7cd
Update the HIP_TRSF_* flags to match their Cuda equivalents. ( #1801 )
...
[ROCm/clr commit: e419a1609f
2020-01-24 11:41:15 -08:00
0f6cbe5ef2
Merge branch 'master' of https://github.com/ROCm-Developer-Tools/HIP into HIP
...
[ROCm/clr commit: 2b77ca7d2e
2020-01-24 16:14:16 +03:00
6fafadae75
Fix for a syntax error in deb packages ( #1814 )
...
[ROCm/clr commit: ef3dbc1f91
2020-01-24 16:23:47 +05:30
a49cbb1580
SWDEV-220503: this_grid().thread_rank() gives incorrect result ( #1808 )
...
* fix a minor bug while computing this.grid()::thread_rank()
[ROCm/clr commit: 0605426049
2020-01-24 16:23:28 +05:30
fec5105d9c
Fix install script syntax error ( #1805 )
...
Fix hip-nvcc install warning on postinstall and prerm script
[ROCm/clr commit: 5cd5c62f29
2020-01-24 16:22:57 +05:30
adb93af8c3
Fix associate code object symbols with host allocation bug ( #1799 )
...
The current implementation skips this procedure for a given device
object when a global symbol is found in the cache. This is incorrect:
- There could be other undefined globals that have not been previously
encountered further down the list
- If a symbol is found in the cache, it doesn't need to be pinned again
but it still need to be defined for the current executable
Added special case for the printf buffer symbol (already pinned by HCC)
The bug was exposed by running printf on different GPUs.
[ROCm/clr commit: 8fc7cad90f
2020-01-24 16:22:49 +05:30
64b531e782
Clear HIP_PATH before version detection ( #1786 )
...
Don't allow `HIP_PATH` to be propagated to `hipconfig`,
when run by CMake to detect the package version, as it
leads to the wrong version is detected: when there's
already HIP of some different version installed in the
system and `HIP_PATH` points to its location, `hipconfig`
tends to return the version of the installed HIP, rather
than the value defined for the distribution. The compiled
results report wrong version and spoils the rest of the
stack in this case.
[ROCm/clr commit: 9f5a4148ce
2020-01-24 16:21:49 +05:30
0b193b5b68
P4 to Git Change 2062258 by cpaquot@cpaquot-ocl-lc-lnx on 2020/01/23 16:04:59
...
SWDEV-145570 - [hip] hipMallocManaged
Basic implementation of hipMallocManaged behaving like hipHostMalloc for hipMemAttachGlobal.
Return hipErrorInvalidValue for the hipMemAttachHost for now.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.def.in#39 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#37 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#97 edit
[ROCm/clr commit: 1fe8cc8a7e
2020-01-23 16:13:57 -05:00
8274fd3723
[HIP][HIPIFY] Readmes actualization
...
[ROCm/clr commit: 0a380694c5
2020-01-23 20:55:10 +03:00
b4672ff210
Merge pull request #1812 from emankov/HIP
...
[HIPIFY][doc] Readme - update versions
[ROCm/clr commit: 9f40056297
2020-01-23 18:04:39 +03:00
f7d4d85a80
[HIPIFY][doc] Readme - update versions
...
[ROCm/clr commit: 85b76bac70
2020-01-23 18:01:48 +03:00
4cd70cf51e
Merge pull request #1811 from emankov/HIP
...
[HIPIFY][cmake] Formatting
[ROCm/clr commit: ea9307b60b
2020-01-23 17:48:52 +03:00
3c6f0c909f
[HIPIFY][cmake] Formatting
...
[ROCm/clr commit: 584ce03173
2020-01-23 17:47:11 +03:00
1f42d29c86
Merge pull request #1810 from emankov/HIP
...
[HIPIFY][cmake] Send error on CUDA 10.2 and higher as yet unsupported
[ROCm/clr commit: e563b67207
2020-01-23 17:29:38 +03:00
51f277ec96
[HIPIFY][cmake] Send error on CUDA 10.2 and higher as yet unsupported
...
[ROCm/clr commit: 9b739bfa15
2020-01-23 16:37:25 +03:00
b78b5fa7d4
Simplify hipDispatchLatency sample ( #1793 )
...
* Use hipExtLaunchKernelGGL in dispatchlatency sample
* Let it run on NVCC path too
* Refactoring
* Add test_kernel source
* Remove ResultDB
* Remove error checks
[ROCm/clr commit: 8b8e4a66b4
2020-01-22 14:37:47 -08:00
a8bdddc382
Merge 'master' into 'amd-master'
...
Change-Id: I747654bdd481c906a88bd6bb65f6ba1a5f38142e
[ROCm/clr commit: c00154541a
2020-01-22 10:25:03 +00:00
8ec1ee47fa
P4 to Git Change 2061101 by skudchad@skudchad_test2_win_opencl on 2020/01/21 16:47:25
...
SWDEV-219917 - [VDI Cleanup] Remove some direct OpenCL references, introduce a common functionality.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/18488/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/build/Makefile.hip#30 edit
... //depot/stg/opencl/drivers/opencl/api/hip/fixme.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_internal.hpp#51 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hiprtc_internal.hpp#3 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/build/Makefile.api#190 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_common.hpp#25 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_context.cpp#61 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_device.cpp#75 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_execute.cpp#31 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_icd.cpp#36 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_platform_amd.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#54 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#610 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#180 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#150 edit
... //depot/stg/opencl/drivers/opencl/runtime/include/vdi_agent_amd.h#1 add
... //depot/stg/opencl/drivers/opencl/runtime/include/vdi_common.hpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/os/os.hpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/os/os_posix.cpp#49 edit
... //depot/stg/opencl/drivers/opencl/runtime/os/os_win32.cpp#50 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/agent.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/agent.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#54 edit
... //depot/stg/opencl/drivers/opencl/runtime/runtimedefs#54 edit
[ROCm/clr commit: 0096cc552b
2020-01-21 16:52:40 -05:00
c9c4645328
Changes for multiple ROCm installation ( #1771 )
...
* FBA-29, FBA-69, multiple rocm support, shared library conflicts
Changes to resolve:
1) Multiple rocm release installation support
2) Multiple rocm shared lib conflicts
3) Add the so versioning also
[ROCm/clr commit: c5ed5c71a3
2020-01-21 14:17:35 +05:30
74115ddd67
P4 to Git Change 2060446 by vsytchen@vsytchen-ocl-win10-2 on 2020/01/20 18:58:37
...
SWDEV-215533 - [HIP][Windows]Output mismatch with tex3D()
When calculating the pitch for hipMallocPitch() align it to the device's image pitch alignment. If we don't, PAL backend will overalign the pitch when creating an image buffer.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/18496/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#96 edit
[ROCm/clr commit: 37bb58b556
2020-01-20 19:05:16 -05:00
99e2be1355
Merge pull request #1795 from aakanksha555/master
...
[HIPIFY][cmake] Packaging for hipify-clang
[ROCm/clr commit: 30baf8fdf4
2020-01-20 19:10:20 +03:00
e6f3f63636
Merge 'master' into 'amd-master'
...
Change-Id: I35af993320b9694efb88ba6a8567c58b62213fb9
[ROCm/clr commit: 5d0b11543b
2020-01-19 05:27:18 -05:00
7f788181ec
Fix texture tests, always pass row pitch to HSA API for linear layout images ( #1785 )
...
=> New ROCr calculates pitch as per HSA specification and addrlib is used to check whether HW can support that configuration. Hence few texture tests are failing with HSA_EXT_STATUS_ERROR_IMAGE_PITCH_UNSUPPORTED.
=> Determine pitch for linear images and always pass rowpitch to HSA API's.
[ROCm/clr commit: 688b6e6af0
2020-01-16 08:54:30 +05:30
2d617bba3b
Don't use accelerated vector element access for hip-clang. ( #1796 )
...
[ROCm/clr commit: 1d6a2fb064
2020-01-15 18:17:08 -08:00
a2ce848fab
P4 to Git Change 2057410 by skudchad@skudchad_rocm on 2020/01/15 18:24:33
...
SWDEV-219341 - Free memory correctly. hiprtcProgram is a pointer by itself. So release *prog
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_rtc.cpp#10 edit
[ROCm/clr commit: 37c900f2a1
2020-01-15 18:32:44 -05:00
efc95906b5
[HIPIFY][cmake] Packaging for hipify-clang
...
[ROCm/clr commit: 545ad0dad3
2020-01-15 11:39:02 -05:00
8bf4210095
Add missing constructors for Scalar_accessor class. ( #1792 )
...
[ROCm/clr commit: 0918614615
2020-01-14 11:30:21 -08:00
b9d4649d30
Merge pull request #1788 from emankov/HIP
...
[HIPIFY][fix] Add "--" separator in-place if needed
[ROCm/clr commit: 84ee66314e
2020-01-13 18:53:02 +03:00
d7647096f6
[HIPIFY][fix] Add "--" separator in-place if needed
...
[ROCm/clr commit: df563c966c
2020-01-13 18:49:28 +03:00
c9209dc860
Merge pull request #1787 from emankov/HIP
...
[HIPIFY] Sync with hipSPARSE
[ROCm/clr commit: 083bfaeb6b
2020-01-13 18:40:10 +03:00
271c1447e2
[HIPIFY] Sync with hipSPARSE
...
+ Update hipify-perl and doc accordingly
[ROCm/clr commit: 41beed4839
2020-01-13 18:34:10 +03:00
f3edec3ec2
P4 to Git Change 2055228 by jujiang@JJ-HIP on 2020/01/10 16:36:01
...
SWDEV-205925 - Update HIP texture APIs for issue in hipTexRefSetAddress in HIP/PAL on Windows
-Update HIP texture function parameter to use hipChannelFormatDesc& desc
http://ocltc.amd.com/reviews/r/18456/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_texture.cpp#33 edit
[ROCm/clr commit: ec3fbfd60c
2020-01-10 16:43:46 -05:00
f538e3b581
Merge 'master' into 'amd-master'
...
Change-Id: I59a0793711937b997b97735d6ab10dee889cc1f9
[ROCm/clr commit: e7aaac2ccd
2020-01-10 17:19:54 +00:00
8550b344a2
Remove filesystem dependency in hipRTC ( #1749 )
...
Removing dependency on filesystem, so libstdc++fs is no longer required to link
[ROCm/clr commit: 0b211478dd
2020-01-10 13:47:54 +05:30
d1d680a1d6
[HIP] Unify hipError_t (Step 3): Sync nvcc path ( #1778 )
...
* [HIP] Unify hipError_t (Step 3): Sync nvcc path
* [HIP][fix] Add CUDA 10.x support to nvcc path
[ROCm/clr commit: 9c2fcff9ce
2020-01-10 13:47:18 +05:30
87887f6152
Fix test hip_bitextract.cpp ( #1784 )
...
The randomly generated offset+width may exceeds 32, which causes
a left shift operation with 32-offset-width. As an unsigned number
that is greater than 32 and causes undefined behavior. When the
test is compiled without -mavx it is still OK. However when
the test is compiled with -mavx, the undefined behavior causes
wrong results and test failure.
This patch adjusts width so that offset+width<=32 always.
[ROCm/clr commit: 55525fa466
2020-01-10 13:46:57 +05:30
Aryan Salmanpour
Laurent Morichetti
jujiang-del
Evgeny Mankov
satyanveshd
vsytch
aakanksha555
mshivama
paulfreddy
Siu Chi Chan
Alexey Chernov
foreman
Rahul Garg
Jenkins
ansurya
kpyzhov
Aakanksha Patil
Jatin Chaudhary
Yaxun (Sam) Liu