718ac775f7
[perf]hipMalloc perf optimization
...
Change-Id: I9cd1d29205cb0c9938d26bb8e336fc9fe8a262ed
2020-10-06 12:22:57 -04:00
3949675ab0
Change __HIP_ENABLE_PCH to be an option
...
Currently all the logic checks if __HIP_ENABLE_PCH is set, so setting it
to OFF will still enable PCH.
Switching __HIP_ENABLE_PCH to be a CMake option will enable correct
build behaviour.
Change-Id: I77a663589ffb5f2595c6ad3d144eb9466adcf250
2020-10-06 11:17:47 -04:00
c4505bede3
SWDEV-254363 - Checks to make sure kernel is launched on the same device as it was launched.
...
Change-Id: I2f273a70b1a5fc0e9fc9c6144eabd32466ff4e59
2020-10-06 08:38:09 -04:00
b673a56fcb
Remove libhip_hcc references
...
These were added in commit bf443fef82
2020-10-06 04:29:35 -04:00
ad2d55c144
Revert "Revert "Merge branch 'amd-master-next' into amd-npi-next""
...
This reverts commit 374ead1d19
2020-10-05 13:20:58 -04:00
374ead1d19
Revert "Merge branch 'amd-master-next' into amd-npi-next"
...
This reverts commit 73558e3363
2020-10-05 13:02:39 -04:00
23a9cb15eb
Fix error codes in HMM interfaces
...
Change-Id: I16490c575f2840b1116a4135431a611cf812f3a4
2020-10-05 12:54:16 -04:00
a8ce1881bc
Use availableRegistersPerCU_ to populate number of registers
...
Change-Id: I58f2323bf454f910d22ab31f05aa3024a3d1106f
2020-10-05 00:33:27 -04:00
677a854f4f
fix a bug for calculating the prev_sum of MGSyncInfo struct used in multi-gpu cooperative launch
...
SWDEV-251619
Change-Id: I6566bfc9384bb4677562085991a7a01d3cea3935
2020-10-01 14:05:22 -04:00
464e27829c
SWDEV-253654 : Added invalid parameter checks
...
Change-Id: I8a2ae1ee6898f111aac1c68663a653cca410daec
2020-09-29 13:20:27 -04:00
9f1a177dc7
SWDEV-247518-fix HPC multi gpu test performance drop
...
Change-Id: I2f07d9ba183cf88b3845d8d61607a8a0462d015f
2020-09-29 12:04:40 -04:00
e46dc7b96d
fix a pagefault when wrong argument (extent) passed in hipMemset3D API
...
Change-Id: I779fc14ccd7c942d1ae0a938ebfd3c2e728ff761
2020-09-25 10:57:37 -04:00
dcaec76d41
SWDEV-241896 - Remove extern support in ROCclr/HIP since compiler added Texture reference support.
...
Change-Id: I1b0a7377b803b4e2b94ffef6ffd91e376fdb2b2f
2020-09-24 14:28:16 -04:00
a3e5e6360f
Return hipMemoryTypeHost as memory type for hipHostRegistered pointer
...
Fixes SWDEV-253741
Change-Id: I42c2c9df00862157314d5767b6f175a0d2f28b47
2020-09-24 12:27:32 -04:00
288fbe5af3
SWDEV-249870 - Short-Term solution for Pre-Compiled Headers for Online Compilation
...
Change-Id: Iec989787e546ff2eb68c4b146dc540655698b569
2020-09-24 12:18:06 -04:00
bf443fef82
CMake changes to now write to test folder
...
Change-Id: Ia898b31a09f3c59ef8e7d64253f28ae93c501277
2020-09-21 00:37:15 -04:00
a779350181
Adding checks for return type compatibility with CUDA
...
Change-Id: I09b6bd9a7299f0a97ac9011ea0903a1f81e28251
2020-09-21 00:36:02 -04:00
36ecdf9c3a
Fix Windows build
...
Change-Id: I8769bafba199b9258c610e51b58e454fe10a75e6
2020-09-18 18:51:25 -04:00
146177bcf7
SWDEV-252542 - Fixing Win Compilation on SWDEV-241902.
...
Change-Id: I0ef196231acd8e778018bade684a10ec977261a5
2020-09-18 14:11:07 -04:00
cede497cb2
Print size_t variables with %zu
...
Change-Id: I02bb073b07e9efd03dea2b76b6ba1bd2f552bcaa
Total Memory is not being printed correctly with %u.
%zu represents size_t variables appropriately.
2020-09-18 11:55:41 -04:00
89e5e8b90c
SWDEV-241902 - Changes to pass file descriptor and offset to load code object.
...
Change-Id: I96add27f4fde1b5ee5501e206b7e85ab77e87dfc
2020-09-15 07:54:28 -04:00
5241c76a9d
Reinsert __gnu_h2f_ieee and __gnu_f2h_ieee.
...
Fixes SWDEV-251676
Reverts Ide24d245d851e20961020323e52f33322a33fff9 and adds
__attribute__((weak)) to __gnu_h2f_ieee and __gnu_f2h_ieee.
Change-Id: If4f9e2f867b56a3f0121a907a49ae4032220d9af
2020-09-15 01:39:14 -04:00
5c7b7d1dd2
Fix for hipPointerGetAttributes [github#2137]
...
Change-Id: I5295575638ecc4d3b7129552a9c26c6f6a7195fc
2020-09-10 10:51:30 -04:00
9e2fa6e215
SWDEV-249870 - Short-Term solution for Pre-Compiled Headers for Online Compilation
...
Change-Id: Ibcb365ce2ff27c4c2379609964078da42e1226b1
2020-09-09 13:44:13 -04:00
1f8543560f
SWDEV-240800 - P2P device attributes support
...
Change-Id: Ia32b87ffea17e0d98b69a07f2633ba14e7637b8a
2020-09-03 09:41:05 -04:00
08cf695e1f
SWDEV-248293 - Fix elapsedTime
...
Fixes the elapsed time for the scenarios where HIP API takes one of the start/stop events
and another one is recorded using hipEventRecord.
Change-Id: I51831b2651fc8e7207ff0e3fcc6dc7c1b4239fa8
2020-09-02 03:22:47 -04:00
76824a7f04
SWDEV-246142: Improve performance for sync with multiple streams
...
Change-Id: Ifc625c4c1311ac235b08ea705a3df216d47b2c5e
2020-09-02 00:56:46 -04:00
4e1344de0f
Replace private libelf with elfio
...
Change-Id: I59ae33f7cc55e73f6519af14be91dd9863b03af3
2020-09-01 10:29:11 -04:00
519ef3f22e
Return error when mismatch in copy kind and ptrs
...
Change-Id: I70e4d06e850843697035b42c5d1d56287c874ac8
2020-08-27 20:53:48 -04:00
61b84e246c
Fix memory leak
...
getLastQueuedCommand(true) will implictly retain the last command, hence if we're not putting it in the waitlist, we should release it.
Change-Id: I1ad4ddcdf1df5237b83e1ea2447eb39a59f7dc3a
2020-08-26 12:45:18 -04:00
9c75797d9f
SWDEV-249499 - Add message to Guarantee assert code in hip runtime.
...
Change-Id: I1850463675bbc3e6ff5e3cef8211b1fd40e55f96
2020-08-24 17:35:39 -04:00
99eb486937
SWDEV-240803 - add hipFuncSetSharedMemConfig
...
Change-Id: I160b04677b3e7b99b3981ae7ecc84a0e3811d5e8
2020-08-20 18:18:24 -04:00
efcb882e19
move hipFuncSetCacheConfig from hip_device to hip_module
...
Change-Id: If5a930e1210e76531f5ba9a0e5f5ec98ad473a19
2020-08-17 17:39:01 -04:00
4f400bc5e9
SWDEV-248057 - fix the calculation of allGridSize used in multi_grid_group() API
...
Change-Id: Ib470094e28dcacaa4769dc5c7ab08924f5b7fa41
2020-08-17 12:52:40 -04:00
1340b3f07f
Adding Anyorder flag to HIP
...
Change-Id: Ie20931541b3febe23fa9ac36ebc0c90de75a5f0a
2020-08-17 08:46:52 -04:00
9dfe15a843
SWDEV-240803 - add hipFuncSetAttribute and hipFuncAttribute
...
Change-Id: I3f4d67b19d89fd348fa5b884af4a2542ee4aba60
2020-08-14 17:39:29 -04:00
6f8909be34
SWDEV-237658 - Do not attach events to user invisible Marker.
...
Change-Id: I3a74fd2614d6e2e1d51543471bbd5ae51a713a47
2020-08-14 10:55:34 -04:00
6e50c0f755
Enable developers to build hip without CMAKE_PREFIX_PATH
...
With recent changes in ROCclr to take HSA cmake target it require
HIP to have CMAKE_PREFIX_PATH added for install location for HSA,
amd_comgr,llvm.
User can provide CMAKE_PREFIX_PATH if above
packages are built/installed at custom location as:
cmake -DCMAKE_PREFIX_PATH="<path_hsa> <path_amd_comgr> <path_llvm>"
For default ROCm installation adding a default path will help.
Change-Id: Iefa443dc198da76b57422a641c9821c63cde4922
2020-08-13 23:13:40 -04:00
e2169ce6d0
SWDEV-232197 - Remove refering to gfxipVersion_
...
Change-Id: I91b6b972e26b18dabf6deda5a142bff491c8bb45
2020-08-12 16:34:18 -04:00
505877acea
Allow prefetch on the null stream
...
Change-Id: I87e950460361fab65ab140988fc2288bcb194f08
2020-08-12 13:07:43 -04:00
d620a25b64
Return error from hipMallocManaged for size =0
...
Change-Id: Ida0cecf05e1df731176d41e59422d1e606cc9bd9
2020-08-10 18:25:31 +00:00
844dab3b22
Don't align 2D image buffer size
...
Cuda allows creating 2D textures from memory with unaligned size.
Aligning it will cause us to overshoot the size of the underlying
allocation.
Change-Id: Ia20dec2105e36ca4a8448c9c6299d0001b388d25
2020-08-09 15:53:52 -04:00
36b420ce68
Fixing the memchannel calculation
...
Change-Id: Ib5f5931cc0e1ee5b7cb356c2ede0cb951ee8c9de
2020-08-07 05:34:23 -04:00
2ef062480b
Enable queue profile only if we attach a profiler
...
Submit explicit profile marker for hipEventRecord to record
timestamps. Enable explicit signal profiling if the API specifies
start and stop events.
Toggle this with env var HIP_FORCE_QUEUE_PROFILING=0
Change-Id: Iae449a63ec3ebf6c2880e65d7b1dd1031a29018f
2020-08-06 11:28:16 -04:00
39d681b6be
adding duration to print log for hip api calls
...
Change-Id: Icffa8fcacfb8ba24861d980b9553faeee4efec8c
2020-08-06 06:42:21 -04:00
d768406ec4
Added free device memory info
...
Recently there were few OOM(out of Memory) issues poped. Adding trace will help know genuine OOM issue.
Change-Id: Ie2a56bba95cead24caf1af5c807e73c383c2f5d9
2020-08-06 01:16:36 -04:00
9ea54f7797
SWDEV-243961 Added overflow check for globalWorkSize
...
Change-Id: I153d99398eb4619baad8c0a52466e0d5d5f898ca
2020-08-05 11:18:07 -04:00
678b3eeed5
SWDEV-243576 - Fix hipMemcpy regression.
...
If the queue device doesn't match the device on any memory object, use the queue device from the memory object.
Change-Id: I5fdcf00494f8391574f4443332c01788b8da44ef
2020-07-28 03:04:00 -04:00
dc904abd8a
Remove libhip_hcc symlinks to libamdhip64
...
Change-Id: I7b5b47fc7ca9760316c2424c16b454d7919c665c
2020-07-27 23:58:29 +00:00
448008348e
SWDEV-242344-hipMemcpyAll failed on MGPU
...
Change-Id: I01671e322c84213964d3d48bd6b5dc704dba731a
2020-07-27 13:30:30 -04:00
Sarbojit Sarkar
Vladislav Sytchenko
kjayapra-amd
Rahul Garg
German Andryeyev
Jatin Chaudhary
Aryan Salmanpour
Julia Jiang
agodavar
Satyanvesh Dittakavi
Tao Sang
Vladislav Sytchenko
Todd tiantuo Li
Freddy Paul
Jason Tang
Saleel Kudchadker
Payam
Jason Tang