AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
13,474 Commits 3 Branches 0 Tags
fcaefe97b862afe12aaac0147f1004e6dc595fce
Commit Graph

13474 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Julia Jiang 699b61b5c1 SWDEV-271125 - update ROCclr readme 
Change-Id: Icc3df1eca16c685d5ab1c74bebf37bbf169841c0
 2021-02-02 17:20:46 -05:00
Julia Jiang f5e6934216 SWDEV-271131 - update opencl readme 
Change-Id: I6ffcde28f11f1d73a78b0a837a41992114415f31
 2021-02-02 13:22:37 -05:00
Satyanvesh Dittakavi 4d61107615 SWDEV-269440 - Fix build error in HIP-CUDA path 
Change-Id: Icf5763449ccec333d9efda90ffe3a86fb53bdb81
 2021-02-02 05:40:31 -05:00
Chauncey Hui 20ab999164 SWDEV-2 - Change OpenCL version number from 3250 to 3251 2021-02-02 03:00:06 -05:00
Jason Tang 4791447370 SWDEV-269880 - Fix luxmark 3.1 segfaults 
To workaround a bug in std::regex() implementation.

Change-Id: I4ea2b40e0b74ee1ee79d31283937e43d361d37c2
 2021-02-01 16:12:36 -05:00
Alex Xie 5330679473 SWDEV-268914 - Linux, AMF, tests fail to scale images down 
In pitch workaround, we need to copy the image to copy buffer
when application wants to read image to buffer. After this
patch, we unconditionally copy the image data to the copy buffer.

Change-Id: I71b0d19459542dfbb3ca51a2c8a3a81367fa2fb5
 2021-02-01 15:22:15 -05:00
Joseph Greathouse 54d1d69c0a SWDEV-270773 - Fix workgroup calculation logic for GWS initialization 
The existing workgroup calculation logic for GWS initialization is
incorrect. It tries to add together workgroups across dimensions,
leading to major under-count in 2D and 3D kernels. An (x,y,z) kernel
uses x * y * z blocks, not x + y + z.

In addition, the previous logic was incorrect for the case of launching
a single-threaded kernel. It calculated 0 workgroups, leading to
initializing GWS to -1.

Change-Id: I1bb20a0d5b6e0cc10ac55901c28d8f93aac61c09
 2021-01-31 01:16:48 -06:00
Chauncey Hui b7f0fd0354 SWDEV-2 - Change OpenCL version number from 3249 to 3250 2021-01-29 03:00:06 -05:00
agodavar eb58a0285c SWDEV-269085 - Add support for build with ADDRESS_SANITIZER 
Change-Id: I102cbe197727ec059d3dc9fae3a41bb559b0dff1
 2021-01-29 01:54:43 -05:00
Saleel Kudchadker 629a2d8ef3 SWDEV-257787 - Add log for tracking copy signals 
Change-Id: I713e8463916a85a634a1ec2309bbd46a11c461a8
 2021-01-28 13:25:49 -05:00
Sarbojit Sarkar cee3e1aa37 SWDEV-265469 - added constexpr constructor for dim3 
Change-Id: I2e23a403f272d1ff0ade24fec11190d2f3244e5f
 2021-01-28 13:23:51 -05:00
Vladislav Sytchenko 0d0739a39b SWDEV-268186 - [PAL] Enable MALL for persistent allocations 
Change-Id: Ibc21255d5be52289cb4de3de7d12e0415fd1bc91
 2021-01-28 12:47:18 -05:00
Vladislav Sytchenko 81e331dc42 SWDEV-1 - Update ISA table 
Disable gfx9+ for GSL.

Enable gfx9+ (except MI100/200/300) for PAL.

Change-Id: Ic5a238af939e1d8795503aae39df6a6ece50a9d2
 2021-01-28 11:26:22 -05:00
Vladislav Sytchenko f174d98893 SWDEV-1 - Fix Windows build 
Change-Id: I20c727a8718941694da6dc024efdfd1eb6af828b
 2021-01-28 10:22:25 -05:00
kjayapra-amd 85fafb0561 SWDEV-270013 - Adding code to differentiate between kern_arg + fine_grain and fine_grain segment of system memory. 
Change-Id: Id0404b2dab8561946ad0a90a77030582f7e021a4
 2021-01-28 09:48:17 -05:00
kjayapra-amd e8208de6c1 SWDEV-261215 - Updating file handle APIs with file sharing option to accomodate back to back hipModuleLoad calls. 
Change-Id: I8fd833b678ca38c60e2d7d02295fd01df0af5592
 2021-01-28 09:47:41 -05:00
kjayapra-amd d13124d90f SWDEV-270007 - Fixing the hipMemoryAllocateCoherent test binary path for hipMemoryAllocateCoherentDriver test path. 
Change-Id: Iae5363685d10fce32ff80ac5d6bfba460dc2b574
 2021-01-28 09:47:01 -05:00
Satyanvesh Dittakavi 0074429d05 SWDEV-269784 - managed memory support for HIP CUDA 
Change-Id: I01f9fc64573f402031eceab24395e5cbd93007f9
 2021-01-28 07:51:52 -05:00
agodavar 160f0edffa SWDEV-269400 - handle nullptr in hipFuncGetAttributes and blockSizeLimit<0 in hipModuleOccupancyMaxPotentialBlockSize 
Change-Id: Ia1c6e5713f40876b4a9c7a1c56b7b3a589c4497a
 2021-01-27 23:41:31 -05:00
agodavar 6e7ff3aaae SWDEV-270198 - hip-hcc cleanup remove lpl_ca 
Change-Id: I6cae9435397e9070efb4a953c7ba8bd3dcd98c0e
 2021-01-27 23:40:58 -05:00
agodavar 2d2f127b8a SWDEV-268552 - HIP sample segfaults during hipModuleLoad, fix mmap bug 
Change-Id: I51c6061e7ac6b2524586d96fdd69b9f084b1906a
 2021-01-27 23:39:50 -05:00
Rahul Garg fecaab1179 SWDEV-270166 - Remove Linux specific includes 
Change-Id: I929285941f28941cb41718f9fb8f618d11f1a69b
 2021-01-27 12:10:37 -05:00
agodavar a16d91a708 SWDEV-267154 - Add checks for grid and block dimensions 0 
Change-Id: I54799c0a4a42a91f6226f94a1e3ff7bc79046a98
 2021-01-27 00:32:31 -05:00
Vladislav Sytchenko 09c28dcbf4 SWDEV-1 - Fix Windows build 
Change-Id: I144142b2b31785fe7b1d319fb7e88eb2b41099ac
 2021-01-26 15:51:57 -05:00
Vladislav Sytchenko 70ac5c3bd8 SWDEV-1 - Fix Windows build 
Change-Id: I3867b4a7175316121246a639fb8d704ad491adb6
 2021-01-26 11:01:30 -05:00
Chauncey Hui a231391423 SWDEV-2 - Change OpenCL version number from 3248 to 3249 2021-01-26 03:00:05 -05:00
Todd tiantuo Li 280b759175 Merge "SWDEV-267762 - add RMB(gfx1035) to deviceQuery" into amd-staging 2021-01-25 19:40:02 -05:00
Aaron En Ye Shi 31e772adb5 SWDEV-263964 - Fix hipconfig to work on Windows 
Modify hipconfig and hipcc to properly run Windows compiler
executables. Support Windows Environmental Variables and
AMD Display Adapter info. Update flags to include quotes for
paths that have spaces, such as Program Files.

Change-Id: Ib721b318bd88be7dfa1247a30ce78c7ed6a334e8
 2021-01-25 12:53:03 -05:00
Aaron En Ye Shi db43d7a3ac SWDEV-263964 - Add Windows CMake find_package(hip) 
Modify hip-config.cmake to support building on Windows
using CMake's find_package(hip). Windows CMake will work
with Ninja Generator and inheritEnvironments clang_cl_x64.

Change-Id: I03d76b5f8d695ce50ecaacb449e4eb1c1ca49700
 2021-01-25 12:52:46 -05:00
German Andryeyev dbc7abaecf SWDEV-257787 - Add engine tracking per signal 
- The logic will trace compute, sdma read/write operations and
apply signals when necessary
- ROC_CPU_WAIT_FOR_SIGNAL, ROC_SYSTEM_SCOPE_SIGNAL
and ROC_SKIP_COPY_SYNC were added to control the tracking

Change-Id: I9e8e6174c63bf7784f7ab00964e2918c8667d364
 2021-01-25 12:34:45 -05:00
Chauncey Hui 99da7ecba5 SWDEV-2 - Change OpenCL version number from 3247 to 3248 2021-01-24 03:00:07 -05:00
Jason Tang 1e08a3e0cd SWDEV-269147 - Disable ROC offline devices for now 
Change-Id: I520f3c8e56db91cbc384d08beba4e0bd4626941d
 2021-01-23 14:48:07 -05:00
Chauncey Hui 29596ac3be SWDEV-2 - Change OpenCL version number from 3246 to 3247 2021-01-23 03:00:04 -05:00
Vladislav Sytchenko 290a16716d SWDEV-264411 - Disable OCLDynamicBLines test 
Change-Id: I067afa99b988e0b32edee7d27c1403d31775655c
 2021-01-22 16:55:18 -05:00
Joseph Greathouse 51e53b6b56 SWDEV-269756 - Add missing Cooperative Groups error string 
Change-Id: I1833f8bb4b48b19bb3d6cac57dda429231cf3562
 2021-01-22 15:48:18 -06:00
Jason Tang 64714fdbbe SWDEV-268345 - Enable address sanitizer build when ADDRESS_SANITIZER is ON 
Change-Id: I09e5c5b2c21637bc67c23267411c2996ee57aad4
 2021-01-22 16:21:50 -05:00
Jason Tang 8d75c7e76f SWDEV-268345 - Enable address sanitizer build when ADDRESS_SANITIZER is ON 
Change-Id: Iaef46358f33a399f8b047aaebc5154bb7352a69a
 2021-01-21 18:31:14 -05:00
German Andryeyev ce2e5eba6b SWDEV-257787 - Reset active signal if ROCR call failed 
- ROCR fails the call for some reason, then the signal will
become invalid and can hang on a wait. The logic will reset the
active signal in such cases

Change-Id: Ia131420200f1bbd7c9a162b8f1b06db8cecf41c6
 2021-01-21 17:29:34 -05:00
Tao Sang a0c8c30ae5 SWDEV-268757 - Disable deprecation warning 
Disable it as it will fail rocgdb test

Change-Id: Ibf34c780d5bd4278adcedba1d6e057639c258483
 2021-01-21 15:35:32 -05:00
Tao Sang 8cf28aa5b3 SWDEV-257056 - Fix cyclic dependence of hip/rocclr libs 
Solve upstream building failure due to the cyclic dependence.

Change-Id: Ibf34c789d5bd4278adcedba1d6e057639c258488
 2021-01-21 13:00:22 -05:00
jujiang cfca71352a SWDEV-265003 - update HIP document 
Change-Id: I1e8ec3ad380330b48d164a2ca60b0a70f7e54ae6
 2021-01-20 16:24:20 -05:00
Chauncey Hui de3e8b092c SWDEV-2 - Change OpenCL version number from 3245 to 3246 2021-01-20 03:00:06 -05:00
Satyanvesh Dittakavi 8da9f4d432 SWDEV-268989 - Modify atomicAdd double to use clang builtin 
Change-Id: If9d40046df2f3f5af7cc1bd6c935fbe7d686e7d8
 2021-01-20 02:39:15 -05:00
German Andryeyev 5a8946190a SWDEV-268381 - Enable wait on CPU before SDMA transfer 
- There is a performance regression with a HW wait for HSA signal
on ROCr async operation. For now move the logic back to CPU wait.

- Fix profiling issue with multiple HSA signal per single timestamp
object. Some copies require multiple ROCR calls and if profiling is
required, then the execution time is derived from all used signals.

Change-Id: Id003e4abb8c2de378eedc152a7e389500fc6f4ce
 2021-01-19 18:24:21 -05:00
agodavar 2b84b58c31 SWDEV-267298 - update install script to build hip-rocclr 
Change-Id: Ia8d72ebc41184d2fc58aa4e99966ef9b71a7fc26
 2021-01-19 11:50:42 -05:00
agodavar f4edf51736 SWDEV-268552 - HIP sample hipDispatchEnqueueRateMT segfaults, updated to use hipModuleLoadData 
Change-Id: Ibf34c780d5bd4278adcedba1d6e057637c258485
 2021-01-19 09:32:14 -05:00
Chauncey Hui 44659d5d7e SWDEV-2 - Change OpenCL version number from 3244 to 3245 2021-01-19 03:00:05 -05:00
Tony Tye 6b641fb368 SWDEV-268864 - Use new isa class to access isa related information (part 2) 
Change-Id: If7ed535b3012aec3f2cb4eb7ab93d8f5aed9783f
 2021-01-19 03:36:22 +00:00
Tony Tye 91bb64409b SWDEV-268864 - Use new isa class to access isa related information 
Change-Id: I866eeef06f86df77c651a25fdf7bceed2c28af52
 2021-01-18 22:33:25 +00:00
Tony Tye c2308216dd SWDEV-268864 - Remove duplicatation of isa related information 
Remove targetId_, gfxipMajor_, gfxipMinor_ and gfxipStepping_ from
device::Info as they are now available in device::Isa.

Change-Id: I381b1d4798ebf50655740e004a01ac7f86dbf668
 2021-01-18 22:32:37 +00:00