AI/rocm-systems
2
0
Forc 0
Cód Saincheisteanna Iarratais Tarraingthe Gníomhartha Pacáistí Tionscadail Scaoileann Vicí Gníomhaíocht
3,554 Tiomáintí 3 Brainsí 0 Clibeanna
abc115bda88b3f0aa0a7cd88d81bbbdf83f50d32
Graf Tiomantas

3554 Tiomáintí

An Brainse seo
An Brainse seo
Gach Brainse
Údar SHA1 Teachtaireacht Dáta
Aakash Sudhanwa abc115bda8 Revert "Reenable cooperative groups" 
This reverts commit 82dc1a6343.

Reason for revert: <INSERT REASONING HERE>

Change-Id: I8954b37c354382804a139d80e2551c381fd9b2ed
 2020-05-19 18:21:48 -04:00
Jason Tang 49224d95c7 SWDEV-236894 - Rename LOG_LEVEL to AMD_LOG_LEVEL 
Change-Id: Ibdfaf0fb615ac343c05d0fa3c3ace9cbb592ecf3
 2020-05-19 17:32:24 -04:00
Jason Tang cd2a713d63 Add major/minor/stepping to device layer 
Change-Id: If82ea55a46b166b243a98089a6e9c40ccfdb479f
 2020-05-17 12:57:34 -04:00
Chauncey Hui 90c975224f SWDEV-2 - Change OpenCL version number from 3143 to 3144 2020-05-16 03:00:03 -04:00
Jason Tang 9b5e1fec6c Correct the way to get subtarget 
Change-Id: I47805424c0bd69547cff0ab71c369552016052b5
 2020-05-15 17:18:39 -04:00
Matt Arsenault 8edad73f14 Remove empty file 
Looks accidentally added

Change-Id: Ib7dce6ffe9c131b08674a1e304b561fbd940362e
 2020-05-15 16:30:37 -04:00
Aryan Salmanpour fed94b8604 Add support for setting CU mask on ROCclr for ROCm backend 
Change-Id: I0dbe2eeb33467fc0f24b26929119c10e9b455da7
 2020-05-15 14:23:43 -04:00
German Andryeyev 82dc1a6343 Reenable cooperative groups 
Change-Id: Ia43049ef550bffa6d21704dbd306ddb9c1d56af0
 2020-05-15 12:41:12 -04:00
Christophe Paquot 6a5af4056e Use system scope for packet following sdma copies 
SWDEV-234947
SWDEV-236298
Instead of forcing a barrier packet, just inject system scope on the next packet.

Change-Id: If9bcee23e08dfe5db731235e2fcb30582cbd4c1c
 2020-05-15 12:20:06 -04:00
Matt Arsenault 3624b8df16 Fix missing target includes for GL/EGL headers 
Change-Id: I9a31eae40cb7187dd0264ad5b9577fab96464b41
 2020-05-14 16:56:34 -04:00
Chauncey Hui 345a8a89b3 SWDEV-2 - Change OpenCL version number from 3142 to 3143 2020-05-14 03:00:03 -04:00
Matt Arsenault 3a7f2e3682 Improve usage of target_include_directories 
Eliminates most of the global include_directories. The install header
paths are different from the build directory, so we have to separate
those for the exported target include paths.

Change-Id: I13e4c56c1218cb31c29a316422dc5fd1d09d8b1b
 2020-05-13 17:25:58 -04:00
Vlad Sytchenko 614aaa8409 Load versioned comgr library 
Change-Id: I4cc81f33e6889ac81a82747159bc210256f33c21
 2020-05-13 16:46:35 -04:00
Matt Arsenault 199f6114d0 Move top.hpp into include directory 
This partially avoids a difference in the include paths between a
build and install tree, and simplifies the install configuration.

Change-Id: If8119507594e0d284ac08c141c6c51c88ec619ef
 2020-05-13 16:30:43 -04:00
German Andryeyev 8904848abc Set CPU access flag for SVM 
Make sure all GPUs have CPU access flag for the fine grain buffer.

Change-Id: Ifc843c2807e70a271b269192ae7859205ff458f3
 2020-05-13 16:05:46 -04:00
Payam a3b730b595 adding HIP_ENABLE_LAZY_KERNEL_LOADING flag 
Change-Id: Ia4425e00d97a25bcea656e2ade5cd3a5d92b4de6
 2020-05-13 13:06:55 -04:00
Chauncey Hui c15d217f1a SWDEV-2 - Change OpenCL version number from 3141 to 3142 2020-05-13 03:00:03 -04:00
German Andryeyev d2b9a57c4f Disable cooperative groups support 
Change-Id: I1b526f2228d083ecad7907a6eaf37c1dd4428277
 2020-05-12 14:31:10 -04:00
Saleel Kudchadker d10d691e76 Add env var to toggle large bar support in runtime 
Use ROC_ENABLE_LARGE_BAR (0/1) to toggle. The support is
enabled by default.

Change-Id: I6cb93a46594cb6f5e90bf6057738330225efb553
 2020-05-12 13:20:06 -04:00
Jason Tang b4f1239f34 device/rocm: split gfxVersion to major/minor/stepping 
Change-Id: I1e437eaee30794147713d9516229211670f01d90
 2020-05-12 12:17:13 -04:00
kjayapra-amd c97ef9f84a SWDEV-232464 - Use Fstat to retrieve file size. 
Change-Id: I4051645cd322c2afaf89e014452657db1a1fdc2c
 2020-05-12 08:53:51 -04:00
Chauncey Hui 81ed982f27 SWDEV-2 - Change OpenCL version number from 3140 to 3141 2020-05-12 03:00:04 -04:00
German Andryeyev ae4aceb55e Make sure the list of HSA agents is valid 
If HIP_VISIBLE_DEVICES is active, then make sure the list of HSA
agents contains the valid agents

Change-Id: I584aad999a230ab7f88a0cfe20dcd0abe79c43a5
 2020-05-11 15:49:30 -04:00
jujiang bc9351f904 SWDEV-230009-Cltrace log is not created as expected-fix build errors on windows 
Change-Id: I9eaa15f39fff0f65858f4a0b8b43ef4288ea97b1
 2020-05-11 13:51:55 -04:00
Christophe Paquot 3ed185307e Fix cooperative flag for hsa_queue creation in case they're not available 
SWDEV-233766

Change-Id: If410ecfed61f2b3bb50b847cf2ededc573139494
 2020-05-11 13:40:50 -04:00
Chauncey Hui da8c217e6f SWDEV-2 - Change OpenCL version number from 3139 to 3140 2020-05-09 03:00:03 -04:00
Christophe Paquot 2a02026696 Add gpu().hasPendingDispatch() in the SDMA path 
SWDEV-234947

Change-Id: I8aa501f8755d136708b0d12ee3c30229c238660d
 2020-05-08 18:19:51 -04:00
Vlad Sytchenko 6e985845b3 Take into account dynamic LDS size when validating the launch parameters. 
Bottom layers don't error check this value, so we might and up writing a bad value to a register and cause the SPI to hang.

Change-Id: I6da4ae71c66a25c63ebb804da4afe4ca7fb831b7
 2020-05-08 09:37:06 -04:00
Chauncey Hui 06ee6f209a SWDEV-2 - Change OpenCL version number from 3138 to 3139 2020-05-08 03:00:03 -04:00
Michael LIAO 12fcfee41d Fix build failure. 
- Also fix `-Wreorder` warning. NFC.

Change-Id: I766fdc622c9107f901a55498bdc8fef3d821d1b7
 2020-05-07 10:39:10 -04:00
Michael LIAO 503ef06555 Clear executable permission. 
Change-Id: Ia0d363b1ba89d7947e5b5a55cb67edba86f0515e
 2020-05-07 10:38:58 -04:00
Chauncey Hui 3c7f376ec0 SWDEV-2 - Change OpenCL version number from 3137 to 3138 2020-05-07 03:00:03 -04:00
German Andryeyev 3446d4e638 Switch PAL version to 592 
Change-Id: I7e90b8fd55c57d8d49e4ec1273ab671f96197bae
 2020-05-06 14:51:32 -04:00
Chauncey Hui 0981ba433b SWDEV-2 - Change OpenCL version number from 3136 to 3137 2020-05-06 03:00:03 -04:00
Payam d6100a9547 name change vdi to rocclr 
Change-Id: I856d6ac1a9a83d89715d6e33dec4aa17abc2f2f2
 2020-05-06 00:54:45 -04:00
Alex Xie bfbc8cd09b SWDEV-234684 - hipmemcpy optimization does not work in tests 
Change-Id: I899d172c5b2af88c796fe9a36f97d15ac45caf94
 2020-05-05 15:58:03 -04:00
Saleel Kudchadker 0fbc0a895b Disable small copy optimization for now 
Change-Id: Ib7a4aa676bb60940e067c985eb19070bd63b2fc2
 2020-05-05 11:52:42 -04:00
kjayapra-amd 8931ac106c SWDEV-209747 - Enable DevLogs on DEBUG or DEV_LOG_ENABLE Compiletime var 
Change-Id: Ie5b7855c469f03947b680d4844c1657cbae55b11
 2020-05-05 09:55:54 -04:00
Chauncey Hui 339a830bc0 SWDEV-2 - Change OpenCL version number from 3135 to 3136 2020-05-05 03:00:04 -04:00
kjayapra-amd 347e36e31b SWDEV-232464 - Memory Map modules loaded via file from hipModuleLoad 
Change-Id: I0e644a161c8000abe1b07fbec72de09f1c0a4b18
 2020-05-04 12:40:16 -04:00
Chauncey Hui 6d0fa49c5d SWDEV-2 - Change OpenCL version number from 3134 to 3135 2020-05-01 03:00:03 -04:00
German Andryeyev 7302ebcfbc Optimize synch operations 
- Stall the queue only for HSA copy operations

Change-Id: Ia3debcc0f36284c5f8cd2776d31674f3aeed04ea
 2020-04-30 11:17:48 -04:00
Alex Xie 6c5a42b33c SWDEV-232894 Port hipMemcpy optimizations from HCC to VDI 
Apply the optimization to change for OpenCL too.
Clean up some unnecessary checks.

Change-Id: I840261fe35baeeadeba7388e86779d482f509aad
 2020-04-30 11:06:28 -04:00
Chauncey Hui 1de8abd031 SWDEV-2 - Change OpenCL version number from 3133 to 3134 2020-04-30 03:00:03 -04:00
Laurent Morichetti 9e1964ddaa Make the device binary copy optional 
Device binaries that are embedded inside the host binary do not
require a copy. Their lifetime is guaranteed to exceed that of the
loaded executable.

Add a 'make_copy' parameter to amd::Program::addDeviceProgram. If
make_copy is false the original image will be used and will not
get freed when the amd::Program is destroyed.

Change-Id: I7973bb0243f5a2d1b639b8a88445cfe6af919dd7
 2020-04-29 18:39:57 -04:00
Christophe Paquot b54c3f7db9 Couple of cleanups. 
Remove queue limitation since we loop through HW queues now.
Add a DevLogError if we fail to create the hsa_queue. A ticket showed a regression there.

Change-Id: I4f58e405f88e75600a762f6d6352838c969cdb5e
 2020-04-29 09:18:07 -07:00
Chauncey Hui 860ba6f0a1 SWDEV-2 - Change OpenCL version number from 3132 to 3133 2020-04-29 03:00:03 -04:00
Saleel Kudchadker 5f64e6e7ad Add a threshold for forcing ROCr to take blit path 
This workaround is to avoid performance penalty of SDMA engine
taking a while to clock up from a lower DPM state. Add env var
GPU_FORCE_BLIT_COPY_SIZE (1024 by default for HIP in KB). Forcing
Src and Dst agent to be amdgpu makes ROCr take blit copy path for
what otherwise should have been SDMA copy

Change-Id: I222f687155f86000d17d66d25182e490b6710463
 2020-04-28 17:11:24 -04:00
Matt Arsenault cba7a4d20e Avoid intermediate object library 
Object libraries are weird, and producing a library by using the
target objects from them doesn't automatically import the interface
properties of the linked targets. These object libraries only have
single uses, so just directly create the final library from the
sources.

Leaves libelf as an object library, since there seems to be some cmake
oddity when trying to link an unexported target to an exported one.

Change-Id: Ic379612c89340c40085c9862cfe111fa4bbff425
 2020-04-28 16:41:34 -04:00
Vlad Sytchenko 2963d0d454 Add entry for another unannounced asic 
Change-Id: I63c6ce6221e812a33e9427841be49840a8f48154
 2020-04-28 14:23:57 -04:00