AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4,615 Commits 3 Branches 0 Tags
29acb61caeed2f1fdfbe8fcc847fc94de5605155
Commit Graph

187 Commits

Author SHA1 Message Date
Tao Sang ce1baf5d04 Support numa policy set by user 
Add CL_MEM_FOLLOW_USER_NUMA_POLICY

Change-Id: I90a19dac7641827dff2ceb9ef8ae5f3467ed87a1


[ROCm/clr commit: 53264a8a4a]
 2020-06-19 18:16:47 -04:00
German Andryeyev 51db339313 Disable P2P emulation for HIP 
Some apps use P2P transfer without any validation for peer access.
Report an error if runtime has found such a request.

Change-Id: I3bf728f1fc3969697ade97bb1d2f1dce294078e2


[ROCm/clr commit: 01c2727a3a]
 2020-06-16 11:21:54 -04:00
Vlad Sytchenko baaf3e9d1f Fix typo from previous change 
Change-Id: Ib8f3418a3460d86d75fc5529ed6270a164e9b10e


[ROCm/clr commit: b835120dfa]
 2020-06-16 11:12:33 -04:00
Vlad Sytchenko 0b3fc7bc5d Fix some -Wunused-but-set-variable warnings 
Change-Id: I281583b5abdfc09d5dd8b7dfb20b8821581db193


[ROCm/clr commit: 5b9af8f28d]
 2020-06-15 17:51:01 -04:00
Vlad Sytchenko 23b193fcd8 Fix -Wsequence-point warning 
Change-Id: Ib6322e06f83887da4a29f8eafb99b743211e851d


[ROCm/clr commit: e50a9eec9d]
 2020-06-15 17:40:11 -04:00
Tao Sang 7ab0bcb3b6 Make hipHostMalloc() respect hipSetDevice() 
Change-Id: Ibdb666fe8dd049735df2288878501a66f7eedc28


[ROCm/clr commit: db10d42e50]
 2020-06-12 18:32:10 -04:00
German Andryeyev 7c1591d98c Add missing return 
Change-Id: Ibe9c1ccb377ce14ad69a0e9828ea70b707acba34


[ROCm/clr commit: e4177b75bc]
 2020-06-12 17:35:45 -04:00
German Andryeyev 0a6056ac82 Initial HMM support 
- Expose ROCclr interfaces for HIP usage
- ROCr interfaces aren't available in staging, thus control the
build with AMD_HMM_SUPPORT define

Change-Id: Iadc2bcc230e78d3b0dc22b235189c8cc80843446


[ROCm/clr commit: c5afd5d412]
 2020-06-12 09:06:07 -04:00
Aryan Salmanpour 55c58ebfaa Add support for setting queue priority for ROCm backend 
Change-Id: I67ed5a6868af79538f7f4522d8d11c043cdf3c1e


[ROCm/clr commit: b5552aa97f]
 2020-06-04 20:16:32 -04:00
German Andryeyev 3d2182f8ba Revert "Avoid lock for last queued command" 
This reverts commit 88c3f77bed.

Reason for revert: <INSERT REASONING HERE>

Change-Id: Ie10442c9447f010bb90c679b6cffca5b48b8d054


[ROCm/clr commit: 44bc0cb35d]
 2020-06-04 18:08:17 -04:00
kjayapra-amd a9ead10354 SWDEV-234295 - Dont clear device programs during amd::program::build() 
Change-Id: I87bc7e2c830edee783ee490bbb087492467f2704


[ROCm/clr commit: e9bd41bf1a]
 2020-06-03 12:18:25 -04:00
German Andryeyev 88c3f77bed Avoid lock for last queued command 
Use atomics for last queued command update

Change-Id: I759e9d78ea72f23c0d45dbede6250b231e122276


[ROCm/clr commit: dc4e09a63a]
 2020-05-29 11:06:55 -04:00
Christophe Paquot 992fbe8215 Use a dedicated lock for last queued command set/get 
Change-Id: If3d2144841c7863cf7afe2ca85aea62e0a3a33c7


[ROCm/clr commit: 0782acabb5]
 2020-05-28 12:49:39 -07:00
Evgeny 288fd692b7 fixing a typo 
Change-Id: I2fc113e1f52ae9356636ddd4597c36c822bed49b


[ROCm/clr commit: 4ffe859cee]
 2020-05-26 14:49:27 -04:00
Aryan Salmanpour dee687d2d7 Add support for setting CU mask on ROCclr for ROCm backend 
Change-Id: I0dbe2eeb33467fc0f24b26929119c10e9b455da7


[ROCm/clr commit: fed94b8604]
 2020-05-15 14:23:43 -04:00
Vlad Sytchenko 9896d70910 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


[ROCm/clr commit: 6e985845b3]
 2020-05-08 09:37:06 -04:00
Michael LIAO 0e2c6ebac3 Fix build failure. 
- Also fix `-Wreorder` warning. NFC.

Change-Id: I766fdc622c9107f901a55498bdc8fef3d821d1b7


[ROCm/clr commit: 12fcfee41d]
 2020-05-07 10:39:10 -04:00
Michael LIAO b785d25506 Clear executable permission. 
Change-Id: Ia0d363b1ba89d7947e5b5a55cb67edba86f0515e


[ROCm/clr commit: 503ef06555]
 2020-05-07 10:38:58 -04:00
kjayapra-amd 6c270f2292 SWDEV-232464 - Memory Map modules loaded via file from hipModuleLoad 
Change-Id: I0e644a161c8000abe1b07fbec72de09f1c0a4b18


[ROCm/clr commit: 347e36e31b]
 2020-05-04 12:40:16 -04:00
Alex Xie a97194485a 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


[ROCm/clr commit: 6c5a42b33c]
 2020-04-30 11:06:28 -04:00
Laurent Morichetti 963bae11a2 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


[ROCm/clr commit: 9e1964ddaa]
 2020-04-29 18:39:57 -04:00
Alex Xie c158b9b3d0 SWDEV-232894 Port hipMemcpy optimizations from HCC to VDI 
Change-Id: I6bebe9ac503a9f80d067aeea8a848409ad210338


[ROCm/clr commit: 009d0b5f55]
 2020-04-27 14:53:58 -04:00
kjayapra-amd 236705c62f SWDEV-229840 - Improve error messages on ROCCLR Layer. 
Change-Id: Iab7d9156cdc206db86385aa05023a0095ed40f92


[ROCm/clr commit: 7458bf9964]
 2020-04-19 20:01:49 -04:00
Saleel Kudchadker 031b6c87be Fix env var name for CL_AGENT 
This got incorrectly renamed to VDI_AGENT
Change-Id: Ifd7f7c89c0a4e4bfc29e0bceae2c22bf6ba01379


[ROCm/clr commit: b4d852de7f]
 2020-04-08 14:07:11 -04:00
Saleel Kudchadker 2dbe0d2391 Change for OpenCL2.2 header promotion 
Change-Id: Icd579e5c94af6e8d984a3f6c2606be44dec72e91


[ROCm/clr commit: a97f206ab1]
 2020-04-01 16:32:03 -04:00
German Andryeyev 29c091d624 SWDEV-224639 - Device memory is still occupied 
- Add cache free on OCL context destroy
- Remove std::mem_fun() usage, since it was removed in c++17

Change-Id: If6acd08f13a2298912ecd78fc025dcf0b32aee54


[ROCm/clr commit: 9f795d750d]
 2020-03-30 17:39:21 -04:00
German Andryeyev a0b28d035d SWDEV-79445 - Remove cl_amd_object_metadata extension 
Change-Id: I35502d5e3bd4be4a087f4b49b68098f8aa31fdb4


[ROCm/clr commit: 85c09043f3]
 2020-03-24 19:12:52 -04:00
Payam 17f6a41982 removing AMD emails per palamida scan 
Change-Id: If7307f5b1f81a43f2725ec5abd3b8989cbddbcc5


[ROCm/clr commit: 1b6f21ad9a]
 2020-03-11 21:26:55 -04:00
German Andryeyev f70545256b SWDEV-193956 - Fix a regression in OCL for user events 
- Check the queue for nullptr, since the user events may not have
a queue, associated with them

Change-Id: Ib969a052acc9108ca3fd0c063157fe4d47c5b244


[ROCm/clr commit: 288967eff4]
 2020-03-09 11:10:23 -04:00
German Andryeyev 35dee1ac53 SWDEV-193956 - [hipclang-vdi-rocm][perf] 
~45% to 50% of Performance drop on rocBLAS_int8 test

Add support for active waits without blocking the host thread.

Change-Id: Ie7bb48dcafcb4c93d448bf74749b829b626c3578


[ROCm/clr commit: 0fc433e076]
 2020-03-04 17:02:15 -05:00
German Andryeyev ebc40e115c SWDEV-193956 - [hipclang-vdi-rocm][perf] 
Retain command before a wait.

Change-Id: I0ab8f1352af32c96567dad9e31b3687bdf407bf6


[ROCm/clr commit: 77ff161324]
 2020-02-21 16:43:21 -05:00
German Andryeyev 039621e7b9 SWDEV-193956 - [hipclang-vdi-rocm][perf] 
~45% to 50% of Performance drop on rocBLAS_int8 test

Use the last command in the queue for a wait.
Add extra print information about processed commands.
Add an option to disable file location printing.

Change-Id: I4187883e1a90e571fde3128af98368108fda8785


[ROCm/clr commit: a66d09f5a3]
 2020-02-21 15:21:15 -05:00
Christophe Paquot a213e5d155 Append before setting last command to avoid corner case 
Change-Id: Iafe5f899427f0119e7f43e96af38e6e3a1dbfc93


[ROCm/clr commit: 566144edb2]
 2020-02-13 22:23:20 -05:00
Laurent Morichetti b3297f189d Replace cl_* integral types with standard types. 
cl_bool -> bool
cl_int -> int32_t
cl_uint -> uint32_t
cl_long -> int64_t
cl_ulong -> uint64_t
cl_float -> float
cl_double -> double
cl_bitfield -> uint64_t

Change-Id: I840c8993b55f98f5b745d21e27f5f28233647a58


[ROCm/clr commit: d9d9c69399]
 2020-02-12 13:16:06 -08:00
German Andryeyev aaf154b30b Add CMake support for PAL backend 
Change-Id: Id0673d43217be305aa4ca7a612c416baee3fb23c


[ROCm/clr commit: da5f4c554e]
 2020-02-10 11:18:24 -05:00
Laurent Morichetti e284923583 Update copyright info 
Change-Id: Ia4f9ff0f5f873b4223a8cca154188bb0d2f1abba


[ROCm/clr commit: b4c6143a2f]
 2020-02-04 09:26:14 -08:00
Laurent Morichetti 011f3e945b Merge branch 'origin/pghafari/vdi-prototype' into lmoriche/amd-master 
Change-Id: Id3b833d405596735becb3346f3b08c6da57033fe


[ROCm/clr commit: 20c7173849]
 2020-01-30 20:12:13 -08:00