AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
13,218 Commits 3 Branches 0 Tags
9f1cc590d8106f5d9d2a3fd0400a29dd1fd226cd
Commit Graph

13218 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jatin Chaudhary ec832d42d1 SWDEV-272361 - Dont call memcpy2d if width is 0 or height or depth is 0 
Change-Id: I22324a536d2a5e68b9fc3e5ee4ad821b49021a17
 2021-03-01 14:34:58 -05:00
cjatin 564417d00f SWDEV-271274 - Changing DevLogPrintf to LogPrintf for cases where error condition is being returned 
Change-Id: I153d071f7859e9412ea0c69f53c53d190453d73d
 2021-03-01 14:33:46 -05:00
German Andryeyev 24299e25bd SWDEV-272496 - Fix multiple timing issues 
- Don't notify if the batch is empty, because that means
the current command was processed already.
- Disable pinning optimization to avoid a race condition on stall.
- TS marker submition requires extra AQL barrier
to track the status.

Change-Id: I17eff4ad12ac66cfe1bb44048bebb1891805279d
 2021-03-01 12:46:57 -05:00
Alex Xie 639d67866c SWDEV-272382 - [OCL][LNX] OCLMemoryInfo[1] subtest of oclruntime is failing 
1. Fix the size of the memory when releasing.
2. Make sure we only count the device memory

Change-Id: Ib4dcda79f313c4ee9cc1c7bab53f8076bce5f583
 2021-02-28 16:00:51 -05:00
Chauncey Hui b7c0f180da SWDEV-2 - Change OpenCL version number from 3265 to 3266 2021-02-27 03:00:06 -05:00
German Andryeyev b123dbed2a SWDEV-274464 - Align image width for pitch calculation 
Change-Id: I2f817993da06d2e6fe23e8b4b9d0fe10a2e61760
 2021-02-27 01:30:52 -05:00
Ashutosh Mishra b9c0065e4f SWDEV-271126 - Memory obtained from getDeviceMEmory can be NULL 
which can cause segmentation faults. Hence checking for its sanity

Signed-off-by: Ashutosh Mishra <ashutosh.mishra@amd.com>
Change-Id: I78b4d029f0926a1369a8ebbeb4aef951a8f1f1d7
 2021-02-26 23:29:53 -05:00
Payam 5b7dd3a4b9 SWDEV-273405 - updated roctracer path to use env var 
Change-Id: I9ec74c475161a3e310f57d193449023e921f2922
 2021-02-26 14:51:26 -05:00
Vladislav Sytchenko 4e1232a110 SWDEV-193973 - Enable HSAIL for all Navi Asics 
Change-Id: I0a48442f9a970de3d449e512293bc4600c62db13
 2021-02-26 11:56:09 -05:00
Vladislav Sytchenko 1f8bdcaf20 SWDEV-232428 - Enable device printf for Windows 
Change-Id: Id72cfc34cfcfcbcb459bd8d84979637eaf7947dd
 2021-02-26 11:46:38 -05:00
Chauncey Hui ebda86f961 SWDEV-2 - Change OpenCL version number from 3264 to 3265 2021-02-26 03:00:10 -05:00
Satyanvesh Dittakavi c2a767a66e SWDEV-271491 - Fix flags for hipSetDeviceFlags on HIP-CUDA path 
Change-Id: I29446d5cc5a26a4b83fa45175ccdf1d8f3a9ea40
 2021-02-25 12:06:33 -05:00
German Andryeyev a9b0e20d26 SWDEV-272496 - Fix a regression in PAL 
Skip notification for markers with direct dispatch only,
since they are blocking always

Change-Id: I6bb17650f73371dae6e29c59fd6bb2012cc062fd
 2021-02-25 11:11:42 -05:00
Jatin Chaudhary 474493b929 SWDEV-272811 - hipCabs returns a double and uses sqrtf, which maps to f32 operation. sqrt should be used instead 
Change-Id: I4f74ee8853113fcebfa508bea9308ae93c7ad13b
 2021-02-25 08:47:19 -05:00
Satyanvesh Dittakavi 3abd25b1e9 SWDEV-272082 - Fix Cooperative groups tests on HIP CUDA path 
Change-Id: Icc68bc1e48c01ee120aaab17c928ffbbb96eae96
 2021-02-25 04:54:27 -05:00
Chauncey Hui 9c2f9b208a SWDEV-2 - Change OpenCL version number from 3263 to 3264 2021-02-25 03:00:07 -05:00
Rahul Garg 62c278c39d SWDEV-269604 - Revert "Update dispatch latency with wall time measurements" 
This reverts commit 66776ae8de.

Hold wall time related updates till direct dispatch is ready.

Change-Id: I53b232f6f51bc2fc71b6b639fe0081e2907e9707
 2021-02-25 04:50:44 +00:00
cjatin 41d7c688c9 SWDEV-273859 - Add --hip-version to comgr call 
Change-Id: Iae6c1a5e958a73f5d9849c13c8b49eede914e25e
 2021-02-24 23:41:34 -05:00
Arya.Rafii 5c2eb09624 SWDEV-269246 - Fixed null-case logic for hipCtxPopCurrent 
Change-Id: Ic173980caccde8afee85a75c55a5d536f421549e
 2021-02-24 13:20:24 -05:00
Vladislav Sytchenko 184b2631d5 SWDEV-271964 - Revert "SWDEV-264244 Fix StreamSync" 
This reverts commit a148a71075.

Change-Id: I870c8b71edeb31f587fffe2447762acba61a7938
 2021-02-24 11:43:08 -05:00
Vladislav Sytchenko 9e8a2f3266 SWDEV-86035 - [PAL] Correct allocation logging 
Since the allocation can be a suballocation, we should print both the
VA range for the allocation and the underlying memory object.

Change-Id: Ic9c707bbb78113b366d1b2c688e6fd33bdc8fd94
 2021-02-24 11:35:49 -05:00
kjayapra-amd 46a50965c4 SWDEV-274058 - Porting HIP, ROCclr gfx90a changes to mainline. 
Change-Id: I4f4220df77e57f749a00c1dbb66743ac5af4959a
 2021-02-24 09:55:54 -05:00
kjayapra-amd 20dd93a3be SWDEV-274058 - Porting HIP, ROCclr gfx90a changes to mainline. 
Change-Id: I02f53d4c7897d26243620cfc961fa9bd984cede4
 2021-02-24 09:55:43 -05:00
DURGESH KROTTAPALLI 2a0593258c SWDEV-238517 - Enhancing hip unit tests 
[dtest] Tests for hipEvent related APIs

Added Negative scenarios for hipEvent related APIs

1. Verifying all hipEvent related APIs by passing nullptr.
2. Pass illegal/unknown flag to hipEventCreateWithFlags API

Change-Id: Ia0a24065d16fe0f5ee28a88e280c25c1be0c3590
 2021-02-24 06:29:26 -05:00
Chauncey Hui d5e6769959 SWDEV-2 - Change OpenCL version number from 3262 to 3263 2021-02-24 03:00:06 -05:00
German Andryeyev 0587fb7450 SWDEV-272496 - Disable notification for the previous notify 
Direct disaptch doesn't insert extra barriers for Markers if
AQL barrier was the last issued command already.

Change-Id: I00fbc658547d83dd3ee64ec391ed50e5f8a08e30
 2021-02-23 17:04:59 -05:00
Jason Tang 54a7170e40 SWDEV-198364 - Only enable clgl sharing in ROCm path when building LinuxPro 
Change-Id: Ie4d87e252519d090a62b930f7ebb315d3477b690
 2021-02-23 14:15:04 -05:00
German Andryeyev fe7501a64b SWDEV-272496 - Add marker if notification was the last command. 
If MT is enabled, then a new callback can be received before the previous
command is processed, causing a conflict of 2 callbacks.

Change-Id: I5ff8f231208e8d62824d590d3c8e791e8e36affb
 2021-02-23 13:12:06 -05:00
Tao Sang b9cf12e920 SWDEV-272088 - Fix runtimeApi/event/hipEventElapsedTime issue 
runtimeApi/event/hipEventElapsedTime will report invalid resource error
on cuda due to wrong calling sequence. The fix will arrange the calling
in right sequence.

Change-Id: I3db28a962888566ea135e3cbdefa68d373e2d369
 2021-02-23 12:36:40 -05:00
Vladislav Sytchenko c93f66a5ec SWDEV-270013 - Fix uninitialized variable warning 
Change-Id: Ic4c8090e94e82798c294ac4532ca20efbc5a3a54
 2021-02-23 11:49:28 -05:00
Chauncey Hui 708d3d6621 SWDEV-2 - Change OpenCL version number from 3261 to 3262 2021-02-23 03:00:06 -05:00
Tao Sang 657a515e60 SWDEV-272089 - Shorten memory test time 
memory/hipMalloc_MultiThreaded_MultiGpu costs too much time to finish.
    1 GPU: about 1000s, 2 GPUs: about 2200s
But Jenkin build need quick return and ctest will kill test that last
1500+s. So we need shorten the test time.

Change-Id: I3db27a962808566ea135e3cbdefa66d373e2d369
 2021-02-22 18:01:00 -05:00
Vladislav Sytchenko dbcf023cb1 SWDEV-86035 - [PAL] Propagate gl2Uncached setting to the backend 
Change-Id: I594f304a20d448fe198ec27901e6c97b265c1183
 2021-02-21 13:52:38 -05:00
Vladislav Sytchenko 263173914f SWDEV-86035 - [PAL] Fix runtime init 
The settings need to be populated ASAP, otherwise the dummy context is
not created properly.

Change-Id: Iede0066308bb601dc68164e894775a646a0372f1
 2021-02-20 16:39:13 -05:00
Tao Sang f055582473 SWDEV-273484 - Fix static lib build failure 
Exclude gcc/LaunchKernel from static lib as
it's shared lib test case only

Change-Id: I3db17a962808565ea135e3cbcefa66d373e2d364
 2021-02-19 17:11:26 -05:00
Vladislav Sytchenko be3c5183b2 SWDEV-255979 - Fix Windows build 
Change-Id: I1f1375911d90ded9043a4716e7d09a3ca6a33c23
 2021-02-19 11:31:52 -05:00
Chauncey Hui b625a46db1 SWDEV-2 - Change OpenCL version number from 3260 to 3261 2021-02-19 03:00:07 -05:00
Rahul Garg 18bd7b0c13 SWDEV-270994 - Bump version to 4.1 
Change-Id: Ibe3fcff157f9e0872852dc690ed5db8a8c248049
 2021-02-19 01:59:39 -05:00
Jason Tang 0d47b06928 SWDEV-1 - Fix warnings when building with clang++ 
Change-Id: Idebd2b618b9a3360147984a0e33852dbe2e65818
 2021-02-18 10:02:46 -05:00
Chauncey Hui ae7cb73fe5 SWDEV-2 - Change OpenCL version number from 3259 to 3260 2021-02-18 03:00:06 -05:00
German Andryeyev ac387f9b03 SWDEV-272496 - Wait on CPU before switching to GPU wait 
GPU waits have noticeable overheads on compute with extra
AQL barrier packet and on SDMA with power saving features. This
change introduces a wait on CPU for 30 us in case the app has tiny
operations.

Change-Id: I761ba3af595f3f48544980058a9077dda15aa5f9
 2021-02-17 15:19:17 -05:00
agodavar d5b4762d96 SWDEV-255979 - Added support of __managed__ static variable 
Change-Id: I9d5cbbecc8c19ec38a95c94ab4130465ba76c102
 2021-02-17 13:01:29 -05:00
Satyanvesh Dittakavi d721c79f36 SWDEV-272543 - Fix hipDeviceGetP2PAttribute when both devices are same 
Change-Id: I3db17a962807565ea134e3cbcefa66d373e2d363
 2021-02-17 12:41:59 -05:00
Rupam Chetia a28c367ed0 SWDEV-238517 - [dtest] Adding new test case to validate hipDeviceProp_t arch values 
1. Added 1 scenario to validate value of deviceProp.arch.has* with
value of __HIP_ARCH_HAS_* device flag.

SWDEV-238517 - Enhancing hip unit tests

Change-Id: Idb237a76b75180ce77808853a5351f19077a0d33
 2021-02-17 03:23:42 -05:00
Chauncey Hui 9900b46c21 SWDEV-2 - Change OpenCL version number from 3258 to 3259 2021-02-17 03:00:07 -05:00
Sarbojit Sarkar ed7f4560cf SWDEV-272769 - Enabled gcc based hip test 
Change-Id: I48bc850df00848bf11de71e3f614273111d31b47
 2021-02-16 21:20:00 -05:00
Jason Tang d21913f140 SWDEV-268345 - Remove ADDRESS_SANITIZER option from cmake 
DevOps is going to add this through build scripts.

Change-Id: Id48ac9c1729d60f337e4cb7f0203822a05038e5e
 2021-02-16 18:31:07 -05:00
Jason Tang 82c6aabb0a SWDEV-268345 - Remove ADDRESS_SANITIZER option from cmake 
DevOps is going to add this through build script.

Change-Id: I536d691ea8c05d8289bad1448cac532a8ef93cc4
 2021-02-16 17:37:48 -05:00
Vladislav Sytchenko 671778bdd3 SWDEV-232428 - Push hostcall implementation to the device layer 
This change unifies the hostcall implementation for all the backends,
by pushing the common logic to the device layer. This is done by
replacing the use of hsa_signal_t with device::Signal (a light wrapper
around it).

Change-Id: I7b6fca7930b5a0b199da5d85e2e048354cc04e7b
 2021-02-16 17:19:57 -05:00
German Andryeyev 4dc90dae10 SWDEV-273071 - add mipmaps detection for FillImage 
If mipmap was detected, then create a view with single mip level

Change-Id: I4519b35bd0365c108c42fdb37bfaad729dbc684e
 2021-02-16 16:19:28 -05:00