AI/rocm-systems
2
0
Fork 0
Code Issues Pull-Requests Actions Pakete Projekte Releases Wiki Aktivität
13.197 Commits 3 Branches 0 Tags
f6c8bbf4dcc2ec0022ea4faa5a9d75afb2a58a11
Commit graph

13197 Commits

Dieser Branch
Dieser Branch
Alle Branches
Autor SHA1 Nachricht Datum
foreman 55a79e227a P4 to Git Change 1441225 by johtaylo@johtaylo-jtincrementor-increment on 2017/07/29 03:00:04 
SWDEV-2 - Change OpenCL version number from 2464 to 2465.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2212 edit
 2017-07-29 03:13:41 -04:00
Ben Sander 9e9f384899 Some fixes to tracing. 2017-07-28 22:13:43 -05:00
Rahul Garg 320ae86d44 fix hipMemcpy2DAsync 2017-07-29 06:50:56 +05:30
Ben Sander fad59ea8c3 Merge pull request #119 from emankov/master 
[HIPIFY] CUDA RT Textures support
 2017-07-28 12:12:41 -05:00
foreman 6b27cc35a1 P4 to Git Change 1440849 by jatang@jatang-opencl-hsa-stg1 on 2017/07/28 10:17:34 
SWDEV-95919 - Avoid flushing when PerfCounter is enabled.

	To make sure PerfStart/dispatch/PerfEnd are in the same cmdBuffer

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#27 edit
 2017-07-28 10:35:46 -04:00
Maneesh Gupta 2a2c7575eb [hipcc] Cleanup amdgpu target logic 
Existing logic has a bug. If user specifies targetA via commandline
options, while enumerator returns targetB, hipcc will create a fatbin
containing targets targetA and targetB. enumerator should only be used
when no target is specified by user (commandline or env var).

Change-Id: I6da857f86860c0e671b5988cd858644a08f723b9
 2017-07-28 16:18:15 +05:30
foreman e69572cd38 P4 to Git Change 1440715 by johtaylo@johtaylo-jtincrementor-increment on 2017/07/28 03:00:04 
SWDEV-2 - Change OpenCL version number from 2463 to 2464.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2211 edit
 2017-07-28 03:14:42 -04:00
Aditya Atluri b3f8c3fb8e fixed device selection during compilation to use rocm_agent_enumerator 
1. Changed hipcc to use rocm_agent_enumerator
2. Changed square sample test to use device variable
 2017-07-28 10:43:11 +05:30
Maneesh Gupta cb5cf20c21 Renable frexp(f) device math function 
Change-Id: I53c022b8ddf38cd17ddb42eba457b9020db66395
 2017-07-28 10:42:51 +05:30
Maneesh Gupta 791063ad6e Merge pull request #127 from bensander/pass_module_kname 
Pass kernel name to HCC dispatch_hsa_kernel, for debug/profile
 2017-07-28 10:19:15 +05:30
Ben Sander 2781293e89 Add workweek check to make sure we have a new enough compiler 2017-07-27 23:00:58 -05:00
Maneesh Gupta 8330fb3fe0 Merge pull request #122 from bensander/enable_async_null_stream 
Set HIP_SYNC_NULL_STREAM=0.
 2017-07-28 09:15:56 +05:30
Maneesh Gupta 6835f5ac59 Merge pull request #121 from syifan/master 
Allow hip cmake to link libraries
 2017-07-28 09:12:15 +05:30
Ben Sander a282351763 Pass kernel name to HCC dispatch_hsa_kernel, for debug/profile 2017-07-27 22:00:15 -05:00
Evgeny Mankov 6c5adf42dd Update Cuda2Hip.cpp 2017-07-28 01:45:24 +03:00
Evgeny Mankov 4486f91350 Update CUDA_Runtime_API_functions_supported_by_HIP.md 2017-07-28 01:41:14 +03:00
Evgeny Mankov 681dd9e14d Update CUDA_Runtime_API_functions_supported_by_HIP.md 2017-07-28 01:38:50 +03:00
Ben Sander bd563bf761 Merge pull request #110 from sunway513/fix_hipEnvVar_test 
Fix hipEnvVar test
 2017-07-27 13:03:43 -05:00
sunway513 b7c34fb80f Change to use hipDeviceGetPCIBusId api for hipEnvVarDriver test 2017-07-27 17:41:49 +00:00
Ben Sander cd42711134 Set HIP_SYNC_NULL_STREAM=0. 
Optimizes null stream synchronization so it uses GPU-side dependency
resolution. Requires HCC __hcc_workweek__ > 17300.
 2017-07-27 11:11:54 -05:00
Yifan Sun 679075e2f0 Allow hip cmake to link libraries 2017-07-27 11:46:18 -04:00
Evgeny Mankov fa7719b5b5 [HIPIFY] CUDA RT Textures support 2017-07-27 18:39:40 +03:00
foreman bbce92464b P4 to Git Change 1440143 by johtaylo@johtaylo-jtincrementor-increment on 2017/07/27 03:00:05 
SWDEV-2 - Change OpenCL version number from 2462 to 2463.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2210 edit
 2017-07-27 03:18:48 -04:00
Maneesh Gupta 9086c14936 Merge pull request #116 from bensander/enable_coh_host 
Make host memory allocations coherent by default.
 2017-07-27 10:45:32 +05:30
Ben Sander 702651fc85 Merge pull request #100 from weixingzhang/texture 
HIP Texture Support
 2017-07-26 19:28:15 -05:00
Ben Sander 1be14ad733 Merge pull request #114 from emankov/master 
[HIPIFY] CUDA Stream Callback support
 2017-07-26 19:27:05 -05:00
Ben Sander 9e120e3dd3 Merge pull request #113 from mangupta/avoid_rebuild_cache 
[cmake] No longer rebuild cmake cache on each build
 2017-07-26 19:24:43 -05:00
Ben Sander ed9647ad25 Merge pull request #115 from bensander/README 
Update release notes.
 2017-07-26 19:23:26 -05:00
Ben Sander 6576201ec2 Make host memory allocations coherent by default. 
Associated change is to optimize event recording so it uses
agent-scope releaes (since it was only using system-scope release
to support non-coherent host mem).

Flags and environment variables exist to obtain previous behavior
if desired.  Options are documented in new performance guide.
 2017-07-26 19:20:34 -05:00
Ben Sander e29a53f4a6 Update release notes. 2017-07-26 19:03:32 -05:00
foreman 3a805c96cc P4 to Git Change 1439905 by cpaquot@cpaquot-ocl-lc-lnx on 2017/07/26 15:57:06 
SWDEV-121486 - Clean up sampler list if we run out of memory.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#42 edit
 2017-07-26 16:14:35 -04:00
Evgeny Mankov af9dadf20a [HIPIFY] CUDA Stream Callback support 2017-07-26 19:29:50 +03:00
Maneesh Gupta 1b5d19ff36 [cmake] No longer rebuild cmake cache on each build 
Cmake cache was being rebuilt on each build. This was being done
to update HIP_VERSION, HCC_VERSION, .hipInfo and .hipVersion.
However, rebuilding cache also re-runs HIT parser which is slow.
Removing the cache rebuild should speed up the build. But user
needs to explicitly rebuild the cache in case HIP_VERSION or
HCC_VERSION changes by calling "make rebuild_cache"

Change-Id: Ia5476eb7105aa614239c4dc7968c37f5e6cb0b29
 2017-07-26 13:51:32 +05:30
foreman 0b5300069f P4 to Git Change 1439543 by johtaylo@johtaylo-jtincrementor-increment on 2017/07/26 03:00:03 
SWDEV-2 - Change OpenCL version number from 2461 to 2462.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2209 edit
 2017-07-26 03:22:03 -04:00
Evgeny Mankov 9b10efe419 [HIPIFY] Finally finished syncing with CUDA 8.0.61 Driver and Runtime… (#105) 
[hipify-clang] Finally finished syncing with CUDA 8.0.61 Driver and Runtime API (including missing data types, D3D, OpenGL, VDPAU and EGL interop).

    + All the Modules are supported now:
	1) 4.1 – 4.31 from CUDA 8.0.61 Driver API
	2) CUDA_Driver_API_functions_supported_by_HIP.md updated accordingly
	3) 4.1 – 4.31 from CUDA 8.0.61 Runtime API
	4) CUDA_Runtime_API_functions_supported_by_HIP.md updated accordingly
    + Typos fixing
    + Annotating
 2017-07-26 09:38:03 +05:30
foreman 18617446da P4 to Git Change 1439116 by jatang@jatang-opencl-hsa-stg1 on 2017/07/25 11:47:36 
SWDEV-95919 - Make sure PerfCounters_Start, Kernel_dispatch, and PerfCounters_End are in the same command buffer.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#85 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/runtime/OCLPerfCounters.cpp#38 edit
 2017-07-25 12:01:02 -04:00
foreman 8a40282f4a P4 to Git Change 1438847 by johtaylo@johtaylo-jtincrementor-increment on 2017/07/25 03:00:06 
SWDEV-2 - Change OpenCL version number from 2460 to 2461.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2208 edit
 2017-07-25 03:14:06 -04:00
Maneesh Gupta c5790aed94 Merge pull request #111 from bensander/master 
Enable HCC_OPT_FLUSH=1 (if HCC compiler new enough)
 2017-07-25 12:02:33 +05:30
Ben Sander cdc4291431 Enable HCC_OPT_FLUSH=1 (if HCC compiler new enough) 2017-07-24 18:57:19 -05:00
sunway513 af8d028aa4 Update Jenkinsfile to run all the built tests 2017-07-24 19:02:00 +00:00
sunway513 ebd9708dfe Re-enable hipEnvVarDriver in Jenkinsfile 2017-07-24 18:53:46 +00:00
sunway513 046e9c570d Fix indentation, binary path and add wait on popen calls to hipEnvVar test 2017-07-24 17:16:13 +00:00
Maneesh Gupta efdb6608aa Merge pull request #109 from mangupta/disable_failing_tests 
[ci] Exclude sporadically failing test in CI only
 2017-07-24 20:22:45 +05:30
Maneesh Gupta db24ee4cfa [ci] Exclude sporadically failing test in CI only 
Change-Id: If76bc89d39aa35f5c246cbcd41a997b580832450
 2017-07-24 15:16:41 +05:30
foreman 5f2839e8dd P4 to Git Change 1437971 by johtaylo@johtaylo-jtincrementor-increment on 2017/07/22 03:00:04 
SWDEV-2 - Change OpenCL version number from 2459 to 2460.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2207 edit
 2017-07-22 03:14:07 -04:00
Ben Sander 5fdcdf72bd Merge pull request #108 from adityaatluri/enum-fix 
fixed device selection during compilation to use rocm_agent_enumerator
 2017-07-21 16:42:48 -05:00
Aditya Atluri b10962a539 fixed device selection during compilation to use rocm_agent_enumerator 
1. Changed hipcc to use rocm_agent_enumerator
2. Changed square sample test to use device variable
 2017-07-21 15:50:12 -05:00
foreman 9ac2fe6abe P4 to Git Change 1437475 by johtaylo@johtaylo-jtincrementor-increment on 2017/07/21 03:00:03 
SWDEV-2 - Change OpenCL version number from 2458 to 2459.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2206 edit
 2017-07-21 03:13:44 -04:00
Maneesh Gupta 99fbfdf9dc Merge pull request #107 from mangupta/enable_frexp 
Renable frexp(f) device math function
 2017-07-20 14:58:45 +05:30
Maneesh Gupta 1bd1c6bea8 Renable frexp(f) device math function 
Change-Id: I53c022b8ddf38cd17ddb42eba457b9020db66395
 2017-07-20 14:41:30 +05:30