AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,313 Commits 3 Branches 0 Tags
b73c021c8fc97daa517896977fb64cf6fa0e88bf
Commit Graph

691 Commits

Author SHA1 Message Date
Maneesh Gupta b37cc92f36 Merge pull request #138 from scchan/threadfence_system 
implement __threadfence_system

[ROCm/clr commit: 2bd79ab9f5]
 2017-08-10 12:51:05 +05:30
Ben Sander 34775b1296 Merge pull request #145 from gargrahul/context_mgmt_changes 
Updated context management logic:

[ROCm/clr commit: dfc87a85bd]
 2017-08-09 17:47:45 -05:00
Weixing Zhang a7f95bb8ee [HIP Texture] The GPU virtual address for texture memory needs to be 
aligned.

In hcc_am, a bigger buffer will be allocated for alignment purpose
and _unalignedDevicePointer is added in struct AmPointerInfo for
original allocated address.


[ROCm/clr commit: e4de2d1138]
 2017-08-08 11:18:00 -04:00
Maneesh Gupta 51c48e4cef Bump min hcc_workweek required for named kernel dispatch to 17312 
Change-Id: I8c7b58306b279ed113d03260e4bc6086bb8b4e68


[ROCm/clr commit: dabd6d2bc6]
 2017-08-08 11:08:55 +05:30
Rahul Garg 687fac97dc Updated context management logic: 
1) hipSetDevice sets a flag so that next call to hipCtxGetCurrent returns primary context on current device
2) hipCtxGetCurrent returns primary context on current device if TLS context stack is empty
3) hipCtxPopCurrent falls back to primary context on current device as default
4) hipCtxPushCurrent, hipCtxSetCurrent and hipCtxCreate reset the flag set in hipSetDevice


[ROCm/clr commit: c4e9323877]
 2017-08-08 07:02:22 +05:30
Siu Chi Chan 6598eabd24 implement __threadfence_system 
[ROCm/clr commit: b6e22b5c93]
 2017-08-02 08:50:18 +00:00
Maneesh Gupta d3d3cedc1d Merge pull request #134 from gargrahul/fix_hipMemcpy2DAsync 
fix hipMemcpy2DAsync

[ROCm/clr commit: 9ded1d02a1]
 2017-07-31 10:27:18 +05:30
Maneesh Gupta 602c3466f9 Merge pull request #135 from bensander/fix_tracing 
Some fixes to tracing.

[ROCm/clr commit: 06b51109c6]
 2017-07-31 10:24:41 +05:30
Ben Sander 6079b4b4f6 Some fixes to tracing. 
[ROCm/clr commit: 9e9f384899]
 2017-07-28 22:13:43 -05:00
Rahul Garg 5a1578847e fix hipMemcpy2DAsync 
[ROCm/clr commit: 320ae86d44]
 2017-07-29 06:50:56 +05:30
Maneesh Gupta 2405c239e1 Merge pull request #127 from bensander/pass_module_kname 
Pass kernel name to HCC dispatch_hsa_kernel, for debug/profile

[ROCm/clr commit: 791063ad6e]
 2017-07-28 10:19:15 +05:30
Ben Sander 004080bff8 Add workweek check to make sure we have a new enough compiler 
[ROCm/clr commit: 2781293e89]
 2017-07-27 23:00:58 -05:00
Maneesh Gupta 8b7ce77fc0 Merge pull request #122 from bensander/enable_async_null_stream 
Set HIP_SYNC_NULL_STREAM=0.

[ROCm/clr commit: 8330fb3fe0]
 2017-07-28 09:15:56 +05:30
Ben Sander c8b72cb926 Pass kernel name to HCC dispatch_hsa_kernel, for debug/profile 
[ROCm/clr commit: a282351763]
 2017-07-27 22:00:15 -05:00
Ben Sander 1aa0656d34 Set HIP_SYNC_NULL_STREAM=0. 
Optimizes null stream synchronization so it uses GPU-side dependency
resolution. Requires HCC __hcc_workweek__ > 17300.


[ROCm/clr commit: cd42711134]
 2017-07-27 11:11:54 -05:00
Maneesh Gupta 97edbda54d Merge pull request #116 from bensander/enable_coh_host 
Make host memory allocations coherent by default.

[ROCm/clr commit: 9086c14936]
 2017-07-27 10:45:32 +05:30
Ben Sander a5b3f825c2 Merge pull request #100 from weixingzhang/texture 
HIP Texture Support

[ROCm/clr commit: 702651fc85]
 2017-07-26 19:28:15 -05:00
Ben Sander 235b60165f 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.


[ROCm/clr commit: 6576201ec2]
 2017-07-26 19:20:34 -05:00
Ben Sander 0e9272cfd7 Enable HCC_OPT_FLUSH=1 (if HCC compiler new enough) 
[ROCm/clr commit: cdc4291431]
 2017-07-24 18:57:19 -05:00
Maneesh Gupta a73a17763d Don't crash for hipEventDestroy(NULL) 
Change-Id: I3f4de1ad2712dbe8af81e10c5d3bef16d468c582


[ROCm/clr commit: 21de66889c]
 2017-07-18 11:01:02 +05:30
Weixing Zhang d9abb032f7 HIP Texture Support 
[ROCm/clr commit: ccbd3b13fc]
 2017-07-17 15:16:12 -04:00
Maneesh Gupta 59bf223264 remove unsupported erf(c)inv related host functionality 
Change-Id: I665c33616359a0124b5552076359d2f8faa54930


[ROCm/clr commit: cc6e6b2a0a]
 2017-07-14 11:31:40 +05:30
Wen-Heng (Jack) Chung c824a3ea0c Temporarily disables HCC_OPT_FLUSH 
Change-Id: I290791e58dd52ab3823f6c3315e42b0d386e9d64


[ROCm/clr commit: 32909c4a92]
 2017-07-12 16:08:36 +00:00
Wen-Heng (Jack) Chung 608adc7bbe Fix hip_db header inclusion path 
Change-Id: I8a95798301de73887dde3316dc593a1847002712


[ROCm/clr commit: 0dcfd2b909]
 2017-07-12 16:08:20 +00:00
Wen-Heng (Jack) Chung 4ce97c30e9 Remove explicit address spaces declarations 
[ROCm/clr commit: 0237aeab06]
 2017-07-07 12:46:29 -05:00
Ben Sander 57733404c1 Add hipdbPrintMem - wrapper for hcc memory tracker. 
[ROCm/clr commit: 18660be8ce]
 2017-07-03 15:05:30 -05:00
Rahul Garg ce0833f3bb Fixed build error in hipDeviceGetByPCIBusId 
Change-Id: I33be362910c4c5dca7435fb9c41f427b54f0e9a7


[ROCm/clr commit: cbc98cc098]
 2017-07-01 07:56:30 +05:30
Ben Sander f1f98a0d2f Set default HIP_SYNC_NULL_STREAM=1. 
[ROCm/clr commit: 61fafdceb1]
 2017-06-30 19:01:14 -05:00
Rahul Garg 1be7dc7cc2 Fixed hipDeviceGetByPCIBusId 
Change-Id: Ia36bb9425671ef7659541c9aeedae4098456a31b


[ROCm/clr commit: 467a2ba014]
 2017-06-30 10:11:41 +05:30
Aditya Atluri bd427d5b47 automate gcnarch detection 
Change-Id: Ibbad22db136f7f5e2be84c82e9169298a144cc77


[ROCm/clr commit: 0fe0381608]
 2017-06-29 12:01:40 -05:00
Rahul Garg 1ff995a92a Fixed hipDeviceGetPCIBusId for HIP/HCC 
Change-Id: I3688fa2476e1baada2d3c5fc3735cec3f15a1e21


[ROCm/clr commit: a7c727f352]
 2017-06-28 23:48:27 +05:30
Ben Sander 639a6d5e46 Set default HIP_HIDDEN_FREE_MEM 
[ROCm/clr commit: eb2c5e166c]
 2017-06-27 12:17:12 -05:00
Sun, Peng 2582679911 Add support of HIP_HIDDEN_FREE_MEM, to deduct the returned available 
memory from hipMemGetInfo API, measured in MB.

Change-Id: I7a8260c12e032e04e26611db4c38c893a29f2653


[ROCm/clr commit: e5ce585307]
 2017-06-26 15:29:38 -05:00
Ben Sander ccc085e4db Add option to pass names to HCC dispatch API (for debug) 
[ROCm/clr commit: c7382f7da6]
 2017-06-23 18:05:30 -05:00
Ben Sander f1bed37a34 Clean up old USE_* and RELEASE.md notes. 
[ROCm/clr commit: 42882ddf9c]
 2017-06-23 18:05:30 -05:00
Rahul Garg 20dd968547 Abort device function in HIP/HCC, need new HCC 
Change-Id: I4195ab75e9b7b48c8b8128d6925ddc0fa5e9e009


[ROCm/clr commit: d9935cd089]
 2017-06-18 12:31:31 +05:30
Aditya Atluri 1634130267 fixed float2int functions 
Change-Id: I67be79149f06daacf0f0d131bdedabf294126248


[ROCm/clr commit: f139d5a52f]
 2017-06-16 09:07:06 -05:00
Rahul Garg 52af9a3cf3 Arguments validation in hipDeviceGetPCIBusId 
Change-Id: I89770517c3ac94e4bf476344d27c18f03cfcde08


[ROCm/clr commit: 3f25611692]
 2017-06-15 00:21:47 +05:30
Rahul Garg 389f1d6aa8 Validity check of input arguments in Ipc Mem APIs 
Change-Id: Ia48e949d19f354f10c7e44cc2457fd4154bf6d76


[ROCm/clr commit: 85708089d1]
 2017-06-14 15:18:57 +05:30
Rahul Garg f48cbf564a Input args NULL check in hipChooseDevice 
Change-Id: I1a7b8cded2f81d739645bbf3dab2f04bb9c3c796


[ROCm/clr commit: 0efd737767]
 2017-06-13 13:35:50 +05:30
Sun, Peng 14e51d052e Fix error related to undefined reference of __get_dynamicgroupbaseptr(). 
Change-Id: I14951e1725e35dd5f5e53805f81cdb58661f59f2


[ROCm/clr commit: 682dda4418]
 2017-06-08 19:24:32 -05:00
Ben Sander 2408d0cf79 Use amHostCoherentFlag. Requires new HCC version. 
[ROCm/clr commit: 9bfc7b0e13]
 2017-06-07 09:06:40 -05:00
Ben Sander daae691cdb Enable HCC_OPT_FLUSH=1. 
Requires appropriate HCC with this support   :
commit 38e392b517a46a09a3b1c8f388e6a0db3741c510


[ROCm/clr commit: c2baa4f6e6]
 2017-06-07 00:15:05 -05:00
Ben Sander d1fe7f1683 Enable HIP_SYNC_NULL_STREAM=0 optimization. 
[ROCm/clr commit: 344b6cb0c0]
 2017-06-05 08:50:41 -05:00
Ben Sander 7237ed04f3 Fix HIP_SYNC_NULL_STREAM=0 mode. 
- Fix null-stream sync
- hipStreamDestroy of null stream returns hipErrorInvalidResourceHandle
- Update documentation.
- Add tests for null stream sync, hipEventElapsedTime.
- Rename internal enum hipEventStatusRecorded to hipEventStatusComplete
- refactor hipStreamWaitEvent to streamline control-flow


[ROCm/clr commit: 823281dcba]
 2017-06-05 08:50:22 -05:00
Ben Sander 6aaeed821d Update tests, add p2p coherency test. 
[ROCm/clr commit: 15f54fb943]
 2017-06-03 17:11:34 -05:00
Siu Chi Chan 8514cf513a fix atomicCAS:remove load for the return value after CAS 
[ROCm/clr commit: 969931b1ce]
 2017-05-31 15:20:19 -04:00
Ben Sander 81354999e8 Set event->_stream on hipHccModuleLaunchKernel path if start/stop used 
Ensure _stream is always non-null in recorded events.
Fixes isDefaultStream fault.


[ROCm/clr commit: 6cc5dc0326]
 2017-05-30 21:55:46 -05:00
Maneesh Gupta 06cdafe311 Disable normcdfinvf on __host__ 
Change-Id: If7bfc9826a09eb9b7675ea2a417b9418759b7912


[ROCm/clr commit: 445012d451]
 2017-05-30 15:45:22 +05:30
Ben Sander 0ca3262f0a Add event controls for release fences. 
Env var : HIP_EVENT_SYS_RELEASE
Event allocation flags : hipEventReleaseToDevice, hipEventReleaseToSystem
   (remove hipEventDisableSystemRelease)

Update test for new functionality.


[ROCm/clr commit: 942ec0eff8]
 2017-05-27 16:02:34 -05:00