1efc99e69f
Bump device major version from 2 to 3
...
This would significantly improve performance for certain apps in kernel
selection logic.
2017-09-15 15:47:39 +00:00
b54ab82694
Merge pull request #179 from gargrahul/fix_hipmallocarray
...
Fixed hipMallocArray for 1D cases
2017-09-14 12:59:33 -05:00
1ea468e279
Merge branch 'master' into hip_init_alloc
2017-09-14 11:53:33 -05:00
fff42fd591
Add HIP_INIT_ALLOC to init allocated memory.
2017-09-13 23:31:48 +00:00
baef2321c8
Fixed hipMallocArray for 1D cases
2017-09-12 21:52:11 +05:30
fff74eee21
hipStreamQuery uses av::is_empty. Add HIP_FORCE_NULL_STREAM.
2017-08-31 03:00:14 +00:00
ed8c3ba7e7
Refactor hipStreamWaitEvent
...
- Null streams use same flow as non-null.
- Add HIP_SYNC_STREAM_WAIT
- Resolve null stream.
2017-08-31 03:00:14 +00:00
8add022539
Merge pull request #167 from bensander/event_safety
...
Event safety
2017-08-29 13:55:46 -05:00
bc9ba7cd81
Lock streams when waiting on event completion or querying event safety.
2017-08-28 18:40:16 -05:00
765d7f3c7b
Null check on input pointer arguments
2017-08-25 08:46:34 +05:30
04a5a36ef7
Device count check on input device id
2017-08-22 14:05:44 +05:30
d6aee9ad8f
Add some new HIP_TRACE_API options.
2017-08-16 04:00:33 +00:00
94554500db
Merge pull request #148 from weixingzhang/vmaddr1
...
[HIP Texture] The GPU virtual address for texture memory needs to be
2017-08-15 14:19:45 -05:00
172a568aa6
[texture] guard new HCC APIs under workweek
...
Change-Id: I4f60a64fb0b0496ca1eb01ffe6ddda121c25d976
2017-08-15 15:51:38 +05:30
2bd79ab9f5
Merge pull request #138 from scchan/threadfence_system
...
implement __threadfence_system
2017-08-10 12:51:05 +05:30
dfc87a85bd
Merge pull request #145 from gargrahul/context_mgmt_changes
...
Updated context management logic:
2017-08-09 17:47:45 -05:00
e4de2d1138
[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.
2017-08-08 11:18:00 -04:00
dabd6d2bc6
Bump min hcc_workweek required for named kernel dispatch to 17312
...
Change-Id: I8c7b58306b279ed113d03260e4bc6086bb8b4e68
2017-08-08 11:08:55 +05:30
c4e9323877
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
2017-08-08 07:02:22 +05:30
b6e22b5c93
implement __threadfence_system
2017-08-02 08:50:18 +00:00
9ded1d02a1
Merge pull request #134 from gargrahul/fix_hipMemcpy2DAsync
...
fix hipMemcpy2DAsync
2017-07-31 10:27:18 +05:30
06b51109c6
Merge pull request #135 from bensander/fix_tracing
...
Some fixes to tracing.
2017-07-31 10:24:41 +05:30
9e9f384899
Some fixes to tracing.
2017-07-28 22:13:43 -05:00
320ae86d44
fix hipMemcpy2DAsync
2017-07-29 06:50:56 +05:30
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
2781293e89
Add workweek check to make sure we have a new enough compiler
2017-07-27 23:00:58 -05:00
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
a282351763
Pass kernel name to HCC dispatch_hsa_kernel, for debug/profile
2017-07-27 22:00:15 -05:00
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
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
702651fc85
Merge pull request #100 from weixingzhang/texture
...
HIP Texture Support
2017-07-26 19:28:15 -05:00
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
cdc4291431
Enable HCC_OPT_FLUSH=1 (if HCC compiler new enough)
2017-07-24 18:57:19 -05:00
21de66889c
Don't crash for hipEventDestroy(NULL)
...
Change-Id: I3f4de1ad2712dbe8af81e10c5d3bef16d468c582
2017-07-18 11:01:02 +05:30
ccbd3b13fc
HIP Texture Support
2017-07-17 15:16:12 -04:00
cc6e6b2a0a
remove unsupported erf(c)inv related host functionality
...
Change-Id: I665c33616359a0124b5552076359d2f8faa54930
2017-07-14 11:31:40 +05:30
32909c4a92
Temporarily disables HCC_OPT_FLUSH
...
Change-Id: I290791e58dd52ab3823f6c3315e42b0d386e9d64
2017-07-12 16:08:36 +00:00
0dcfd2b909
Fix hip_db header inclusion path
...
Change-Id: I8a95798301de73887dde3316dc593a1847002712
2017-07-12 16:08:20 +00:00
0237aeab06
Remove explicit address spaces declarations
2017-07-07 12:46:29 -05:00
18660be8ce
Add hipdbPrintMem - wrapper for hcc memory tracker.
2017-07-03 15:05:30 -05:00
cbc98cc098
Fixed build error in hipDeviceGetByPCIBusId
...
Change-Id: I33be362910c4c5dca7435fb9c41f427b54f0e9a7
2017-07-01 07:56:30 +05:30
61fafdceb1
Set default HIP_SYNC_NULL_STREAM=1.
2017-06-30 19:01:14 -05:00
467a2ba014
Fixed hipDeviceGetByPCIBusId
...
Change-Id: Ia36bb9425671ef7659541c9aeedae4098456a31b
2017-06-30 10:11:41 +05:30
0fe0381608
automate gcnarch detection
...
Change-Id: Ibbad22db136f7f5e2be84c82e9169298a144cc77
2017-06-29 12:01:40 -05:00
a7c727f352
Fixed hipDeviceGetPCIBusId for HIP/HCC
...
Change-Id: I3688fa2476e1baada2d3c5fc3735cec3f15a1e21
2017-06-28 23:48:27 +05:30
eb2c5e166c
Set default HIP_HIDDEN_FREE_MEM
2017-06-27 12:17:12 -05:00
e5ce585307
Add support of HIP_HIDDEN_FREE_MEM, to deduct the returned available
...
memory from hipMemGetInfo API, measured in MB.
Change-Id: I7a8260c12e032e04e26611db4c38c893a29f2653
2017-06-26 15:29:38 -05:00
c7382f7da6
Add option to pass names to HCC dispatch API (for debug)
2017-06-23 18:05:30 -05:00
42882ddf9c
Clean up old USE_* and RELEASE.md notes.
2017-06-23 18:05:30 -05:00
d9935cd089
Abort device function in HIP/HCC, need new HCC
...
Change-Id: I4195ab75e9b7b48c8b8128d6925ddc0fa5e9e009
2017-06-18 12:31:31 +05:30
Wen-Heng (Jack) Chung
Ben Sander
Rahul Garg
Maneesh Gupta
Weixing Zhang
Siu Chi Chan
Aditya Atluri
Sun, Peng