Граф коммитов

578 Коммитов

Автор SHA1 Сообщение Дата
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 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
Ben Sander d6e8f5bbdc Cleanup hipEvent. (Intermediate checkpoint)
Support hipEventDisableSystemRelease flag.
Update test.
Remove stray printf


[ROCm/clr commit: c8178c6838]
2017-05-27 16:02:34 -05:00
Ben Sander d9587ae2f0 Add isDefaultStream() accessor.
Fix code that checked for stream==nullptr after stream had been
resolved to a "true stream".


[ROCm/clr commit: b2b620c12b]
2017-05-26 13:46:48 -05:00
Siu Chi Chan 6c3a05ac5b fix hip_fast_dsqrt* to call a double fp sqrt function
[ROCm/clr commit: a3595d2e8c]
2017-05-25 23:15:30 -04:00
Ben Sander b4363ffcba Remove HIP_NUM_KERNELS_INFLIGHT. (redundant with HCC controls)
[ROCm/clr commit: 35212632e7]
2017-05-24 01:03:28 -05:00
Ben Sander d302498787 Add hipHostMallocCoherent, hipHostMallocNonCoherent
Provide per-allocation control over coherent/non-coherent mem.
These overrid the default HIP_COHERENT_HOST_ALLOC setting.


[ROCm/clr commit: dda70ae514]
2017-05-24 00:48:10 -05:00
Ben Sander ae983e1b09 Remove HIP_MAX_QUEUES (replaced with HCC_MAX_QUEUES)
[ROCm/clr commit: d43d57d39c]
2017-05-23 23:48:01 -05:00
Ben Sander 2e8625a208 Use accelerator_scope for create_marker and create_blocking_marker.
As optimization when system-scope is not needed.


[ROCm/clr commit: 2d5b3359c6]
2017-05-23 23:15:45 -05:00
Ben Sander 0cde8e5db4 Fix trace category for hipHostMalloc
[ROCm/clr commit: ca07615c37]
2017-05-23 23:15:45 -05:00
Aditya Atluri e7813b1933 fixed erfinv build error as it is implemented in hcc
Change-Id: I27a512147c53f658a63fdf3e90f5e9cfac09ada8


[ROCm/clr commit: 490355203b]
2017-05-23 09:32:19 -05:00
Evgeny Mankov 052f630bd3 [HIP] [HIPIFY] [FIX] cuModuleLoadDataEx -> hipModuleLoadDataEx
https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/issues/81

1.	Do not use JIT options on HCC path, call hipModuleLoadData instead.
2.	NVCC path is unchanged, to call cuModuleLoadDataEx with all options.
3.	Get rid of manual hipification, based on #ifdef #else for NVCC/HIP.
4.	Update documentation accordingly.


[ROCm/clr commit: ae9f14ef9c]
2017-05-19 17:22:14 +03:00
Ben Sander 8c50285d30 Return precise address for hipHostGetDevicePointer.
[ROCm/clr commit: ee37a31799]
2017-05-17 07:36:06 -05:00
Aditya Atluri 0318e91450 changed vector types to make sure it generate proper llvm vector types
Change-Id: I6c4616dae137dc4eac35e5827dc5b7f3251e0247


[ROCm/clr commit: 93fa174900]
2017-05-16 21:35:40 -05:00
Ben Sander c098221a46 Fix HIP_TRACE_API so kernel launch only printed when requested.
[ROCm/clr commit: fad9104b5f]
2017-05-16 19:04:25 -05:00