AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
88 Commits 3 Branches 0 Tags
beae41517d43de7903e151e78bbfc0c8b5823b02
Commit Graph

31 Commits

Author SHA1 Message Date
Ben Sander 8ed32daefa Remove HIP-local AM tracker (now in HCC) 
[ROCm/clr commit: b08e468c06]
 2016-02-17 21:33:32 -06:00
Ben Sander 0e83efe14d Add per-stream pool for hsa_signals. 
[ROCm/clr commit: 5d721a2649]
 2016-02-16 01:59:13 -06:00
Ben Sander f8f40e07bf Update before checkin to HCC. 
Add support for USE_AM_TRACKER=2 (HCC version).
Add AM_ALLOC, AM_FREE indirection to ease swapping AM implementations.


[ROCm/clr commit: 1ed431c0f6]
 2016-02-15 21:16:00 -06:00
Ben Sander 93c07bc3d1 Move warpSize to header, have shuffles use default warpsize. 
[ROCm/clr commit: bd7e3b83b9]
 2016-02-15 05:41:09 -06:00
Ben Sander 84810268c0 Update docs, cleanup 
[ROCm/clr commit: 322a3bd9b2]
 2016-02-15 05:40:12 -06:00
Ben Sander 89e461988e Step1 in staging buffer copy. 
- use StagingBuffer class for copies.
- refactor g_device to use array rather than vector.
   (keeps pointers from moving).


[ROCm/clr commit: 90af462b85]
 2016-02-12 18:24:08 -06:00
Ben Sander 5978d5f372 Query tracked memory sizes. 
Support more accurate hipMemGetInfo.  Add test to hipPointerAttrib.


[ROCm/clr commit: f464cedcf4]
 2016-02-12 18:24:08 -06:00
Ben Sander 2089e549eb Tracker improvements 
- add API to add / remove user-pointers from the tracker.
- test for thread-safety with MultiThreadtest_2 - rapid
  insertions/removal.
- add mutex to provide thread-safety.
- rename tracker interface to "memtracker_..." for consistency.
- add am_memtracker_reset, connect to hipDeviceReset.
-


[ROCm/clr commit: 7216727fba]
 2016-02-12 18:24:08 -06:00
Ben Sander fe67be1134 Create address tracker for am_alloc. 
Tracks device where memory is allocated, pinned-host or device, and
more.

Uses memory-range-based lookups - so pointers that exist anywhere in

the range of hostPtr + size will find the associated AmPointerInfo.

The insertions and lookups use a self-balancing binary tree and
should support O(logN) lookup speed.


[ROCm/clr commit: 721508cc2f]
 2016-02-12 18:24:08 -06:00
Evgeny Mankov 6add51ef8c Fix typo: maxThreadsPerMultiProcessor -> MaxSharedMemoryPerMultiprocessor 
Device property MaxSharedMemoryPerMultiprocessor set equal to totalGlobalMem (HIP path).
Reason: MaxSharedMemoryPerMultiprocessor should be as the same as group memory size. Group memory will not be paged out, so, the physical memory size = total shared memory size = group region size. NVCC path remains untouched: CUDA's device property MaxSharedMemoryPerMultiprocessor is reported.

hipify is updated as well.


[ROCm/clr commit: 460b501cbb]
 2016-02-12 01:29:20 +03:00
Evgeny Mankov a8b7647f8b BDFID (BusID/DeviceID/FunctionID) support. 
Except FunctionID (or DomainID in CUDA) support, because cudaDeviceProp::pciDomainID is not reported by CUDA.


[ROCm/clr commit: 658e9f0484]
 2016-02-11 22:26:01 +03:00
Evgeny Mankov 2478fc078f Formatting, no functional changes 
[ROCm/clr commit: d9a94191f2]
 2016-02-10 17:21:18 +03:00
gargrahul 91a5b0aa77 Removed atomicInc and atomicDec support from HIP 
[ROCm/clr commit: 51f46d9ddf]
 2016-02-10 04:29:55 +05:30
Evgeny Mankov 9f596e0aab Device property concurrentKernels is added to hipDeviceProp_t struct. 
For HCC path concurrentKernels is set to true since all ROCR hardware supports this feature.
For NVCC path concurrentKernels is obtained from CUDA's device property cudaDeviceProp::concurrentKernels.


[ROCm/clr commit: 4d4ca3ef3f]
 2016-02-09 17:10:35 +03:00
Maneesh Gupta 8442259da0 Move HIP_DEVICE_COMPILE defines to hip_common.h 
[ROCm/clr commit: f6e7abd710]
 2016-02-09 10:57:20 +05:30
Ben Sander 3b04ce4e81 minor doc touchup 
[ROCm/clr commit: 2ecb345a67]
 2016-02-08 22:11:11 -06:00
Ben Sander 0f1752e720 Fix getdeviceattr compilation for NVCC 
[ROCm/clr commit: 9aec91a3b7]
 2016-02-04 16:26:33 -06:00
Sam Kolton 136baccbe5 Implementation of hipDeviceGetAttribute() 
[ROCm/clr commit: afe45964ae]
 2016-02-04 17:39:27 +03:00
Peng Sun b9367aedec Fix all TODO-doc 
[ROCm/clr commit: d4835c7416]
 2016-02-02 21:29:09 -06:00
Peng Sun 4afe96bf21 Finish all TODO for error code 
[ROCm/clr commit: b20e02ae58]
 2016-02-02 17:39:46 -06:00
scchan a9745be3f4 add inline attribute to shfl functions 
[ROCm/clr commit: 63a6bce3d9]
 2016-02-02 12:53:17 -06:00
streamhsa c832718f42 Adjusted the value of __any as per CUDA -sandeep 
[ROCm/clr commit: b14c890851]
 2016-02-02 15:25:42 +05:30
streamhsa fa391f72c9 ADDED Support for __ffs() and __ffsll() having signed input -sandeep 
[ROCm/clr commit: a7c0be6e4b]
 2016-02-02 15:05:46 +05:30
scchan 4ca3c297be adding shfl, shfl_up, shfl_down, shfl_xor intrinsics 
[ROCm/clr commit: ed0a4fc1b7]
 2016-02-01 23:55:31 -06:00
Maneesh Gupta b5634c1e26 Add double and integer intrinsics to test 
[ROCm/clr commit: 405ee35a04]
 2016-02-01 16:00:45 +05:30
Maneesh Gupta 79b6e4bda6 Add few more single precision intrinsics to hcc_detail/hip_runtime.h 
[ROCm/clr commit: 4b94638bd3]
 2016-02-01 14:29:50 +05:30
Maneesh Gupta 3f648ea239 Restrict using namespace hc::precise_math to device only 
[ROCm/clr commit: c5990d5651]
 2016-02-01 14:26:50 +05:30
Maneesh Gupta 7152009198 Remove redundant #define __HCC__ in hcc_detail/hip_runtime.h 
[ROCm/clr commit: 0f4fe765c4]
 2016-02-01 14:24:41 +05:30
sunway513 90f385fc55 Fix some typos and incorrect namings in comments 
[ROCm/clr commit: 04aa623569]
 2016-01-28 13:17:44 -06:00
sunway513 d89011badf Fix @file and @brief tag on header files 
[ROCm/clr commit: f531ab50e5]
 2016-01-28 10:59:21 -06:00
Ben Sander 28f87a0428 Initial commit for GPUOpen Launch 
[ROCm/clr commit: 304171c1a2]
 2016-01-26 20:14:33 -06:00