AI/rocm-systems
2
0
Çatalla 0
Kod Konular Değişiklik İstekleri İşlemler Paketler Projeler Sürüm Viki Aktivite
1.545 İşleme 3 Dal 0 Etiketler
a9268008acd094e052d184dfc148b5930e5bbb42
İşleme Grafiği

53 İşleme

Yazar SHA1 Mesaj Tarih
Ben Sander b7acb85fa8 Refactor registered memory calls. 2017-03-11 09:18:27 -06:00
Ben Sander f23b5a1f90 Add first step to a "registerd" mode in hipBusBandwidth. 2017-03-11 09:18:27 -06:00
Rahul Garg 73b56e690f Command scripts for latency measurements 
Change-Id: I8c28765a09fb0358447367939de524b12699a317
 2017-02-07 15:03:46 +05:30
Rahul Garg aa3f278475 Fixed hipcommander default execution for HCSWAP-106 
Change-Id: I9fbd10dfaeeb4928b2ec23ceed131b5200a658f9
 2017-01-19 15:04:32 +05:30
Ben Sander ab07d9b4a7 Print limits on CUDA devices 2016-12-16 08:55:11 -06:00
Ben Sander a30b36afdc remove TODO file 2016-12-15 14:42:52 -06:00
Ben Sander a504df955e Add more debug info 2016-11-26 08:56:02 -06:00
Ben Sander 44aee4b61c Print non-peers too 
Change-Id: I2a6905edcdf144aa732ae3120c17780477f232ac
 2016-11-04 06:34:07 -05:00
Maneesh Gupta 945a09c241 samples: Updated copyright header 
Change-Id: I821f514ced5e34d492cb167b65d7273e26ed7b84
 2016-10-15 23:05:04 +05:30
Maneesh Gupta ead394ec09 samples: Updated to use new hip include path 
Change-Id: I53a1385a17f13a997ea21d14315f15a3ad851dab
 2016-10-04 22:21:10 +05:30
Ben Sander 061bcc6a5c Small tool, doc, sample enhancements. 
- Expand message when HIP version mismatch detected.
- Doc touchup.
- change sorting of hipBusBandwidth so byte results shown at top.
-

Change-Id: Ifb4e44a5fdfb65d59c4994b11e5f13385705f7e0
 2016-09-26 16:36:01 -05:00
Ben Sander e8beacbfb1 Sample improvements. 
- Enable -O3 for hipDispatchLatency.
- Use nearly-null kernel to prevent it from being optimized away.
- Formatting for hipDispatchLatency.
- Formatting for hipInfo.
 2016-09-22 13:05:47 -05:00
Maneesh Gupta 3d4bbc4224 hipDispatchLatency: reduce iterations to 5120 
Change-Id: I94ae4993ff5058cf15f9487a5a528fc24c1ad5fa
 2016-06-13 14:23:51 +05:30
Maneesh Gupta 273f4b4cbe Fix makefiles in samples 2016-04-18 10:15:35 +05:30
Ben Sander a894ca3abb fix peer query order 2016-04-11 07:58:59 -05:00
Ben Sander 9e7efd7c65 P2p checkpoint. 
- set USE_PEER_TO_PEER=3 (requires HCC "am_memtracker_update_peers")
- when enabling peer, turn it on for previously allocated memory.
- hipDeviceCanAccessPeer is no longer self-ware (self does not qualify
  as a peer)
- device peerlist always includes self, so when we call allow_access
  we never remove self access.
- hipDeviceReset() removes old peer mappings.
 2016-04-11 07:58:59 -05:00
Ben Sander a4d97c3172 Remove stray debug msgs, hipInfo don't print self as peer. 2016-04-11 07:58:58 -05:00
Ben Sander 034bf3d31c Use HIP_PATH if set else use relative ../... 2016-04-11 07:58:58 -05:00
Ben Sander 23dbffb207 Print peers in hipConfig. 
Also include peer APIs in vim hilighting.
 2016-04-11 07:58:58 -05:00
streamhsa a629d4975f change makefile for samples 2016-03-29 16:02:09 +08:00
Aditya Atluri 867554c423 Logging dispatch latency through database util 2016-03-23 11:39:57 -05:00
Ben Sander 004b4ada93 Only include activity logger if CodeXL installed. 
Fix hipHostMalloc in hipBusBandwidth.
 2016-03-22 09:27:10 -05:00
Ben Sander 2d0fade1f7 hipHostRegister and hipHostMalloc refactor. 
Note hipHostMalloc (not hipHostAlloc or hipMallocHost).
 -  the hipHost* is used for all HIP APIs dealing with Host memory.
    (including hipHostMalloc, hipHostFree, hipHostRegister,
hipHostUnregister, hipHostGetFlags, hipHostGetDevicePointer).
  - hipMallocHost is consistent with "hipMalloc" for allocating device
    memory.  Enumerations hipHostMalloc* also used as optional
    flags parm to hipHostMalloc.
 2016-03-22 02:30:10 -05:00
Ben Sander 90ad8ddc5d Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 
Conflicts:
	src/hip_hcc.cpp
 2016-03-19 03:22:09 -05:00
Ben Sander 5197cf250d Add beastperiteration and onesize for testing. 
onesize allows running tests at one specific size.
 2016-03-19 02:43:04 -05:00
Ben Sander c5d0813f03 Improve formatting - line up cols 2016-03-18 23:43:04 -05:00
Ben Sander 3dc6906855 Print Pinned or Unpinned in result summary 2016-03-18 21:28:29 -05:00
Ben Sander 690486b9eb Supported --aliged mode. Add results check for H2D and D2H. 2016-03-18 03:09:52 -05:00
Aditya Atluri 369d01086f corrected first and second kernel dispatch 2016-03-15 14:22:00 -05:00
Aditya Atluri a6441c3334 Added single kernel launch to sample 2016-03-15 21:05:15 -05:00
Aditya Atluri b7bf5830c1 added performance metrics for kernel dispatch 2016-03-15 12:37:24 -05:00
Aditya Atluri 2743a5082f v2 deprecating hipMallocHost with hipHostAlloc 2016-03-15 13:39:15 -05:00
Ben Sander bdefb70862 print device config info 2016-03-14 23:02:49 -05:00
Ben Sander 15a8e8f8a0 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 
Conflicts:
	src/hip_hcc.cpp
	tests/src/CMakeLists.txt
 2016-03-14 15:01:26 -05:00
Ben Sander 87c15a3629 Add Bidir copy test and help. 2016-03-14 14:39:23 -05:00
Ben Sander 0aab91123b refactor, add support for speccing xfers in bytes 2016-03-13 09:41:06 -05:00
Aditya Atluri 8a21b42943 corrected hipDeviceGetProperties to hipGetDeviceProperties - not docs 2016-03-06 08:31:04 -06:00
Ben Sander 8105bd636f fixes for titan platform 2016-02-26 05:25:30 -06:00
Ben Sander 4a6173fe58 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 2016-02-26 06:15:09 -06:00
Ben Sander af97f5e317 Merge branch 'memtracker' into privatestaging 
Conflicts:
	src/hip_hcc.cpp
 2016-02-25 19:38:46 -06:00
Evgeny Mankov 7bb0f17656 Attribute hipDeviceAttributeIsMultiGpuBoard for obtaining Device property isMultiGpuBoard is added. 
On HIP path property obtaining done through hsa_iterate_agents and counting the devices of HSA_DEVICE_TYPE_GPU type.

P.S.
On multi-boards systems it might be problems with detection what board a GPU plugged into (not tested).
 2016-02-25 23:44:39 +03:00
Evgeny Mankov d4b15399f5 Guard #ifdef USE_ROCR_20 is added for ROCR_20 device properties (memoryClockRate, memoryBusWidth) 
By default isn't defined.
To add ROCR_20 support HIP have to be compiled as follows: make CXX_DEFINES+=-DUSE_ROCR_20
 2016-02-19 13:27:03 +03:00
Evgeny Mankov da8169dd89 Device property memoryBusWidth implementation. 
+ Device property memoryBusWidth is added to hipDeviceProp_t struct.
+ Device attribute hipDeviceAttributeMemoryBusWidth is added to hipDeviceAttribute_t struct.
+ Tests update.
 2016-02-18 18:15:01 +03:00
Evgeny Mankov 8aace64dce Device property memoryClockRate implementation. 
+ Device property memoryClockRate is added to hipDeviceProp_t struct.
+ Device attribute hipDeviceAttributeMemoryClockRate is added to hipDeviceAttribute_t struct.
+ Tests update.
+ Rename hipDevAttrConcurrentKernels to hipDeviceAttributeConcurrentKernels.
 2016-02-18 17:25:28 +03:00
Evgeny Mankov 859208d6f0 hipInfo sample update with new Device Properties. 2016-02-18 15:08:55 +03:00
Evgeny Mankov 763aa5ea5a Formatting, no functional changes. 2016-02-15 13:16:05 +03:00
Ben Sander 56b3d2e7c4 Enable -O3, style points on array size 2016-02-13 03:17:42 -06:00
Ben Sander 8e3dd664eb Result formatting 2016-02-13 01:14:01 -06:00
Ben Sander 1cd35f6371 Add D2H test 2016-02-12 22:47:26 -06:00
Ben Sander 81c275da13 Add D2H test 2016-02-12 22:46:34 -06:00