Commit-Graf

453 Incheckningar

Upphovsman SHA1 Meddelande Datum
Aditya Atluri a730d60930 fixed hipmemset to use native ihip api 2016-04-25 11:05:30 -05:00
Ben Sander e020d68309 Fixes for P2P and hipDeviceReset
- devicereset would lose track of default stream and thus subsequent
  synchronization calls might not actually sychronize.
- Also deviceReset now correctly frees streams.
- fix waits in P2P staging copy - first phase (Device0-to-Staging) must
  wait for second phase (Staging to Device1) to finish draining the
  buffer.
2016-04-18 20:49:33 -05:00
Ben Sander 8ec1aad95d test update 2016-04-17 07:54:39 -05:00
Ben Sander 65abde6626 Move HIP_HCC define to CMake 2016-04-17 07:40:04 -05:00
Ben Sander 74a7dee58f fix direction of peer enable/disable APIs
- Enable(peerId) makes memory physically located on peer visible to
current device.
2016-04-17 07:38:05 -05:00
Ben Sander 49cc5aec91 Merge branch 'privatestaging' into p2p
Conflicts:
	include/hcc_detail/hip_hcc.h
	src/hip_hcc.cpp
2016-04-17 06:46:52 -05:00
Aditya Atluri 50d6cc6b11 added memcpy and p2p test 2016-04-16 17:38:06 -05:00
Aditya Atluri 8412e9cbba Added copyright 2016-04-16 17:21:53 -05:00
Aditya Atluri 846432a1c1 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 2016-04-16 17:10:32 -05:00
Aditya Atluri 8dc1bdcbe6 Corrected Memcpydefault 2016-04-16 17:10:13 -05:00
Ben Sander dcabc9dbf7 P2P Update.
- add P2P staging buffer copy.
- If copy device does not have sufficient access permissions, fall back
  to staging buffer.
- improve docs for which copy device is used.
2016-04-16 10:18:56 -05:00
streamhsa 76f2670cef Add __ldg 2016-04-16 21:12:09 +08:00
Aditya Atluri 22d15dcdbc Update README.md 2016-04-15 11:08:48 -05:00
Aditya Atluri 2e80de6dcb improved error returns for hipHostRegister/UnRegister functions 2016-04-15 10:42:31 -05:00
Aditya Atluri 8a43f18333 added more features to hipHostRegister 2016-04-15 10:32:01 -05:00
Aditya Atluri fa7a3822f6 added hipHostRegister/UnRegister api 2016-04-15 10:08:10 -05:00
Maneesh Gupta 5a31bad821 Replace /opt/hcc -> /opt/rocm/hcc and /opt/hsa -> /opt/rocm/hsa 2016-04-15 12:56:31 +05:30
Maneesh Gupta f0e11d9856 Split hip packages into smaller components 2016-04-15 12:13:04 +05:30
pensun bdd26bd1f1 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 2016-04-14 09:02:16 -05:00
Aditya Atluri facc7a39be Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 2016-04-14 09:17:30 -05:00
Aditya Atluri 573224e55f Enabling make_* device code 2016-04-14 09:17:13 -05:00
pensun 234727c801 Add missing cudaMemsetAsync transformation 2016-04-14 09:02:02 -05:00
Ben Sander 8712ae98c8 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 2016-04-14 07:19:20 -05:00
Ben Sander 5bb753acde update README for new make/installation steps, new FAQ 2016-04-14 07:19:07 -05:00
Maneesh Gupta 011a0335d4 Add hip soft-link to include for migrating to new include format 2016-04-14 16:37:27 +05:30
Maneesh Gupta 18af18476b Change default HIP installation to /opt/rocm/hip 2016-04-14 16:36:55 +05:30
Ben Sander 8bbe32a708 Fix HIP_PATH, CHECK macro in samples. 2016-04-13 17:37:39 -05:00
Ben Sander 624b2f35ff add hcc dialects sample 2016-04-13 17:32:38 -05:00
Jack Chung 210ba67b84 Add missing USE_PEER_TO_PEER macro definition 2016-04-13 13:56:26 +08:00
Aditya Atluri 4dfe27e8b5 Removed pragma once 2016-04-12 09:22:03 -05:00
Maneesh Gupta 119de66cd2 Refactor and add support for nvcc path in cmake 2016-04-12 12:42:12 +05:30
Aditya Atluri f85ed17fde changed c/hip xcompiling source 2016-04-11 13:26:09 -05:00
Aditya Atluri 9e7ee4062b added back hc flag 2016-04-11 13:04:13 -05:00
Aditya Atluri d5feabfa1c added C guard to hip_runtime.h 2016-04-11 13:01:02 -05:00
Aditya Atluri ce6383f549 Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging 2016-04-11 10:28:30 -05:00
Aditya Atluri 07d570468e added hipHostRegister support no multi-gpu 2016-04-11 10:28:16 -05:00
Ben Sander 31dc13d2ec Merge branch 'p2p' of https://github.com/AMDComputeLibraries/HIP-privatestaging into p2p
Conflicts:
	RELEASE.md
	include/hcc_detail/hip_hcc.h
	samples/1_Utils/hipInfo/hipInfo.cpp
	src/hip_hcc.cpp
	src/hip_peer.cpp
2016-04-11 09:17:27 -05:00
Ben Sander c40c36aff7 add simple negative P2P tests 2016-04-11 13:46:53 -05:00
Ben Sander 1f53c55d3e 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 12:52:18 -05:00
Ben Sander b0529e04f1 Clean up disable.
Add USE_HCC_LOCK (disabled)
Disable USE_PEER_TO_PEER.
2016-04-11 09:09:36 -05:00
Maneesh Gupta 8efc2cb499 Checked in postinstall and pre-uninstall scripts for packaging 2016-04-11 19:18:17 +05:30
Ben Sander e4d1863ce8 fix peer query order 2016-04-11 07:58:59 -05:00
Ben Sander 4a0c0479d4 add simple negative P2P tests 2016-04-11 07:58:59 -05:00
Ben Sander 83f0de7806 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 c2d37b4bbd Improve P2P test.
- Ensure proper device is set before each command.

- Add command line switches:
    +bool p_memcpyWithPeer = false; // use the peer device for the P2P copy
    +bool p_mirrorPeers = false; // in addition to mapping current to peer
            space, map peer to current space.
    +int  p_peerDevice = -1;  // explicly specify which peer to use, else
use p_gpuDevice + 1.
2016-04-11 07:58:58 -05:00
Ben Sander 40d24f67f5 Improve P2P test.
Add option to select which device does the copy.
2016-04-11 07:58:58 -05:00
Ben Sander d89539d40f Remove stray debug msgs, hipInfo don't print self as peer. 2016-04-11 07:58:58 -05:00
Ben Sander fb31eaf07b fix bugs in P2P implementation
- addPeers polarity reversed, would never add.
- check allow_access return value, pipe error to hipMalloc.
2016-04-11 07:58:58 -05:00
Ben Sander eeb41955e4 Fix simple P2P test, had device ptrs swapped 2016-04-11 07:58:58 -05:00
Ben Sander 40e72dcd4a Use HIP_PATH if set else use relative ../... 2016-04-11 07:58:58 -05:00