- 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.
- 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.
- partition hipThreadSafeDevice into smaller pieces.
- Add debug to hipMultiThreadStream.
- print more precision when mismatch detected.
- enable more tests in CMakeFiles.txt.
Move critical data into separate class and protect with LockAccessor
wrapper class.
For device, the streams list is the critical data since it is modified when
streams are created or destroyed. The streams list is accessed in
several places including when synchronizing across all streams on the
device (ie from the default stream).
Other device data is set once by the device cosntructor and is not critical
so
All functions which acquire the LockAccessor now named with "locked_" prefix.
- Creates markers in HIP group and they show up in CodeXL trace
- Marker text includes HIP functioin arguments
- (Add trace_helper to convert arguments to strings)
- Still need to add HIP_INIT_API for ~30 HIP functions.
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.
Ben Sander
Aditya Atluri
Maneesh Gupta
scchan