Refactor copy and P2P logic.

Prefer use of source-engine for DMA copies, even if user submits copy
in a stream attached to a different device.
The stream is now used only for synchronization, and HIP
makes the most optimal decision for which engine to perform the
copy - typically the source copy engine.

HIP now makes decision on which engine should perform the copy
and passes this to HCC using new apis.
HIP has additional information about peer
visibility and will make a decision which agent should perform
the copy .

Change-Id: I0cf4cfebeae256e6ca795f08a7ed7130f4857d1f

src/hip_hcc.h

@@ -496,10 +496,10 @@ private:
 
     // The unsigned return is hipMemcpyKind
     unsigned resolveMemcpyDirection(bool srcInDeviceMem, bool dstInDeviceMem);
-    void resolveHcMemcpyDirection(unsigned hipMemKind, const hc::AmPointerInfo *dstPtrInfo, const hc::AmPointerInfo *srcPtrInfo,
-                                  hc::hcCommandKind *hcCopyDir, bool *forceHostCopyEngine);
+    void resolveHcMemcpyDirection(unsigned hipMemKind, const hc::AmPointerInfo *dstPtrInfo, const hc::AmPointerInfo *srcPtrInfo, 
+                                  hc::hcCommandKind *hcCopyDir, ihipCtx_t **copyDevice);
 
-    bool canSeePeerMemory(const ihipCtx_t *thisCtx, const hc::AmPointerInfo *dstInfo, const hc::AmPointerInfo *srcInfo);
+    bool chooseDirectPeerToPeer(const ihipCtx_t *thisCtx, const hc::AmPointerInfo *dstInfo, const hc::AmPointerInfo *srcInfo);
 
 
 private: // Data
@@ -764,4 +764,10 @@ inline std::ostream& operator<<(std::ostream& os, const ihipCtx_t* c)
 }
 
 
+// Helper functions that are used across src files:
+namespace hip_internal {
+    hipError_t memcpyAsync (void* dst, const void* src, size_t sizeBytes, hipMemcpyKind kind, hipStream_t stream);
+};
+
+
 #endif