SWDEV-244772 - Fix dtest hipMemcpyWithStreamMultiThread.cpp.

hipSetDevice is not used correctly to allocate on multiple devices in mGPU setup.
Due to which hipMalloc was called on the same device on multiple threads leading to out of memory issues on some devices with lesser memory.

Change-Id: I0e5b1bc028b9ecb11bd40c3a5edf715f8bd721ff


[ROCm/hip commit: 8fc4d64d2a]

projects/hip/tests/src/runtimeApi/memory/hipMemcpyWithStreamMultiThread.cpp

@@ -467,6 +467,7 @@ void HipMemcpyWithStreamMultiThreadtests::TestkindDefaultForDtoD(void) {
                       &A_h[0], &B_h[0], &C_h[0], N, false);
 
   for (int i=1; i < numDevices; ++i) {
+    HIPCHECK(hipSetDevice(i));
     HIPCHECK(hipMalloc(&A_d[i], Nbytes));
     HIPCHECK(hipMalloc(&B_d[i], Nbytes));
     HIPCHECK(hipMalloc(&C_d[i], Nbytes));
@@ -476,6 +477,7 @@ void HipMemcpyWithStreamMultiThreadtests::TestkindDefaultForDtoD(void) {
 
   hipStream_t stream[numDevices];
   for (int i=0; i < numDevices; ++i) {
+    HIPCHECK(hipSetDevice(i));
     HIPCHECK(hipStreamCreate(&stream[i]));
   }